From 6bee835dd54e279f3d3ae2eca92a9c394b4fd028 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Fri, 16 Sep 2016 15:53:52 -0600 Subject: samples: move mic/mpssd example code from Documentation Move mic/mpssd examples to samples and remove it from Documentation Makefile. Create a new Makefile to build mic/mpssd. It can be built from top level directory or from mic/mpssd directory: Run make -C samples/mic/mpssd or cd samples/mic/mpssd; make Acked-by: Jonathan Corbet Signed-off-by: Shuah Khan --- samples/mic/mpssd/.gitignore | 1 + samples/mic/mpssd/Makefile | 27 + samples/mic/mpssd/micctrl | 173 ++++ samples/mic/mpssd/mpss | 200 +++++ samples/mic/mpssd/mpssd.c | 1826 ++++++++++++++++++++++++++++++++++++++++++ samples/mic/mpssd/mpssd.h | 103 +++ samples/mic/mpssd/sysfs.c | 102 +++ 7 files changed, 2432 insertions(+) create mode 100644 samples/mic/mpssd/.gitignore create mode 100644 samples/mic/mpssd/Makefile create mode 100755 samples/mic/mpssd/micctrl create mode 100755 samples/mic/mpssd/mpss create mode 100644 samples/mic/mpssd/mpssd.c create mode 100644 samples/mic/mpssd/mpssd.h create mode 100644 samples/mic/mpssd/sysfs.c (limited to 'samples') diff --git a/samples/mic/mpssd/.gitignore b/samples/mic/mpssd/.gitignore new file mode 100644 index 000000000000..8b7c72f07c92 --- /dev/null +++ b/samples/mic/mpssd/.gitignore @@ -0,0 +1 @@ +mpssd diff --git a/samples/mic/mpssd/Makefile b/samples/mic/mpssd/Makefile new file mode 100644 index 000000000000..3e3ef91fed6b --- /dev/null +++ b/samples/mic/mpssd/Makefile @@ -0,0 +1,27 @@ +ifndef CROSS_COMPILE +uname_M := $(shell uname -m 2>/dev/null || echo not) +ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) + +ifeq ($(ARCH),x86) + +PROGS := mpssd +CC = $(CROSS_COMPILE)gcc +CFLAGS := -I../../../usr/include -I../../../tools/include + +ifdef DEBUG +CFLAGS += -DDEBUG=$(DEBUG) +endif + +all: $(PROGS) +mpssd: mpssd.c sysfs.c + $(CC) $(CFLAGS) mpssd.c sysfs.c -o mpssd -lpthread + +install: + install mpssd /usr/sbin/mpssd + install micctrl /usr/sbin/micctrl + +clean: + rm -fr $(PROGS) + +endif +endif diff --git a/samples/mic/mpssd/micctrl b/samples/mic/mpssd/micctrl new file mode 100755 index 000000000000..8f2629b41c5f --- /dev/null +++ b/samples/mic/mpssd/micctrl @@ -0,0 +1,173 @@ +#!/bin/bash +# Intel MIC Platform Software Stack (MPSS) +# +# Copyright(c) 2013 Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License, version 2, as +# published by the Free Software Foundation. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# General Public License for more details. +# +# The full GNU General Public License is included in this distribution in +# the file called "COPYING". +# +# Intel MIC User Space Tools. +# +# micctrl - Controls MIC boot/start/stop. +# +# chkconfig: 2345 95 05 +# description: start MPSS stack processing. +# +### BEGIN INIT INFO +# Provides: micctrl +### END INIT INFO + +# Source function library. +. /etc/init.d/functions + +sysfs="/sys/class/mic" + +_status() +{ + f=$sysfs/$1 + echo -e $1 state: "`cat $f/state`" shutdown_status: "`cat $f/shutdown_status`" +} + +status() +{ + if [ "`echo $1 | head -c3`" == "mic" ]; then + _status $1 + return $? + fi + for f in $sysfs/* + do + _status `basename $f` + RETVAL=$? + [ $RETVAL -ne 0 ] && return $RETVAL + done + return 0 +} + +_reset() +{ + f=$sysfs/$1 + echo reset > $f/state +} + +reset() +{ + if [ "`echo $1 | head -c3`" == "mic" ]; then + _reset $1 + return $? + fi + for f in $sysfs/* + do + _reset `basename $f` + RETVAL=$? + [ $RETVAL -ne 0 ] && return $RETVAL + done + return 0 +} + +_boot() +{ + f=$sysfs/$1 + echo "linux" > $f/bootmode + echo "mic/uos.img" > $f/firmware + echo "mic/$1.image" > $f/ramdisk + echo "boot" > $f/state +} + +boot() +{ + if [ "`echo $1 | head -c3`" == "mic" ]; then + _boot $1 + return $? + fi + for f in $sysfs/* + do + _boot `basename $f` + RETVAL=$? + [ $RETVAL -ne 0 ] && return $RETVAL + done + return 0 +} + +_shutdown() +{ + f=$sysfs/$1 + echo shutdown > $f/state +} + +shutdown() +{ + if [ "`echo $1 | head -c3`" == "mic" ]; then + _shutdown $1 + return $? + fi + for f in $sysfs/* + do + _shutdown `basename $f` + RETVAL=$? + [ $RETVAL -ne 0 ] && return $RETVAL + done + return 0 +} + +_wait() +{ + f=$sysfs/$1 + while [ "`cat $f/state`" != "offline" -a "`cat $f/state`" != "online" ] + do + sleep 1 + echo -e "Waiting for $1 to go offline" + done +} + +wait() +{ + if [ "`echo $1 | head -c3`" == "mic" ]; then + _wait $1 + return $? + fi + # Wait for the cards to go offline + for f in $sysfs/* + do + _wait `basename $f` + RETVAL=$? + [ $RETVAL -ne 0 ] && return $RETVAL + done + return 0 +} + +if [ ! -d "$sysfs" ]; then + echo -e $"Module unloaded " + exit 3 +fi + +case $1 in + -s) + status $2 + ;; + -r) + reset $2 + ;; + -b) + boot $2 + ;; + -S) + shutdown $2 + ;; + -w) + wait $2 + ;; + *) + echo $"Usage: $0 {-s (status) |-r (reset) |-b (boot) |-S (shutdown) |-w (wait)}" + exit 2 +esac + +exit $? diff --git a/samples/mic/mpssd/mpss b/samples/mic/mpssd/mpss new file mode 100755 index 000000000000..5fcf9fa4b082 --- /dev/null +++ b/samples/mic/mpssd/mpss @@ -0,0 +1,200 @@ +#!