* [v3 RFC PATCH 4/4] qemu changes
From: Krishna Kumar @ 2010-10-20 8:55 UTC (permalink / raw)
To: rusty, davem, mst
Cc: eric.dumazet, kvm, netdev, arnd, avi, anthony, Krishna Kumar
In-Reply-To: <20101020085452.15579.76002.sendpatchset@krkumar2.in.ibm.com>
Changes in qemu to support mq TX.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
hw/vhost.c | 7 ++++--
hw/vhost.h | 2 -
hw/vhost_net.c | 16 +++++++++----
hw/vhost_net.h | 2 -
hw/virtio-net.c | 53 ++++++++++++++++++++++++++++++++--------------
hw/virtio-net.h | 2 +
hw/virtio-pci.c | 2 +
net.c | 17 ++++++++++++++
net.h | 1
net/tap.c | 34 ++++++++++++++++++++++++++---
10 files changed, 107 insertions(+), 29 deletions(-)
diff -ruNp org3/hw/vhost.c new3/hw/vhost.c
--- org3/hw/vhost.c 2010-10-19 19:38:11.000000000 +0530
+++ new3/hw/vhost.c 2010-10-20 12:44:21.000000000 +0530
@@ -580,7 +580,7 @@ static void vhost_virtqueue_cleanup(stru
0, virtio_queue_get_desc_size(vdev, idx));
}
-int vhost_dev_init(struct vhost_dev *hdev, int devfd)
+int vhost_dev_init(struct vhost_dev *hdev, int devfd, int numtxqs)
{
uint64_t features;
int r;
@@ -592,11 +592,14 @@ int vhost_dev_init(struct vhost_dev *hde
return -errno;
}
}
- r = ioctl(hdev->control, VHOST_SET_OWNER, NULL);
+
+ r = ioctl(hdev->control, VHOST_SET_OWNER, numtxqs);
if (r < 0) {
goto fail;
}
+ hdev->nvqs = numtxqs + 1;
+
r = ioctl(hdev->control, VHOST_GET_FEATURES, &features);
if (r < 0) {
goto fail;
diff -ruNp org3/hw/vhost.h new3/hw/vhost.h
--- org3/hw/vhost.h 2010-07-01 11:42:09.000000000 +0530
+++ new3/hw/vhost.h 2010-10-20 12:47:10.000000000 +0530
@@ -40,7 +40,7 @@ struct vhost_dev {
unsigned long long log_size;
};
-int vhost_dev_init(struct vhost_dev *hdev, int devfd);
+int vhost_dev_init(struct vhost_dev *hdev, int devfd, int numtxqs);
void vhost_dev_cleanup(struct vhost_dev *hdev);
int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev);
void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev);
diff -ruNp org3/hw/vhost_net.c new3/hw/vhost_net.c
--- org3/hw/vhost_net.c 2010-09-28 10:07:31.000000000 +0530
+++ new3/hw/vhost_net.c 2010-10-19 19:46:52.000000000 +0530
@@ -36,7 +36,8 @@
struct vhost_net {
struct vhost_dev dev;
- struct vhost_virtqueue vqs[2];
+ struct vhost_virtqueue *vqs;
+ int nvqs;
int backend;
VLANClientState *vc;
};
@@ -81,7 +82,8 @@ static int vhost_net_get_fd(VLANClientSt
}
}
-struct vhost_net *vhost_net_init(VLANClientState *backend, int devfd)
+struct vhost_net *vhost_net_init(VLANClientState *backend, int devfd,
+ int numtxqs)
{
int r;
struct vhost_net *net = qemu_malloc(sizeof *net);
@@ -98,10 +100,14 @@ struct vhost_net *vhost_net_init(VLANCli
(1 << VHOST_NET_F_VIRTIO_NET_HDR);
net->backend = r;
- r = vhost_dev_init(&net->dev, devfd);
+ r = vhost_dev_init(&net->dev, devfd, numtxqs);
if (r < 0) {
goto fail;
}
+
+ net->nvqs = numtxqs + 1;
+ net->vqs = qemu_malloc(net->nvqs * (sizeof *net->vqs));
+
if (!tap_has_vnet_hdr_len(backend,
sizeof(struct virtio_net_hdr_mrg_rxbuf))) {
net->dev.features &= ~(1 << VIRTIO_NET_F_MRG_RXBUF);
@@ -131,7 +137,6 @@ int vhost_net_start(struct vhost_net *ne
sizeof(struct virtio_net_hdr_mrg_rxbuf));
}
- net->dev.nvqs = 2;
net->dev.vqs = net->vqs;
r = vhost_dev_start(&net->dev, dev);
if (r < 0) {
@@ -188,7 +193,8 @@ void vhost_net_cleanup(struct vhost_net
qemu_free(net);
}
#else
-struct vhost_net *vhost_net_init(VLANClientState *backend, int devfd)
+struct vhost_net *vhost_net_init(VLANClientState *backend, int devfd,
+ int nvqs)
{
return NULL;
}
diff -ruNp org3/hw/vhost_net.h new3/hw/vhost_net.h
--- org3/hw/vhost_net.h 2010-07-01 11:42:09.000000000 +0530
+++ new3/hw/vhost_net.h 2010-10-19 19:46:52.000000000 +0530
@@ -6,7 +6,7 @@
struct vhost_net;
typedef struct vhost_net VHostNetState;
-VHostNetState *vhost_net_init(VLANClientState *backend, int devfd);
+VHostNetState *vhost_net_init(VLANClientState *backend, int devfd, int nvqs);
int vhost_net_start(VHostNetState *net, VirtIODevice *dev);
void vhost_net_stop(VHostNetState *net, VirtIODevice *dev);
diff -ruNp org3/hw/virtio-net.c new3/hw/virtio-net.c
--- org3/hw/virtio-net.c 2010-10-19 19:38:11.000000000 +0530
+++ new3/hw/virtio-net.c 2010-10-19 21:02:33.000000000 +0530
@@ -32,7 +32,7 @@ typedef struct VirtIONet
uint8_t mac[ETH_ALEN];
uint16_t status;
VirtQueue *rx_vq;
- VirtQueue *tx_vq;
+ VirtQueue **tx_vq;
VirtQueue *ctrl_vq;
NICState *nic;
QEMUTimer *tx_timer;
@@ -65,6 +65,7 @@ typedef struct VirtIONet
} mac_table;
uint32_t *vlans;
DeviceState *qdev;
+ uint16_t numtxqs;
} VirtIONet;
/* TODO
@@ -82,6 +83,7 @@ static void virtio_net_get_config(VirtIO
struct virtio_net_config netcfg;
netcfg.status = n->status;
+ netcfg.numtxqs = n->numtxqs;
memcpy(netcfg.mac, n->mac, ETH_ALEN);
memcpy(config, &netcfg, sizeof(netcfg));
}
@@ -196,6 +198,8 @@ static uint32_t virtio_net_get_features(
VirtIONet *n = to_virtio_net(vdev);
features |= (1 << VIRTIO_NET_F_MAC);
+ if (n->numtxqs > 1)
+ features |= (1 << VIRTIO_NET_F_NUMTXQS);
if (peer_has_vnet_hdr(n)) {
tap_using_vnet_hdr(n->nic->nc.peer, 1);
@@ -659,13 +663,16 @@ static void virtio_net_tx_complete(VLANC
{
VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
- virtqueue_push(n->tx_vq, &n->async_tx.elem, n->async_tx.len);
- virtio_notify(&n->vdev, n->tx_vq);
+ /*
+ * If this function executes, we are single TX and hence use only txq[0]
+ */
+ virtqueue_push(n->tx_vq[0], &n->async_tx.elem, n->async_tx.len);
+ virtio_notify(&n->vdev, n->tx_vq[0]);
n->async_tx.elem.out_num = n->async_tx.len = 0;
- virtio_queue_set_notification(n->tx_vq, 1);
- virtio_net_flush_tx(n, n->tx_vq);
+ virtio_queue_set_notification(n->tx_vq[0], 1);
+ virtio_net_flush_tx(n, n->tx_vq[0]);
}
/* TX */
@@ -679,7 +686,7 @@ static int32_t virtio_net_flush_tx(VirtI
}
if (n->async_tx.elem.out_num) {
- virtio_queue_set_notification(n->tx_vq, 0);
+ virtio_queue_set_notification(n->tx_vq[0], 0);
return num_packets;
}
@@ -714,7 +721,7 @@ static int32_t virtio_net_flush_tx(VirtI
ret = qemu_sendv_packet_async(&n->nic->nc, out_sg, out_num,
virtio_net_tx_complete);
if (ret == 0) {
- virtio_queue_set_notification(n->tx_vq, 0);
+ virtio_queue_set_notification(n->tx_vq[0], 0);
n->async_tx.elem = elem;
n->async_tx.len = len;
return -EBUSY;
@@ -771,8 +778,8 @@ static void virtio_net_tx_timer(void *op
if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
return;
- virtio_queue_set_notification(n->tx_vq, 1);
- virtio_net_flush_tx(n, n->tx_vq);
+ virtio_queue_set_notification(n->tx_vq[0], 1);
+ virtio_net_flush_tx(n, n->tx_vq[0]);
}
static void virtio_net_tx_bh(void *opaque)
@@ -786,7 +793,7 @@ static void virtio_net_tx_bh(void *opaqu
if (unlikely(!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)))
return;
- ret = virtio_net_flush_tx(n, n->tx_vq);
+ ret = virtio_net_flush_tx(n, n->tx_vq[0]);
if (ret == -EBUSY) {
return; /* Notification re-enable handled by tx_complete */
}
@@ -802,9 +809,9 @@ static void virtio_net_tx_bh(void *opaqu
/* If less than a full burst, re-enable notification and flush
* anything that may have come in while we weren't looking. If
* we find something, assume the guest is still active and reschedule */
- virtio_queue_set_notification(n->tx_vq, 1);
- if (virtio_net_flush_tx(n, n->tx_vq) > 0) {
- virtio_queue_set_notification(n->tx_vq, 0);
+ virtio_queue_set_notification(n->tx_vq[0], 1);
+ if (virtio_net_flush_tx(n, n->tx_vq[0]) > 0) {
+ virtio_queue_set_notification(n->tx_vq[0], 0);
qemu_bh_schedule(n->tx_bh);
n->tx_waiting = 1;
}
@@ -820,6 +827,7 @@ static void virtio_net_save(QEMUFile *f,
virtio_save(&n->vdev, f);
qemu_put_buffer(f, n->mac, ETH_ALEN);
+ qemu_put_be16(f, n->numtxqs);
qemu_put_be32(f, n->tx_waiting);
qemu_put_be32(f, n->mergeable_rx_bufs);
qemu_put_be16(f, n->status);
@@ -849,6 +857,7 @@ static int virtio_net_load(QEMUFile *f,
virtio_load(&n->vdev, f);
qemu_get_buffer(f, n->mac, ETH_ALEN);
+ n->numtxqs = qemu_get_be32(f);
n->tx_waiting = qemu_get_be32(f);
n->mergeable_rx_bufs = qemu_get_be32(f);
@@ -966,11 +975,14 @@ VirtIODevice *virtio_net_init(DeviceStat
virtio_net_conf *net)
{
VirtIONet *n;
+ int i;
n = (VirtIONet *)virtio_common_init("virtio-net", VIRTIO_ID_NET,
sizeof(struct virtio_net_config),
sizeof(VirtIONet));
+ n->numtxqs = conf->peer->numtxqs;
+
n->vdev.get_config = virtio_net_get_config;
n->vdev.set_config = virtio_net_set_config;
n->vdev.get_features = virtio_net_get_features;
@@ -978,8 +990,8 @@ VirtIODevice *virtio_net_init(DeviceStat
n->vdev.bad_features = virtio_net_bad_features;
n->vdev.reset = virtio_net_reset;
n->vdev.set_status = virtio_net_set_status;
- n->rx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_rx);
+ n->rx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_rx);
if (net->tx && strcmp(net->tx, "timer") && strcmp(net->tx, "bh")) {
fprintf(stderr, "virtio-net: "
"Unknown option tx=%s, valid options: \"timer\" \"bh\"\n",
@@ -987,12 +999,21 @@ VirtIODevice *virtio_net_init(DeviceStat
fprintf(stderr, "Defaulting to \"bh\"\n");
}
+ /* Allocate per tx vq's */
+ n->tx_vq = qemu_mallocz(n->numtxqs * sizeof(*n->tx_vq));
+ for (i = 0; i < n->numtxqs; i++) {
+ if (net->tx && !strcmp(net->tx, "timer")) {
+ n->tx_vq[i] = virtio_add_queue(&n->vdev, 256,
+ virtio_net_handle_tx_timer);
+ } else {
+ n->tx_vq[i] = virtio_add_queue(&n->vdev, 256,
+ virtio_net_handle_tx_bh);
+ }
+ }
if (net->tx && !strcmp(net->tx, "timer")) {
- n->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx_timer);
n->tx_timer = qemu_new_timer(vm_clock, virtio_net_tx_timer, n);
n->tx_timeout = net->txtimer;
} else {
- n->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx_bh);
n->tx_bh = qemu_bh_new(virtio_net_tx_bh, n);
}
n->ctrl_vq = virtio_add_queue(&n->vdev, 64, virtio_net_handle_ctrl);
diff -ruNp org3/hw/virtio-net.h new3/hw/virtio-net.h
--- org3/hw/virtio-net.h 2010-09-28 10:07:31.000000000 +0530
+++ new3/hw/virtio-net.h 2010-10-19 19:46:52.000000000 +0530
@@ -44,6 +44,7 @@
#define VIRTIO_NET_F_CTRL_RX 18 /* Control channel RX mode support */
#define VIRTIO_NET_F_CTRL_VLAN 19 /* Control channel VLAN filtering */
#define VIRTIO_NET_F_CTRL_RX_EXTRA 20 /* Extra RX mode control support */
+#define VIRTIO_NET_F_NUMTXQS 21 /* Supports multiple TX queues */
#define VIRTIO_NET_S_LINK_UP 1 /* Link is up */
@@ -72,6 +73,7 @@ struct virtio_net_config
uint8_t mac[ETH_ALEN];
/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
uint16_t status;
+ uint16_t numtxqs; /* number of transmit queues */
} __attribute__((packed));
/* This is the first element of the scatter-gather list. If you don't
diff -ruNp org3/hw/virtio-pci.c new3/hw/virtio-pci.c
--- org3/hw/virtio-pci.c 2010-10-19 19:38:11.000000000 +0530
+++ new3/hw/virtio-pci.c 2010-10-19 19:46:52.000000000 +0530
@@ -99,6 +99,7 @@ typedef struct {
uint32_t addr;
uint32_t class_code;
uint32_t nvectors;
+ uint32_t mq;
BlockConf block;
NICConf nic;
uint32_t host_features;
@@ -788,6 +789,7 @@ static PCIDeviceInfo virtio_info[] = {
.romfile = "pxe-virtio.bin",
.qdev.props = (Property[]) {
DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3),
+ DEFINE_PROP_UINT32("mq", VirtIOPCIProxy, mq, 1),
DEFINE_VIRTIO_NET_FEATURES(VirtIOPCIProxy, host_features),
DEFINE_NIC_PROPERTIES(VirtIOPCIProxy, nic),
DEFINE_PROP_UINT32("x-txtimer", VirtIOPCIProxy,
diff -ruNp org3/net/tap.c new3/net/tap.c
--- org3/net/tap.c 2010-09-28 10:07:31.000000000 +0530
+++ new3/net/tap.c 2010-10-20 12:39:56.000000000 +0530
@@ -320,13 +320,14 @@ static NetClientInfo net_tap_info = {
static TAPState *net_tap_fd_init(VLANState *vlan,
const char *model,
const char *name,
- int fd,
+ int fd, int numtxqs,
int vnet_hdr)
{
VLANClientState *nc;
TAPState *s;
nc = qemu_new_net_client(&net_tap_info, vlan, NULL, model, name);
+ nc->numtxqs = numtxqs;
s = DO_UPCAST(TAPState, nc, nc);
@@ -424,6 +425,27 @@ int net_init_tap(QemuOpts *opts, Monitor
{
TAPState *s;
int fd, vnet_hdr = 0;
+ int vhost;
+ int numtxqs = 1;
+
+ vhost = qemu_opt_get_bool(opts, "vhost", 0);
+
+ /*
+ * We support multiple tx queues if:
+ * 1. smp > 1
+ * 2. vhost=on
+ * 3. mq=on
+ * In this case, #txqueues = #cpus. This value can be changed by
+ * using the "numtxqs" option.
