Release 4.9 samples/mic/mpssd/mpssd.c

/*
 * Intel MIC Platform Software Stack (MPSS)
 *
 * Copyright(c) 2013 Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * The full GNU General Public License is included in this distribution in
 * the file called "COPYING".
 *
 * Intel MIC User Space Tools.
 */


#define _GNU_SOURCE

#include <stdlib.h>
#include <fcntl.h>
#include <getopt.h>
#include <assert.h>
#include <unistd.h>
#include <stdbool.h>
#include <signal.h>
#include <poll.h>
#include <features.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <sys/socket.h>
#include <linux/virtio_ring.h>
#include <linux/virtio_net.h>
#include <linux/virtio_console.h>
#include <linux/virtio_blk.h>
#include <linux/version.h>
#include "mpssd.h"
#include <linux/mic_ioctl.h>
#include <linux/mic_common.h>
#include <tools/endian.h>

static void *init_mic(void *arg);


static FILE *logfp;

static struct mic_info mic_list;


#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))


#define min_t(type, x, y) ({                              \
                type __min1 = (x);                      \
                type __min2 = (y);                      \
                __min1 < __min2 ? __min1 : __min2; })

/* align addr on a size boundary - adjust address up/down if needed */

#define _ALIGN_DOWN(addr, size)  ((addr)&(~((size)-1)))

#define _ALIGN_UP(addr, size)    _ALIGN_DOWN(addr + size - 1, size)

/* align addr on a size boundary - adjust address up if needed */

#define _ALIGN(addr, size)     _ALIGN_UP(addr, size)

/* to align the pointer to the (next) page boundary */

#define PAGE_ALIGN(addr)        _ALIGN(addr, PAGE_SIZE)


#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))


#define GSO_ENABLED		1

#define MAX_GSO_SIZE		(64 * 1024)

#define ETH_H_LEN		14

#define MAX_NET_PKT_SIZE	(_ALIGN_UP(MAX_GSO_SIZE + ETH_H_LEN, 64))

#define MIC_DEVICE_PAGE_END	0x1000

#ifndef VIRTIO_NET_HDR_F_DATA_VALID

#define VIRTIO_NET_HDR_F_DATA_VALID	2	
/* Csum is valid */
#endif

static struct {
	
struct mic_device_desc dd;
	
struct mic_vqconfig vqconfig[2];
	

__u32 host_features, guest_acknowledgements;
	
struct virtio_console_config cons_config;
} 
virtcons_dev_page = {
	.dd = {
		.type = VIRTIO_ID_CONSOLE,
		.num_vq = ARRAY_SIZE(virtcons_dev_page.vqconfig),
		.feature_len = sizeof(virtcons_dev_page.host_features),
		.config_len = sizeof(virtcons_dev_page.cons_config),
        },
	.vqconfig[0] = {
		.num = htole16(MIC_VRING_ENTRIES),
        },
	.vqconfig[1] = {
		.num = htole16(MIC_VRING_ENTRIES),
        },
};

static struct {
	
struct mic_device_desc dd;
	
struct mic_vqconfig vqconfig[2];
	

__u32 host_features, guest_acknowledgements;
	
struct virtio_net_config net_config;
} 
virtnet_dev_page = {
	.dd = {
		.type = VIRTIO_ID_NET,
		.num_vq = ARRAY_SIZE(virtnet_dev_page.vqconfig),
		.feature_len = sizeof(virtnet_dev_page.host_features),
		.config_len = sizeof(virtnet_dev_page.net_config),
        },
	.vqconfig[0] = {
		.num = htole16(MIC_VRING_ENTRIES),
        },
	.vqconfig[1] = {
		.num = htole16(MIC_VRING_ENTRIES),
        },
#if GSO_ENABLED
	.host_features = htole32(
		1 << VIRTIO_NET_F_CSUM |
		1 << VIRTIO_NET_F_GSO |
		1 << VIRTIO_NET_F_GUEST_TSO4 |
		1 << VIRTIO_NET_F_GUEST_TSO6 |
		1 << VIRTIO_NET_F_GUEST_ECN),
#else
		.host_features = 0,
#endif
};


static const char *mic_config_dir = "/etc/mpss";

static const char *virtblk_backend = "VIRTBLK_BACKEND";
static struct {
	
struct mic_device_desc dd;
	
struct mic_vqconfig vqconfig[1];
	