/bin/bash +# 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. +# +# mpss Start mpssd. +# +# chkconfig: 2345 95 05 +# description: start MPSS stack processing. +# +### BEGIN INIT INFO +# Provides: mpss +# Required-Start: +# Required-Stop: +# Short-Description: MPSS stack control +# Description: MPSS stack control +### END INIT INFO + +# Source function library. +. /etc/init.d/functions + +exec=/usr/sbin/mpssd +sysfs="/sys/class/mic" +mic_modules="mic_host mic_x100_dma scif vop" + +start() +{ + [ -x $exec ] || exit 5 + + if [ "`ps -e | awk '{print $4}' | grep mpssd | head -1`" = "mpssd" ]; then + echo -e $"MPSSD already running! " + success + echo + return 0 + fi + + echo -e $"Starting MPSS Stack" + echo -e $"Loading MIC drivers:" $mic_modules + + modprobe -a $mic_modules + RETVAL=$? + if [ $RETVAL -ne 0 ]; then + failure + echo + return $RETVAL + fi + + # Start the daemon + echo -n $"Starting MPSSD " + $exec + RETVAL=$? + if [ $RETVAL -ne 0 ]; then + failure + echo + return $RETVAL + fi + success + echo + + sleep 5 + + # Boot the cards + micctrl -b + + # Wait till ping works + for f in $sysfs/* + do + count=100 + ipaddr=`cat $f/cmdline` + ipaddr=${ipaddr#*address,} + ipaddr=`echo $ipaddr | cut -d, -f1 | cut -d\; -f1` + while [ $count -ge 0 ] + do + echo -e "Pinging "`basename $f`" " + ping -c 1 $ipaddr &> /dev/null + RETVAL=$? + if [ $RETVAL -eq 0 ]; then + success + break + fi + sleep 1 + count=`expr $count - 1` + done + [ $RETVAL -ne 0 ] && failure || success + echo + done + return $RETVAL +} + +stop() +{ + echo -e $"Shutting down MPSS Stack: " + + # Bail out if module is unloaded + if [ ! -d "$sysfs" ]; then + echo -n $"Module unloaded " + success + echo + return 0 + fi + + # Shut down the cards. + micctrl -S + + # Wait for the cards to go offline + for f in $sysfs/* + do + while [ "`cat $f/state`" != "ready" ] + do + sleep 1 + echo -e "Waiting for "`basename $f`" to become ready" + done + done + + # Display the status of the cards + micctrl -s + + # Kill MPSSD now + echo -n $"Killing MPSSD" + killall -9 mpssd 2>/dev/null + RETVAL=$? + [ $RETVAL -ne 0 ] && failure || success + echo + return $RETVAL +} + +restart() +{ + stop + sleep 5 + start +} + +status() +{ + micctrl -s + if [ "`ps -e | awk '{print $4}' | grep mpssd | head -n 1`" = "mpssd" ]; then + echo "mpssd is running" + else + echo "mpssd is stopped" + fi + return 0 +} + +unload() +{ + if [ ! -d "$sysfs" ]; then + echo -n $"No MIC_HOST Module: " + success + echo + return + fi + + stop + + sleep 5 + echo -n $"Removing MIC drivers:" $mic_modules + modprobe -r $mic_modules + RETVAL=$? + [ $RETVAL -ne 0 ] && failure || success + echo + return $RETVAL +} + +case $1 in + start) + start + ;; + stop) + stop + ;; + restart) + restart + ;; + status) + status + ;; + unload) + unload + ;; + *) + echo $"Usage: $0 {start|stop|restart|status|unload}" + exit 2 +esac + +exit $? diff --git a/samples/mic/mpssd/mpssd.c b/samples/mic/mpssd/mpssd.c new file mode 100644 index 000000000000..49db1def1721 --- /dev/null +++ b/samples/mic/mpssd/mpssd.c @@ -0,0 +1,1826 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "mpssd.h" +#include +#include +#include + +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<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; +} + +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; +} + +#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); +} + +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; +} + +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; +} + +/* 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; +} + +/* 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; +} + +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)); + } +} + +/* 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); +} + +static inline __u16 read_avail_idx(struct mic_vring *vr) +{ + return ACCESS_ONCE(vr->info->avail_idx); +} + +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; +} + +/* 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; +} + +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; +} + +/* + * 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; +} + +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; +} + +/* 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(); + } +} + +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; + net_poll[NET_FD_TUN].fd = mic->mic_net.tap_fd; + net_poll[NET_FD_TUN].events = POLLIN; + + if (MAP_FAILED == init_vr(mic, mic->mic_net.virtio_net_fd, + VIRTIO_ID_NET, &tx_vr, &rx_vr, + virtnet_dev_page.dd.num_vq)) { + mpsslog("%s init_vr failed %s\n", + mic->name, strerror(errno)); + goto done; + } + + copy.iovcnt = 2; + desc = get_device_desc(mic, VIRTIO_ID_NET); + + while (1) { + ssize_t len; + + net_poll[NET_FD_VIRTIO_NET].revents = 0; + net_poll[NET_FD_TUN].revents = 0; + + /* Start polling for data from tap and virtio net */ + err = poll(net_poll, 2, -1); + if (err < 0) { + mpsslog("%s poll failed %s\n", + __func__, strerror(errno)); + continue; + } + if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) { + err = wait_for_card_driver(mic, + mic->mic_net.virtio_net_fd, + VIRTIO_ID_NET); + if (err) { + mpsslog("%s %s %d Exiting...