+ */
+ if (vhost && smp_cpus > 1) {
+ if (qemu_opt_get_bool(opts, "mq", 0)) {
+#define VIRTIO_MAX_TXQS 32
+ int dflt = MIN(smp_cpus, VIRTIO_MAX_TXQS);
+
+ numtxqs = qemu_opt_get_number(opts, "numtxqs", dflt);
+ }
+ }
if (qemu_opt_get(opts, "fd")) {
if (qemu_opt_get(opts, "ifname") ||
@@ -457,7 +479,7 @@ int net_init_tap(QemuOpts *opts, Monitor
}
}
- s = net_tap_fd_init(vlan, "tap", name, fd, vnet_hdr);
+ s = net_tap_fd_init(vlan, "tap", name, fd, numtxqs, vnet_hdr);
if (!s) {
close(fd);
return -1;
@@ -486,7 +508,7 @@ int net_init_tap(QemuOpts *opts, Monitor
}
}
- if (qemu_opt_get_bool(opts, "vhost", !!qemu_opt_get(opts, "vhostfd"))) {
+ if (vhost) {
int vhostfd, r;
if (qemu_opt_get(opts, "vhostfd")) {
r = net_handle_fd_param(mon, qemu_opt_get(opts, "vhostfd"));
@@ -497,9 +519,13 @@ int net_init_tap(QemuOpts *opts, Monitor
} else {
vhostfd = -1;
}
- s->vhost_net = vhost_net_init(&s->nc, vhostfd);
+ s->vhost_net = vhost_net_init(&s->nc, vhostfd, numtxqs);
if (!s->vhost_net) {
error_report("vhost-net requested but could not be initialized");
+ if (numtxqs > 1) {
+ error_report("Need vhost support for numtxqs > 1, exiting...");
+ exit(1);
+ }
return -1;
}
} else if (qemu_opt_get(opts, "vhostfd")) {
diff -ruNp org3/net.c new3/net.c
--- org3/net.c 2010-10-19 19:38:11.000000000 +0530
+++ new3/net.c 2010-10-19 19:46:52.000000000 +0530
@@ -849,6 +849,15 @@ static int net_init_nic(QemuOpts *opts,
return -1;
}
+ if (nd->netdev->numtxqs > 1 && nd->nvectors == DEV_NVECTORS_UNSPECIFIED) {
+ /*
+ * User specified mq for guest, but no "vectors=", tune
+ * it automatically to 'numtxqs' TX + 1 RX + 1 controlq.
+ */
+ nd->nvectors = nd->netdev->numtxqs + 1 + 1;
+ monitor_printf(mon, "nvectors tuned to %d\n", nd->nvectors);
+ }
+
nd->used = 1;
nb_nics++;
@@ -992,6 +1001,14 @@ static const struct {
},
#ifndef _WIN32
{
+ .name = "mq",
+ .type = QEMU_OPT_BOOL,
+ .help = "enable multiqueue on network i/f",
+ }, {
+ .name = "numtxqs",
+ .type = QEMU_OPT_NUMBER,
+ .help = "optional number of TX queues, if mq is enabled",
+ }, {
.name = "fd",
.type = QEMU_OPT_STRING,
.help = "file descriptor of an already opened tap",
diff -ruNp org3/net.h new3/net.h
--- org3/net.h 2010-10-19 19:38:11.000000000 +0530
+++ new3/net.h 2010-10-19 19:46:52.000000000 +0530
@@ -62,6 +62,7 @@ struct VLANClientState {
struct VLANState *vlan;
VLANClientState *peer;
NetQueue *send_queue;
+ int numtxqs;
char *model;
char *name;
char info_str[256];
^ permalink raw reply
* [v3 RFC PATCH 3/4] Changes for vhost
From: Krishna Kumar @ 2010-10-20 8:55 UTC (permalink / raw)
To: rusty, davem, mst
Cc: arnd, eric.dumazet, netdev, avi, anthony, kvm, Krishna Kumar
In-Reply-To: <20101020085452.15579.76002.sendpatchset@krkumar2.in.ibm.com>
Changes for mq vhost.
vhost_net_open is changed to allocate a vhost_net and
return. The remaining initializations are delayed till
SET_OWNER. SET_OWNER is changed so that the argument
is used to determine how many txqs to use. Unmodified
qemu's will pass NULL, so this is recognized and handled
as numtxqs=1.
Besides changing handle_tx to use 'vq', this patch also
changes handle_rx to take vq as parameter. The mq RX
patch requires this change, but till then it is consistent
(and less confusing) to make the interfaces for handling
rx and tx similar.
vhost thread handling for RX and TX is as follows. The
first vhost thread handles RX traffic, while the remaining
threads handles TX. The number of threads is <= #txqs, and
threads handle more than one txq when #txqs is more than
MAX_VHOST_THREADS (4). When guest is started with >1 txqs
and there is only one stream of traffic from the guest,
that is recognized and handled such that vhost[0] processes
both RX and TX. This can change dynamically. vhost_poll
has a new element - find_vq(), which allows optimizing some
code for cases where numtxqs=1 or a packet on vhost[0]
needs processing.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
drivers/vhost/net.c | 284 ++++++++++++++++++++++++++--------------
drivers/vhost/vhost.c | 275 ++++++++++++++++++++++++++++----------
drivers/vhost/vhost.h | 42 +++++
3 files changed, 430 insertions(+), 171 deletions(-)
diff -ruNp org/drivers/vhost/vhost.h new/drivers/vhost/vhost.h
--- org/drivers/vhost/vhost.h 2010-10-11 10:21:14.000000000 +0530
+++ new/drivers/vhost/vhost.h 2010-10-20 14:11:23.000000000 +0530
@@ -35,11 +35,13 @@ struct vhost_poll {
wait_queue_t wait;
struct vhost_work work;
unsigned long mask;
- struct vhost_dev *dev;
+ struct vhost_virtqueue *(*find_vq)(struct vhost_poll *poll);
+ struct vhost_virtqueue *vq; /* points back to vq */
};
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
- unsigned long mask, struct vhost_dev *dev);
+ unsigned long mask, struct vhost_virtqueue *vq,
+ int single_queue);
void vhost_poll_start(struct vhost_poll *poll, struct file *file);
void vhost_poll_stop(struct vhost_poll *poll);
void vhost_poll_flush(struct vhost_poll *poll);
@@ -108,6 +110,10 @@ struct vhost_virtqueue {
/* Log write descriptors */
void __user *log_base;
struct vhost_log *log;
+ struct task_struct *worker; /* vhost for this vq, can be shared */
+ spinlock_t *work_lock;
+ struct list_head *work_list;
+ int qnum; /* 0 for RX, 1 -> n-1 for TX */
};
struct vhost_dev {
@@ -119,15 +125,39 @@ struct vhost_dev {
struct mutex mutex;
unsigned acked_features;
struct vhost_virtqueue *vqs;
+ unsigned long *jiffies;
int nvqs;
struct file *log_file;
struct eventfd_ctx *log_ctx;
- spinlock_t work_lock;
- struct list_head work_list;
- struct task_struct *worker;
+ spinlock_t *work_lock;
+ struct list_head *work_list;
};
-long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue *vqs, int nvqs);
+/*
+ * Define maximum number of TX threads, and use that to have a maximum
+ * number of vhost threads to handle RX & TX. First thread handles RX.
+ * If guest is started with #txqs=1, only one vhost thread is started.
+ * Else, upto MAX_VHOST_THREADS are started where th[0] handles RX and
+ * remaining handles TX. However, vhost_poll_queue has an optimization
+ * where th[0] is selected for both RX & TX if there is only one flow.
+ */
+#define MAX_TXQ_THREADS 4
+#define MAX_VHOST_THREADS (MAX_TXQ_THREADS + 1)
+
+static inline int get_nvhosts(int nvqs)
+{
+ int num_vhosts = nvqs - 1;
+
+ if (nvqs > 2)
+ num_vhosts = min_t(int, nvqs, MAX_VHOST_THREADS);
+
+ return num_vhosts;
+}
+
+int vhost_setup_vqs(struct vhost_dev *dev, int numtxqs);
+void vhost_free_vqs(struct vhost_dev *dev);
+long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue *vqs, int nvqs,
+ int nvhosts);
long vhost_dev_check_owner(struct vhost_dev *);
long vhost_dev_reset_owner(struct vhost_dev *);
void vhost_dev_cleanup(struct vhost_dev *);
diff -ruNp org/drivers/vhost/net.c new/drivers/vhost/net.c
--- org/drivers/vhost/net.c 2010-10-11 10:21:14.000000000 +0530
+++ new/drivers/vhost/net.c 2010-10-20 14:20:10.000000000 +0530
@@ -33,12 +33,6 @@
* Using this limit prevents one virtqueue from starving others. */
#define VHOST_NET_WEIGHT 0x80000
-enum {
- VHOST_NET_VQ_RX = 0,
- VHOST_NET_VQ_TX = 1,
- VHOST_NET_VQ_MAX = 2,
-};
-
enum vhost_net_poll_state {
VHOST_NET_POLL_DISABLED = 0,
VHOST_NET_POLL_STARTED = 1,
@@ -47,12 +41,13 @@ enum vhost_net_poll_state {
struct vhost_net {
struct vhost_dev dev;
- struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX];
- struct vhost_poll poll[VHOST_NET_VQ_MAX];
+ struct vhost_virtqueue *vqs;
+ struct vhost_poll *poll;
+ struct socket **socks;
/* Tells us whether we are polling a socket for TX.
* We only do this when socket buffer fills up.
* Protected by tx vq lock. */
- enum vhost_net_poll_state tx_poll_state;
+ enum vhost_net_poll_state *tx_poll_state;
};
/* Pop first len bytes from iovec. Return number of segments used. */
@@ -92,28 +87,28 @@ static void copy_iovec_hdr(const struct
}
/* Caller must have TX VQ lock */
-static void tx_poll_stop(struct vhost_net *net)
+static void tx_poll_stop(struct vhost_net *net, int qnum)
{
- if (likely(net->tx_poll_state != VHOST_NET_POLL_STARTED))
+ if (likely(net->tx_poll_state[qnum] != VHOST_NET_POLL_STARTED))
return;
- vhost_poll_stop(net->poll + VHOST_NET_VQ_TX);
- net->tx_poll_state = VHOST_NET_POLL_STOPPED;
+ vhost_poll_stop(&net->poll[qnum]);
+ net->tx_poll_state[qnum] = VHOST_NET_POLL_STOPPED;
}
/* Caller must have TX VQ lock */
-static void tx_poll_start(struct vhost_net *net, struct socket *sock)
+static void tx_poll_start(struct vhost_net *net, struct socket *sock, int qnum)
{
- if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED))
+ if (unlikely(net->tx_poll_state[qnum] != VHOST_NET_POLL_STOPPED))
return;
- vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file);
- net->tx_poll_state = VHOST_NET_POLL_STARTED;
+ vhost_poll_start(&net->poll[qnum], sock->file);
+ net->tx_poll_state[qnum] = VHOST_NET_POLL_STARTED;
}
/* 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)
+static void handle_tx(struct vhost_virtqueue *vq)
{
- struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
+ struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
unsigned out, in, s;
int head;
struct msghdr msg = {
@@ -134,7 +129,7 @@ static void handle_tx(struct vhost_net *
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
if (wmem >= sock->sk->sk_sndbuf) {
mutex_lock(&vq->mutex);
- tx_poll_start(net, sock);
+ tx_poll_start(net, sock, vq->qnum);
mutex_unlock(&vq->mutex);
return;
}
@@ -144,7 +139,7 @@ static void handle_tx(struct vhost_net *
vhost_disable_notify(vq);
if (wmem < sock->sk->sk_sndbuf / 2)
- tx_poll_stop(net);
+ tx_poll_stop(net, vq->qnum);
hdr_size = vq->vhost_hlen;
for (;;) {
@@ -159,7 +154,7 @@ static void handle_tx(struct vhost_net *
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);
+ tx_poll_start(net, sock, vq->qnum);
set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
break;
}
@@ -189,7 +184,7 @@ static void handle_tx(struct vhost_net *
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
vhost_discard_vq_desc(vq, 1);
- tx_poll_start(net, sock);
+ tx_poll_start(net, sock, vq->qnum);
break;
}
if (err != len)
@@ -282,9 +277,9 @@ err:
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
-static void handle_rx_big(struct vhost_net *net)
+static void handle_rx_big(struct vhost_virtqueue *vq,
+ struct vhost_net *net)
{
- struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
unsigned out, in, log, s;
int head;
struct vhost_log *vq_log;
@@ -393,9 +388,9 @@ static void handle_rx_big(struct vhost_n
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
-static void handle_rx_mergeable(struct vhost_net *net)
+static void handle_rx_mergeable(struct vhost_virtqueue *vq,
+ struct vhost_net *net)
{
- struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
unsigned uninitialized_var(in), log;
struct vhost_log *vq_log;
struct msghdr msg = {
@@ -500,96 +495,184 @@ static void handle_rx_mergeable(struct v
unuse_mm(net->dev.mm);
}
-static void handle_rx(struct vhost_net *net)
+static void handle_rx(struct vhost_virtqueue *vq)
{
+ struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
+
if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF))
- handle_rx_mergeable(net);
+ handle_rx_mergeable(vq, net);
else
- handle_rx_big(net);
+ handle_rx_big(vq, net);
}
static void handle_tx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
- struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
- handle_tx(net);
+ handle_tx(vq);
}
static void handle_rx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
- struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
- handle_rx(net);
+ handle_rx(vq);
}
static void handle_tx_net(struct vhost_work *work)
{
- struct vhost_net *net = container_of(work, struct vhost_net,
- poll[VHOST_NET_VQ_TX].work);
- handle_tx(net);
+ struct vhost_virtqueue *vq = container_of(work, struct vhost_poll,
+ work)->vq;
+
+ handle_tx(vq);
}
static void handle_rx_net(struct vhost_work *work)
{
- struct vhost_net *net = container_of(work, struct vhost_net,
- poll[VHOST_NET_VQ_RX].work);
- handle_rx(net);
+ struct vhost_virtqueue *vq = container_of(work, struct vhost_poll,
+ work)->vq;
+
+ handle_rx(vq);
}
-static int vhost_net_open(struct inode *inode, struct file *f)
+void vhost_free_vqs(struct vhost_dev *dev)
{
- struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
- struct vhost_dev *dev;
- int r;
+ struct vhost_net *n = container_of(dev, struct vhost_net, dev);
+
+ kfree(dev->work_list);
+ kfree(dev->work_lock);
+ kfree(dev->jiffies);
+ kfree(n->socks);
+ kfree(n->tx_poll_state);
+ kfree(n->poll);
+ kfree(n->vqs);
+
+ /*
+ * Reset so that vhost_net_release (after vhost_dev_set_owner call)
+ * will notice.