__u32 host_features, guest_acknowledgements;
	
struct virtio_blk_config blk_config;
} 
virtblk_dev_page = {
	.dd = {
		.type = VIRTIO_ID_BLOCK,
		.num_vq = ARRAY_SIZE(virtblk_dev_page.vqconfig),
		.feature_len = sizeof(virtblk_dev_page.host_features),
		.config_len = sizeof(virtblk_dev_page.blk_config),
        },
	.vqconfig[0] = {
		.num = htole16(MIC_VRING_ENTRIES),
        },
	.host_features =
		htole32(1<<VIRTIO_BLK_F_SEG_MAX),
	.blk_config = {
		.seg_max = htole32(MIC_VRING_ENTRIES - 2),
		.capacity = htole64(0),
         }
};


static char *myname;


static int

tap_configure(struct mic_info *mic, char *dev)
{
	pid_t pid;
	char *ifargv[7];
	char ipaddr[IFNAMSIZ];
	int ret = 0;

	pid = fork();
	if (pid == 0) {
		ifargv[0] = "ip";
		ifargv[1] = "link";
		ifargv[2] = "set";
		ifargv[3] = dev;
		ifargv[4] = "up";
		ifargv[5] = NULL;
		mpsslog("Configuring %s\n", dev);
		ret = execvp("ip", ifargv);
		if (ret < 0) {
			mpsslog("%s execvp failed errno %s\n",
				mic->name, strerror(errno));
			return ret;
		}
	}
	if (pid < 0) {
		mpsslog("%s fork failed errno %s\n",
			mic->name, strerror(errno));
		return ret;
	}

	ret = waitpid(pid, NULL, 0);
	if (ret < 0) {
		mpsslog("%s waitpid failed errno %s\n",
			mic->name, strerror(errno));
		return ret;
	}

	snprintf(ipaddr, IFNAMSIZ, "172.31.%d.254/24", mic->id + 1);

	pid = fork();
	if (pid == 0) {
		ifargv[0] = "ip";
		ifargv[1] = "addr";
		ifargv[2] = "add";
		ifargv[3] = ipaddr;
		ifargv[4] = "dev";
		ifargv[5] = dev;
		ifargv[6] = NULL;
		mpsslog("Configuring %s ipaddr %s\n", dev, ipaddr);
		ret = execvp("ip", ifargv);
		if (ret < 0) {
			mpsslog("%s execvp failed errno %s\n",
				mic->name, strerror(errno));
			return ret;
		}
	}
	if (pid < 0) {
		mpsslog("%s fork failed errno %s\n",
			mic->name, strerror(errno));
		return ret;
	}

	ret = waitpid(pid, NULL, 0);
	if (ret < 0) {
		mpsslog("%s waitpid failed errno %s\n",
			mic->name, strerror(errno));
		return ret;
	}
	mpsslog("MIC name %s %s %d DONE!\n",
		mic->name, __func__, __LINE__);
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
388
99.49%
1
50.00%
ashutosh dixit
ashutosh dixit
2
0.51%
1
50.00%
Total
390
100.00%
2
100.00%



static int tun_alloc(struct mic_info *mic, char *dev)
{
	struct ifreq ifr;
	int fd, err;
#if GSO_ENABLED
	unsigned offload;
#endif
	fd = open("/dev/net/tun", O_RDWR);
	if (fd < 0) {
		mpsslog("Could not open /dev/net/tun %s\n", strerror(errno));
		goto done;
	}

	memset(&ifr, 0, sizeof(ifr));

	ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
	if (*dev)
		strncpy(ifr.ifr_name, dev, IFNAMSIZ);

	err = ioctl(fd, TUNSETIFF, (void *)&ifr);
	if (err < 0) {
		mpsslog("%s %s %d TUNSETIFF failed %s\n",
			mic->name, __func__, __LINE__, strerror(errno));
		close(fd);
		return err;
	}
#if GSO_ENABLED
	offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | TUN_F_TSO_ECN;

	err = ioctl(fd, TUNSETOFFLOAD, offload);
	if (err < 0) {
		mpsslog("%s %s %d TUNSETOFFLOAD failed %s\n",
			mic->name, __func__, __LINE__, strerror(errno));
		close(fd);
		return err;
	}
#endif
	strcpy(dev, ifr.ifr_name);
	mpsslog("Created TAP %s\n", dev);
done:
	return fd;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
232
100.00%
1
100.00%
Total
232
100.00%
1
100.00%


#define NET_FD_VIRTIO_NET 0

#define NET_FD_TUN 1

#define MAX_NET_FD 2



static void set_dp(struct mic_info *mic, int type, void *dp)
{
	switch (type) {
	case VIRTIO_ID_CONSOLE:
		mic->mic_console.console_dp = dp;
		return;
	case VIRTIO_ID_NET:
		mic->mic_net.net_dp = dp;
		return;
	case VIRTIO_ID_BLOCK:
		mic->mic_virtblk.block_dp = dp;
		return;
	}
	mpsslog("%s %s %d not found\n", mic->name, __func__, type);
	assert(0);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
78
100.00%
1
100.00%
Total
78
100.00%
1
100.00%



static void *get_dp(struct mic_info *mic, int type)
{
	switch (type) {
	case VIRTIO_ID_CONSOLE:
		return mic->mic_console.console_dp;
	case VIRTIO_ID_NET:
		return mic->mic_net.net_dp;
	case VIRTIO_ID_BLOCK:
		return mic->mic_virtblk.block_dp;
	}
	mpsslog("%s %s %d not found\n", mic->name, __func__, type);
	assert(0);
	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
72
100.00%
1
100.00%
Total
72
100.00%
1
100.00%



static struct mic_device_desc *get_device_desc(struct mic_info *mic, int type)
{
	struct mic_device_desc *d;
	int i;
	void *dp = get_dp(mic, type);

	for (i = sizeof(struct mic_bootparam); i < PAGE_SIZE;
		i += mic_total_desc_size(d)) {
		d = dp + i;

		/* End of list */
		if (d->type == 0)
			break;

		if (d->type == -1)
			continue;

		mpsslog("%s %s d-> type %d d %p\n",
			mic->name, __func__, d->type, d);

		if (d->type == (__u8)type)
			return d;
	}
	mpsslog("%s %s %d not found\n", mic->name, __func__, type);
	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
130
99.24%
1
50.00%
ashutosh dixit
ashutosh dixit
1
0.76%
1
50.00%
Total
131
100.00%
2
100.00%

/* See comments in vhost.c for explanation of next_desc() */


static unsigned next_desc(struct vring_desc *desc)
{
	unsigned int next;

	if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT))
		return -1U;
	next = le16toh(desc->next);
	return next;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
45
100.00%
1
100.00%
Total
45
100.00%
1
100.00%

/* Sum up all the IOVEC length */

static ssize_t

sum_iovec_len(struct mic_copy_desc *copy)
{
	ssize_t sum = 0;
	unsigned int i;

	for (i = 0; i < copy->iovcnt; i++)
		sum += copy->iov[i].iov_len;
	return sum;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
48
97.96%
1
50.00%
mahesh khanwalkar
mahesh khanwalkar
1
2.04%
1
50.00%
Total
49
100.00%
2
100.00%



static inline void verify_out_len(struct mic_info *mic,
	struct mic_copy_desc *copy)
{
	if (copy->out_len != sum_iovec_len(copy)) {
		mpsslog("%s %s %d BUG copy->out_len 0x%x len 0x%zx\n",
			mic->name, __func__, __LINE__,
			copy->out_len, sum_iovec_len(copy));
		assert(copy->out_len == sum_iovec_len(copy));
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
63
98.44%
1
50.00%
sudeep dutt
sudeep dutt
1
1.56%
1
50.00%
Total
64
100.00%
2
100.00%