\n", + mic->name, __func__, __LINE__); + break; + } + } + /* + * Check if there is data to be read from TUN and write to + * virtio net fd if there is. + */ + if (net_poll[NET_FD_TUN].revents & POLLIN) { + copy.iov = iov0; + len = readv(net_poll[NET_FD_TUN].fd, + copy.iov, copy.iovcnt); + if (len > 0) { + struct virtio_net_hdr *hdr + = (struct virtio_net_hdr *)vnet_hdr[0]; + + /* Disable checksums on the card since we are on + a reliable PCIe link */ + hdr->flags |= VIRTIO_NET_HDR_F_DATA_VALID; +#ifdef DEBUG + mpsslog("%s %s %d hdr->flags 0x%x ", mic->name, + __func__, __LINE__, hdr->flags); + mpsslog("copy.out_len %d hdr->gso_type 0x%x\n", + copy.out_len, hdr->gso_type); +#endif +#ifdef DEBUG + disp_iovec(mic, copy, __func__, __LINE__); + mpsslog("%s %s %d read from tap 0x%lx\n", + mic->name, __func__, __LINE__, + len); +#endif + spin_for_descriptors(mic, &tx_vr); + txrx_prepare(VIRTIO_ID_NET, 1, &tx_vr, ©, + len); + + err = mic_virtio_copy(mic, + mic->mic_net.virtio_net_fd, &tx_vr, + ©); + if (err < 0) { + mpsslog("%s %s %d mic_virtio_copy %s\n", + mic->name, __func__, __LINE__, + strerror(errno)); + } + if (!err) + verify_out_len(mic, ©); +#ifdef DEBUG + disp_iovec(mic, copy, __func__, __LINE__); + mpsslog("%s %s %d wrote to net 0x%lx\n", + mic->name, __func__, __LINE__, + sum_iovec_len(©)); +#endif + /* Reinitialize IOV for next run */ + iov0[1].iov_len = MAX_NET_PKT_SIZE; + } else if (len < 0) { + disp_iovec(mic, ©, __func__, __LINE__); + mpsslog("%s %s %d read failed %s ", mic->name, + __func__, __LINE__, strerror(errno)); + mpsslog("cnt %d sum %zd\n", + copy.iovcnt, sum_iovec_len(©)); + } + } + + /* + * Check if there is data to be read from virtio net and + * write to TUN if there is. + */ + if (net_poll[NET_FD_VIRTIO_NET].revents & POLLIN) { + while (rx_vr.info->avail_idx != + le16toh(rx_vr.vr.avail->idx)) { + copy.iov = iov1; + txrx_prepare(VIRTIO_ID_NET, 0, &rx_vr, ©, + MAX_NET_PKT_SIZE + + sizeof(struct virtio_net_hdr)); + + err = mic_virtio_copy(mic, + mic->mic_net.virtio_net_fd, &rx_vr, + ©); + if (!err) { +#ifdef DEBUG + struct virtio_net_hdr *hdr + = (struct virtio_net_hdr *) + vnet_hdr[1]; + + mpsslog("%s %s %d hdr->flags 0x%x, ", + mic->name, __func__, __LINE__, + hdr->flags); + mpsslog("out_len %d gso_type 0x%x\n", + copy.out_len, + hdr->gso_type); +#endif + /* Set the correct output iov_len */ + iov1[1].iov_len = copy.out_len - + sizeof(struct virtio_net_hdr); + verify_out_len(mic, ©); +#ifdef DEBUG + disp_iovec(mic, copy, __func__, + __LINE__); + mpsslog("%s %s %d ", + mic->name, __func__, __LINE__); + mpsslog("read from net 0x%lx\n", + sum_iovec_len(copy)); +#endif + len = writev(net_poll[NET_FD_TUN].fd, + copy.iov, copy.iovcnt); + if (len != sum_iovec_len(©)) { + mpsslog("Tun write failed %s ", + strerror(errno)); + mpsslog("len 0x%zx ", len); + mpsslog("read_len 0x%zx\n", + sum_iovec_len(©)); + } else { +#ifdef DEBUG + disp_iovec(mic, ©, __func__, + __LINE__); + mpsslog("%s %s %d ", + mic->name, __func__, + __LINE__); + mpsslog("wrote to tap 0x%lx\n", + len); +#endif + } + } else { + mpsslog("%s %s %d mic_virtio_copy %s\n", + mic->name, __func__, __LINE__, + strerror(errno)); + break; + } + } + } + if (net_poll[NET_FD_VIRTIO_NET].revents & POLLERR) + mpsslog("%s: %s: POLLERR\n", __func__, mic->name); + } +done: + pthread_exit(NULL); +} + +/* virtio_console */ +#define VIRTIO_CONSOLE_FD 0 +#define MONITOR_FD (VIRTIO_CONSOLE_FD + 1) +#define MAX_CONSOLE_FD (MONITOR_FD + 1) /* must be the last one + 1 */ +#define MAX_BUFFER_SIZE PAGE_SIZE + +static void * +virtio_console(void *arg) +{ + static __u8 vcons_buf[2][PAGE_SIZE]; + struct iovec vcons_iov[2] = { + { .iov_base = vcons_buf[0], .iov_len = sizeof(vcons_buf[0]) }, + { .iov_base = vcons_buf[1], .iov_len = sizeof(vcons_buf[1]) }, + }; + struct iovec *iov0 = &vcons_iov[0], *iov1 = &vcons_iov[1]; + struct mic_info *mic = (struct mic_info *)arg; + int err; + struct pollfd console_poll[MAX_CONSOLE_FD]; + int pty_fd; + char *pts_name; + ssize_t len; + struct mic_vring tx_vr, rx_vr; + struct mic_copy_desc copy; + struct mic_device_desc *desc; + + pty_fd = posix_openpt(O_RDWR); + if (pty_fd < 0) { + mpsslog("can't open a pseudoterminal master device: %s\n", + strerror(errno)); + goto _return; + } + pts_name = ptsname(pty_fd); + if (pts_name == NULL) { + mpsslog("can't get pts name\n"); + goto _close_pty; + } + printf("%s console message goes to %s\n", mic->name, pts_name); + mpsslog("%s console message goes to %s\n", mic->name, pts_name); + err = grantpt(pty_fd); + if (err < 0) { + mpsslog("can't grant access: %s %s\n", + pts_name, strerror(errno)); + goto _close_pty; + } + err = unlockpt(pty_fd); + if (err < 0) { + mpsslog("can't unlock a pseudoterminal: %s %s\n", + pts_name, strerror(errno)); + goto _close_pty; + } + console_poll[MONITOR_FD].fd = pty_fd; + console_poll[MONITOR_FD].events = POLLIN; + + console_poll[VIRTIO_CONSOLE_FD].fd = mic->mic_console.virtio_console_fd; + console_poll[VIRTIO_CONSOLE_FD].events = POLLIN; + + if (MAP_FAILED == init_vr(mic, mic->mic_console.virtio_console_fd, + VIRTIO_ID_CONSOLE, &tx_vr, &rx_vr, + virtcons_dev_page.dd.num_vq)) { + mpsslog("%s init_vr failed %s\n", + mic->name, strerror(errno)); + goto _close_pty; + } + + copy.iovcnt = 1; + desc = get_device_desc(mic, VIRTIO_ID_CONSOLE); + + for (;;) { + console_poll[MONITOR_FD].revents = 0; + console_poll[VIRTIO_CONSOLE_FD].revents = 0; + err = poll(console_poll, MAX_CONSOLE_FD, -1); + if (err < 0) { + mpsslog("%s %d: poll failed: %s\n", __func__, __LINE__, + strerror(errno)); + continue; + } + if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) { + err = wait_for_card_driver(mic, + mic->mic_console.virtio_console_fd, + VIRTIO_ID_CONSOLE); + if (err) { + mpsslog("%s %s %d Exiting...