+ */
+ n->vqs = NULL;
+ n->poll = NULL;
+ n->socks = NULL;
+ n->tx_poll_state = NULL;
+ dev->jiffies = NULL;
+ dev->work_lock = NULL;
+ dev->work_list = NULL;
+}
+
+int vhost_setup_vqs(struct vhost_dev *dev, int numtxqs)
+{
+ struct vhost_net *n = container_of(dev, struct vhost_net, dev);
+ int nvhosts;
+ int i, nvqs;
+ int ret;
+
+ if (numtxqs < 0 || numtxqs > VIRTIO_MAX_SQ)
+ return -EINVAL;
+
+ if (numtxqs == 0) {
+ /* Old qemu doesn't pass arguments to set_owner, use 1 txq */
+ numtxqs = 1;
+ }
+
+ /* Get total number of virtqueues */
+ nvqs = numtxqs + 1;
+
+ /* Get total number of vhost threads */
+ nvhosts = get_nvhosts(nvqs);
+
+ n->vqs = kmalloc(nvqs * sizeof(*n->vqs), GFP_KERNEL);
+ n->poll = kmalloc(nvqs * sizeof(*n->poll), GFP_KERNEL);
+ n->socks = kmalloc(nvqs * sizeof(*n->socks), GFP_KERNEL);
+ n->tx_poll_state = kmalloc(nvqs * sizeof(*n->tx_poll_state),
+ GFP_KERNEL);
+ dev->jiffies = kzalloc(numtxqs * sizeof(*dev->jiffies), GFP_KERNEL);
+ dev->work_lock = kmalloc(nvhosts * sizeof(*dev->work_lock),
+ GFP_KERNEL);
+ dev->work_list = kmalloc(nvhosts * sizeof(*dev->work_list),
+ GFP_KERNEL);
+
+ if (!n->vqs || !n->poll || !n->socks || !n->tx_poll_state ||
+ !dev->jiffies || !dev->work_lock || !dev->work_list) {
+ ret = -ENOMEM;
+ goto err;
+ }
- if (!n)
- return -ENOMEM;
+ /* 1 RX, followed by 'numtxqs' TX queues */
+ n->vqs[0].handle_kick = handle_rx_kick;
- dev = &n->dev;
- n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
- n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
- r = vhost_dev_init(dev, n->vqs, VHOST_NET_VQ_MAX);
- if (r < 0) {
- kfree(n);
- return r;
- }
+ for (i = 1; i < nvqs; i++)
+ n->vqs[i].handle_kick = handle_tx_kick;
+
+ ret = vhost_dev_init(dev, n->vqs, nvqs, nvhosts);
+ if (ret < 0)
+ goto err;
- 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;
+ vhost_poll_init(&n->poll[0], handle_rx_net, POLLIN, &n->vqs[0], 1);
- f->private_data = n;
+ for (i = 1; i < nvqs; i++) {
+ vhost_poll_init(&n->poll[i], handle_tx_net, POLLOUT,
+ &n->vqs[i], (nvqs == 2));
+ n->tx_poll_state[i] = VHOST_NET_POLL_DISABLED;
+ }
return 0;
+
+err:
+ /* Free all pointers that may have been allocated */
+ vhost_free_vqs(dev);
+
+ return ret;
+}
+
+static int vhost_net_open(struct inode *inode, struct file *f)
+{
+ struct vhost_net *n = kzalloc(sizeof *n, GFP_KERNEL);
+ int ret = ENOMEM;
+
+ if (n) {
+ struct vhost_dev *dev = &n->dev;
+
+ f->private_data = n;
+ mutex_init(&dev->mutex);
+
+ /* Defer all other initialization till user does SET_OWNER */
+ ret = 0;
+ }
+
+ return ret;
}
static void vhost_net_disable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
+ int qnum = vq->qnum;
+
if (!vq->private_data)
return;
- if (vq == n->vqs + VHOST_NET_VQ_TX) {
- tx_poll_stop(n);
- n->tx_poll_state = VHOST_NET_POLL_DISABLED;
+ if (qnum) { /* TX */
+ tx_poll_stop(n, qnum);
+ n->tx_poll_state[qnum] = VHOST_NET_POLL_DISABLED;
} else
- vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
+ vhost_poll_stop(&n->poll[qnum]);
}
static void vhost_net_enable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock = vq->private_data;
+ int qnum = vq->qnum;
+
if (!sock)
return;
- if (vq == n->vqs + VHOST_NET_VQ_TX) {
- n->tx_poll_state = VHOST_NET_POLL_STOPPED;
- tx_poll_start(n, sock);
+
+ if (qnum) { /* TX */
+ n->tx_poll_state[qnum] = VHOST_NET_POLL_STOPPED;
+ tx_poll_start(n, sock, qnum);
} else
- vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
+ vhost_poll_start(&n->poll[qnum], sock->file);
}
static struct socket *vhost_net_stop_vq(struct vhost_net *n,
@@ -605,11 +688,12 @@ static struct socket *vhost_net_stop_vq(
return sock;
}
-static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
- struct socket **rx_sock)
+static void vhost_net_stop(struct vhost_net *n)
{
- *tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
- *rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
+ int i;
+
+ for (i = n->dev.nvqs - 1; i >= 0; i--)
+ n->socks[i] = vhost_net_stop_vq(n, &n->vqs[i]);
}
static void vhost_net_flush_vq(struct vhost_net *n, int index)
@@ -620,26 +704,33 @@ static void vhost_net_flush_vq(struct vh
static void vhost_net_flush(struct vhost_net *n)
{
- vhost_net_flush_vq(n, VHOST_NET_VQ_TX);
- vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
+ int i;
+
+ for (i = n->dev.nvqs - 1; i >= 0; i--)
+ vhost_net_flush_vq(n, i);
}
static int vhost_net_release(struct inode *inode, struct file *f)
{
struct vhost_net *n = f->private_data;
- struct socket *tx_sock;
- struct socket *rx_sock;
+ struct vhost_dev *dev = &n->dev;
+ int i;
- vhost_net_stop(n, &tx_sock, &rx_sock);
+ vhost_net_stop(n);
vhost_net_flush(n);
- vhost_dev_cleanup(&n->dev);
- if (tx_sock)
- fput(tx_sock->file);
- if (rx_sock)
- fput(rx_sock->file);
+ vhost_dev_cleanup(dev);
+
+ for (i = n->dev.nvqs - 1; i >= 0; i--)
+ if (n->socks[i])
+ fput(n->socks[i]->file);
+
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_net_flush(n);
+
+ /* Free all old pointers */
+ vhost_free_vqs(dev);
+
kfree(n);
return 0;
}
@@ -717,7 +808,7 @@ static long vhost_net_set_backend(struct
if (r)
goto err;
- if (index >= VHOST_NET_VQ_MAX) {
+ if (index >= n->dev.nvqs) {
r = -ENOBUFS;
goto err;
}
@@ -738,9 +829,9 @@ static long vhost_net_set_backend(struct
/* start polling new socket */
oldsock = vq->private_data;
if (sock != oldsock) {
- vhost_net_disable_vq(n, vq);
- rcu_assign_pointer(vq->private_data, sock);
- vhost_net_enable_vq(n, vq);
+ vhost_net_disable_vq(n, vq);
+ rcu_assign_pointer(vq->private_data, sock);
+ vhost_net_enable_vq(n, vq);
}
mutex_unlock(&vq->mutex);
@@ -762,22 +853,25 @@ err:
static long vhost_net_reset_owner(struct vhost_net *n)
{
- struct socket *tx_sock = NULL;
- struct socket *rx_sock = NULL;
long err;
+ int i;
+
mutex_lock(&n->dev.mutex);
err = vhost_dev_check_owner(&n->dev);
- if (err)
- goto done;
- vhost_net_stop(n, &tx_sock, &rx_sock);
+ if (err) {
+ mutex_unlock(&n->dev.mutex);
+ return err;
+ }
+
+ vhost_net_stop(n);
vhost_net_flush(n);
err = vhost_dev_reset_owner(&n->dev);
-done:
mutex_unlock(&n->dev.mutex);
- if (tx_sock)
- fput(tx_sock->file);
- if (rx_sock)
- fput(rx_sock->file);
+
+ for (i = n->dev.nvqs - 1; i >= 0; i--)
+ if (n->socks[i])
+ fput(n->socks[i]->file);
+
return err;
}
@@ -806,7 +900,7 @@ static int vhost_net_set_features(struct
}
n->dev.acked_features = features;
smp_wmb();
- for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
+ for (i = 0; i < n->dev.nvqs; ++i) {
mutex_lock(&n->vqs[i].mutex);
n->vqs[i].vhost_hlen = vhost_hlen;
n->vqs[i].sock_hlen = sock_hlen;
diff -ruNp org/drivers/vhost/vhost.c new/drivers/vhost/vhost.c
--- org/drivers/vhost/vhost.c 2010-10-11 10:21:14.000000000 +0530
+++ new/drivers/vhost/vhost.c 2010-10-20 14:20:04.000000000 +0530
@@ -69,16 +69,70 @@ static void vhost_work_init(struct vhost
work->queue_seq = work->done_seq = 0;
}
+/*
+ * __vhost_sq_find_vq: This is the poll->find_vq() handler for cases:
+ * - #numtxqs == 1; or
+ * - this is an RX vq
+ */
+static struct vhost_virtqueue *__vhost_sq_find_vq(struct vhost_poll *poll)
+{
+ return poll->vq;
+}
+
+/* Define how recently a txq was used, beyond this it is considered unused */
+#define RECENTLY_USED 5
+
+/*
+ * __vhost_mq_find_vq: This is the poll->find_vq() handler for cases:
+ * - #numtxqs > 1, and
+ * - this is a TX vq
+ *
+ * Algorithm for selecting vq:
+ *
+ * Condition: Return:
+ * If all txqs unused vq[0]
+ * If one txq used, and new txq is same vq[0]
+ * If one txq used, and new txq is different vq[vq->qnum]
+ * If > 1 txqs used vq[vq->qnum]
+ * Where "used" means the txq was used in the last RECENTLY_USED jiffies.
+ *
+ * Note: locking is not required as an update race will only result in
+ * a different worker being woken up.
+ */
+static struct vhost_virtqueue *__vhost_mq_find_vq(struct vhost_poll *poll)
+{
+ struct vhost_dev *dev = poll->vq->dev;
+ struct vhost_virtqueue *vq = &dev->vqs[0];
+ unsigned long max_time = jiffies - RECENTLY_USED;
+ unsigned long *table = dev->jiffies;
+ int i, used = 0;
+
+ for (i = 0; i < dev->nvqs - 1; i++) {
+ if (time_after_eq(table[i], max_time) && ++used > 1) {
+ vq = poll->vq;
+ break;
+ }
+ }
+
+ table[poll->vq->qnum - 1] = jiffies;
+ return vq;
+}
+
/* Init poll structure */
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
- unsigned long mask, struct vhost_dev *dev)
+ unsigned long mask, struct vhost_virtqueue *vq,
+ int single_queue)
{
init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
init_poll_funcptr(&poll->table, vhost_poll_func);
poll->mask = mask;
- poll->dev = dev;
+ poll->vq = vq;
vhost_work_init(&poll->work, fn);
+ if (single_queue)
+ poll->find_vq = __vhost_sq_find_vq;
+ else
+ poll->find_vq = __vhost_mq_find_vq;
}
/* Start polling a file. We add ourselves to file's wait queue. The caller must
@@ -98,25 +152,25 @@ void vhost_poll_stop(struct vhost_poll *
remove_wait_queue(poll->wqh, &poll->wait);
}
-static void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work)
+static void vhost_work_flush(struct vhost_poll *poll, struct vhost_work *work)
{
unsigned seq;
int left;
int flushing;
- spin_lock_irq(&dev->work_lock);
+ spin_lock_irq(poll->vq->work_lock);
seq = work->queue_seq;
work->flushing++;
- spin_unlock_irq(&dev->work_lock);
+ spin_unlock_irq(poll->vq->work_lock);
wait_event(work->done, ({
- spin_lock_irq(&dev->work_lock);
+ spin_lock_irq(poll->vq->work_lock);
left = seq - work->done_seq <= 0;
- spin_unlock_irq(&dev->work_lock);
+ spin_unlock_irq(poll->vq->work_lock);
left;
}));
- spin_lock_irq(&dev->work_lock);
+ spin_lock_irq(poll->vq->work_lock);
flushing = --work->flushing;
- spin_unlock_irq(&dev->work_lock);
+ spin_unlock_irq(poll->vq->work_lock);
BUG_ON(flushing < 0);
}
@@ -124,26 +178,28 @@ static void vhost_work_flush(struct vhos
* locks that are also used by the callback. */
void vhost_poll_flush(struct vhost_poll *poll)
{
- vhost_work_flush(poll->dev, &poll->work);
+ vhost_work_flush(poll, &poll->work);
}
-static inline void vhost_work_queue(struct vhost_dev *dev,
+static inline void vhost_work_queue(struct vhost_virtqueue *vq,
struct vhost_work *work)
{
unsigned long flags;
- spin_lock_irqsave(&dev->work_lock, flags);
+ spin_lock_irqsave(vq->work_lock, flags);
if (list_empty(&work->node)) {
- list_add_tail(&work->node, &dev->work_list);
+ list_add_tail(&work->node, vq->work_list);
work->queue_seq++;
- wake_up_process(dev->worker);
+ wake_up_process(vq->worker);
}
- spin_unlock_irqrestore(&dev->work_lock, flags);
+ spin_unlock_irqrestore(vq->work_lock, flags);
}
void vhost_poll_queue(struct vhost_poll *poll)
{
- vhost_work_queue(poll->dev, &poll->work);
+ struct vhost_virtqueue *vq = poll->find_vq(poll);
+
+ vhost_work_queue(vq, &poll->work);
}
static void vhost_vq_reset(struct vhost_dev *dev,
@@ -174,7 +230,7 @@ static void vhost_vq_reset(struct vhost_
static int vhost_worker(void *data)
{
- struct vhost_dev *dev = data;
+ struct vhost_virtqueue *vq = data;
struct vhost_work *work = NULL;
unsigned uninitialized_var(seq);
@@ -182,7 +238,7 @@ static int vhost_worker(void *data)
/* mb paired w/ kthread_stop */
set_current_state(TASK_INTERRUPTIBLE);
- spin_lock_irq(&dev->work_lock);
+ spin_lock_irq(vq->work_lock);
if (work) {
work->done_seq = seq;
if (work->flushing)
@@ -190,18 +246,18 @@ static int vhost_worker(void *data)
}
if (kthread_should_stop()) {
- spin_unlock_irq(&dev->work_lock);
+ spin_unlock_irq(vq->work_lock);
__set_current_state(TASK_RUNNING);
return 0;
}
- if (!list_empty(&dev->work_list)) {
- work = list_first_entry(&dev->work_list,
+ if (!list_empty(vq->work_list)) {
+ work = list_first_entry(vq->work_list,
struct vhost_work, node);
list_del_init(&work->node);
seq = work->queue_seq;
} else
work = NULL;
- spin_unlock_irq(&dev->work_lock);
+ spin_unlock_irq(vq->work_lock);
if (work) {
__set_current_state(TASK_RUNNING);
@@ -251,8 +307,19 @@ static void vhost_dev_free_iovecs(struct
}
}
+/* Get index of an existing thread that will handle this txq */
+static int vhost_get_buddy_thread(int index, int nvhosts)
+{
+ int buddy = 0;
+
+ if (nvhosts > 1)
+ buddy = (index - 1) % MAX_TXQ_THREADS + 1;
+
+ return buddy;
+}
+
long vhost_dev_init(struct vhost_dev *dev,
- struct vhost_virtqueue *vqs, int nvqs)
+ struct vhost_virtqueue *vqs, int nvqs, int nvhosts)
{
int i;
@@ -263,20 +330,37 @@ long vhost_dev_init(struct vhost_dev *de
dev->log_file = NULL;
dev->memory = NULL;
dev->mm = NULL;
- spin_lock_init(&dev->work_lock);
- INIT_LIST_HEAD(&dev->work_list);
- dev->worker = NULL;
for (i = 0; i < dev->nvqs; ++i) {
- dev->vqs[i].log = NULL;
- dev->vqs[i].indirect = NULL;
- dev->vqs[i].heads = NULL;
- dev->vqs[i].dev = dev;
- mutex_init(&dev->vqs[i].mutex);
+ struct vhost_virtqueue *vq = &dev->vqs[i];
+ int single_queue = (!i || dev->nvqs == 2);
+
+ if (i < nvhosts) {
+ spin_lock_init(&dev->work_lock[i]);
+ INIT_LIST_HEAD(&dev->work_list[i]);
+
+ vq->work_lock = &dev->work_lock[i];
+ vq->work_list = &dev->work_list[i];
+ } else {
+ /* Share work with another thread */
+ int j = vhost_get_buddy_thread(i, nvhosts);
+
+ vq->work_lock = &dev->work_lock[j];
+ vq->work_list = &dev->work_list[j];
+ }
+
+ vq->worker = NULL;
+ vq->qnum = i;
+ vq->log = NULL;
+ vq->indirect = NULL;
+ vq->heads = NULL;
+ vq->dev = dev;
+ mutex_init(&vq->mutex);
vhost_vq_reset(dev, dev->vqs + i);
- if (dev->vqs[i].handle_kick)
- vhost_poll_init(&dev->vqs[i].poll,
- dev->vqs[i].handle_kick, POLLIN, dev);
+ if (vq->handle_kick)
+ vhost_poll_init(&vq->poll,
+ vq->handle_kick, POLLIN, vq,
+ single_queue);
}
return 0;
@@ -290,61 +374,116 @@ long vhost_dev_check_owner(struct vhost_
}
struct vhost_attach_cgroups_struct {
- struct vhost_work work;
- struct task_struct *owner;
- int ret;
+ struct vhost_work work;
+ struct task_struct *owner;
+ int ret;
};
static void vhost_attach_cgroups_work(struct vhost_work *work)
{
- struct vhost_attach_cgroups_struct *s;
- s = container_of(work, struct vhost_attach_cgroups_struct, work);
- s->ret = cgroup_attach_task_all(s->owner, current);
+ struct vhost_attach_cgroups_struct *s;
+ s = container_of(work, struct vhost_attach_cgroups_struct, work);