/* Display an iovec */

static void

disp_iovec(struct mic_info *mic, struct mic_copy_desc *copy,
	   const char *s, int line)
{
	unsigned int i;

	for (i = 0; i < copy->iovcnt; i++)
		mpsslog("%s %s %d copy->iov[%d] addr %p len 0x%zx\n",
			mic->name, s, line, i,
			copy->iov[i].iov_base, copy->iov[i].iov_len);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
74
97.37%
1
33.33%
sudeep dutt
sudeep dutt
1
1.32%
1
33.33%
mahesh khanwalkar
mahesh khanwalkar
1
1.32%
1
33.33%
Total
76
100.00%
3
100.00%



static inline __u16 read_avail_idx(struct mic_vring *vr)
{
	return ACCESS_ONCE(vr->info->avail_idx);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
22
100.00%
1
100.00%
Total
22
100.00%
1
100.00%



static inline void txrx_prepare(int type, bool tx, struct mic_vring *vr,
				struct mic_copy_desc *copy, ssize_t len)
{
	copy->vr_idx = tx ? 0 : 1;
	copy->update_used = true;
	if (type == VIRTIO_ID_NET)
		copy->iov[1].iov_len = len - sizeof(struct virtio_net_hdr);
	else
		copy->iov[0].iov_len = len;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
77
100.00%
1
100.00%
Total
77
100.00%
1
100.00%

/* Central API which triggers the copies */

static int

mic_virtio_copy(struct mic_info *mic, int fd,
		struct mic_vring *vr, struct mic_copy_desc *copy)
{
	int ret;

	ret = ioctl(fd, MIC_VIRTIO_COPY_DESC, copy);
	if (ret) {
		mpsslog("%s %s %d errno %s ret %d\n",
			mic->name, __func__, __LINE__,
			strerror(errno), ret);
	}
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
67
100.00%
1
100.00%
Total
67
100.00%
1
100.00%



static inline unsigned _vring_size(unsigned int num, unsigned long align)
{
	return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num)
				+ align - 1) & ~(align - 1))
		+ sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
ashutosh dixit
ashutosh dixit
65
100.00%
1
100.00%
Total
65
100.00%
1
100.00%

/*
 * This initialization routine requires at least one
 * vring i.e. vr0. vr1 is optional.
 */

static void *

init_vr(struct mic_info *mic, int fd, int type,
	struct mic_vring *vr0, struct mic_vring *vr1, int num_vq)
{
	int vr_size;
	char *va;

	vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES,
					 MIC_VIRTIO_RING_ALIGN) +
			     sizeof(struct _mic_vring_info));
	va = mmap(NULL, MIC_DEVICE_PAGE_END + vr_size * num_vq,
		PROT_READ, MAP_SHARED, fd, 0);
	if (MAP_FAILED == va) {
		mpsslog("%s %s %d mmap failed errno %s\n",
			mic->name, __func__, __LINE__,
			strerror(errno));
		goto done;
	}
	set_dp(mic, type, va);
	vr0->va = (struct mic_vring *)&va[MIC_DEVICE_PAGE_END];
	vr0->info = vr0->va +
		_vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN);
	vring_init(&vr0->vr,
		   MIC_VRING_ENTRIES, vr0->va, MIC_VIRTIO_RING_ALIGN);
	mpsslog("%s %s vr0 %p vr0->info %p vr_size 0x%x vring 0x%x ",
		__func__, mic->name, vr0->va, vr0->info, vr_size,
		_vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN));
	mpsslog("magic 0x%x expected 0x%x\n",
		le32toh(vr0->info->magic), MIC_MAGIC + type);
	assert(le32toh(vr0->info->magic) == MIC_MAGIC + type);
	if (vr1) {
		vr1->va = (struct mic_vring *)
			&va[MIC_DEVICE_PAGE_END + vr_size];
		vr1->info = vr1->va + _vring_size(MIC_VRING_ENTRIES,
			MIC_VIRTIO_RING_ALIGN);
		vring_init(&vr1->vr,
			   MIC_VRING_ENTRIES, vr1->va, MIC_VIRTIO_RING_ALIGN);
		mpsslog("%s %s vr1 %p vr1->info %p vr_size 0x%x vring 0x%x ",
			__func__, mic->name, vr1->va, vr1->info, vr_size,
			_vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN));
		mpsslog("magic 0x%x expected 0x%x\n",
			le32toh(vr1->info->magic), MIC_MAGIC + type + 1);
		assert(le32toh(vr1->info->magic) == MIC_MAGIC + type + 1);
	}
done:
	return va;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
331
95.11%
1
33.33%
ashutosh dixit
ashutosh dixit
17
4.89%
2
66.67%
Total
348
100.00%
3
100.00%