\n", + mic->name, __func__, __LINE__); + break; + } + } + + if (console_poll[MONITOR_FD].revents & POLLIN) { + copy.iov = iov0; + len = readv(pty_fd, copy.iov, copy.iovcnt); + if (len > 0) { +#ifdef DEBUG + disp_iovec(mic, copy, __func__, __LINE__); + mpsslog("%s %s %d read from tap 0x%lx\n", + mic->name, __func__, __LINE__, + len); +#endif + spin_for_descriptors(mic, &tx_vr); + txrx_prepare(VIRTIO_ID_CONSOLE, 1, &tx_vr, + ©, len); + + err = mic_virtio_copy(mic, + mic->mic_console.virtio_console_fd, + &tx_vr, ©); + if (err < 0) { + mpsslog("%s %s %d mic_virtio_copy %s\n", + mic->name, __func__, __LINE__, + strerror(errno)); + } + if (!err) + verify_out_len(mic, ©); +#ifdef DEBUG + disp_iovec(mic, copy, __func__, __LINE__); + mpsslog("%s %s %d wrote to net 0x%lx\n", + mic->name, __func__, __LINE__, + sum_iovec_len(copy)); +#endif + /* Reinitialize IOV for next run */ + iov0->iov_len = PAGE_SIZE; + } else if (len < 0) { + disp_iovec(mic, ©, __func__, __LINE__); + mpsslog("%s %s %d read failed %s ", + mic->name, __func__, __LINE__, + strerror(errno)); + mpsslog("cnt %d sum %zd\n", + copy.iovcnt, sum_iovec_len(©)); + } + } + + if (console_poll[VIRTIO_CONSOLE_FD].revents & POLLIN) { + while (rx_vr.info->avail_idx != + le16toh(rx_vr.vr.avail->idx)) { + copy.iov = iov1; + txrx_prepare(VIRTIO_ID_CONSOLE, 0, &rx_vr, + ©, PAGE_SIZE); + + err = mic_virtio_copy(mic, + mic->mic_console.virtio_console_fd, + &rx_vr, ©); + if (!err) { + /* Set the correct output iov_len */ + iov1->iov_len = copy.out_len; + verify_out_len(mic, ©); +#ifdef DEBUG + disp_iovec(mic, copy, __func__, + __LINE__); + mpsslog("%s %s %d ", + mic->name, __func__, __LINE__); + mpsslog("read from net 0x%lx\n", + sum_iovec_len(copy)); +#endif + len = writev(pty_fd, + copy.iov, copy.iovcnt); + if (len != sum_iovec_len(©)) { + mpsslog("Tun write failed %s ", + strerror(errno)); + mpsslog("len 0x%zx ", len); + mpsslog("read_len 0x%zx\n", + sum_iovec_len(©)); + } else { +#ifdef DEBUG + disp_iovec(mic, copy, __func__, + __LINE__); + mpsslog("%s %s %d ", + mic->name, __func__, + __LINE__); + mpsslog("wrote to tap 0x%lx\n", + len); +#endif + } + } else { + mpsslog("%s %s %d mic_virtio_copy %s\n", + mic->name, __func__, __LINE__, + strerror(errno)); + break; + } + } + } + if (console_poll[NET_FD_VIRTIO_NET].revents & POLLERR) + mpsslog("%s: %s: POLLERR\n", __func__, mic->name); + } +_close_pty: + close(pty_fd); +_return: + pthread_exit(NULL); +} + +static void +add_virtio_device(struct mic_info *mic, struct mic_device_desc *dd) +{ + char path[PATH_MAX]; + int fd, err; + + snprintf(path, PATH_MAX, "/dev/vop_virtio%d", mic->id); + fd = open(path, O_RDWR); + if (fd < 0) { + mpsslog("Could not open %s %s\n", path, strerror(errno)); + return; + } + + err = ioctl(fd, MIC_VIRTIO_ADD_DEVICE, dd); + if (err < 0) { + mpsslog("Could not add %d %s\n", dd->type, strerror(errno)); + close(fd); + return; + } + switch (dd->type) { + case VIRTIO_ID_NET: + mic->mic_net.virtio_net_fd = fd; + mpsslog("Added VIRTIO_ID_NET for %s\n", mic->name); + break; + case VIRTIO_ID_CONSOLE: + mic->mic_console.virtio_console_fd = fd; + mpsslog("Added VIRTIO_ID_CONSOLE for %s\n", mic->name); + break; + case VIRTIO_ID_BLOCK: + mic->mic_virtblk.virtio_block_fd = fd; + mpsslog("Added VIRTIO_ID_BLOCK for %s\n", mic->name); + break; + } +} + +static bool +set_backend_file(struct mic_info *mic) +{ + FILE *config; + char buff[PATH_MAX], *line, *evv, *p; + + snprintf(buff, PATH_MAX, "%s/mpssd%03d.conf", mic_config_dir, mic->id); + config = fopen(buff, "r"); + if (config == NULL) + return false; + do { /* look for "virtblk_backend=XXXX" */ + line = fgets(buff, PATH_MAX, config); + if (line == NULL) + break; + if (*line == '#') + continue; + p = strchr(line, '\n'); + if (p) + *p = '\0'; + } while (strncmp(line, virtblk_backend, strlen(virtblk_backend)) != 0); + fclose(config); + if (line == NULL) + return false; + evv = strchr(line, '='); + if (evv == NULL) + return false; + mic->mic_virtblk.backend_file = malloc(strlen(evv) + 1); + if (mic->mic_virtblk.backend_file == NULL) { + mpsslog("%s %d can't allocate memory\n", mic->name, mic->id); + return false; + } + strcpy(mic->mic_virtblk.backend_file, evv + 1); + return true; +} + +#define SECTOR_SIZE 512 +static bool +set_backend_size(struct mic_info *mic) +{ + mic->mic_virtblk.backend_size = lseek(mic->mic_virtblk.backend, 0, + SEEK_END); + if (mic->mic_virtblk.backend_size < 0) { + mpsslog("%s: can't seek: %s\n", + mic->name, mic->mic_virtblk.backend_file); + return false; + } + virtblk_dev_page.blk_config.capacity = + mic->mic_virtblk.backend_size / SECTOR_SIZE; + if ((mic->mic_virtblk.backend_size % SECTOR_SIZE) != 0) + virtblk_dev_page.blk_config.capacity++; + + virtblk_dev_page.blk_config.capacity = + htole64(virtblk_dev_page.blk_config.capacity); + + return true; +} + +static bool +open_backend(struct mic_info *mic) +{ + if (!set_backend_file(mic)) + goto _error_exit; + mic->mic_virtblk.backend = open(mic->mic_virtblk.backend_file, O_RDWR); + if (mic->mic_virtblk.backend < 0) { + mpsslog("%s: can't open: %s\n", mic->name, + mic->mic_virtblk.backend_file); + goto _error_free; + } + if (!set_backend_size(mic)) + goto _error_close; + mic->mic_virtblk.backend_addr = mmap(NULL, + mic->mic_virtblk.backend_size, + PROT_READ|PROT_WRITE, MAP_SHARED, + mic->mic_virtblk.backend, 0L); + if (mic->mic_virtblk.backend_addr == MAP_FAILED) { + mpsslog("%s: can't map: %s %s\n", + mic->name, mic->mic_virtblk.backend_file, + strerror(errno)); + goto _error_close; + } + return true; + + _error_close: + close(mic->mic_virtblk.backend); + _error_free: + free(mic->mic_virtblk.backend_file); + _error_exit: + return false; +} + +static void +close_backend(struct mic_info *mic) +{ + munmap(mic->mic_virtblk.backend_addr, mic->mic_virtblk.backend_size); + close(mic->mic_virtblk.backend); + free(mic->mic_virtblk.backend_file); +} + +static bool +start_virtblk(struct mic_info *mic, struct mic_vring *vring) +{ + if (((unsigned long)&virtblk_dev_page.blk_config % 8) != 0) { + mpsslog("%s: blk_config is not 8 byte aligned.