+ s->ret = cgroup_attach_task_all(s->owner, current);
}
-static int vhost_attach_cgroups(struct vhost_dev *dev)
-{
- struct vhost_attach_cgroups_struct attach;
- attach.owner = current;
- vhost_work_init(&attach.work, vhost_attach_cgroups_work);
- vhost_work_queue(dev, &attach.work);
- vhost_work_flush(dev, &attach.work);
- return attach.ret;
+static int vhost_attach_cgroups(struct vhost_virtqueue *vq)
+{
+ struct vhost_attach_cgroups_struct attach;
+ attach.owner = current;
+ vhost_work_init(&attach.work, vhost_attach_cgroups_work);
+ vhost_work_queue(vq, &attach.work);
+ vhost_work_flush(&vq->poll, &attach.work);
+ return attach.ret;
+}
+
+static void __vhost_stop_workers(struct vhost_dev *dev, int nvhosts)
+{
+ int i;
+
+ for (i = 0; i < nvhosts; i++) {
+ WARN_ON(!list_empty(dev->vqs[i].work_list));
+ if (dev->vqs[i].worker) {
+ kthread_stop(dev->vqs[i].worker);
+ dev->vqs[i].worker = NULL;
+ }
+ }
+}
+
+static void vhost_stop_workers(struct vhost_dev *dev)
+{
+ __vhost_stop_workers(dev, get_nvhosts(dev->nvqs));
+}
+
+static int vhost_start_workers(struct vhost_dev *dev)
+{
+ int nvhosts = get_nvhosts(dev->nvqs);
+ int i, err;
+
+ for (i = 0; i < dev->nvqs; ++i) {
+ struct vhost_virtqueue *vq = &dev->vqs[i];
+
+ if (i < nvhosts) {
+ /* Start a new thread */
+ vq->worker = kthread_create(vhost_worker, vq,
+ "vhost-%d-%d",
+ current->pid, i);
+ if (IS_ERR(vq->worker)) {
+ i--; /* no thread to clean at this index */
+ err = PTR_ERR(vq->worker);
+ goto err;
+ }
+
+ wake_up_process(vq->worker);
+
+ /* avoid contributing to loadavg */
+ err = vhost_attach_cgroups(vq);
+ if (err)
+ goto err;
+ } else {
+ /* Share work with an existing thread */
+ int j = vhost_get_buddy_thread(i, nvhosts);
+ struct vhost_virtqueue *share_vq = &dev->vqs[j];
+
+ vq->worker = share_vq->worker;
+ }
+ }
+ return 0;
+
+err:
+ __vhost_stop_workers(dev, i);
+ return err;
}
/* Caller should have device mutex */
-static long vhost_dev_set_owner(struct vhost_dev *dev)
+static long vhost_dev_set_owner(struct vhost_dev *dev, int numtxqs)
{
- struct task_struct *worker;
int err;
/* Is there an owner already? */
if (dev->mm) {
err = -EBUSY;
goto err_mm;
}
+
+ err = vhost_setup_vqs(dev, numtxqs);
+ if (err)
+ goto err_mm;
+
/* No owner, become one */
dev->mm = get_task_mm(current);
- worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
- if (IS_ERR(worker)) {
- err = PTR_ERR(worker);
- goto err_worker;
- }
-
- dev->worker = worker;
- wake_up_process(worker); /* avoid contributing to loadavg */
- err = vhost_attach_cgroups(dev);
+ /* Start threads */
+ err = vhost_start_workers(dev);
if (err)
- goto err_cgroup;
+ goto err_worker;
err = vhost_dev_alloc_iovecs(dev);
if (err)
- goto err_cgroup;
+ goto err_iovec;
return 0;
-err_cgroup:
- kthread_stop(worker);
- dev->worker = NULL;
+err_iovec:
+ vhost_stop_workers(dev);
+ vhost_free_vqs(dev);
err_worker:
if (dev->mm)
mmput(dev->mm);
@@ -405,11 +544,7 @@ void vhost_dev_cleanup(struct vhost_dev
mmput(dev->mm);
dev->mm = NULL;
- WARN_ON(!list_empty(&dev->work_list));
- if (dev->worker) {
- kthread_stop(dev->worker);
- dev->worker = NULL;
- }
+ vhost_stop_workers(dev);
}
static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
@@ -760,7 +895,7 @@ long vhost_dev_ioctl(struct vhost_dev *d
/* If you are not the owner, you can become one */
if (ioctl == VHOST_SET_OWNER) {
- r = vhost_dev_set_owner(d);
+ r = vhost_dev_set_owner(d, arg);
goto done;
}
^ permalink raw reply
* [v3 RFC PATCH 1/4] Change virtqueue structure
From: Krishna Kumar @ 2010-10-20 8:54 UTC (permalink / raw)
To: rusty, davem, mst
Cc: eric.dumazet, kvm, netdev, arnd, avi, anthony, Krishna Kumar
In-Reply-To: <20101020085452.15579.76002.sendpatchset@krkumar2.in.ibm.com>
Move queue_index from virtio_pci_vq_info to virtqueue. This
allows callback handlers to figure out the queue number for
the vq that needs attention.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
drivers/virtio/virtio_pci.c | 10 +++-------
include/linux/virtio.h | 1 +
2 files changed, 4 insertions(+), 7 deletions(-)
diff -ruNp org/include/linux/virtio.h new.dynamic.optimize_vhost/include/linux/virtio.h
--- org/include/linux/virtio.h 2010-10-11 10:20:22.000000000 +0530
+++ new.dynamic.optimize_vhost/include/linux/virtio.h 2010-10-15 13:25:42.000000000 +0530
@@ -22,6 +22,7 @@ struct virtqueue {
void (*callback)(struct virtqueue *vq);
const char *name;
struct virtio_device *vdev;
+ int queue_index; /* the index of the queue */
void *priv;
};
diff -ruNp org/drivers/virtio/virtio_pci.c new.dynamic.optimize_vhost/drivers/virtio/virtio_pci.c
--- org/drivers/virtio/virtio_pci.c 2010-10-11 10:20:15.000000000 +0530
+++ new.dynamic.optimize_vhost/drivers/virtio/virtio_pci.c 2010-10-15 13:25:42.000000000 +0530
@@ -75,9 +75,6 @@ struct virtio_pci_vq_info
/* the number of entries in the queue */
int num;
- /* the index of the queue */
- int queue_index;
-
/* the virtual address of the ring queue */
void *queue;
@@ -185,11 +182,10 @@ static void vp_reset(struct virtio_devic
static void vp_notify(struct virtqueue *vq)
{
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
- struct virtio_pci_vq_info *info = vq->priv;
/* we write the queue's selector into the notification register to
* signal the other end */
- iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+ iowrite16(vq->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
}
/* Handle a configuration change: Tell driver if it wants to know. */
@@ -385,7 +381,6 @@ static struct virtqueue *setup_vq(struct
if (!info)
return ERR_PTR(-ENOMEM);
- info->queue_index = index;
info->num = num;
info->msix_vector = msix_vec;
@@ -408,6 +403,7 @@ static struct virtqueue *setup_vq(struct
goto out_activate_queue;
}
+ vq->queue_index = index;
vq->priv = info;
info->vq = vq;
@@ -446,7 +442,7 @@ static void vp_del_vq(struct virtqueue *
list_del(&info->node);
spin_unlock_irqrestore(&vp_dev->lock, flags);
- iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+ iowrite16(vq->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
if (vp_dev->msix_enabled) {
iowrite16(VIRTIO_MSI_NO_VECTOR,
^ permalink raw reply
* [v3 RFC PATCH 2/4] Changes for virtio-net
From: Krishna Kumar @ 2010-10-20 8:55 UTC (permalink / raw)
To: rusty, davem, mst
Cc: kvm, arnd, netdev, avi, anthony, eric.dumazet, Krishna Kumar
In-Reply-To: <20101020085452.15579.76002.sendpatchset@krkumar2.in.ibm.com>
Implement mq virtio-net driver.
Though struct virtio_net_config changes, it works with old
qemu's since the last element is not accessed, unless qemu
sets VIRTIO_NET_F_NUMTXQS. Patch also adds a macro for the
maximum number of TX vq's (VIRTIO_MAX_SQ) that the user can
specify.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
drivers/net/virtio_net.c | 234 ++++++++++++++++++++++++++---------
include/linux/virtio_net.h | 6
2 files changed, 185 insertions(+), 55 deletions(-)
diff -ruNp org/include/linux/virtio_net.h new.dynamic.optimize_vhost/include/linux/virtio_net.h
--- org/include/linux/virtio_net.h 2010-10-11 10:20:22.000000000 +0530
+++ new.dynamic.optimize_vhost/include/linux/virtio_net.h 2010-10-19 13:24:38.000000000 +0530
@@ -7,6 +7,9 @@
#include <linux/virtio_config.h>
#include <linux/if_ether.h>
+/* Maximum number of TX queues supported */
+#define VIRTIO_MAX_SQ 32
+
/* The feature bitmap for virtio net */
#define VIRTIO_NET_F_CSUM 0 /* Host handles pkts w/ partial csum */
#define VIRTIO_NET_F_GUEST_CSUM 1 /* Guest handles pkts w/ partial csum */
@@ -26,6 +29,7 @@
#define VIRTIO_NET_F_CTRL_RX 18 /* Control channel RX mode support */
#define VIRTIO_NET_F_CTRL_VLAN 19 /* Control channel VLAN filtering */
#define VIRTIO_NET_F_CTRL_RX_EXTRA 20 /* Extra RX mode control support */
+#define VIRTIO_NET_F_NUMTXQS 21 /* Device supports multiple TX queue */
#define VIRTIO_NET_S_LINK_UP 1 /* Link is up */
@@ -34,6 +38,8 @@ struct virtio_net_config {
__u8 mac[6];
/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
__u16 status;
+ /* number of transmit queues */
+ __u16 numtxqs;
} __attribute__((packed));
/* This is the first element of the scatter-gather list. If you don't
diff -ruNp org/drivers/net/virtio_net.c new.dynamic.optimize_vhost/drivers/net/virtio_net.c
--- org/drivers/net/virtio_net.c 2010-10-11 10:20:02.000000000 +0530
+++ new.dynamic.optimize_vhost/drivers/net/virtio_net.c 2010-10-19 17:01:53.000000000 +0530
@@ -40,11 +40,24 @@ module_param(gso, bool, 0444);
#define VIRTNET_SEND_COMMAND_SG_MAX 2
+/* Our representation of a send virtqueue */
+struct send_queue {
+ struct virtqueue *svq;
+
+ /* TX: fragments + linear part + virtio header */
+ struct scatterlist tx_sg[MAX_SKB_FRAGS + 2];
+};
+
struct virtnet_info {
+ struct send_queue **sq;
+ struct napi_struct napi ____cacheline_aligned_in_smp;
+
+ /* read-mostly variables */
+ int numtxqs ____cacheline_aligned_in_smp;
struct virtio_device *vdev;
- struct virtqueue *rvq, *svq, *cvq;
+ struct virtqueue *rvq;
+ struct virtqueue *cvq;
struct net_device *dev;
- struct napi_struct napi;
unsigned int status;
/* Number of input buffers, and max we've ever had. */
@@ -62,9 +75,8 @@ struct virtnet_info {
/* Chain pages by the private ptr. */
struct page *pages;
- /* fragments + linear part + virtio header */
+ /* RX: fragments + linear part + virtio header */
struct scatterlist rx_sg[MAX_SKB_FRAGS + 2];
- struct scatterlist tx_sg[MAX_SKB_FRAGS + 2];
};
struct skb_vnet_hdr {
@@ -120,12 +132,13 @@ static struct page *get_a_page(struct vi
static void skb_xmit_done(struct virtqueue *svq)
{
struct virtnet_info *vi = svq->vdev->priv;
+ int qnum = svq->queue_index - 1; /* 0 is RX vq */
/* Suppress further interrupts. */
virtqueue_disable_cb(svq);
/* We were probably waiting for more output buffers. */
- netif_wake_queue(vi->dev);
+ netif_wake_subqueue(vi->dev, qnum);
}
static void set_skb_frag(struct sk_buff *skb, struct page *page,
@@ -495,12 +508,13 @@ again:
return received;
}
-static unsigned int free_old_xmit_skbs(struct virtnet_info *vi)
+static unsigned int free_old_xmit_skbs(struct virtnet_info *vi,
+ struct virtqueue *svq)
{
struct sk_buff *skb;
unsigned int len, tot_sgs = 0;
- while ((skb = virtqueue_get_buf(vi->svq, &len)) != NULL) {
+ while ((skb = virtqueue_get_buf(svq, &len)) != NULL) {
pr_debug("Sent skb %p\n", skb);
vi->dev->stats.tx_bytes += skb->len;
vi->dev->stats.tx_packets++;
@@ -510,7 +524,8 @@ static unsigned int free_old_xmit_skbs(s
return tot_sgs;
}
-static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
+static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb,
+ struct virtqueue *svq, struct scatterlist *tx_sg)
{
struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
@@ -548,12 +563,12 @@ static int xmit_skb(struct virtnet_info
/* Encode metadata header at front. */
if (vi->mergeable_rx_bufs)
- sg_set_buf(vi->tx_sg, &hdr->mhdr, sizeof hdr->mhdr);
+ sg_set_buf(tx_sg, &hdr->mhdr, sizeof hdr->mhdr);
else
- sg_set_buf(vi->tx_sg, &hdr->hdr, sizeof hdr->hdr);
+ sg_set_buf(tx_sg, &hdr->hdr, sizeof hdr->hdr);
- hdr->num_sg = skb_to_sgvec(skb, vi->tx_sg + 1, 0, skb->len) + 1;
- return virtqueue_add_buf(vi->svq, vi->tx_sg, hdr->num_sg,
+ hdr->num_sg = skb_to_sgvec(skb, tx_sg + 1, 0, skb->len) + 1;
+ return virtqueue_add_buf(svq, tx_sg, hdr->num_sg,
0, skb);
}
@@ -561,31 +576,34 @@ static netdev_tx_t start_xmit(struct sk_
{
struct virtnet_info *vi = netdev_priv(dev);
int capacity;
+ int qnum = skb_get_queue_mapping(skb);
+ struct virtqueue *svq = vi->sq[qnum]->svq;
/* Free up any pending old buffers before queueing new ones. */
- free_old_xmit_skbs(vi);
+ free_old_xmit_skbs(vi, svq);
/* Try to transmit */
- capacity = xmit_skb(vi, skb);
+ capacity = xmit_skb(vi, skb, svq, vi->sq[qnum]->tx_sg);
/* This can happen with OOM and indirect buffers. */
if (unlikely(capacity < 0)) {
if (net_ratelimit()) {
if (likely(capacity == -ENOMEM)) {
dev_warn(&dev->dev,
- "TX queue failure: out of memory\n");
+ "TXQ (%d) failure: out of memory\n",
+ qnum);
} else {
dev->stats.tx_fifo_errors++;
dev_warn(&dev->dev,
- "Unexpected TX queue failure: %d\n",
- capacity);
+ "Unexpected TXQ (%d) failure: %d\n",
+ qnum, capacity);
}
}
dev->stats.tx_dropped++;
kfree_skb(skb);
return NETDEV_TX_OK;
}
- virtqueue_kick(vi->svq);
+ virtqueue_kick(svq);
/* Don't wait up for transmitted skbs to be freed. */
skb_orphan(skb);
@@ -594,13 +612,13 @@ static netdev_tx_t start_xmit(struct sk_
/* Apparently nice girls don't return TX_BUSY; stop the queue
* before it gets out of hand. Naturally, this wastes entries. */
if (capacity < 2+MAX_SKB_FRAGS) {
- netif_stop_queue(dev);
- if (unlikely(!virtqueue_enable_cb(vi->svq))) {
+ netif_stop_subqueue(dev, qnum);
+ if (unlikely(!virtqueue_enable_cb(svq))) {
/* More just got used, free them then recheck. */
- capacity += free_old_xmit_skbs(vi);
+ capacity += free_old_xmit_skbs(vi, svq);
if (capacity >= 2+MAX_SKB_FRAGS) {
- netif_start_queue(dev);
- virtqueue_disable_cb(vi->svq);
+ netif_start_subqueue(dev, qnum);
+ virtqueue_disable_cb(svq);
}
}
}
@@ -871,10 +889,10 @@ static void virtnet_update_status(struct
if (vi->status & VIRTIO_NET_S_LINK_UP) {
netif_carrier_on(vi->dev);
- netif_wake_queue(vi->dev);
+ netif_tx_wake_all_queues(vi->dev);
} else {
netif_carrier_off(vi->dev);
- netif_stop_queue(vi->dev);
+ netif_tx_stop_all_queues(vi->dev);
}
}
@@ -885,18 +903,122 @@ static void virtnet_config_changed(struc
virtnet_update_status(vi);
}
+#define MAX_DEVICE_NAME 16
+static int initialize_vqs(struct virtnet_info *vi, int numtxqs)
+{
+ vq_callback_t **callbacks;
+ struct virtqueue **vqs;
+ int i, err = -ENOMEM;
+ int totalvqs;
+ char **names;
+
+ vi->sq = kzalloc(numtxqs * sizeof(*vi->sq), GFP_KERNEL);
+ if (!vi->sq)
+ goto out;
+ for (i = 0; i < numtxqs; i++) {
+ vi->sq[i] = kzalloc(sizeof(*vi->sq[i]), GFP_KERNEL);
+ if (!vi->sq[i])
+ goto out;
+ }
+
+ /* setup initial send queue parameters */
+ for (i = 0; i < numtxqs; i++)
+ sg_init_table(vi->sq[i]->tx_sg, ARRAY_SIZE(vi->sq[i]->tx_sg));
+
+ /*
+ * We expect 1 RX virtqueue followed by 'numtxqs' TX virtqueues, and
+ * optionally one control virtqueue.