static int

wait_for_card_driver(struct mic_info *mic, int fd, int type)
{
	struct pollfd pollfd;
	int err;
	struct mic_device_desc *desc = get_device_desc(mic, type);
	__u8 prev_status;

	if (!desc)
		return -ENODEV;
	prev_status = desc->status;
	pollfd.fd = fd;
	mpsslog("%s %s Waiting .... desc-> type %d status 0x%x\n",
		mic->name, __func__, type, desc->status);

	while (1) {
		pollfd.events = POLLIN;
		pollfd.revents = 0;
		err = poll(&pollfd, 1, -1);
		if (err < 0) {
			mpsslog("%s %s poll failed %s\n",
				mic->name, __func__, strerror(errno));
			continue;
		}

		if (pollfd.revents) {
			if (desc->status != prev_status) {
				mpsslog("%s %s Waiting... desc-> type %d "
					"status 0x%x\n",
					mic->name, __func__, type,
					desc->status);
				prev_status = desc->status;
			}
			if (desc->status & VIRTIO_CONFIG_S_DRIVER_OK) {
				mpsslog("%s %s poll.revents %d\n",
					mic->name, __func__, pollfd.revents);
				mpsslog("%s %s desc-> type %d status 0x%x\n",
					mic->name, __func__, type,
					desc->status);
				break;
			}
		}
	}
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
181
81.90%
1
50.00%
ashutosh dixit
ashutosh dixit
40
18.10%
1
50.00%
Total
221
100.00%
2
100.00%

/* Spin till we have some descriptors */

static void

spin_for_descriptors(struct mic_info *mic, struct mic_vring *vr)
{
	__u16 avail_idx = read_avail_idx(vr);

	while (avail_idx == le16toh(ACCESS_ONCE(vr->vr.avail->idx))) {
#ifdef DEBUG
		mpsslog("%s %s waiting for desc avail %d info_avail %d\n",
			mic->name, __func__,
			le16toh(vr->vr.avail->idx), vr->info->avail_idx);
#endif
		sched_yield();
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
caz yokoyama
caz yokoyama
80
100.00%
1
100.00%
Total
80
100.00%
1
100.00%


static void *

virtio_net(void *arg)
{
	static __u8 vnet_hdr[2][sizeof(struct virtio_net_hdr)];
	static __u8 vnet_buf[2][MAX_NET_PKT_SIZE] __attribute__ ((aligned(64)));
	struct iovec vnet_iov[2][2] = {
		{ { .iov_base = vnet_hdr[0], .iov_len = sizeof(vnet_hdr[0]) },
		  { .iov_base = vnet_buf[0], .iov_len = sizeof(vnet_buf[0]) } },
		{ { .iov_base = vnet_hdr[1], .iov_len = sizeof(vnet_hdr[1]) },
		  { .iov_base = vnet_buf[1], .iov_len = sizeof(vnet_buf[1]) } },
        };
	struct iovec *iov0 = vnet_iov[0], *iov1 = vnet_iov[1];
	struct mic_info *mic = (struct mic_info *)arg;
	char if_name[IFNAMSIZ];
	struct pollfd net_poll[MAX_NET_FD];
	struct mic_vring tx_vr, rx_vr;
	struct mic_copy_desc copy;
	struct mic_device_desc *desc;
	int err;

	snprintf(if_name, IFNAMSIZ, "mic%d", mic->id);
	mic->mic_net.tap_fd = tun_alloc(mic, if_name);
	if (mic->mic_net.tap_fd < 0)
		goto done;

	if (tap_configure(mic, if_name))
		goto done;
	mpsslog("MIC name %s id %d\n", mic->name, mic->id);

	net_poll[NET_FD_VIRTIO_NET].fd = mic->mic_net.virtio_net_fd;
	net_poll[NET_FD_VIRTIO_NET].events = POLLIN;