\n", + mic->name); + return false; + } + add_virtio_device(mic, &virtblk_dev_page.dd); + if (MAP_FAILED == init_vr(mic, mic->mic_virtblk.virtio_block_fd, + VIRTIO_ID_BLOCK, vring, NULL, + virtblk_dev_page.dd.num_vq)) { + mpsslog("%s init_vr failed %s\n", + mic->name, strerror(errno)); + return false; + } + return true; +} + +static void +stop_virtblk(struct mic_info *mic) +{ + int vr_size, ret; + + vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES, + MIC_VIRTIO_RING_ALIGN) + + sizeof(struct _mic_vring_info)); + ret = munmap(mic->mic_virtblk.block_dp, + MIC_DEVICE_PAGE_END + vr_size * virtblk_dev_page.dd.num_vq); + if (ret < 0) + mpsslog("%s munmap errno %d\n", mic->name, errno); + close(mic->mic_virtblk.virtio_block_fd); +} + +static __u8 +header_error_check(struct vring_desc *desc) +{ + if (le32toh(desc->len) != sizeof(struct virtio_blk_outhdr)) { + mpsslog("%s() %d: length is not sizeof(virtio_blk_outhd)\n", + __func__, __LINE__); + return -EIO; + } + if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT)) { + mpsslog("%s() %d: alone\n", + __func__, __LINE__); + return -EIO; + } + if (le16toh(desc->flags) & VRING_DESC_F_WRITE) { + mpsslog("%s() %d: not read\n", + __func__, __LINE__); + return -EIO; + } + return 0; +} + +static int +read_header(int fd, struct virtio_blk_outhdr *hdr, __u32 desc_idx) +{ + struct iovec iovec; + struct mic_copy_desc copy; + + iovec.iov_len = sizeof(*hdr); + iovec.iov_base = hdr; + copy.iov = &iovec; + copy.iovcnt = 1; + copy.vr_idx = 0; /* only one vring on virtio_block */ + copy.update_used = false; /* do not update used index */ + return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©); +} + +static int +transfer_blocks(int fd, struct iovec *iovec, __u32 iovcnt) +{ + struct mic_copy_desc copy; + + copy.iov = iovec; + copy.iovcnt = iovcnt; + copy.vr_idx = 0; /* only one vring on virtio_block */ + copy.update_used = false; /* do not update used index */ + return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©); +} + +static __u8 +status_error_check(struct vring_desc *desc) +{ + if (le32toh(desc->len) != sizeof(__u8)) { + mpsslog("%s() %d: length is not sizeof(status)\n", + __func__, __LINE__); + return -EIO; + } + return 0; +} + +static int +write_status(int fd, __u8 *status) +{ + struct iovec iovec; + struct mic_copy_desc copy; + + iovec.iov_base = status; + iovec.iov_len = sizeof(*status); + copy.iov = &iovec; + copy.iovcnt = 1; + copy.vr_idx = 0; /* only one vring on virtio_block */ + copy.update_used = true; /* Update used index */ + return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©); +} + +#ifndef VIRTIO_BLK_T_GET_ID +#define VIRTIO_BLK_T_GET_ID 8 +#endif + +static void * +virtio_block(void *arg) +{ + struct mic_info *mic = (struct mic_info *)arg; + int ret; + struct pollfd block_poll; + struct mic_vring vring; + __u16 avail_idx; + __u32 desc_idx; + struct vring_desc *desc; + struct iovec *iovec, *piov; + __u8 status; + __u32 buffer_desc_idx; + struct virtio_blk_outhdr hdr; + void *fos; + + for (;;) { /* forever */ + if (!open_backend(mic)) { /* No virtblk */ + for (mic->mic_virtblk.signaled = 0; + !mic->mic_virtblk.signaled;) + sleep(1); + continue; + } + + /* backend file is specified. */ + if (!start_virtblk(mic, &vring)) + goto _close_backend; + iovec = malloc(sizeof(*iovec) * + le32toh(virtblk_dev_page.blk_config.seg_max)); + if (!iovec) { + mpsslog("%s: can't alloc iovec: %s\n", + mic->name, strerror(ENOMEM)); + goto _stop_virtblk; + } + + block_poll.fd = mic->mic_virtblk.virtio_block_fd; + block_poll.events = POLLIN; + for (mic->mic_virtblk.signaled = 0; + !mic->mic_virtblk.signaled;) { + block_poll.revents = 0; + /* timeout in 1 sec to see signaled */ + ret = poll(&block_poll, 1, 1000); + if (ret < 0) { + mpsslog("%s %d: poll failed: %s\n", + __func__, __LINE__, + strerror(errno)); + continue; + } + + if (!(block_poll.revents & POLLIN)) { +#ifdef DEBUG + mpsslog("%s %d: block_poll.revents=0x%x\n", + __func__, __LINE__, block_poll.revents); +#endif + continue; + } + + /* POLLIN */ + while (vring.info->avail_idx != + le16toh(vring.vr.avail->idx)) { + /* read header element */ + avail_idx = + vring.info->avail_idx & + (vring.vr.num - 1); + desc_idx = le16toh( + vring.vr.avail->ring[avail_idx]); + desc = &vring.vr.desc[desc_idx]; +#ifdef DEBUG + mpsslog("%s() %d: avail_idx=%d ", + __func__, __LINE__, + vring.info->avail_idx); + mpsslog("vring.vr.num=%d desc=%p\n", + vring.vr.num, desc); +#endif + status = header_error_check(desc); + ret = read_header( + mic->mic_virtblk.virtio_block_fd, + &hdr, desc_idx); + if (ret < 0) { + mpsslog("%s() %d %s: ret=%d %s\n", + __func__, __LINE__, + mic->name, ret, + strerror(errno)); + break; + } + /* buffer