+ */
+ totalvqs = 1 + numtxqs +
+ virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ);
+
+ /* Setup parameters for find_vqs */
+ vqs = kmalloc(totalvqs * sizeof(*vqs), GFP_KERNEL);
+ callbacks = kmalloc(totalvqs * sizeof(*callbacks), GFP_KERNEL);
+ names = kzalloc(totalvqs * sizeof(*names), GFP_KERNEL);
+ if (!vqs || !callbacks || !names)
+ goto free_mem;
+
+ /* Parameters for recv virtqueue */
+ callbacks[0] = skb_recv_done;
+ names[0] = "input";
+
+ /* Parameters for send virtqueues */
+ for (i = 1; i <= numtxqs; i++) {
+ callbacks[i] = skb_xmit_done;
+ names[i] = kmalloc(MAX_DEVICE_NAME * sizeof(*names[i]),
+ GFP_KERNEL);
+ if (!names[i])
+ goto free_mem;
+ sprintf(names[i], "output.%d", i - 1);
+ }
+
+ /* Parameters for control virtqueue, if any */
+ if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
+ callbacks[i] = NULL;
+ names[i] = "control";
+ }
+
+ err = vi->vdev->config->find_vqs(vi->vdev, totalvqs, vqs, callbacks,
+ (const char **)names);
+ if (err)
+ goto free_mem;
+
+ vi->rvq = vqs[0];
+ for (i = 0; i < numtxqs; i++)
+ vi->sq[i]->svq = vqs[i + 1];
+
+ if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
+ vi->cvq = vqs[i + 1];
+
+ if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
+ vi->dev->features |= NETIF_F_HW_VLAN_FILTER;
+ }
+
+free_mem:
+ if (names) {
+ for (i = 1; i <= numtxqs; i++)
+ kfree(names[i]);
+ kfree(names);
+ }
+
+ kfree(callbacks);
+ kfree(vqs);
+
+out:
+ if (err) {
+ for (i = 0; i < numtxqs; i++)
+ kfree(vi->sq[i]);
+ kfree(vi->sq);
+ }
+
+ return err;
+}
+
static int virtnet_probe(struct virtio_device *vdev)
{
- int err;
+ int i, err;
+ u16 numtxqs;
struct net_device *dev;
struct virtnet_info *vi;
- struct virtqueue *vqs[3];
- vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL};
- const char *names[] = { "input", "output", "control" };
- int nvqs;
+
+ /*
+ * Find if host passed the number of transmit queues supported
+ * by the device
+ */
+ err = virtio_config_val(vdev, VIRTIO_NET_F_NUMTXQS,
+ offsetof(struct virtio_net_config, numtxqs),
+ &numtxqs);
+
+ /* We need atleast one txq */
+ if (err || !numtxqs)
+ numtxqs = 1;
+
+ if (numtxqs > VIRTIO_MAX_SQ)
+ return -EINVAL;
/* Allocate ourselves a network device with room for our info */
- dev = alloc_etherdev(sizeof(struct virtnet_info));
+ dev = alloc_etherdev_mq(sizeof(struct virtnet_info), numtxqs);
if (!dev)
return -ENOMEM;
@@ -940,9 +1062,9 @@ static int virtnet_probe(struct virtio_d
vi->vdev = vdev;
vdev->priv = vi;
vi->pages = NULL;
+ vi->numtxqs = numtxqs;
INIT_DELAYED_WORK(&vi->refill, refill_work);
sg_init_table(vi->rx_sg, ARRAY_SIZE(vi->rx_sg));
- sg_init_table(vi->tx_sg, ARRAY_SIZE(vi->tx_sg));
/* If we can receive ANY GSO packets, we must allocate large ones. */
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
@@ -953,23 +1075,10 @@ static int virtnet_probe(struct virtio_d
if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
vi->mergeable_rx_bufs = true;
- /* We expect two virtqueues, receive then send,
- * and optionally control. */
- nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2;
-
- err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
+ /* Initialize our rx/tx queue parameters, and invoke find_vqs */
+ err = initialize_vqs(vi, numtxqs);
if (err)
- goto free;
-
- vi->rvq = vqs[0];
- vi->svq = vqs[1];
-
- if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
- vi->cvq = vqs[2];
-
- if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
- dev->features |= NETIF_F_HW_VLAN_FILTER;
- }
+ goto free_netdev;
err = register_netdev(dev);
if (err) {
@@ -986,6 +1095,9 @@ static int virtnet_probe(struct virtio_d
goto unregister;
}
+ dev_info(&dev->dev, "(virtio-net) Allocated 1 RX and %d TX vq's\n",
+ numtxqs);
+
vi->status = VIRTIO_NET_S_LINK_UP;
virtnet_update_status(vi);
netif_carrier_on(dev);
@@ -998,7 +1110,10 @@ unregister:
cancel_delayed_work_sync(&vi->refill);
free_vqs:
vdev->config->del_vqs(vdev);
-free:
+ for (i = 0; i < numtxqs; i++)
+ kfree(vi->sq[i]);
+ kfree(vi->sq);
+free_netdev:
free_netdev(dev);
return err;
}
@@ -1006,12 +1121,21 @@ free:
static void free_unused_bufs(struct virtnet_info *vi)
{
void *buf;
- while (1) {
- buf = virtqueue_detach_unused_buf(vi->svq);
- if (!buf)
- break;
- dev_kfree_skb(buf);
+ int i;
+
+ for (i = 0; i < vi->numtxqs; i++) {
+ struct virtqueue *svq = vi->sq[i]->svq;
+
+ while (1) {
+ buf = virtqueue_detach_unused_buf(svq);
+ if (!buf)
+ break;
+ dev_kfree_skb(buf);
+ }
+ kfree(vi->sq[i]);
}
+ kfree(vi->sq);
+
while (1) {
buf = virtqueue_detach_unused_buf(vi->rvq);
if (!buf)
@@ -1059,7 +1183,7 @@ static unsigned int features[] = {
VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
- VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
+ VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, VIRTIO_NET_F_NUMTXQS,
};
static struct virtio_driver virtio_net_driver = {
^ permalink raw reply
* [v3 RFC PATCH 0/4] Implement multiqueue virtio-net
From: Krishna Kumar @ 2010-10-20 8:54 UTC (permalink / raw)
To: rusty, davem, mst
Cc: arnd, eric.dumazet, netdev, avi, anthony, kvm, Krishna Kumar
Following set of patches implement transmit MQ in virtio-net. Also
included is the user qemu changes. MQ is disabled by default unless
qemu specifies it.
Changes from rev2:
------------------
1. Define (in virtio_net.h) the maximum send txqs; and use in
virtio-net and vhost-net.
2. vi->sq[i] is allocated individually, resulting in cache line
aligned sq[0] to sq[n]. Another option was to define
'send_queue' as:
struct send_queue {
struct virtqueue *svq;
struct scatterlist tx_sg[MAX_SKB_FRAGS + 2];
} ____cacheline_aligned_in_smp;
and to statically allocate 'VIRTIO_MAX_SQ' of those. I hope
the submitted method is preferable.
3. Changed vhost model such that vhost[0] handles RX and vhost[1-MAX]
handles TX[0-n].
4. Further change TX handling such that vhost[0] handles both RX/TX
for single stream case.
Enabling MQ on virtio:
-----------------------
When following options are passed to qemu:
- smp > 1
- vhost=on
- mq=on (new option, default:off)
then #txqueues = #cpus. The #txqueues can be changed by using an
optional 'numtxqs' option. e.g. for a smp=4 guest:
vhost=on -> #txqueues = 1
vhost=on,mq=on -> #txqueues = 4
vhost=on,mq=on,numtxqs=2 -> #txqueues = 2
vhost=on,mq=on,numtxqs=8 -> #txqueues = 8
Performance (guest -> local host):
-----------------------------------
System configuration:
Host: 8 Intel Xeon, 8 GB memory
Guest: 4 cpus, 2 GB memory
Test: Each test case runs for 60 secs, sum over three runs (except
when number of netperf sessions is 1, which has 10 runs of 12 secs
each). No tuning (default netperf) other than taskset vhost's to
cpus 0-3. numtxqs=32 gave the best results though the guest had
only 4 vcpus (I haven't tried beyond that).
______________ numtxqs=2, vhosts=3 ____________________
#sessions BW% CPU% RCPU% SD% RSD%
________________________________________________________
1 4.46 -1.96 .19 -12.50 -6.06
2 4.93 -1.16 2.10 0 -2.38
4 46.17 64.77 33.72 19.51 -2.48
8 47.89 70.00 36.23 41.46 13.35
16 48.97 80.44 40.67 21.11 -5.46
24 49.03 78.78 41.22 20.51 -4.78
32 51.11 77.15 42.42 15.81 -6.87
40 51.60 71.65 42.43 9.75 -8.94
48 50.10 69.55 42.85 11.80 -5.81
64 46.24 68.42 42.67 14.18 -3.28
80 46.37 63.13 41.62 7.43 -6.73
96 46.40 63.31 42.20 9.36 -4.78
128 50.43 62.79 42.16 13.11 -1.23
________________________________________________________
BW: 37.2%, CPU/RCPU: 66.3%,41.6%, SD/RSD: 11.5%,-3.7%
______________ numtxqs=8, vhosts=5 ____________________
#sessions BW% CPU% RCPU% SD% RSD%
________________________________________________________
1 -.76 -1.56 2.33 0 3.03
2 17.41 11.11 11.41 0 -4.76
4 42.12 55.11 30.20 19.51 .62
8 54.69 80.00 39.22 24.39 -3.88
16 54.77 81.62 40.89 20.34 -6.58
24 54.66 79.68 41.57 15.49 -8.99
32 54.92 76.82 41.79 17.59 -5.70
40 51.79 68.56 40.53 15.31 -3.87
48 51.72 66.40 40.84 9.72 -7.13
64 51.11 63.94 41.10 5.93 -8.82
80 46.51 59.50 39.80 9.33 -4.18
96 47.72 57.75 39.84 4.20 -7.62
128 54.35 58.95 40.66 3.24 -8.63
________________________________________________________
BW: 38.9%, CPU/RCPU: 63.0%,40.1%, SD/RSD: 6.0%,-7.4%
______________ numtxqs=16, vhosts=5 ___________________
#sessions BW% CPU% RCPU% SD% RSD%
________________________________________________________
1 -1.43 -3.52 1.55 0 3.03
2 33.09 21.63 20.12 -10.00 -9.52
4 67.17 94.60 44.28 19.51 -11.80
8 75.72 108.14 49.15 25.00 -10.71
16 80.34 101.77 52.94 25.93 -4.49
24 70.84 93.12 43.62 27.63 -5.03
32 69.01 94.16 47.33 29.68 -1.51
40 58.56 63.47 25.91 -3.92 -25.85
48 61.16 74.70 34.88 .89 -22.08
64 54.37 69.09 26.80 -6.68 -30.04
80 36.22 22.73 -2.97 -8.25 -27.23
96 41.51 50.59 13.24 9.84 -16.77
128 48.98 38.15 6.41 -.33 -22.80
________________________________________________________
BW: 46.2%, CPU/RCPU: 55.2%,18.8%, SD/RSD: 1.2%,-22.0%
______________ numtxqs=32, vhosts=5 ___________________
# BW% CPU% RCPU% SD% RSD%
________________________________________________________
1 7.62 -38.03 -26.26 -50.00 -33.33
2 28.95 20.46 21.62 0 -7.14
4 84.05 60.79 45.74 -2.43 -12.42
8 86.43 79.57 50.32 15.85 -3.10
16 88.63 99.48 58.17 9.47 -13.10
24 74.65 80.87 41.99 -1.81 -22.89
32 63.86 59.21 23.58 -18.13 -36.37
40 64.79 60.53 22.23 -15.77 -35.84
48 49.68 26.93 .51 -36.40 -49.61
64 54.69 36.50 5.41 -26.59 -43.23
80 45.06 12.72 -13.25 -37.79 -52.08
96 40.21 -3.16 -24.53 -39.92 -52.97
128 36.33 -33.19 -43.66 -5.68 -20.49
________________________________________________________
BW: 49.3%, CPU/RCPU: 15.5%,-8.2%, SD/RSD: -22.2%,-37.0%
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
^ permalink raw reply
* Re: [PATCH 2/2] Revert napi_poll fix for bonding driver
From: David Miller @ 2010-10-20 8:45 UTC (permalink / raw)
To: amwang; +Cc: nhorman, netdev, bonding-devel, fubar, andy
In-Reply-To: <4CBE9FA0.6010900@redhat.com>
From: Cong Wang <amwang@redhat.com>
Date: Wed, 20 Oct 2010 15:52:00 +0800
> On 10/20/10 01:04, nhorman@tuxdriver.com wrote:
>> Signed-off-by: Neil Horman<nhorman@tuxdriver.com>
...
> Reviewed-by: WANG Cong <amwang@redhat.com>
Also applied, thanks.
^ permalink raw reply
* Re: [PATCH 1/2] Remove netpoll blocking from uninit path
From: David Miller @ 2010-10-20 8:45 UTC (permalink / raw)
To: amwang; +Cc: nhorman, netdev, bonding-devel, fubar, andy
In-Reply-To: <4CBE9E7F.60107@redhat.com>
From: Cong Wang <amwang@redhat.com>
Date: Wed, 20 Oct 2010 15:47:11 +0800
> On 10/20/10 01:04, nhorman@tuxdriver.com wrote:
>> From: Neil Horman<nhorman@tuxdriver.com>
>>
>> Some recent testing in netpoll with bonding showed this backtrace
...
>> Signed-off-by: Neil Horman<nhorman@tuxdriver.com>
>
> Reviewed-by: WANG Cong <amwang@redhat.com>
Applied.
Neil, please add proper subsystem prefixes to your subject
lines, I've had to add them by hand as I add your patches.
Thanks.
^ permalink raw reply
* Re: [RFC PATCH 1/9] ipvs network name space aware
From: Hans Schillstrom @ 2010-10-20 8:25 UTC (permalink / raw)
To: paulmck@linux.vnet.ibm.com
Cc: Daniel Lezcano, lvs-devel@vger.kernel.org, netdev@vger.kernel.org,
netfilter-devel@vger.kernel.org, horms@verge.net.au, ja@ssi.bg,
wensong@linux-vs.org
In-Reply-To: <20101019184436.GG2362@linux.vnet.ibm.com>
On Tuesday 19 October 2010 20:44:36 Paul E. McKenney wrote:
> On Mon, Oct 18, 2010 at 03:23:48PM +0200, Hans Schillstrom wrote:
> > On Monday 18 October 2010 13:37:38 Daniel Lezcano wrote:
> > > On 10/18/2010 11:54 AM, Hans Schillstrom wrote:
> > > > On Monday 18 October 2010 10:59:25 Daniel Lezcano wrote:
> > > >
> > > >> On 10/08/2010 01:16 PM, Hans Schillstrom wrote:
> > > >>
> > > >>> This part contains the include files
> > > >>> where include/net/netns/ip_vs.h is new and contains all moved vars.
> > > >>>
> > > >>> SUMMARY
> > > >>>
> > > >>> include/net/ip_vs.h | 136 ++++---
> > > >>> include/net/net_namespace.h | 2 +
> > > >>> include/net/netns/ip_vs.h | 112 +++++
> > > >>>
> > > >>> Signed-off-by:Hans Schillstrom<hans.schillstrom@ericsson.com>
> > > >>> ---
> > > >>>
> > > >>>
> > > >>>
> > > >> [ ... ]
> > > >>
> > > >>
> > > >>> #ifdef CONFIG_IP_VS_IPV6
> > > >>> diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
> > > >>> index bd10a79..b59cdc5 100644
> > > >>> --- a/include/net/net_namespace.h
> > > >>> +++ b/include/net/net_namespace.h
> > > >>> @@ -15,6 +15,7 @@
> > > >>> #include<net/netns/ipv4.h>
> > > >>> #include<net/netns/ipv6.h>
> > > >>> #include<net/netns/dccp.h>
> > > >>> +#include<net/netns/ip_vs.h>
> > > >>> #include<net/netns/x_tables.h>
> > > >>> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
> > > >>> #include<net/netns/conntrack.h>
> > > >>> @@ -91,6 +92,7 @@ struct net {
> > > >>> struct sk_buff_head wext_nlevents;
> > > >>> #endif
> > > >>> struct net_generic *gen;
> > > >>> + struct netns_ipvs *ipvs;
> > > >>> };
> > > >>>
> > > >>>
> > > >> IMHO, it would be better to use the net_generic infra-structure instead
> > > >> of adding a new field in the netns structure.
> > > >>
> > > >>
> > > >>
> > > > I realized that to, but the performance penalty is quite high with net_generic :-(
> > > > But on the other hand if you are going to backport it, (without recompiling the kernel)
> > > > you gonna need it!