element */ + piov = iovec; + status = 0; + fos = mic->mic_virtblk.backend_addr + + (hdr.sector * SECTOR_SIZE); + buffer_desc_idx = next_desc(desc); + desc_idx = buffer_desc_idx; + for (desc = &vring.vr.desc[buffer_desc_idx]; + desc->flags & VRING_DESC_F_NEXT; + desc_idx = next_desc(desc), + desc = &vring.vr.desc[desc_idx]) { + piov->iov_len = desc->len; + piov->iov_base = fos; + piov++; + fos += desc->len; + } + /* Returning NULLs for VIRTIO_BLK_T_GET_ID. */ + if (hdr.type & ~(VIRTIO_BLK_T_OUT | + VIRTIO_BLK_T_GET_ID)) { + /* + VIRTIO_BLK_T_IN - does not do + anything. Probably for documenting. + VIRTIO_BLK_T_SCSI_CMD - for + virtio_scsi. + VIRTIO_BLK_T_FLUSH - turned off in + config space. + VIRTIO_BLK_T_BARRIER - defined but not + used in anywhere. + */ + mpsslog("%s() %d: type %x ", + __func__, __LINE__, + hdr.type); + mpsslog("is not supported\n"); + status = -ENOTSUP; + + } else { + ret = transfer_blocks( + mic->mic_virtblk.virtio_block_fd, + iovec, + piov - iovec); + if (ret < 0 && + status != 0) + status = ret; + } + /* write status and update used pointer */ + if (status != 0) + status = status_error_check(desc); + ret = write_status( + mic->mic_virtblk.virtio_block_fd, + &status); +#ifdef DEBUG + mpsslog("%s() %d: write status=%d on desc=%p\n", + __func__, __LINE__, + status, desc); +#endif + } + } + free(iovec); +_stop_virtblk: + stop_virtblk(mic); +_close_backend: + close_backend(mic); + } /* forever */ + + pthread_exit(NULL); +} + +static void +reset(struct mic_info *mic) +{ +#define RESET_TIMEOUT 120 + int i = RESET_TIMEOUT; + setsysfs(mic->name, "state", "reset"); + while (i) { + char *state; + state = readsysfs(mic->name, "state"); + if (!state) + goto retry; + mpsslog("%s: %s %d state %s\n", + mic->name, __func__, __LINE__, state); + + if (!strcmp(state, "ready")) { + free(state); + break; + } + free(state); +retry: + sleep(1); + i--; + } +} + +static int +get_mic_shutdown_status(struct mic_info *mic, char *shutdown_status) +{ + if (!strcmp(shutdown_status, "nop")) + return MIC_NOP; + if (!strcmp(shutdown_status, "crashed")) + return MIC_CRASHED; + if (!strcmp(shutdown_status, "halted")) + return MIC_HALTED; + if (!strcmp(shutdown_status, "poweroff")) + return MIC_POWER_OFF; + if (!strcmp(shutdown_status, "restart")) + return MIC_RESTART; + mpsslog("%s: BUG invalid status %s\n", mic->name, shutdown_status); + /* Invalid state */ + assert(0); +}; + +static int get_mic_state(struct mic_info *mic) +{ + char *state = NULL; + enum mic_states mic_state; + + while (!state) { + state = readsysfs(mic->name, "state"); + sleep(1); + } + mpsslog("%s: %s %d state %s\n", + mic->name, __func__, __LINE__, state); + + if (!strcmp(state, "ready")) { + mic_state = MIC_READY; + } else if (!strcmp(state, "booting")) { + mic_state = MIC_BOOTING; + } else if (!strcmp(state, "online")) { + mic_state = MIC_ONLINE; + } else if (!strcmp(state, "shutting_down")) { + mic_state = MIC_SHUTTING_DOWN; + } else if (!strcmp(state, "reset_failed")) { + mic_state = MIC_RESET_FAILED; + } else if (!strcmp(state, "resetting")) { + mic_state = MIC_RESETTING; + } else { + mpsslog("%s: BUG invalid state %s\n", mic->name, state); + assert(0); + } + + free(state); + return mic_state; +}; + +static void mic_handle_shutdown(struct mic_info *mic) +{ +#define SHUTDOWN_TIMEOUT 60 + int i = SHUTDOWN_TIMEOUT; + char *shutdown_status; + while (i) { + shutdown_status = readsysfs(mic->name, "shutdown_status"); + if (!shutdown_status) { + sleep(1); + continue; + } + mpsslog("%s: %s %d shutdown_status %s\n", + mic->name, __func__, __LINE__, shutdown_status); + switch (get_mic_shutdown_status(mic, shutdown_status)) { + case MIC_RESTART: + mic->restart = 1; + case MIC_HALTED: + case MIC_POWER_OFF: + case MIC_CRASHED: + free(shutdown_status); + goto reset; + default: + break; + } + free(shutdown_status); + sleep(1); + i--; + } +reset: + if (!i) + mpsslog("%s: %s %d timing out waiting for shutdown_status %s\n", + mic->name, __func__, __LINE__, shutdown_status); + reset(mic); +} + +static int open_state_fd(struct mic_info *mic) +{ + char pathname[PATH_MAX]; + int fd; + + snprintf(pathname, PATH_MAX - 1, "%s/%s/%s", + MICSYSFSDIR, mic->name, "state"); + + fd = open(pathname, O_RDONLY); + if (fd < 0) + mpsslog("%s: opening file %s failed %s\n", + mic->name, pathname, strerror(errno)); + return fd; +} + +static int block_till_state_change(int fd, struct mic_info *mic) +{ + struct pollfd ufds[1]; + char value[PAGE_SIZE]; + int ret; + + ufds[0].fd = fd; + ufds[0].events = POLLERR | POLLPRI; + ret = poll(ufds, 1, -1); + if (ret < 0) { + mpsslog("%s: %s %d poll failed %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + return ret; + } + + ret = lseek(fd, 0, SEEK_SET); + if (ret < 0) { + mpsslog("%s: %s %d Failed to seek to 0: %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + return ret; + } + + ret = read(fd, value, sizeof(value)); + if (ret < 0) { + mpsslog("%s: %s %d Failed to read sysfs entry: %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + return ret; + } + + return 0; +} + +static void * +mic_config(void *arg) +{ + struct mic_info *mic = (struct mic_info *)arg; + int fd, ret, stat = 0; + + fd = open_state_fd(mic); + if (fd < 0) { + mpsslog("%s: %s %d open state fd failed %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + goto exit; + } + + do { + ret = block_till_state_change(fd, mic); + if (ret < 0) { + mpsslog("%s: %s %d block_till_state_change error %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + goto close_exit; + } + + switch (get_mic_state(mic)) { + case MIC_SHUTTING_DOWN: + mic_handle_shutdown(mic); + break; + case MIC_READY: + case MIC_RESET_FAILED: + ret = kill(mic->pid, SIGTERM); + mpsslog("%s: %s %d kill pid %d ret %d\n", + mic->name, __func__, __LINE__, + mic->pid, ret); + if (!ret) { + ret = waitpid(mic->pid, &stat, + WIFSIGNALED(stat)); + mpsslog("%s: %s %d waitpid ret %d pid %d\n", + mic->name, __func__, __LINE__, + ret, mic->pid); + } + if (mic->boot_on_resume) { + setsysfs(mic->name, "state", "boot"); + mic->boot_on_resume = 0; + } + goto close_exit; + default: + break; + } + } while (1); + +close_exit: + close(fd); +exit: + init_mic(mic); + pthread_exit(NULL); +} + +static void +set_cmdline(struct mic_info *mic) +{ + char buffer[PATH_MAX]; + int len; + + len = snprintf(buffer, PATH_MAX, + "clocksource=tsc highres=off nohz=off "); + len += snprintf(buffer + len, PATH_MAX - len, + "cpufreq_on;corec6_off;pc3_off;pc6_off "); + len += snprintf(buffer + len, PATH_MAX - len, + "ifcfg=static;address,172.31.%d.1;netmask,255.255.255.0", + mic->id + 1); + + setsysfs(mic->name, "cmdline", buffer); + mpsslog("%s: Command line: \"%s\"\n", mic->name, buffer); + snprintf(buffer, PATH_MAX, "172.31.%d.1", mic->id + 1); + mpsslog("%s: IPADDR: \"%s\"\n", mic->name, buffer); +} + +static void +set_log_buf_info(struct mic_info *mic) +{ + int fd; + off_t len; + char system_map[] = "/lib/firmware/mic/System.map"; + char *map, *temp, log_buf[17] = {'\0'}; + + fd = open(system_map, O_RDONLY); + if (fd < 0) { + mpsslog("%s: Opening System.map failed: %d\n", + mic->name, errno); + return; + } + len = lseek(fd, 0, SEEK_END); + if (len < 0) { + mpsslog("%s: Reading System.map size failed: %d\n", + mic->name, errno); + close(fd); + return; + } + map = mmap(NULL, len, PROT_READ, MAP_PRIVATE, fd, 0); + if (map == MAP_FAILED) { + mpsslog("%s: mmap of System.map failed: %d\n", + mic->name, errno); + close(fd); + return; + } + temp = strstr(map, "__log_buf"); + if (!temp) { + mpsslog("%s: __log_buf not found: %d\n", mic->name, errno); + munmap(map, len); + close(fd); + return; + } + strncpy(log_buf, temp - 19, 16); + setsysfs(mic->name, "log_buf_addr", log_buf); + mpsslog("%s: log_buf_addr: %s\n", mic->name, log_buf); + temp = strstr(map, "log_buf_len"); + if (!temp) { + mpsslog("%s: log_buf_len not found: %d\n", mic->name, errno); + munmap(map, len); + close(fd); + return; + } + strncpy(log_buf, temp - 19, 16); + setsysfs(mic->name, "log_buf_len", log_buf); + mpsslog("%s: log_buf_len: %s\n", mic->name, log_buf); + munmap(map, len); + close(fd); +} + +static void +change_virtblk_backend(int x, siginfo_t *siginfo, void *p) +{ + struct mic_info *mic; + + for (mic = mic_list.next; mic != NULL; mic = mic->next) + mic->mic_virtblk.signaled = 1/* true */; +} + +static void +set_mic_boot_params(struct mic_info *mic) +{ + set_log_buf_info(mic); + set_cmdline(mic); +} + +static void * +init_mic(void *arg) +{ + struct mic_info *mic = (struct mic_info *)arg; + struct sigaction ignore = { + .sa_flags = 0, + .sa_handler = SIG_IGN + }; + struct sigaction act = { + .sa_flags = SA_SIGINFO, + .sa_sigaction = change_virtblk_backend, + }; + char buffer[PATH_MAX]; + int err, fd; + + /* + * Currently, one virtio block device is supported for each MIC card + * at a time. Any user (or test) can send a SIGUSR1 to the MIC daemon. + * The signal informs the virtio block backend about a change in the + * configuration file which specifies the virtio backend file name on + * the host. Virtio block backend then re-reads the configuration file + * and switches to the new block device. This signalling mechanism may + * not be required once multiple virtio block devices are supported by + * the MIC daemon. + */ + sigaction(SIGUSR1, &ignore, NULL); +retry: + fd = open_state_fd(mic); + if (fd < 0) { + mpsslog("%s: %s %d open state fd failed %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + sleep(2); + goto retry; + } + + if (mic->restart) { + snprintf(buffer, PATH_MAX, "boot"); + setsysfs(mic->name, "state", buffer); + mpsslog("%s restarting mic %d\n", + mic->name, mic->restart); + mic->restart = 0; + } + + while (1) { + while (block_till_state_change(fd, mic)) { + mpsslog("%s: %s %d block_till_state_change error %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + sleep(2); + continue; + } + + if (get_mic_state(mic) == MIC_BOOTING) + break; + } + + mic->pid = fork(); + switch (mic->pid) { + case 0: + add_virtio_device(mic, &virtcons_dev_page.dd); + add_virtio_device(mic, &virtnet_dev_page.dd); + err = pthread_create(&mic->mic_console.console_thread, NULL, + virtio_console, mic); + if (err) + mpsslog("%s virtcons pthread_create failed %s\n", + mic->name, strerror(err)); + err = pthread_create(&mic->mic_net.net_thread, NULL, + virtio_net, mic); + if (err) + mpsslog("%s virtnet pthread_create failed %s\n", + mic->name, strerror(err)); + err = pthread_create(&mic->mic_virtblk.block_thread, NULL, + virtio_block, mic); + if (err) + mpsslog("%s virtblk pthread_create failed %s\n", + mic->name, strerror(err)); + sigemptyset(&act.sa_mask); + err = sigaction(SIGUSR1, &act, NULL); + if (err) + mpsslog("%s sigaction SIGUSR1 failed %s\n", + mic->name, strerror(errno)); + while (1) + sleep(60); + case -1: + mpsslog("fork failed MIC name %s id %d errno %d\n", + mic->name, mic->id, errno); + break; + default: + err = pthread_create(&mic->config_thread, NULL, + mic_config, mic); + if (err) + mpsslog("%s mic_config pthread_create failed %s\n", + mic->name, strerror(err)); + } + + return NULL; +} + +static void +start_daemon(void) +{ + struct mic_info *mic; + int err; + + for (mic = mic_list.next; mic; mic = mic->next) { + set_mic_boot_params(mic); + err = pthread_create(&mic->init_thread, NULL, init_mic, mic); + if (err) + mpsslog("%s init_mic pthread_create failed %s\n", + mic->name, strerror(err)); + } + + while (1) + sleep(60); +} + +static int +init_mic_list(void) +{ + struct mic_info *mic = &mic_list; + struct dirent *file; + DIR *dp; + int cnt = 0; + + dp = opendir(MICSYSFSDIR); + if (!dp) + return 0; + + while ((file = readdir(dp)) != NULL) { + if (!strncmp(file->d_name, "mic", 3)) { + mic->next = calloc(1, sizeof(struct mic_info)); + if (mic->next) { + mic = mic->next; + mic->id = atoi(&file->d_name[3]); + mic->name = malloc(strlen(file->d_name) + 16); + if (mic->name) + strcpy(mic->name, file->d_name); + mpsslog("MIC name %s id %d\n", mic->name, + mic->id); + cnt++; + } + } + } + + closedir(dp); + return cnt; +} + +void +mpsslog(char *format, ...) +{ + va_list args; + char buffer[4096]; + char ts[52], *ts1; + time_t t; + + if (logfp == NULL) + return; + + va_start(args, format); + vsprintf(buffer, format, args); + va_end(args); + + time(&t); + ts1 = ctime_r(&t, ts); + ts1[strlen(ts1) - 1] = '\0'; + fprintf(logfp, "%s: %s", ts1, buffer); + + fflush(logfp); +} + +int +main(int argc, char *argv[]) +{ + int cnt; + pid_t pid; + + myname = argv[0]; + + logfp = fopen(LOGFILE_NAME, "a+"); + if (!logfp) { + fprintf(stderr, "cannot open logfile '%s'\n", LOGFILE_NAME); + exit(1); + } + pid = fork(); + switch (pid) { + case 0: + break; + case -1: + exit(2); + default: + exit(0); + } + + mpsslog("MIC Daemon start\n"); + + cnt = init_mic_list(); + if (cnt == 0) { + mpsslog("MIC module not loaded\n"); + exit(3); + } + mpsslog("MIC found %d devices\n", cnt); + + start_daemon(); + + exit(0); +} diff --git a/samples/mic/mpssd/mpssd.h b/samples/mic/mpssd/mpssd.h new file mode 100644 index 000000000000..8bd64944aacc --- /dev/null +++ b/samples/mic/mpssd/mpssd.h @@ -0,0 +1,103 @@ +/* + * 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. + */ +#ifndef _MPSSD_H_ +#define _MPSSD_H_ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MICSYSFSDIR "/sys/class/mic" +#define LOGFILE_NAME "/var/log/mpssd" +#define PAGE_SIZE 4096 + +struct mic_console_info { + pthread_t console_thread; + int virtio_console_fd; + void *console_dp; +}; + +struct mic_net_info { + pthread_t net_thread; + int virtio_net_fd; + int tap_fd; + void *net_dp; +}; + +struct mic_virtblk_info { + pthread_t block_thread; + int virtio_block_fd; + void *block_dp; + volatile sig_atomic_t signaled; + char *backend_file; + int backend; + void *backend_addr; + long backend_size; +}; + +struct mic_info { + int id; + char *name; + pthread_t config_thread; + pthread_t init_thread; + pid_t pid; + struct mic_console_info mic_console; + struct mic_net_info mic_net; + struct mic_virtblk_info mic_virtblk; + int restart; + int boot_on_resume; + struct mic_info *next; +}; + +__attribute__((format(printf, 1, 2))) +void mpsslog(char *format, ...); +char *readsysfs(char *dir, char *entry); +int setsysfs(char *dir, char *entry, char *value); +#endif diff --git a/samples/mic/mpssd/sysfs.c b/samples/mic/mpssd/sysfs.c new file mode 100644 index 000000000000..8dd326936083 --- /dev/null +++ b/samples/mic/mpssd/sysfs.c @@ -0,0 +1,102 @@ +/* + * 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. + */ + +#include "mpssd.h" + +#define PAGE_SIZE 4096 + +char * +readsysfs(char *dir, char *entry) +{ + char filename[PATH_MAX]; + char value[PAGE_SIZE]; + char *string = NULL; + int fd; + int len; + + if (dir == NULL) + snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry); + else + snprintf(filename, PATH_MAX, + "%s/%s/%s", MICSYSFSDIR, dir, entry); + + fd = open(filename, O_RDONLY); + if (fd < 0) { + mpsslog("Failed to open sysfs entry '%s': %s\n", + filename, strerror(errno)); + return NULL; + } + + len = read(fd, value, sizeof(value)); + if (len < 0) { + mpsslog("Failed to read sysfs entry '%s': %s\n", + filename, strerror(errno)); + goto readsys_ret; + } + if (len == 0) + goto readsys_ret; + + value[len - 1] = '\0'; + + string = malloc(strlen(value) + 1); + if (string) + strcpy(string, value); + +readsys_ret: + close(fd); + return string; +} + +int +setsysfs(char *dir, char *entry, char *value) +{ + char filename[PATH_MAX]; + char *oldvalue; + int fd, ret = 0; + + if (dir == NULL) + snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry); + else + snprintf(filename, PATH_MAX, "%s/%s/%s", + MICSYSFSDIR, dir, entry); + + oldvalue = readsysfs(dir, entry); + + fd = open(filename, O_RDWR); + if (fd < 0) { + ret = errno; + mpsslog("Failed to open sysfs entry '%s': %s\n", + filename, strerror(errno)); + goto done; + } + + if (!oldvalue || strcmp(value, oldvalue)) { + if (write(fd, value, strlen(value)) < 0) { + ret = errno; + mpsslog("Failed to write new sysfs entry '%s': %s\n", + filename, strerror(errno)); + } + } + close(fd); +done: + if (oldvalue) + free(oldvalue); + return ret; +} -- cgit v1.2.3