> > > >
> > >
> > > Hmm, yes. We don't want to have the init_net_ns performances to be impacted.
> > >
> > > You use here a pointer which will be dereferenced like the net_generic,
> > > I don't think there will be
> > > a big difference between using net_generic and using a pointer in the
> > > net namespace structure.
> > >
> > > The difference is the id usage, but this one is based on the idr which
> > > is quite fast.
> > >
> >
> > I'm not so sure about that, have a look at net_generic and rcu_read_lock
> > and compare
> > ipvs = net->ipvs;
> > vs.
> > ipvs = net_generic(net, id)
> >
> > static inline void *net_generic(struct net *net, int id)
> > {
> > struct net_generic *ng;
> > void *ptr;
> >
> > rcu_read_lock();
> > ng = rcu_dereference(net->gen);
> > BUG_ON(id == 0 || id > ng->len);
> > ptr = ng->ptr[id - 1];
> > rcu_read_unlock();
> >
> > return ptr;
> > }
> > ...
> > static inline void rcu_read_lock(void)
> > {
> > __rcu_read_lock();
> > __acquire(RCU);
> > rcu_read_acquire();
> > }
> >
> > Another way of doing it is to pass the ipvs ptr instead of the net ptr,
> > and add *net to the ipvs struct.
> >
> > > We should experiment a bit here to compare both solutions.
> > Agre
> > >
> > I single stepped through the rcu_read_lock() on a x86_64
> > and it's quite many "stepi" that you need to enter :-(
>
> Was this by chance with lockdep enabled? If not, could you please send
> your .config?
>
> Thanx, Paul
No lockdep, but what I ment is that net_generic is not as fast as a plain ptr->xxx.
IPVS has hooks in the netfilter chain, and gets a huge amount of packets .
I don't think IPVS is a candidate for net_generic, it should have its own part in "struct net"
That was my point.
( No critic to locking or net_generic)
--
Regards
Hans Schillstrom <hans.schillstrom@ericsson.com>
^ permalink raw reply
* [PATCH] phonet: remove the unused variable pn
From: Changli Gao @ 2010-10-20 7:51 UTC (permalink / raw)
To: Remi Denis-Courmont; +Cc: David S. Miller, netdev, Changli Gao
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
---
net/phonet/pep.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 9c903f9..3e60f2e 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -300,7 +300,6 @@ static int pipe_handler_send_ind(struct sock *sk, u8 utid, u8 msg_id)
static int pipe_handler_enable_pipe(struct sock *sk, int enable)
{
- struct pep_sock *pn = pep_sk(sk);
int utid, req;
if (enable) {
^ permalink raw reply related
* Re: [PATCH 2/2] Revert napi_poll fix for bonding driver
From: Cong Wang @ 2010-10-20 7:52 UTC (permalink / raw)
To: nhorman; +Cc: netdev, bonding-devel, fubar, davem, andy
In-Reply-To: <1287507866-25156-3-git-send-email-nhorman@tuxdriver.com>
On 10/20/10 01:04, nhorman@tuxdriver.com wrote:
> From: Neil Horman<nhorman@tuxdriver.com>
>
> In an erlier patch I modified napi_poll so that devices with IFF_MASTER polled
> the per_cpu list instead of the device list for napi. I did this because the
> bonding driver has no napi instances to poll, it instead expects to check the
> slave devices napi instances, which napi_poll was unaware of. Looking at this
> more closely however, I now see this isn't strictly needed. As the bond driver
> poll_controller calls the slaves poll_controller via netpoll_poll_dev, which
> recursively calls poll_napi on each slave, allowing those napi instances to get
> serviced. The earlier patch isn't at all harmfull, its just not needed, so lets
> revert it to make the code cleaner. Sorry for the noise,
>
> Signed-off-by: Neil Horman<nhorman@tuxdriver.com>
Looks reasonable to me,
Reviewed-by: WANG Cong <amwang@redhat.com>
Thanks.
^ permalink raw reply
* Re: [PATCH 1/2] Remove netpoll blocking from uninit path
From: Cong Wang @ 2010-10-20 7:47 UTC (permalink / raw)
To: nhorman; +Cc: netdev, bonding-devel, fubar, davem, andy
In-Reply-To: <1287507866-25156-2-git-send-email-nhorman@tuxdriver.com>
On 10/20/10 01:04, nhorman@tuxdriver.com wrote:
> From: Neil Horman<nhorman@tuxdriver.com>
>
> Some recent testing in netpoll with bonding showed this backtrace
>
> ------------[ cut here ]------------
> kernel BUG at drivers/net/bonding/bonding.h:134!
> invalid opcode: 0000 [#1] SMP
> last sysfs file: /sys/devices/pci0000:00/0000:00:1d.2/usb7/devnum
> CPU 0
> Pid: 1876, comm: rmmod Not tainted 2.6.36-rc3+ #10 D26928/
> RIP: 0010:[<ffffffffa0514ba4>] [<ffffffffa0514ba4>] bond_uninit+0x6f4/0x7a0
> RSP: 0018:ffff88003b1b5d58 EFLAGS: 00010296
> RAX: ffff88003b9b6200 RBX: ffff8800373e8e00 RCX: 00000000000f4240
> RDX: 00000000ffffffff RSI: 0000000000000286 RDI: 0000000000000286
> RBP: ffff88003b1b5dc8 R08: 0000000000000000 R09: 00000001af7de920
> R10: 0000000000000000 R11: ffff880002495e98 R12: ffff880037922700
> R13: ffff880038c31000 R14: ffff880037922730 R15: 0000000000000286
> FS: 00007f90e6d72700(0000) GS:ffff880002400000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> CR2: 000000346f0d9ad0 CR3: 000000003b263000 CR4: 00000000000006f0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
> Process rmmod (pid: 1876, threadinfo ffff88003b1b4000, task ffff88003b36aa80)
> Stack:
> 00000000ffffffff ffff88003b1b5d7a ffff8800379221e8 ffff880037922000
> <0> ffff88003b1b5dc8 ffffffff813eb5fb ffff88003b1b5da8 0000000031b177a3
> <0> ffff88003b1b5da8 ffff880037922000 ffff88003b1b5e48 ffff88003b1b5e48
> Call Trace:
> [<ffffffff813eb5fb>] ? rtmsg_ifinfo+0xcb/0xf0
> [<ffffffff813daad8>] rollback_registered_many+0x168/0x280
> [<ffffffff813dac09>] unregister_netdevice_many+0x19/0x80
> [<ffffffff813e97b3>] __rtnl_kill_links+0x63/0x90
> [<ffffffff813e980b>] __rtnl_link_unregister+0x2b/0x60
> [<ffffffff813e9bde>] rtnl_link_unregister+0x1e/0x30
> [<ffffffffa052124b>] bonding_exit+0x37/0x51 [bonding]
> [<ffffffff81098b2e>] sys_delete_module+0x19e/0x270
> [<ffffffff810bb2b2>] ? audit_syscall_entry+0x252/0x280
> [<ffffffff8100b0b2>] system_call_fastpath+0x16/0x1b
> RIP [<ffffffffa0514ba4>] bond_uninit+0x6f4/0x7a0 [bonding]
> RSP<ffff88003b1b5d58>
> ---[ end trace 1395ad691cea24d1 ]---
>
> It occurs because of my recent netpoll blocking patches, which I added to avoid
> recursive deadlock in the bonding driver. It relies on some per cpu bits, but
> the shutdown path forces some rescheduling as we cancel workqueues for the
> driver and wait for some device refcounts. If after the forced reschedule, we
> wind up on a different cpu we trigger the bughalt in unblock_netpoll_tx.
>
> The fix is to remove the netpoll block/unblock calls from bond_release_all.
> This is safe to do because bond_uninit, which is called via ndo_uninit in
> rollback_registered_many, doesn't occur until we send a NETDEV_UNREGISTER event,
> which triggers netconsole to remove us as a netpoll client, so we are guaranteed
> not to recurse into our own tx path here.
Also bond_release_all() is called after bond_netpoll_cleanup()
in bond_uninit().
>
> Signed-off-by: Neil Horman<nhorman@tuxdriver.com>
Reviewed-by: WANG Cong <amwang@redhat.com>
Thanks.
^ permalink raw reply
* Re: [Ksummit-2010-discuss] [v2] Remaining BKL users, what to do
From: Arnd Bergmann @ 2010-10-20 6:50 UTC (permalink / raw)
To: Dave Young
Cc: Greg KH, Oliver Neukum, Valdis.Kletnieks, Dave Airlie, codalist,
ksummit-2010-discuss, autofs, Jan Harkes, Samuel Ortiz, Jan Kara,
Arnaldo Carvalho de Melo, netdev, Anders Larsen, linux-kernel,
dri-devel, Bryan Schumaker, Christoph Hellwig, Petr Vandrovec,
Mikulas Patocka, linux-fsdevel, Evgeniy Dushistov, Ingo Molnar,
Andrew Hendry, linux-media
In-Reply-To: <AANLkTimRFxKT5p1K=Rd1MxXZymonx_t6rHKBhn=8CsW=@mail.gmail.com>
On Wednesday 20 October 2010, Dave Young wrote:
> be curious, why can't just fix the lock_kernel logic of i810? Fixing
> is too hard?
>
> Find a i810 hardware should be possible, even if the hardware does not
> support SMP, can't we test the fix with preemption?
Yes, that should work too. My usual approach for removing the BKL without
having the hardware myself was to make locking stricter, i.e. replace
the BKL with a new spinlock or mutex. This way all the code would still
be serialized and if I did something wrong, lockdep would complain about
it, but there would be no risk of silent data corruption.
In case of i810, locking across DRM is rather complicated and there is no
way of doing this without making changes to other DRM code.
In fact, the only critical section that is actually protected by the BKL
are the few lines in i810_mmap_buffers. They look like they might not even
need the BKL to start with and we can just remove it even on SMP/PREEMPT,
except for perhaps the assignment to buf_priv->currently_mapped.
Someone who understands more about the driver than I do can probably figure
this out easily, but I couldn't come up with a way that doesn't risk
breaking in corner cases.
Arnd
^ permalink raw reply
* Re: 2.6.36-rc7: net/bridge causes temporary network I/O lockups [2]
From: Herbert Xu @ 2010-10-20 6:16 UTC (permalink / raw)
To: Patrick Ringl; +Cc: netdev, linux-kernel, bridge
In-Reply-To: <4CBCB014.9080108@freenet.de>
On Mon, Oct 18, 2010 at 10:37:40PM +0200, Patrick Ringl wrote:
>
> Anything else I could possibly provide? :-)
Yes, testing :)
First of all I'd like to rule out (or in) the IPv6 query code,
which is clearly generating a bogus packet (wrong payload_len).
So can you apply this patch and see if it makes the problem
go away? Please take packet dumps so we know that the IPv6 query
is no longer being sent.
Thanks,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
--
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index eb5b256..66f39d7 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -832,11 +832,6 @@ static void br_multicast_send_query(struct net_bridge *br,
br_group.proto = htons(ETH_P_IP);
__br_multicast_send_query(br, port, &br_group);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
- br_group.proto = htons(ETH_P_IPV6);
- __br_multicast_send_query(br, port, &br_group);
-#endif
-
time = jiffies;
time += sent < br->multicast_startup_query_count ?
br->multicast_startup_query_interval :
^ permalink raw reply related
* Re: [PATCH] net: make ctl_path local and const
From: Changli Gao @ 2010-10-20 5:10 UTC (permalink / raw)
To: Joe Perches
Cc: Andy Grover, linux-sctp, rds-devel, Pekka Savola (ipv6),
linux-x25, dccp, bridge, James Morris, coreteam,
Arnaldo Carvalho de Melo, Alexey Kuznetsov, Joerg Reuter,
Sridhar Samudrala, Samuel Ortiz, Vlad Yasevich, netfilter,
Remi Denis-Courmont, linux-hams, Hideaki YOSHIFUJI, netdev,
linux-decnet-user, linux-kernel, Ralf Baechle <ralf
In-Reply-To: <1287550779.10409.620.camel@Joe-Laptop>
On Wed, Oct 20, 2010 at 12:59 PM, Joe Perches <joe@perches.com> wrote:
>
> Not using static requires the compiler to emit
> initialization code for any use of the routine
> that otherwise would only be done once.
>
If the code isn't performance critical, I think we can afford.
Otherwise, we have to reserve the memory used to save the static data,
if we don't specify it as initial data.
--
Regards,
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [PATCH] net: make ctl_path local and const
From: Joe Perches @ 2010-10-20 4:59 UTC (permalink / raw)
To: Changli Gao
Cc: Andy Grover, James Morris, linux-sctp, rds-devel,
Pekka Savola (ipv6), linux-x25, dccp, bridge, Andrew, coreteam,
Arnaldo Carvalho de Melo, Alexey Kuznetsov, Joerg Reuter,
Sridhar Samudrala, Samuel Ortiz, Vlad Yasevich, netfilter,
Remi Denis-Courmont, linux-hams, Hideaki YOSHIFUJI, netdev,
linux-decnet-user, linux-kernel
In-Reply-To: <AANLkTimGUB-+TTsje1kc3q9PyoB2jJdgCK2Z7n9u7N1J@mail.gmail.com>
On Wed, 2010-10-20 at 12:52 +0800, Changli Gao wrote:
> On Wed, Oct 20, 2010 at 11:28 AM, Joe Perches <joe@perches.com> wrote:
> > At least some objects are smaller with static.
> > $ size net/appletalk/sysctl_net_atalk.o.*
> > text data bss dec hex filename
> > 324 236 48 608 260 net/appletalk/sysctl_net_atalk.o.withstatic
> > 344 236 48 628 274 net/appletalk/sysctl_net_atalk.o.withoutstatic
> I got the opposite result for the size of the whole kernel image with
> allyesconfig.
> original: 33531456
> patched: 33531424
> It seems random.
Not using static requires the compiler to emit
initialization code for any use of the routine
that otherwise would only be done once.
^ permalink raw reply
* Re: [PATCH] net: make ctl_path local and const
From: Changli Gao @ 2010-10-20 4:52 UTC (permalink / raw)
To: Joe Perches
Cc: Andy Grover, linux-sctp, rds-devel, Pekka Savola (ipv6),
linux-x25, dccp, bridge, James Morris, coreteam,
Arnaldo Carvalho de Melo, Alexey Kuznetsov, Joerg Reuter,
Sridhar Samudrala, Samuel Ortiz, Vlad Yasevich, netfilter,
Remi Denis-Courmont, linux-hams, Hideaki YOSHIFUJI, netdev,
linux-decnet-user, linux-kernel, Ralf Baechle <ralf
In-Reply-To: <1287545337.10409.602.camel@Joe-Laptop>
On Wed, Oct 20, 2010 at 11:28 AM, Joe Perches <joe@perches.com> wrote:
>
> At least some objects are smaller with static.
>
> $ size net/appletalk/sysctl_net_atalk.o.*
> text data bss dec hex filename
> 324 236 48 608 260 net/appletalk/sysctl_net_atalk.o.withstatic
> 344 236 48 628 274 net/appletalk/sysctl_net_atalk.o.withoutstatic
>
>
I got the opposite result for the size of the whole kernel image with
allyesconfig.
original: 33531456
patched: 33531424
It seems random.
--
Regards,
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [Ksummit-2010-discuss] [v2] Remaining BKL users, what to do
From: Dave Young @ 2010-10-20 4:43 UTC (permalink / raw)
To: Arnd Bergmann
Cc: Greg KH, Oliver Neukum, Valdis.Kletnieks, Dave Airlie, codalist,
ksummit-2010-discuss, autofs, Jan Harkes, Samuel Ortiz, Jan Kara,
Arnaldo Carvalho de Melo, netdev, Anders Larsen, linux-kernel,
dri-devel, Bryan Schumaker, Christoph Hellwig, Petr Vandrovec,
Mikulas Patocka, linux-fsdevel, Evgeniy Dushistov, Ingo Molnar,
Andrew Hendry, linux-media
In-Reply-To: <201010192244.41913.arnd@arndb.de>
On Wed, Oct 20, 2010 at 4:44 AM, Arnd Bergmann <arnd@arndb.de> wrote:
> On Tuesday 19 October 2010 22:29:12 Greg KH wrote:
>> On Tue, Oct 19, 2010 at 09:40:47PM +0200, Oliver Neukum wrote:
>> > Am Dienstag, 19. Oktober 2010, 21:37:35 schrieb Greg KH:
>> > > > So no need to clean it up for multiprocessor support.
>> > > >
>> > > > http://download.intel.com/design/chipsets/datashts/29067602.pdf
>> > > > http://www.intel.com/design/chipsets/specupdt/29069403.pdf
>> > >
>> > > Great, we can just drop all calls to lock_kernel() and the like in the
>> > > driver and be done with it, right?
>> >
>> > No,
>> >
>> > you still need to switch off preemption.
>>
>> Hm, how would you do that from within a driver?
>
> I think this would do:
> ---
> drm/i810: remove SMP support and BKL
>
> The i810 and i815 chipsets supported by the i810 drm driver were not
> officially designed for SMP operation, so the big kernel lock is
> only required for kernel preemption. This disables the driver if
> preemption is enabled and removes all calls to lock_kernel in it.
>
> If you own an Acorp 6A815EPD mainboard with a i815 chipset and
> two Pentium-III sockets, and want to run recent kernels on it,
> tell me about it.
>
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
> ---
>
> diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
> index b755301..e071bc8 100644
> --- a/drivers/gpu/drm/Kconfig
> +++ b/drivers/gpu/drm/Kconfig
> @@ -73,8 +73,8 @@ source "drivers/gpu/drm/radeon/Kconfig"
>
> config DRM_I810
> tristate "Intel I810"
> - # BKL usage in order to avoid AB-BA deadlocks, may become BROKEN_ON_SMP
> - depends on DRM && AGP && AGP_INTEL && BKL
> + # PREEMPT requires BKL support here, which was removed
> + depends on DRM && AGP && AGP_INTEL && !PREEMPT
be curious, why can't just fix the lock_kernel logic of i810? Fixing
is too hard?
Find a i810 hardware should be possible, even if the hardware does not
support SMP, can't we test the fix with preemption?
--
Regards
dave
^ permalink raw reply
* Re: [PATCH] net: make ctl_path local and const
From: Joe Perches @ 2010-10-20 3:28 UTC (permalink / raw)
To: Changli Gao
Cc: Andy Grover, James Morris, linux-sctp, rds-devel,
Pekka Savola (ipv6), linux-x25, dccp, bridge, Andrew, coreteam,
Arnaldo Carvalho de Melo, Alexey Kuznetsov, Joerg Reuter,
Sridhar Samudrala, Samuel Ortiz, Vlad Yasevich, netfilter,
Remi Denis-Courmont, linux-hams, Hideaki YOSHIFUJI, netdev,
linux-decnet-user, linux-kernel
In-Reply-To: <AANLkTi=pz4zYnnUSvb9FjVvCAURruHhJTz7pBKDi8Pdw@mail.gmail.com>
On Wed, 2010-10-20 at 11:10 +0800, Changli Gao wrote:
> On Wed, Oct 20, 2010 at 11:01 AM, Joe Perches <joe@perches.com> wrote:
> > On Wed, 2010-10-20 at 10:54 +0800, Changli Gao wrote:
> >> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
> > []
> >> diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c
> >> index 04e9c0d..b92f269 100644
> >> --- a/net/appletalk/sysctl_net_atalk.c
> >> +++ b/net/appletalk/sysctl_net_atalk.c
> >> @@ -42,16 +42,16 @@ static struct ctl_table atalk_table[] = {
> >> { },
> >> };
> >> -static struct ctl_path atalk_path[] = {
> >> - { .procname = "net", },
> >> - { .procname = "appletalk", },
> >> - { }
> >> -};
> >> -
> >> static struct ctl_table_header *atalk_table_header;
> >>
> >> void atalk_register_sysctl(void)
> >> {
> >> + const struct ctl_path atalk_path[] = {
> > Shouldn't all of these be static const struct ?
> They needn't. And some variables are specified __net_initdata currently.
At least some objects are smaller with static.
$ size net/appletalk/sysctl_net_atalk.o.*
text data bss dec hex filename
324 236 48 608 260 net/appletalk/sysctl_net_atalk.o.withstatic
344 236 48 628 274 net/appletalk/sysctl_net_atalk.o.withoutstatic
^ permalink raw reply
* Re: [PATCH] net: make ctl_path local and const
From: Changli Gao @ 2010-10-20 3:10 UTC (permalink / raw)
To: Joe Perches
Cc: Andy Grover, linux-sctp, rds-devel, Pekka Savola (ipv6),
linux-x25, dccp, bridge, James Morris, coreteam,
Arnaldo Carvalho de Melo, Alexey Kuznetsov, Joerg Reuter,
Sridhar Samudrala, Samuel Ortiz, Vlad Yasevich, netfilter,
Remi Denis-Courmont, linux-hams, Hideaki YOSHIFUJI, netdev,
linux-decnet-user, linux-kernel, Ralf Baechle <ralf
In-Reply-To: <1287543701.10409.599.camel@Joe-Laptop>
On Wed, Oct 20, 2010 at 11:01 AM, Joe Perches <joe@perches.com> wrote:
> On Wed, 2010-10-20 at 10:54 +0800, Changli Gao wrote:
>> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
> []
>> diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c
>> index 04e9c0d..b92f269 100644
>> --- a/net/appletalk/sysctl_net_atalk.c
>> +++ b/net/appletalk/sysctl_net_atalk.c
>> @@ -42,16 +42,16 @@ static struct ctl_table atalk_table[] = {
>> { },
>> };
>>
>> -static struct ctl_path atalk_path[] = {
>> - { .procname = "net", },
>> - { .procname = "appletalk", },
>> - { }
>> -};
>> -
>> static struct ctl_table_header *atalk_table_header;
>>
>> void atalk_register_sysctl(void)
>> {
>> + const struct ctl_path atalk_path[] = {
>
> Shouldn't all of these be static const struct ?
>
>
They needn't. And some variables are specified __net_initdata currently.
--
Regards,
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [PATCH] net: make ctl_path local and const
From: Joe Perches @ 2010-10-20 3:01 UTC (permalink / raw)
To: Changli Gao
Cc: Andy Grover, James Morris, linux-sctp, rds-devel,
Pekka Savola (ipv6), linux-x25, dccp, bridge, Andrew, coreteam,
Arnaldo Carvalho de Melo, Alexey Kuznetsov, Joerg Reuter,
Sridhar Samudrala, Samuel Ortiz, Vlad Yasevich, netfilter,
Remi Denis-Courmont, linux-hams, Hideaki YOSHIFUJI, netdev,
linux-decnet-user, linux-kernel
In-Reply-To: <1287543276-4511-1-git-send-email-xiaosuo@gmail.com>
On Wed, 2010-10-20 at 10:54 +0800, Changli Gao wrote:
> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
[]
> diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c
> index 04e9c0d..b92f269 100644
> --- a/net/appletalk/sysctl_net_atalk.c
> +++ b/net/appletalk/sysctl_net_atalk.c
> @@ -42,16 +42,16 @@ static struct ctl_table atalk_table[] = {
> { },
> };
>
> -static struct ctl_path atalk_path[] = {
> - { .procname = "net", },
> - { .procname = "appletalk", },
> - { }
> -};
> -
> static struct ctl_table_header *atalk_table_header;
>
> void atalk_register_sysctl(void)
> {
> + const struct ctl_path atalk_path[] = {
Shouldn't all of these be static const struct ?
^ permalink raw reply
* [PATCH] net: make ctl_path local and const
From: Changli Gao @ 2010-10-20 2:54 UTC (permalink / raw)
To: David S. Miller
Cc: Arnaldo Carvalho de Melo, Joerg Reuter, Ralf Baechle,
Stephen Hemminger, Alexey Kuznetsov, Pekka Savola (ipv6),
James Morris, Hideaki YOSHIFUJI, Patrick McHardy, Samuel Ortiz,
Remi Denis-Courmont, Andy Grover, Vlad Yasevich,
Sridhar Samudrala, Andrew Hendry, linux-kernel, netdev,
linux-hams, bridge, dccp, linux-decnet-user, netfilter-devel,
netfilter, coreteam
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
---
net/appletalk/sysctl_net_atalk.c | 12 ++++++------
net/ax25/sysctl_net_ax25.c | 11 +++++------
net/bridge/br_netfilter.c | 13 +++++++------
net/dccp/sysctl.c | 14 +++++++-------
net/decnet/sysctl_net_decnet.c | 12 ++++++------
net/ipv4/devinet.c | 10 +++++-----
net/ipv4/route.c | 25 ++++++++++++-------------
net/ipx/sysctl_net_ipx.c | 11 +++++------
net/irda/irsysctl.c | 12 ++++++------
net/llc/sysctl_net_llc.c | 12 ++++++------
net/netfilter/nf_conntrack_standalone.c | 9 ++++-----
net/netfilter/nf_log.c | 15 +++++++--------
net/netrom/sysctl_net_netrom.c | 12 ++++++------
net/phonet/sysctl.c | 12 ++++++------
net/rds/ib_sysctl.c | 17 +++++++++--------
net/rds/iw_sysctl.c | 17 +++++++++--------
net/rds/sysctl.c | 16 ++++++++--------
net/rose/sysctl_net_rose.c | 12 ++++++------
net/sctp/sysctl.c | 12 ++++++------
net/unix/sysctl_net_unix.c | 11 +++++------
net/x25/sysctl_net_x25.c | 12 ++++++------
21 files changed, 137 insertions(+), 140 deletions(-)
diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c
index 04e9c0d..b92f269 100644
--- a/net/appletalk/sysctl_net_atalk.c
+++ b/net/appletalk/sysctl_net_atalk.c
@@ -42,16 +42,16 @@ static struct ctl_table atalk_table[] = {
{ },
};
-static struct ctl_path atalk_path[] = {
- { .procname = "net", },
- { .procname = "appletalk", },
- { }
-};
-
static struct ctl_table_header *atalk_table_header;
void atalk_register_sysctl(void)
{
+ const struct ctl_path atalk_path[] = {
+ { .procname = "net", },
+ { .procname = "appletalk", },
+ { }
+ };
+
atalk_table_header = register_sysctl_paths(atalk_path, atalk_table);
}
diff --git a/net/ax25/sysctl_net_ax25.c b/net/ax25/sysctl_net_ax25.c
index ebe0ef3..6d461ae 100644
--- a/net/ax25/sysctl_net_ax25.c
+++ b/net/ax25/sysctl_net_ax25.c
@@ -34,12 +34,6 @@ static struct ctl_table_header *ax25_table_header;
static ctl_table *ax25_table;
static int ax25_table_size;
-static struct ctl_path ax25_path[] = {
- { .procname = "net", },
- { .procname = "ax25", },
- { }
-};
-
static const ctl_table ax25_param_table[] = {
{
.procname = "ip_default_mode",
@@ -163,6 +157,11 @@ void ax25_register_sysctl(void)
{
ax25_dev *ax25_dev;
int n, k;
+ const struct ctl_path ax25_path[] = {
+ { .procname = "net", },
+ { .procname = "ax25", },
+ { }
+ };
spin_lock_bh(&ax25_dev_lock);
for (ax25_table_size = sizeof(ctl_table), ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next)
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 7f9ce96..6a89631 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -990,17 +990,18 @@ static ctl_table brnf_table[] = {
},
{ }
};
-
-static struct ctl_path brnf_path[] = {
- { .procname = "net", },
- { .procname = "bridge", },
- { }
-};
#endif
int __init br_netfilter_init(void)
{
int ret;
+#ifdef CONFIG_SYSCTL
+ const struct ctl_path brnf_path[] = {
+ { .procname = "net", },
+ { .procname = "bridge", },
+ { }
+ };
+#endif
ret = dst_entries_init(&fake_dst_ops);
if (ret < 0)
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index 5639438..bfb80d1 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -96,17 +96,17 @@ static struct ctl_table dccp_default_table[] = {
{ }
};
-static struct ctl_path dccp_path[] = {
- { .procname = "net", },
- { .procname = "dccp", },
- { .procname = "default", },
- { }
-};
-
static struct ctl_table_header *dccp_table_header;
int __init dccp_sysctl_init(void)
{
+ const struct ctl_path dccp_path[] = {
+ { .procname = "net", },
+ { .procname = "dccp", },
+ { .procname = "default", },
+ { }
+ };
+
dccp_table_header = register_sysctl_paths(dccp_path,
dccp_default_table);
diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c
index be3eb8e..910927f 100644
--- a/net/decnet/sysctl_net_decnet.c
+++ b/net/decnet/sysctl_net_decnet.c
@@ -350,14 +350,14 @@ static ctl_table dn_table[] = {
{ }
};
-static struct ctl_path dn_path[] = {
- { .procname = "net", },
- { .procname = "decnet", },
- { }
-};
-
void dn_register_sysctl(void)
{
+ const struct ctl_path dn_path[] = {
+ { .procname = "net", },
+ { .procname = "decnet", },
+ { }
+ };
+
dn_table_header = register_sysctl_paths(dn_path, dn_table);
}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index c2ff48f..06c55fe 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1519,11 +1519,6 @@ static struct ctl_table ctl_forward_entry[] = {
{ },
};
-static __net_initdata struct ctl_path net_ipv4_path[] = {
- { .procname = "net", },
- { .procname = "ipv4", },
- { },
-};
#endif
static __net_init int devinet_init_net(struct net *net)
@@ -1533,6 +1528,11 @@ static __net_init int devinet_init_net(struct net *net)
#ifdef CONFIG_SYSCTL
struct ctl_table *tbl = ctl_forward_entry;
struct ctl_table_header *forw_hdr;
+ const struct ctl_path net_ipv4_path[] = {
+ { .procname = "net", },
+ { .procname = "ipv4", },
+ { },
+ };
#endif
err = -ENOMEM;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ff98983..13bbac4 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3182,12 +3182,6 @@ static struct ctl_table ipv4_skeleton[] =
{ }
};
-static __net_initdata struct ctl_path ipv4_path[] = {
- { .procname = "net", },
- { .procname = "ipv4", },
- { },
-};
-
static struct ctl_table ipv4_route_flush_table[] = {
{
.procname = "flush",
@@ -3198,16 +3192,15 @@ static struct ctl_table ipv4_route_flush_table[] = {
{ },
};
-static __net_initdata struct ctl_path ipv4_route_path[] = {
- { .procname = "net", },
- { .procname = "ipv4", },
- { .procname = "route", },
- { },
-};
-
static __net_init int sysctl_route_net_init(struct net *net)
{
struct ctl_table *tbl;
+ const struct ctl_path ipv4_route_path[] = {
+ { .procname = "net", },
+ { .procname = "ipv4", },
+ { .procname = "route", },
+ { },
+ };
tbl = ipv4_route_flush_table;
if (!net_eq(net, &init_net)) {
@@ -3343,6 +3336,12 @@ int __init ip_rt_init(void)
*/
void __init ip_static_sysctl_init(void)
{
+ const struct ctl_path ipv4_path[] = {
+ { .procname = "net", },
+ { .procname = "ipv4", },
+ { },
+ };
+
register_sysctl_paths(ipv4_path, ipv4_skeleton);
}
#endif
diff --git a/net/ipx/sysctl_net_ipx.c b/net/ipx/sysctl_net_ipx.c
index bd6dca0..2cd92d2 100644
--- a/net/ipx/sysctl_net_ipx.c
+++ b/net/ipx/sysctl_net_ipx.c
@@ -27,16 +27,15 @@ static struct ctl_table ipx_table[] = {
{ },
};
-static struct ctl_path ipx_path[] = {
- { .procname = "net", },
- { .procname = "ipx", },
- { }
-};
-
static struct ctl_table_header *ipx_table_header;
void ipx_register_sysctl(void)
{
+ const struct ctl_path ipx_path[] = {
+ { .procname = "net", },
+ { .procname = "ipx", },
+ { }
+ };
ipx_table_header = register_sysctl_paths(ipx_path, ipx_table);
}
diff --git a/net/irda/irsysctl.c b/net/irda/irsysctl.c
index d0b70da..b177680 100644
--- a/net/irda/irsysctl.c
+++ b/net/irda/irsysctl.c
@@ -235,12 +235,6 @@ static ctl_table irda_table[] = {
{ }
};
-static struct ctl_path irda_path[] = {
- { .procname = "net", },
- { .procname = "irda", },
- { }
-};
-
static struct ctl_table_header *irda_table_header;
/*
@@ -251,6 +245,12 @@ static struct ctl_table_header *irda_table_header;
*/
int __init irda_sysctl_register(void)
{
+ const struct ctl_path irda_path[] = {
+ { .procname = "net", },
+ { .procname = "irda", },
+ { }
+ };
+
irda_table_header = register_sysctl_paths(irda_path, irda_table);
if (!irda_table_header)
return -ENOMEM;
diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c
index e2ebe35..bb7c153 100644
--- a/net/llc/sysctl_net_llc.c
+++ b/net/llc/sysctl_net_llc.c
@@ -79,16 +79,16 @@ static struct ctl_table llc_table[] = {
{ },
};
-static struct ctl_path llc_path[] = {
- { .procname = "net", },
- { .procname = "llc", },
- { }
-};
-
static struct ctl_table_header *llc_table_header;
int __init llc_sysctl_init(void)
{
+ const struct ctl_path llc_path[] = {
+ { .procname = "net", },
+ { .procname = "llc", },
+ { }
+ };
+
llc_table_header = register_sysctl_paths(llc_path, llc_table);
return llc_table_header ? 0 : -ENOMEM;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index eb973fc..87529bb 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -407,14 +407,13 @@ static ctl_table nf_ct_netfilter_table[] = {
{ }
};
-static struct ctl_path nf_ct_path[] = {
- { .procname = "net", },
- { }
-};
-
static int nf_conntrack_standalone_init_sysctl(struct net *net)
{
struct ctl_table *table;
+ const struct ctl_path nf_ct_path[] = {
+ { .procname = "net", },
+ { }
+ };
if (net_eq(net, &init_net)) {
nf_ct_netfilter_header =
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 7df37fd..ad170df 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -209,13 +209,6 @@ static const struct file_operations nflog_file_ops = {
#endif /* PROC_FS */
#ifdef CONFIG_SYSCTL
-static struct ctl_path nf_log_sysctl_path[] = {
- { .procname = "net", },
- { .procname = "netfilter", },
- { .procname = "nf_log", },
- { }
-};
-
static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3];
static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1];
static struct ctl_table_header *nf_log_dir_header;
@@ -264,6 +257,12 @@ static int nf_log_proc_dostring(ctl_table *table, int write,
static __init int netfilter_log_sysctl_init(void)
{
int i;
+ const struct ctl_path nf_log_sysctl_path[] = {
+ { .procname = "net", },
+ { .procname = "netfilter", },
+ { .procname = "nf_log", },
+ { }
+ };
for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) {
snprintf(nf_log_sysctl_fnames[i-NFPROTO_UNSPEC], 3, "%d", i);
@@ -278,7 +277,7 @@ static __init int netfilter_log_sysctl_init(void)
}
nf_log_dir_header = register_sysctl_paths(nf_log_sysctl_path,
- nf_log_sysctl_table);
+ nf_log_sysctl_table);
if (!nf_log_dir_header)
return -ENOMEM;
diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c
index 1e0fa9e..235840a 100644
--- a/net/netrom/sysctl_net_netrom.c
+++ b/net/netrom/sysctl_net_netrom.c
@@ -146,14 +146,14 @@ static ctl_table nr_table[] = {
{ }
};
-static struct ctl_path nr_path[] = {
- { .procname = "net", },
- { .procname = "netrom", },
- { }
-};
-
void __init nr_register_sysctl(void)
{
+ const struct ctl_path nr_path[] = {
+ { .procname = "net", },
+ { .procname = "netrom", },
+ { }
+ };
+
nr_table_header = register_sysctl_paths(nr_path, nr_table);
}
diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c
index cea1c7d..5363afe 100644
--- a/net/phonet/sysctl.c
+++ b/net/phonet/sysctl.c
@@ -93,14 +93,14 @@ static struct ctl_table phonet_table[] = {
{ }
};
-static struct ctl_path phonet_ctl_path[] = {
- { .procname = "net", },
- { .procname = "phonet", },
- { },
-};
-
int __init phonet_sysctl_init(void)
{
+ const struct ctl_path phonet_ctl_path[] = {
+ { .procname = "net", },
+ { .procname = "phonet", },
+ { },
+ };
+
phonet_table_hrd = register_sysctl_paths(phonet_ctl_path, phonet_table);
return phonet_table_hrd == NULL ? -ENOMEM : 0;
}
diff --git a/net/rds/ib_sysctl.c b/net/rds/ib_sysctl.c
index fc3da37..301a504 100644
--- a/net/rds/ib_sysctl.c
+++ b/net/rds/ib_sysctl.c
@@ -106,13 +106,6 @@ ctl_table rds_ib_sysctl_table[] = {
{ }
};
-static struct ctl_path rds_ib_sysctl_path[] = {
- { .procname = "net", },
- { .procname = "rds", },
- { .procname = "ib", },
- { }
-};
-
void rds_ib_sysctl_exit(void)
{
if (rds_ib_sysctl_hdr)
@@ -121,7 +114,15 @@ void rds_ib_sysctl_exit(void)
int rds_ib_sysctl_init(void)
{
- rds_ib_sysctl_hdr = register_sysctl_paths(rds_ib_sysctl_path, rds_ib_sysctl_table);
+ const struct ctl_path rds_ib_sysctl_path[] = {
+ { .procname = "net", },
+ { .procname = "rds", },
+ { .procname = "ib", },
+ { }
+ };
+
+ rds_ib_sysctl_hdr = register_sysctl_paths(rds_ib_sysctl_path,
+ rds_ib_sysctl_table);
if (!rds_ib_sysctl_hdr)
return -ENOMEM;
return 0;
diff --git a/net/rds/iw_sysctl.c b/net/rds/iw_sysctl.c
index 23e3a9a..27b338f 100644
--- a/net/rds/iw_sysctl.c
+++ b/net/rds/iw_sysctl.c
@@ -109,13 +109,6 @@ ctl_table rds_iw_sysctl_table[] = {
{ }
};
-static struct ctl_path rds_iw_sysctl_path[] = {
- { .procname = "net", },
- { .procname = "rds", },
- { .procname = "iw", },
- { }
-};
-
void rds_iw_sysctl_exit(void)
{
if (rds_iw_sysctl_hdr)
@@ -124,7 +117,15 @@ void rds_iw_sysctl_exit(void)
int rds_iw_sysctl_init(void)
{
- rds_iw_sysctl_hdr = register_sysctl_paths(rds_iw_sysctl_path, rds_iw_sysctl_table);
+ const struct ctl_path rds_iw_sysctl_path[] = {
+ { .procname = "net", },
+ { .procname = "rds", },
+ { .procname = "iw", },
+ { }
+ };
+
+ rds_iw_sysctl_hdr = register_sysctl_paths(rds_iw_sysctl_path,
+ rds_iw_sysctl_table);
if (!rds_iw_sysctl_hdr)
return -ENOMEM;
return 0;
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index 25ad0c7..13fa563 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -92,13 +92,6 @@ static ctl_table rds_sysctl_rds_table[] = {
{ }
};
-static struct ctl_path rds_sysctl_path[] = {
- { .procname = "net", },
- { .procname = "rds", },
- { }
-};
-
-
void rds_sysctl_exit(void)
{
if (rds_sysctl_reg_table)
@@ -107,10 +100,17 @@ void rds_sysctl_exit(void)
int rds_sysctl_init(void)
{
+ const struct ctl_path rds_sysctl_path[] = {
+ { .procname = "net", },
+ { .procname = "rds", },
+ { }
+ };
+
rds_sysctl_reconnect_min = msecs_to_jiffies(1);
rds_sysctl_reconnect_min_jiffies = rds_sysctl_reconnect_min;
- rds_sysctl_reg_table = register_sysctl_paths(rds_sysctl_path, rds_sysctl_rds_table);
+ rds_sysctl_reg_table = register_sysctl_paths(rds_sysctl_path,
+ rds_sysctl_rds_table);
if (!rds_sysctl_reg_table)
return -ENOMEM;
return 0;
diff --git a/net/rose/sysctl_net_rose.c b/net/rose/sysctl_net_rose.c
index df6d9da..ed3da3b 100644
--- a/net/rose/sysctl_net_rose.c
+++ b/net/rose/sysctl_net_rose.c
@@ -118,14 +118,14 @@ static ctl_table rose_table[] = {
{ }
};
-static struct ctl_path rose_path[] = {
- { .procname = "net", },
- { .procname = "rose", },
- { }
-};
-
void __init rose_register_sysctl(void)
{
+ const struct ctl_path rose_path[] = {
+ { .procname = "net", },
+ { .procname = "rose", },
+ { }
+ };
+
rose_table_header = register_sysctl_paths(rose_path, rose_table);
}
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 832590b..6e4855e 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -255,17 +255,17 @@ static ctl_table sctp_table[] = {
{ /* sentinel */ }
};
-static struct ctl_path sctp_path[] = {
- { .procname = "net", },
- { .procname = "sctp", },
- { }
-};
-
static struct ctl_table_header * sctp_sysctl_header;
/* Sysctl registration. */
void sctp_sysctl_register(void)
{
+ const struct ctl_path sctp_path[] = {
+ { .procname = "net", },
+ { .procname = "sctp", },
+ { }
+ };
+
sctp_sysctl_header = register_sysctl_paths(sctp_path, sctp_table);
}
diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c
index 397cffe..397a837 100644
--- a/net/unix/sysctl_net_unix.c
+++ b/net/unix/sysctl_net_unix.c
@@ -26,15 +26,14 @@ static ctl_table unix_table[] = {
{ }
};
-static struct ctl_path unix_path[] = {
- { .procname = "net", },
- { .procname = "unix", },
- { },
-};
-
int __net_init unix_sysctl_register(struct net *net)
{
struct ctl_table *table;
+ const struct ctl_path unix_path[] = {
+ { .procname = "net", },
+ { .procname = "unix", },
+ { },
+ };
table = kmemdup(unix_table, sizeof(unix_table), GFP_KERNEL);
if (table == NULL)
diff --git a/net/x25/sysctl_net_x25.c b/net/x25/sysctl_net_x25.c
index d2efd29..fcd74db 100644
--- a/net/x25/sysctl_net_x25.c
+++ b/net/x25/sysctl_net_x25.c
@@ -73,14 +73,14 @@ static struct ctl_table x25_table[] = {
{ 0, },
};
-static struct ctl_path x25_path[] = {
- { .procname = "net", },
- { .procname = "x25", },
- { }
-};
-
void __init x25_register_sysctl(void)
{
+ const struct ctl_path x25_path[] = {
+ { .procname = "net", },
+ { .procname = "x25", },
+ { }
+ };
+
x25_table_header = register_sysctl_paths(x25_path, x25_table);
}
^ permalink raw reply related
* Re: Linux 2.6.35/TIPC 2.0 ABI breaking changes
From: nhorman @ 2010-10-20 1:09 UTC (permalink / raw)
To: Leandro Lucarella
Cc: jon.maloy, netdev, linux-kernel, tipc-discussion, David Miller
Yeah. I might have missed that. Although it did give me a.success message when I ran the test. That's why I asked.Dave not to pull it yet :). Well look at it.more closely in the am
Neil
Sent from my Verizon Wireless Phone
----- Reply message -----
From: "Leandro Lucarella" <luca@llucax.com.ar>
Date: Tue, Oct 19, 2010 4:43 pm
Subject: Linux 2.6.35/TIPC 2.0 ABI breaking changes
To: "Neil Horman" <nhorman@tuxdriver.com>
Cc: "David Miller" <davem@davemloft.net>, <paul.gortmaker@windriver.com>, <jon.maloy@ericsson.com>, <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>, <tipc-discussion@lists.sourceforge.net>
Neil Horman, el 19 de octubre a las 16:18 me escribiste:
> Hey all-
> Heres what I have so far. Dave as a heads up please don't apply this
> yet. I'd like to go over it a bit more and be sure of the implications here
> before I post it for inclusion officially. I wanted Leandro to have a copy
> though so he could confirm functionality for us. Leandro, This patch lets me
> pass the tipc test code for TIPC 1.6 that you posted earlier this morning. If
> you could confirm that it works for you that would be grand. While your doing
> that, I want to read over the spec for TIPC and make sure that I'm not breaking
> anything new with this patch.
Thanks for the quick response. I didn't tried the patch yet, but I think
spotted an error:
> diff --git a/include/linux/tipc.h b/include/linux/tipc.h
> index 181c8d0..d8de884 100644
> --- a/include/linux/tipc.h
> +++ b/include/linux/tipc.h
> @@ -127,9 +127,10 @@ static inline unsigned int tipc_node(__u32 addr)
> * TIPC topology subscription service definitions
> */
>
> -#define TIPC_SUB_SERVICE 0x00 /* Filter for service availability */
> -#define TIPC_SUB_PORTS 0x01 /* Filter for port availability */
> +#define TIPC_SUB_SERVICE 0x01 /* Filter for service availability */
> +#define TIPC_SUB_PORTS 0x02 /* Filter for port availability */
> #define TIPC_SUB_CANCEL 0x04 /* Cancel a subscription */
> +#define TIPC_SUB_MASK (TIPC_SUB_SERVICE|TIPC_SUB_PORTS|TIPC_SUB_CANCEL)
>
> #define TIPC_WAIT_FOREVER ~0 /* timeout for permanent subscription */
>
The values of TIPC_SUB_SERVICE and TIPC_SUB_PORTS seem to be swapped
compared to the old (TIPC 1.6) values:
#define TIPC_SUB_PORTS 0x01 /* filter for port availability */
#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */
You might missed this error when trying the code I posted earlier (which
BTW are the official TIPC demos) because the change of behaviour when
using TIPC_SUB_SERVICE and TIPC_SUB_PORTS is very subtle (the former
reports only the first published port name that matches, and the later
all the published ports that match).
I'll test the patch tomorrow morning (ART).
Thanks again.
--
Leandro Lucarella (AKA luca) http://llucax.com.ar/
----------------------------------------------------------------------
GPG Key: 5F5A8D05 (F8CD F9A7 BF00 5431 4145 104C 949E BFB6 5F5A 8D05)
----------------------------------------------------------------------
Long you live and high you fly
And smiles you'll give and tears you'll cry
And all you touch and all you see
Is all your life will ever be.
------------------------------------------------------------------------------
Download new Adobe(R) Flash(R) Builder(TM) 4
The new Adobe(R) Flex(R) 4 and Flash(R) Builder(TM) 4 (formerly
Flex(R) Builder(TM)) enable the development of rich applications that run
across multiple browsers and platforms. Download your free trials today!
http://p.sf.net/sfu/adobe-dev2dev
^ permalink raw reply
* DIAMOND LOAN
From: DIAMOND FINANCIAL SERVICE @ 2010-10-20 0:11 UTC (permalink / raw)
We are Diamond Financial Loan service, we are registered and guaranteed
loan company here in Europe, and we give out loans to individuals,
companies, government establishments, churches and business organizations.
Are you in need of a loan for any purpose? Are you in a financial problem?
Do you need financial solution? Diamond loans is the solution to all your
financial problems, our loans are easy, cheap, and quick. Contact us today
for that loan that you desire, we can arrange any loan to suit your budget
at only 3% interest rate,minimum of 5,000euros to maximum of 3 million
euros If interested, contact us immediately,
Best Regards
Mrs White Goldman
E mail:(d.financialloan1@qualityservice.com)
^ permalink raw reply
* Ethernet bridge not passing VLAN'd traffic
From: Erik Schweigert @ 2010-10-19 23:24 UTC (permalink / raw)
To: netdev
Hello list,
I have configured a transparent ethernet bridge containing two network
interfaces: eth0, eth1 in br0. IP forwarding is enabled i.e. cat
/proc/sys/net/ipv4/ip_forward = 1.
All traffic destined through my Linux machine has the 802.1Q tag
(VLAN). However, only ARP with the VLAN tags passes through the
machine correctly (100% of the time) and broadcast and multicast
appears to work. It 'seems' IP layer and above is being dropped if it
is unicast, or intermittently works ( +/- 1 of 10 ICMP passes
through).
All non-VLAN'd traffic passes through my machine flawlessly.
arptables, ebtables, and IPtables are all flushed, so there is no
possibility of any traffic being blocked.
Is there a caveat with ethernet bridging that does not permit VLAN'd traffic?
Any help or suggestions is greatly appreciated!
Thanks,
Erik
^ permalink raw reply
* Bug#595265: linux-image-2.6.32-5-686: Nerwork card fails to come up again after suspend
From: Francois Romieu @ 2010-10-19 23:06 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Ben Hutchings, Arnout Boelens, 595265, netdev
In-Reply-To: <1287442257.2361.11.camel@edumazet-laptop>
Eric Dumazet <eric.dumazet@gmail.com> :
> Le lundi 18 octobre 2010 à 23:45 +0200, Francois Romieu a écrit :
[...]
> > Something like the patch made by Stanislaw at :
> > https://bugzilla.redhat.com/show_bug.cgi?id=502974
> >
>
> Seems to be down at this moment, patch is also here (and included in
> 2.6.36-rc8 ) :
>
> http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=aeb19f6052b5e5c8a24aa444fbff73b84341beac
It's from the same author but it is not included in 2.6.36-stg yet :
Subject: [PATCH] r8169 init phy when resume
For unknown reasons some r8169 devices after resume operate at
100 Mb/s speed instead of 1000 Mb/s like before suspend. To fix
reset phy during resume.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
---
drivers/net/r8169.c | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 17382c3..a4ce127 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -4847,6 +4847,9 @@ static int rtl8169_resume(struct device *device)
{
struct pci_dev *pdev = to_pci_dev(device);
struct net_device *dev = pci_get_drvdata(pdev);
+ struct rtl8169_private *tp = netdev_priv(dev);
+
+ rtl8169_init_phy(dev, tp);
if (!netif_running(dev))
goto out;
--
1.7.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox