diff options
Diffstat (limited to 'tools/hv')
| -rw-r--r-- | tools/hv/.gitignore | 3 | ||||
| -rw-r--r-- | tools/hv/Build | 3 | ||||
| -rw-r--r-- | tools/hv/Makefile | 17 | ||||
| -rw-r--r-- | tools/hv/hv_fcopy_daemon.c | 266 | ||||
| -rw-r--r-- | tools/hv/hv_fcopy_uio_daemon.c | 497 | ||||
| -rwxr-xr-x | tools/hv/hv_get_dns_info.sh | 4 | ||||
| -rw-r--r-- | tools/hv/hv_kvp_daemon.c | 555 | ||||
| -rwxr-xr-x | tools/hv/hv_set_ifconfig.sh | 39 | ||||
| -rwxr-xr-x[-rw-r--r--] | tools/hv/lsvmbus | 2 | ||||
| -rw-r--r-- | tools/hv/vmbus_bufring.c | 318 | ||||
| -rw-r--r-- | tools/hv/vmbus_bufring.h | 158 | ||||
| -rwxr-xr-x | tools/hv/vmbus_testing | 4 |
12 files changed, 1515 insertions, 351 deletions
diff --git a/tools/hv/.gitignore b/tools/hv/.gitignore new file mode 100644 index 000000000000..0c5bc15d602f --- /dev/null +++ b/tools/hv/.gitignore @@ -0,0 +1,3 @@ +hv_fcopy_uio_daemon +hv_kvp_daemon +hv_vss_daemon diff --git a/tools/hv/Build b/tools/hv/Build index 6cf51fa4b306..7d1f1698069b 100644 --- a/tools/hv/Build +++ b/tools/hv/Build @@ -1,3 +1,4 @@ hv_kvp_daemon-y += hv_kvp_daemon.o hv_vss_daemon-y += hv_vss_daemon.o -hv_fcopy_daemon-y += hv_fcopy_daemon.o +hv_fcopy_uio_daemon-y += hv_fcopy_uio_daemon.o +hv_fcopy_uio_daemon-y += vmbus_bufring.o diff --git a/tools/hv/Makefile b/tools/hv/Makefile index b57143d9459c..34ffcec264ab 100644 --- a/tools/hv/Makefile +++ b/tools/hv/Makefile @@ -2,6 +2,7 @@ # Makefile for Hyper-V tools include ../scripts/Makefile.include +ARCH := $(shell uname -m 2>/dev/null) sbindir ?= /usr/sbin libexecdir ?= /usr/libexec sharedstatedir ?= /var/lib @@ -16,8 +17,12 @@ endif MAKEFLAGS += -r override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include +override CFLAGS += -Wno-address-of-packed-member -ALL_TARGETS := hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon +ALL_TARGETS := hv_kvp_daemon hv_vss_daemon +ifneq ($(ARCH), aarch64) +ALL_TARGETS += hv_fcopy_uio_daemon +endif ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) ALL_SCRIPTS := hv_get_dhcp_info.sh hv_get_dns_info.sh hv_set_ifconfig.sh @@ -39,15 +44,15 @@ $(HV_VSS_DAEMON_IN): FORCE $(OUTPUT)hv_vss_daemon: $(HV_VSS_DAEMON_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ -HV_FCOPY_DAEMON_IN := $(OUTPUT)hv_fcopy_daemon-in.o -$(HV_FCOPY_DAEMON_IN): FORCE - $(Q)$(MAKE) $(build)=hv_fcopy_daemon -$(OUTPUT)hv_fcopy_daemon: $(HV_FCOPY_DAEMON_IN) +HV_FCOPY_UIO_DAEMON_IN := $(OUTPUT)hv_fcopy_uio_daemon-in.o +$(HV_FCOPY_UIO_DAEMON_IN): FORCE + $(Q)$(MAKE) $(build)=hv_fcopy_uio_daemon +$(OUTPUT)hv_fcopy_uio_daemon: $(HV_FCOPY_UIO_DAEMON_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ clean: rm -f $(ALL_PROGRAMS) - find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(sbindir); \ diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c deleted file mode 100644 index 16d629b22c25..000000000000 --- a/tools/hv/hv_fcopy_daemon.c +++ /dev/null @@ -1,266 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * An implementation of host to guest copy functionality for Linux. - * - * Copyright (C) 2014, Microsoft, Inc. - * - * Author : K. Y. Srinivasan <kys@microsoft.com> - */ - - -#include <sys/types.h> -#include <stdio.h> -#include <stdlib.h> -#include <unistd.h> -#include <string.h> -#include <errno.h> -#include <linux/hyperv.h> -#include <linux/limits.h> -#include <syslog.h> -#include <sys/stat.h> -#include <fcntl.h> -#include <getopt.h> - -static int target_fd; -static char target_fname[PATH_MAX]; -static unsigned long long filesize; - -static int hv_start_fcopy(struct hv_start_fcopy *smsg) -{ - int error = HV_E_FAIL; - char *q, *p; - - filesize = 0; - p = (char *)smsg->path_name; - snprintf(target_fname, sizeof(target_fname), "%s/%s", - (char *)smsg->path_name, (char *)smsg->file_name); - - syslog(LOG_INFO, "Target file name: %s", target_fname); - /* - * Check to see if the path is already in place; if not, - * create if required. - */ - while ((q = strchr(p, '/')) != NULL) { - if (q == p) { - p++; - continue; - } - *q = '\0'; - if (access((char *)smsg->path_name, F_OK)) { - if (smsg->copy_flags & CREATE_PATH) { - if (mkdir((char *)smsg->path_name, 0755)) { - syslog(LOG_ERR, "Failed to create %s", - (char *)smsg->path_name); - goto done; - } - } else { - syslog(LOG_ERR, "Invalid path: %s", - (char *)smsg->path_name); - goto done; - } - } - p = q + 1; - *q = '/'; - } - - if (!access(target_fname, F_OK)) { - syslog(LOG_INFO, "File: %s exists", target_fname); - if (!(smsg->copy_flags & OVER_WRITE)) { - error = HV_ERROR_ALREADY_EXISTS; - goto done; - } - } - - target_fd = open(target_fname, - O_RDWR | O_CREAT | O_TRUNC | O_CLOEXEC, 0744); - if (target_fd == -1) { - syslog(LOG_INFO, "Open Failed: %s", strerror(errno)); - goto done; - } - - error = 0; -done: - if (error) - target_fname[0] = '\0'; - return error; -} - -static int hv_copy_data(struct hv_do_fcopy *cpmsg) -{ - ssize_t bytes_written; - int ret = 0; - - bytes_written = pwrite(target_fd, cpmsg->data, cpmsg->size, - cpmsg->offset); - - filesize += cpmsg->size; - if (bytes_written != cpmsg->size) { - switch (errno) { - case ENOSPC: - ret = HV_ERROR_DISK_FULL; - break; - default: - ret = HV_E_FAIL; - break; - } - syslog(LOG_ERR, "pwrite failed to write %llu bytes: %ld (%s)", - filesize, (long)bytes_written, strerror(errno)); - } - - return ret; -} - -/* - * Reset target_fname to "" in the two below functions for hibernation: if - * the fcopy operation is aborted by hibernation, the daemon should remove the - * partially-copied file; to achieve this, the hv_utils driver always fakes a - * CANCEL_FCOPY message upon suspend, and later when the VM resumes back, - * the daemon calls hv_copy_cancel() to remove the file; if a file is copied - * successfully before suspend, hv_copy_finished() must reset target_fname to - * avoid that the file can be incorrectly removed upon resume, since the faked - * CANCEL_FCOPY message is spurious in this case. - */ -static int hv_copy_finished(void) -{ - close(target_fd); - target_fname[0] = '\0'; - return 0; -} -static int hv_copy_cancel(void) -{ - close(target_fd); - if (strlen(target_fname) > 0) { - unlink(target_fname); - target_fname[0] = '\0'; - } - return 0; - -} - -void print_usage(char *argv[]) -{ - fprintf(stderr, "Usage: %s [options]\n" - "Options are:\n" - " -n, --no-daemon stay in foreground, don't daemonize\n" - " -h, --help print this help\n", argv[0]); -} - -int main(int argc, char *argv[]) -{ - int fcopy_fd = -1; - int error; - int daemonize = 1, long_index = 0, opt; - int version = FCOPY_CURRENT_VERSION; - union { - struct hv_fcopy_hdr hdr; - struct hv_start_fcopy start; - struct hv_do_fcopy copy; - __u32 kernel_modver; - } buffer = { }; - int in_handshake; - - static struct option long_options[] = { - {"help", no_argument, 0, 'h' }, - {"no-daemon", no_argument, 0, 'n' }, - {0, 0, 0, 0 } - }; - - while ((opt = getopt_long(argc, argv, "hn", long_options, - &long_index)) != -1) { - switch (opt) { - case 'n': - daemonize = 0; - break; - case 'h': - default: - print_usage(argv); - exit(EXIT_FAILURE); - } - } - - if (daemonize && daemon(1, 0)) { - syslog(LOG_ERR, "daemon() failed; error: %s", strerror(errno)); - exit(EXIT_FAILURE); - } - - openlog("HV_FCOPY", 0, LOG_USER); - syslog(LOG_INFO, "starting; pid is:%d", getpid()); - -reopen_fcopy_fd: - if (fcopy_fd != -1) - close(fcopy_fd); - /* Remove any possible partially-copied file on error */ - hv_copy_cancel(); - in_handshake = 1; - fcopy_fd = open("/dev/vmbus/hv_fcopy", O_RDWR); - - if (fcopy_fd < 0) { - syslog(LOG_ERR, "open /dev/vmbus/hv_fcopy failed; error: %d %s", - errno, strerror(errno)); - exit(EXIT_FAILURE); - } - - /* - * Register with the kernel. - */ - if ((write(fcopy_fd, &version, sizeof(int))) != sizeof(int)) { - syslog(LOG_ERR, "Registration failed: %s", strerror(errno)); - exit(EXIT_FAILURE); - } - - while (1) { - /* - * In this loop we process fcopy messages after the - * handshake is complete. - */ - ssize_t len; - - len = pread(fcopy_fd, &buffer, sizeof(buffer), 0); - if (len < 0) { - syslog(LOG_ERR, "pread failed: %s", strerror(errno)); - goto reopen_fcopy_fd; - } - - if (in_handshake) { - if (len != sizeof(buffer.kernel_modver)) { - syslog(LOG_ERR, "invalid version negotiation"); - exit(EXIT_FAILURE); - } - in_handshake = 0; - syslog(LOG_INFO, "kernel module version: %u", - buffer.kernel_modver); - continue; - } - - switch (buffer.hdr.operation) { - case START_FILE_COPY: - error = hv_start_fcopy(&buffer.start); - break; - case WRITE_TO_FILE: - error = hv_copy_data(&buffer.copy); - break; - case COMPLETE_FCOPY: - error = hv_copy_finished(); - break; - case CANCEL_FCOPY: - error = hv_copy_cancel(); - break; - - default: - error = HV_E_FAIL; - syslog(LOG_ERR, "Unknown operation: %d", - buffer.hdr.operation); - - } - - /* - * pwrite() may return an error due to the faked CANCEL_FCOPY - * message upon hibernation. Ignore the error by resetting the - * dev file, i.e. closing and re-opening it. - */ - if (pwrite(fcopy_fd, &error, sizeof(int), 0) != sizeof(int)) { - syslog(LOG_ERR, "pwrite failed: %s", strerror(errno)); - goto reopen_fcopy_fd; - } - } -} diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c new file mode 100644 index 000000000000..0198321d14a2 --- /dev/null +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -0,0 +1,497 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * An implementation of host to guest copy functionality for Linux. + * + * Copyright (C) 2023, Microsoft, Inc. + * + * Author : K. Y. Srinivasan <kys@microsoft.com> + * Author : Saurabh Sengar <ssengar@microsoft.com> + * + */ + +#include <dirent.h> +#include <errno.h> +#include <fcntl.h> +#include <getopt.h> +#include <locale.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syslog.h> +#include <unistd.h> +#include <wchar.h> +#include <sys/stat.h> +#include <linux/hyperv.h> +#include <linux/limits.h> +#include "vmbus_bufring.h" + +#define ICMSGTYPE_NEGOTIATE 0 +#define ICMSGTYPE_FCOPY 7 + +#define WIN8_SRV_MAJOR 1 +#define WIN8_SRV_MINOR 1 +#define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) + +#define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" + +#define FCOPY_VER_COUNT 1 +static const int fcopy_versions[] = { + WIN8_SRV_VERSION +}; + +#define FW_VER_COUNT 1 +static const int fw_versions[] = { + UTIL_FW_VERSION +}; + +#define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ + +static unsigned char desc[HV_RING_SIZE]; + +static int target_fd; +static char target_fname[PATH_MAX]; +static unsigned long long filesize; + +static int hv_fcopy_create_file(char *file_name, char *path_name, __u32 flags) +{ + int error = HV_E_FAIL; + char *q, *p; + + filesize = 0; + p = path_name; + snprintf(target_fname, sizeof(target_fname), "%s/%s", + path_name, file_name); + + /* + * Check to see if the path is already in place; if not, + * create if required. + */ + while ((q = strchr(p, '/')) != NULL) { + if (q == p) { + p++; + continue; + } + *q = '\0'; + if (access(path_name, F_OK)) { + if (flags & CREATE_PATH) { + if (mkdir(path_name, 0755)) { + syslog(LOG_ERR, "Failed to create %s", + path_name); + goto done; + } + } else { + syslog(LOG_ERR, "Invalid path: %s", path_name); + goto done; + } + } + p = q + 1; + *q = '/'; + } + + if (!access(target_fname, F_OK)) { + syslog(LOG_INFO, "File: %s exists", target_fname); + if (!(flags & OVER_WRITE)) { + error = HV_ERROR_ALREADY_EXISTS; + goto done; + } + } + + target_fd = open(target_fname, + O_RDWR | O_CREAT | O_TRUNC | O_CLOEXEC, 0744); + if (target_fd == -1) { + syslog(LOG_INFO, "Open Failed: %s", strerror(errno)); + goto done; + } + + error = 0; +done: + if (error) + target_fname[0] = '\0'; + return error; +} + +/* copy the data into the file */ +static int hv_copy_data(struct hv_do_fcopy *cpmsg) +{ + ssize_t len; + int ret = 0; + + len = pwrite(target_fd, cpmsg->data, cpmsg->size, cpmsg->offset); + + filesize += cpmsg->size; + if (len != cpmsg->size) { + switch (errno) { + case ENOSPC: + ret = HV_ERROR_DISK_FULL; + break; + default: + ret = HV_E_FAIL; + break; + } + syslog(LOG_ERR, "pwrite failed to write %llu bytes: %ld (%s)", + filesize, (long)len, strerror(errno)); + } + + return ret; +} + +static int hv_copy_finished(void) +{ + close(target_fd); + target_fname[0] = '\0'; + + return 0; +} + +static void print_usage(char *argv[]) +{ + fprintf(stderr, "Usage: %s [options]\n" + "Options are:\n" + " -n, --no-daemon stay in foreground, don't daemonize\n" + " -h, --help print this help\n", argv[0]); +} + +static bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, unsigned char *buf, + unsigned int buflen, const int *fw_version, int fw_vercnt, + const int *srv_version, int srv_vercnt, + int *nego_fw_version, int *nego_srv_version) +{ + int icframe_major, icframe_minor; + int icmsg_major, icmsg_minor; + int fw_major, fw_minor; + int srv_major, srv_minor; + int i, j; + bool found_match = false; + struct icmsg_negotiate *negop; + + /* Check that there's enough space for icframe_vercnt, icmsg_vercnt */ + if (buflen < ICMSG_HDR + offsetof(struct icmsg_negotiate, reserved)) { + syslog(LOG_ERR, "Invalid icmsg negotiate"); + return false; + } + + icmsghdrp->icmsgsize = 0x10; + negop = (struct icmsg_negotiate *)&buf[ICMSG_HDR]; + + icframe_major = negop->icframe_vercnt; + icframe_minor = 0; + + icmsg_major = negop->icmsg_vercnt; + icmsg_minor = 0; + + /* Validate negop packet */ + if (icframe_major > IC_VERSION_NEGOTIATION_MAX_VER_COUNT || + icmsg_major > IC_VERSION_NEGOTIATION_MAX_VER_COUNT || + ICMSG_NEGOTIATE_PKT_SIZE(icframe_major, icmsg_major) > buflen) { + syslog(LOG_ERR, "Invalid icmsg negotiate - icframe_major: %u, icmsg_major: %u\n", + icframe_major, icmsg_major); + goto fw_error; + } + + /* + * Select the framework version number we will + * support. + */ + + for (i = 0; i < fw_vercnt; i++) { + fw_major = (fw_version[i] >> 16); + fw_minor = (fw_version[i] & 0xFFFF); + + for (j = 0; j < negop->icframe_vercnt; j++) { + if (negop->icversion_data[j].major == fw_major && + negop->icversion_data[j].minor == fw_minor) { + icframe_major = negop->icversion_data[j].major; + icframe_minor = negop->icversion_data[j].minor; + found_match = true; + break; + } + } + + if (found_match) + break; + } + + if (!found_match) + goto fw_error; + + found_match = false; + + for (i = 0; i < srv_vercnt; i++) { + srv_major = (srv_version[i] >> 16); + srv_minor = (srv_version[i] & 0xFFFF); + + for (j = negop->icframe_vercnt; + (j < negop->icframe_vercnt + negop->icmsg_vercnt); + j++) { + if (negop->icversion_data[j].major == srv_major && + negop->icversion_data[j].minor == srv_minor) { + icmsg_major = negop->icversion_data[j].major; + icmsg_minor = negop->icversion_data[j].minor; + found_match = true; + break; + } + } + + if (found_match) + break; + } + + /* + * Respond with the framework and service + * version numbers we can support. + */ +fw_error: + if (!found_match) { + negop->icframe_vercnt = 0; + negop->icmsg_vercnt = 0; + } else { + negop->icframe_vercnt = 1; + negop->icmsg_vercnt = 1; + } + + if (nego_fw_version) + *nego_fw_version = (icframe_major << 16) | icframe_minor; + + if (nego_srv_version) + *nego_srv_version = (icmsg_major << 16) | icmsg_minor; + + negop->icversion_data[0].major = icframe_major; + negop->icversion_data[0].minor = icframe_minor; + negop->icversion_data[1].major = icmsg_major; + negop->icversion_data[1].minor = icmsg_minor; + + return found_match; +} + +static void wcstoutf8(char *dest, const __u16 *src, size_t dest_size) +{ + size_t len = 0; + + while (len < dest_size) { + if (src[len] < 0x80) + dest[len++] = (char)(*src++); + else + dest[len++] = 'X'; + } + + dest[len] = '\0'; +} + +static int hv_fcopy_start(struct hv_start_fcopy *smsg_in) +{ + setlocale(LC_ALL, "en_US.utf8"); + size_t file_size, path_size; + char *file_name, *path_name; + char *in_file_name = (char *)smsg_in->file_name; + char *in_path_name = (char *)smsg_in->path_name; + + file_size = wcstombs(NULL, (const wchar_t *restrict)in_file_name, 0) + 1; + path_size = wcstombs(NULL, (const wchar_t *restrict)in_path_name, 0) + 1; + + file_name = (char *)malloc(file_size * sizeof(char)); + path_name = (char *)malloc(path_size * sizeof(char)); + + if (!file_name || !path_name) { + free(file_name); + free(path_name); + syslog(LOG_ERR, "Can't allocate memory for file name and/or path name"); + return HV_E_FAIL; + } + + wcstoutf8(file_name, (__u16 *)in_file_name, file_size); + wcstoutf8(path_name, (__u16 *)in_path_name, path_size); + + return hv_fcopy_create_file(file_name, path_name, smsg_in->copy_flags); +} + +static int hv_fcopy_send_data(struct hv_fcopy_hdr *fcopy_msg, int recvlen) +{ + int operation = fcopy_msg->operation; + + /* + * The strings sent from the host are encoded in + * utf16; convert it to utf8 strings. + * The host assures us that the utf16 strings will not exceed + * the max lengths specified. We will however, reserve room + * for the string terminating character - in the utf16s_utf8s() + * function we limit the size of the buffer where the converted + * string is placed to W_MAX_PATH -1 to guarantee + * that the strings can be properly terminated! + */ + + switch (operation) { + case START_FILE_COPY: + return hv_fcopy_start((struct hv_start_fcopy *)fcopy_msg); + case WRITE_TO_FILE: + return hv_copy_data((struct hv_do_fcopy *)fcopy_msg); + case COMPLETE_FCOPY: + return hv_copy_finished(); + } + + return HV_E_FAIL; +} + +/* process the packet recv from host */ +static int fcopy_pkt_process(struct vmbus_br *txbr) +{ + int ret, offset, pktlen; + int fcopy_srv_version; + const struct vmbus_chanpkt_hdr *pkt; + struct hv_fcopy_hdr *fcopy_msg; + struct icmsg_hdr *icmsghdr; + + pkt = (const struct vmbus_chanpkt_hdr *)desc; + offset = pkt->hlen << 3; + pktlen = (pkt->tlen << 3) - offset; + icmsghdr = (struct icmsg_hdr *)&desc[offset + sizeof(struct vmbuspipe_hdr)]; + icmsghdr->status = HV_E_FAIL; + + if (icmsghdr->icmsgtype == ICMSGTYPE_NEGOTIATE) { + if (vmbus_prep_negotiate_resp(icmsghdr, desc + offset, pktlen, fw_versions, + FW_VER_COUNT, fcopy_versions, FCOPY_VER_COUNT, + NULL, &fcopy_srv_version)) { + syslog(LOG_INFO, "FCopy IC version %d.%d", + fcopy_srv_version >> 16, fcopy_srv_version & 0xFFFF); + icmsghdr->status = 0; + } + } else if (icmsghdr->icmsgtype == ICMSGTYPE_FCOPY) { + /* Ensure recvlen is big enough to contain hv_fcopy_hdr */ + if (pktlen < ICMSG_HDR + sizeof(struct hv_fcopy_hdr)) { + syslog(LOG_ERR, "Invalid Fcopy hdr. Packet length too small: %u", + pktlen); + return -ENOBUFS; + } + + fcopy_msg = (struct hv_fcopy_hdr *)&desc[offset + ICMSG_HDR]; + icmsghdr->status = hv_fcopy_send_data(fcopy_msg, pktlen); + } + + icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE; + ret = rte_vmbus_chan_send(txbr, 0x6, desc + offset, pktlen, 0); + if (ret) { + syslog(LOG_ERR, "Write to ringbuffer failed err: %d", ret); + return ret; + } + + return 0; +} + +static void fcopy_get_first_folder(char *path, char *chan_no) +{ + DIR *dir = opendir(path); + struct dirent *entry; + + if (!dir) { + syslog(LOG_ERR, "Failed to open directory (errno=%s).\n", strerror(errno)); + return; + } + + while ((entry = readdir(dir)) != NULL) { + if (entry->d_type == DT_DIR && strcmp(entry->d_name, ".") != 0 && + strcmp(entry->d_name, "..") != 0) { + strcpy(chan_no, entry->d_name); + break; + } + } + + closedir(dir); +} + +int main(int argc, char *argv[]) +{ + int fcopy_fd = -1, tmp = 1; + int daemonize = 1, long_index = 0, opt, ret = -EINVAL; + struct vmbus_br txbr, rxbr; + void *ring; + uint32_t len = HV_RING_SIZE; + char uio_name[NAME_MAX] = {0}; + char uio_dev_path[PATH_MAX] = {0}; + + static struct option long_options[] = { + {"help", no_argument, 0, 'h' }, + {"no-daemon", no_argument, 0, 'n' }, + {0, 0, 0, 0 } + }; + + while ((opt = getopt_long(argc, argv, "hn", long_options, + &long_index)) != -1) { + switch (opt) { + case 'n': + daemonize = 0; + break; + case 'h': + default: + print_usage(argv); + goto exit; + } + } + + if (daemonize && daemon(1, 0)) { + syslog(LOG_ERR, "daemon() failed; error: %s", strerror(errno)); + goto exit; + } + + openlog("HV_UIO_FCOPY", 0, LOG_USER); + syslog(LOG_INFO, "starting; pid is:%d", getpid()); + + fcopy_get_first_folder(FCOPY_UIO, uio_name); + snprintf(uio_dev_path, sizeof(uio_dev_path), "/dev/%s", uio_name); + fcopy_fd = open(uio_dev_path, O_RDWR); + + if (fcopy_fd < 0) { + syslog(LOG_ERR, "open %s failed; error: %d %s", + uio_dev_path, errno, strerror(errno)); + ret = fcopy_fd; + goto exit; + } + + ring = vmbus_uio_map(&fcopy_fd, HV_RING_SIZE); + if (!ring) { + ret = errno; + syslog(LOG_ERR, "mmap ringbuffer failed; error: %d %s", ret, strerror(ret)); + goto close; + } + vmbus_br_setup(&txbr, ring, HV_RING_SIZE); + vmbus_br_setup(&rxbr, (char *)ring + HV_RING_SIZE, HV_RING_SIZE); + + rxbr.vbr->imask = 0; + + while (1) { + /* + * In this loop we process fcopy messages after the + * handshake is complete. + */ + ret = pread(fcopy_fd, &tmp, sizeof(int), 0); + if (ret < 0) { + if (errno == EINTR || errno == EAGAIN) + continue; + syslog(LOG_ERR, "pread failed: %s", strerror(errno)); + goto close; + } + + len = HV_RING_SIZE; + ret = rte_vmbus_chan_recv_raw(&rxbr, desc, &len); + if (unlikely(ret <= 0)) { + /* This indicates a failure to communicate (or worse) */ + syslog(LOG_ERR, "VMBus channel recv error: %d", ret); + } else { + ret = fcopy_pkt_process(&txbr); + if (ret < 0) + goto close; + + /* Signal host */ + if ((write(fcopy_fd, &tmp, sizeof(int))) != sizeof(int)) { + ret = errno; + syslog(LOG_ERR, "Signal to host failed: %s\n", strerror(ret)); + goto close; + } + } + } +close: + close(fcopy_fd); +exit: + return ret; +} diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh index 058c17b46ffc..268521234d4b 100755 --- a/tools/hv/hv_get_dns_info.sh +++ b/tools/hv/hv_get_dns_info.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh # This example script parses /etc/resolv.conf to retrive DNS information. # In the interest of keeping the KVP daemon code free of distro specific @@ -10,4 +10,4 @@ # this script can be based on the Network Manager APIs for retrieving DNS # entries. -cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }' +exec awk '/^nameserver/ { print $2 }' /etc/resolv.conf 2>/dev/null diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index ee9c1bb2293e..1f64c680be13 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -24,6 +24,7 @@ #include <sys/poll.h> #include <sys/utsname.h> +#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> @@ -44,7 +45,7 @@ /* * KVP protocol: The user mode component first registers with the - * the kernel component. Subsequently, the kernel component requests, data + * kernel component. Subsequently, the kernel component requests, data * for the specified keys. In response to this message the user mode component * fills in the value corresponding to the specified key. We overload the * sequence field in the cn_msg header to define our KVP message types. @@ -76,7 +77,14 @@ enum { DNS }; +enum { + IPV4 = 1, + IPV6, + IP_TYPE_MAX +}; + static int in_hand_shake; +static int debug; static char *os_name = ""; static char *os_major = ""; @@ -102,6 +110,11 @@ static struct utsname uts_buf; #define MAX_FILE_NAME 100 #define ENTRIES_PER_BLOCK 50 +/* + * Change this entry if the number of addresses increases in future + */ +#define MAX_IP_ENTRIES 64 +#define OUTSTR_BUF_SIZE ((INET6_ADDRSTRLEN + 1) * MAX_IP_ENTRIES) struct kvp_record { char key[HV_KVP_EXCHANGE_MAX_KEY_SIZE]; @@ -172,6 +185,20 @@ static void kvp_update_file(int pool) kvp_release_lock(pool); } +static void kvp_dump_initial_pools(int pool) +{ + int i; + + syslog(LOG_DEBUG, "===Start dumping the contents of pool %d ===\n", + pool); + + for (i = 0; i < kvp_file_info[pool].num_records; i++) + syslog(LOG_DEBUG, "pool: %d, %d/%d key=%s val=%s\n", + pool, i + 1, kvp_file_info[pool].num_records, + kvp_file_info[pool].records[i].key, + kvp_file_info[pool].records[i].value); +} + static void kvp_update_mem_state(int pool) { FILE *filep; @@ -259,6 +286,8 @@ static int kvp_file_init(void) return 1; kvp_file_info[i].num_records = 0; kvp_update_mem_state(i); + if (debug) + kvp_dump_initial_pools(i); } return 0; @@ -286,6 +315,9 @@ static int kvp_key_delete(int pool, const __u8 *key, int key_size) * Found a match; just move the remaining * entries up. */ + if (debug) + syslog(LOG_DEBUG, "%s: deleting the KVP: pool=%d key=%s val=%s", + __func__, pool, record[i].key, record[i].value); if (i == (num_records - 1)) { kvp_file_info[pool].num_records--; kvp_update_file(pool); @@ -304,20 +336,36 @@ static int kvp_key_delete(int pool, const __u8 *key, int key_size) kvp_update_file(pool); return 0; } + + if (debug) + syslog(LOG_DEBUG, "%s: could not delete KVP: pool=%d key=%s. Record not found", + __func__, pool, key); + return 1; } static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size, const __u8 *value, int value_size) { - int i; - int num_records; struct kvp_record *record; + int num_records; int num_blocks; + int i; + + if (debug) + syslog(LOG_DEBUG, "%s: got a KVP: pool=%d key=%s val=%s", + __func__, pool, key, value); if ((key_size > HV_KVP_EXCHANGE_MAX_KEY_SIZE) || - (value_size > HV_KVP_EXCHANGE_MAX_VALUE_SIZE)) + (value_size > HV_KVP_EXCHANGE_MAX_VALUE_SIZE)) { + syslog(LOG_ERR, "%s: Too long key or value: key=%s, val=%s", + __func__, key, value); + + if (debug) + syslog(LOG_DEBUG, "%s: Too long key or value: pool=%d, key=%s, val=%s", + __func__, pool, key, value); return 1; + } /* * First update the in-memory state. @@ -337,6 +385,9 @@ static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size, */ memcpy(record[i].value, value, value_size); kvp_update_file(pool); + if (debug) + syslog(LOG_DEBUG, "%s: updated: pool=%d key=%s val=%s", + __func__, pool, key, value); return 0; } @@ -348,8 +399,10 @@ static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size, record = realloc(record, sizeof(struct kvp_record) * ENTRIES_PER_BLOCK * (num_blocks + 1)); - if (record == NULL) + if (!record) { + syslog(LOG_ERR, "%s: Memory alloc failure", __func__); return 1; + } kvp_file_info[pool].num_blocks++; } @@ -357,6 +410,11 @@ static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size, memcpy(record[i].key, key, key_size); kvp_file_info[pool].records = record; kvp_file_info[pool].num_records++; + + if (debug) + syslog(LOG_DEBUG, "%s: added: pool=%d key=%s val=%s", + __func__, pool, key, value); + kvp_update_file(pool); return 0; } @@ -437,7 +495,7 @@ void kvp_get_os_info(void) /* * Parse the /etc/os-release file if present: - * http://www.freedesktop.org/software/systemd/man/os-release.html + * https://www.freedesktop.org/software/systemd/man/os-release.html */ file = fopen("/etc/os-release", "r"); if (file != NULL) { @@ -666,6 +724,88 @@ static void kvp_process_ipconfig_file(char *cmd, pclose(file); } +static bool kvp_verify_ip_address(const void *address_string) +{ + char verify_buf[sizeof(struct in6_addr)]; + + if (inet_pton(AF_INET, address_string, verify_buf) == 1) + return true; + if (inet_pton(AF_INET6, address_string, verify_buf) == 1) + return true; + return false; +} + +static void kvp_extract_routes(const char *line, void **output, size_t *remaining) +{ + static const char needle[] = "via "; + const char *match, *haystack = line; + + while ((match = strstr(haystack, needle))) { + const char *address, *next_char; + + /* Address starts after needle. */ + address = match + strlen(needle); + + /* The char following address is a space or end of line. */ + next_char = strpbrk(address, " \t\\"); + if (!next_char) + next_char = address + strlen(address) + 1; + + /* Enough room for address and semicolon. */ + if (*remaining >= (next_char - address) + 1) { + memcpy(*output, address, next_char - address); + /* Terminate string for verification. */ + memcpy(*output + (next_char - address), "", 1); + if (kvp_verify_ip_address(*output)) { + /* Advance output buffer. */ + *output += next_char - address; + *remaining -= next_char - address; + + /* Each address needs a trailing semicolon. */ + memcpy(*output, ";", 1); + *output += 1; + *remaining -= 1; + } + } + haystack = next_char; + } +} + +static void kvp_get_gateway(void *buffer, size_t buffer_len) +{ + static const char needle[] = "default "; + FILE *f; + void *output = buffer; + char *line = NULL; + size_t alloc_size = 0, remaining = buffer_len - 1; + ssize_t num_chars; + + /* Show route information in a single line, for each address family */ + f = popen("ip --oneline -4 route show;ip --oneline -6 route show", "r"); + if (!f) { + /* Convert buffer into C-String. */ + memcpy(output, "", 1); + return; + } + while ((num_chars = getline(&line, &alloc_size, f)) > 0) { + /* Skip short lines. */ + if (num_chars <= strlen(needle)) + continue; + /* Skip lines without default route. */ + if (memcmp(line, needle, strlen(needle))) + continue; + /* Remove trailing newline to simplify further parsing. */ + if (line[num_chars - 1] == '\n') + line[num_chars - 1] = '\0'; + /* Search routes after match. */ + kvp_extract_routes(line + strlen(needle), &output, &remaining); + } + /* Convert buffer into C-String. */ + memcpy(output, "", 1); + free(line); + pclose(f); +} + static void kvp_get_ipconfig_info(char *if_name, struct hv_kvp_ipaddr_value *buffer) { @@ -674,30 +814,7 @@ static void kvp_get_ipconfig_info(char *if_name, char *p; FILE *file; - /* - * Get the address of default gateway (ipv4). - */ - sprintf(cmd, "%s %s", "ip route show dev", if_name); - strcat(cmd, " | awk '/default/ {print $3 }'"); - - /* - * Execute the command to gather gateway info. - */ - kvp_process_ipconfig_file(cmd, (char *)buffer->gate_way, - (MAX_GATEWAY_SIZE * 2), INET_ADDRSTRLEN, 0); - - /* - * Get the address of default gateway (ipv6). - */ - sprintf(cmd, "%s %s", "ip -f inet6 route show dev", if_name); - strcat(cmd, " | awk '/default/ {print $3 }'"); - - /* - * Execute the command to gather gateway info (ipv6). - */ - kvp_process_ipconfig_file(cmd, (char *)buffer->gate_way, - (MAX_GATEWAY_SIZE * 2), INET6_ADDRSTRLEN, 1); - + kvp_get_gateway(buffer->gate_way, sizeof(buffer->gate_way)); /* * Gather the DNS state. @@ -714,7 +831,7 @@ static void kvp_get_ipconfig_info(char *if_name, * . */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s", "hv_get_dns_info"); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dns_info", if_name); /* * Execute the command to gather DNS info. @@ -731,7 +848,7 @@ static void kvp_get_ipconfig_info(char *if_name, * Enabled: DHCP enabled. */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dhcp_info", if_name); file = popen(cmd, "r"); if (file == NULL) @@ -772,11 +889,11 @@ static int kvp_process_ip_address(void *addrp, const char *str; if (family == AF_INET) { - addr = (struct sockaddr_in *)addrp; + addr = addrp; str = inet_ntop(family, &addr->sin_addr, tmp, 50); addr_length = INET_ADDRSTRLEN; } else { - addr6 = (struct sockaddr_in6 *)addrp; + addr6 = addrp; str = inet_ntop(family, &addr6->sin6_addr.s6_addr, tmp, 50); addr_length = INET6_ADDRSTRLEN; } @@ -1171,11 +1288,156 @@ static int process_ip_string(FILE *f, char *ip_string, int type) return 0; } +int ip_version_check(const char *input_addr) +{ + struct in6_addr addr; + + if (inet_pton(AF_INET, input_addr, &addr)) + return IPV4; + else if (inet_pton(AF_INET6, input_addr, &addr)) + return IPV6; + + return -EINVAL; +} + +/* + * Only IPv4 subnet strings needs to be converted to plen + * For IPv6 the subnet is already privided in plen format + */ +static int kvp_subnet_to_plen(char *subnet_addr_str) +{ + int plen = 0; + struct in_addr subnet_addr4; + + /* + * Convert subnet address to binary representation + */ + if (inet_pton(AF_INET, subnet_addr_str, &subnet_addr4) == 1) { + uint32_t subnet_mask = ntohl(subnet_addr4.s_addr); + + while (subnet_mask & 0x80000000) { + plen++; + subnet_mask <<= 1; + } + } else { + return -1; + } + + return plen; +} + +static int process_dns_gateway_nm(FILE *f, char *ip_string, int type, + int ip_sec) +{ + char addr[INET6_ADDRSTRLEN], *output_str; + int ip_offset = 0, error = 0, ip_ver; + char *param_name; + + if (type == DNS) + param_name = "dns"; + else if (type == GATEWAY) + param_name = "gateway"; + else + return -EINVAL; + + output_str = (char *)calloc(OUTSTR_BUF_SIZE, sizeof(char)); + if (!output_str) + return -ENOMEM; + + while (1) { + memset(addr, 0, sizeof(addr)); + + if (!parse_ip_val_buffer(ip_string, &ip_offset, addr, + (MAX_IP_ADDR_SIZE * 2))) + break; + + ip_ver = ip_version_check(addr); + if (ip_ver < 0) + continue; + + if ((ip_ver == IPV4 && ip_sec == IPV4) || + (ip_ver == IPV6 && ip_sec == IPV6)) { + /* + * do a bound check to avoid out-of bound writes + */ + if ((OUTSTR_BUF_SIZE - strlen(output_str)) > + (strlen(addr) + 1)) { + strncat(output_str, addr, + OUTSTR_BUF_SIZE - + strlen(output_str) - 1); + strncat(output_str, ",", + OUTSTR_BUF_SIZE - + strlen(output_str) - 1); + } + } else { + continue; + } + } + + if (strlen(output_str)) { + /* + * This is to get rid of that extra comma character + * in the end of the string + */ + output_str[strlen(output_str) - 1] = '\0'; + error = fprintf(f, "%s=%s\n", param_name, output_str); + } + + free(output_str); + return error; +} + +static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet, + int ip_sec) +{ + char addr[INET6_ADDRSTRLEN]; + char subnet_addr[INET6_ADDRSTRLEN]; + int error = 0, i = 0; + int ip_offset = 0, subnet_offset = 0; + int plen, ip_ver; + + memset(addr, 0, sizeof(addr)); + memset(subnet_addr, 0, sizeof(subnet_addr)); + + while (parse_ip_val_buffer(ip_string, &ip_offset, addr, + (MAX_IP_ADDR_SIZE * 2)) && + parse_ip_val_buffer(subnet, + &subnet_offset, + subnet_addr, + (MAX_IP_ADDR_SIZE * + 2))) { + ip_ver = ip_version_check(addr); + if (ip_ver < 0) + continue; + + if (ip_ver == IPV4 && ip_sec == IPV4) + plen = kvp_subnet_to_plen((char *)subnet_addr); + else if (ip_ver == IPV6 && ip_sec == IPV6) + plen = atoi(subnet_addr); + else + continue; + + if (plen < 0) + return plen; + + error = fprintf(f, "address%d=%s/%d\n", ++i, (char *)addr, + plen); + if (error < 0) + return error; + + memset(addr, 0, sizeof(addr)); + memset(subnet_addr, 0, sizeof(subnet_addr)); + } + + return error; +} + static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) { - int error = 0; - char if_file[PATH_MAX]; - FILE *file; + int error = 0, ip_ver; + char if_filename[PATH_MAX]; + char nm_filename[PATH_MAX]; + FILE *ifcfg_file, *nmfile; char cmd[PATH_MAX]; char *mac_addr; int str_len; @@ -1197,7 +1459,7 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) * in a given distro to configure the interface and so are free * ignore information that may not be relevant. * - * Here is the format of the ip configuration file: + * Here is the ifcfg format of the ip configuration file: * * HWADDR=macaddr * DEVICE=interface name @@ -1220,6 +1482,32 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) * tagged as IPV6_DEFAULTGW and IPV6 NETMASK will be tagged as * IPV6NETMASK. * + * Here is the keyfile format of the ip configuration file: + * + * [ethernet] + * mac-address=macaddr + * [connection] + * interface-name=interface name + * + * [ipv4] + * method=<protocol> (where <protocol> is "auto" if DHCP is configured + * or "manual" if no boot-time protocol should be used) + * + * address1=ipaddr1/plen + * address2=ipaddr2/plen + * + * gateway=gateway1;gateway2 + * + * dns=dns1;dns2 + * + * [ipv6] + * address1=ipaddr1/plen + * address2=ipaddr2/plen + * + * gateway=gateway1;gateway2 + * + * dns=dns1;dns2 + * * The host can specify multiple ipv4 and ipv6 addresses to be * configured for the interface. Furthermore, the configuration * needs to be persistent. A subsequent GET call on the interface @@ -1227,14 +1515,29 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) * call. */ - snprintf(if_file, sizeof(if_file), "%s%s%s", KVP_CONFIG_LOC, - "/ifcfg-", if_name); + /* + * We are populating both ifcfg and nmconnection files + */ + snprintf(if_filename, sizeof(if_filename), "%s%s%s", KVP_CONFIG_LOC, + "/ifcfg-", if_name); - file = fopen(if_file, "w"); + ifcfg_file = fopen(if_filename, "w"); - if (file == NULL) { + if (!ifcfg_file) { syslog(LOG_ERR, "Failed to open config file; error: %d %s", - errno, strerror(errno)); + errno, strerror(errno)); + return HV_E_FAIL; + } + + snprintf(nm_filename, sizeof(nm_filename), "%s%s%s%s", KVP_CONFIG_LOC, + "/", if_name, ".nmconnection"); + + nmfile = fopen(nm_filename, "w"); + + if (!nmfile) { + syslog(LOG_ERR, "Failed to open config file; error: %d %s", + errno, strerror(errno)); + fclose(ifcfg_file); return HV_E_FAIL; } @@ -1248,14 +1551,31 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) goto setval_error; } - error = kvp_write_file(file, "HWADDR", "", mac_addr); - free(mac_addr); + error = kvp_write_file(ifcfg_file, "HWADDR", "", mac_addr); + if (error < 0) + goto setmac_error; + + error = kvp_write_file(ifcfg_file, "DEVICE", "", if_name); + if (error < 0) + goto setmac_error; + + error = fprintf(nmfile, "\n[connection]\n"); + if (error < 0) + goto setmac_error; + + error = kvp_write_file(nmfile, "interface-name", "", if_name); if (error) - goto setval_error; + goto setmac_error; + + error = fprintf(nmfile, "\n[ethernet]\n"); + if (error < 0) + goto setmac_error; - error = kvp_write_file(file, "DEVICE", "", if_name); + error = kvp_write_file(nmfile, "mac-address", "", mac_addr); if (error) - goto setval_error; + goto setmac_error; + + free(mac_addr); /* * The dhcp_enabled flag is only for IPv4. In the case the host only @@ -1263,47 +1583,138 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) * proceed to parse and pass the IPv6 information to the * disto-specific script hv_set_ifconfig. */ + + /* + * First populate the ifcfg file format + */ if (new_val->dhcp_enabled) { - error = kvp_write_file(file, "BOOTPROTO", "", "dhcp"); + error = kvp_write_file(ifcfg_file, "BOOTPROTO", "", "dhcp"); if (error) goto setval_error; - } else { - error = kvp_write_file(file, "BOOTPROTO", "", "none"); + error = kvp_write_file(ifcfg_file, "BOOTPROTO", "", "none"); if (error) goto setval_error; } - /* - * Write the configuration for ipaddress, netmask, gateway and - * name servers. - */ - - error = process_ip_string(file, (char *)new_val->ip_addr, IPADDR); + error = process_ip_string(ifcfg_file, (char *)new_val->ip_addr, + IPADDR); if (error) goto setval_error; - error = process_ip_string(file, (char *)new_val->sub_net, NETMASK); + error = process_ip_string(ifcfg_file, (char *)new_val->sub_net, + NETMASK); if (error) goto setval_error; - error = process_ip_string(file, (char *)new_val->gate_way, GATEWAY); + error = process_ip_string(ifcfg_file, (char *)new_val->gate_way, + GATEWAY); if (error) goto setval_error; - error = process_ip_string(file, (char *)new_val->dns_addr, DNS); + error = process_ip_string(ifcfg_file, (char *)new_val->dns_addr, DNS); if (error) goto setval_error; - fclose(file); + /* + * Now we populate the keyfile format + * + * The keyfile format expects the IPv6 and IPv4 configuration in + * different sections. Therefore we iterate through the list twice, + * once to populate the IPv4 section and the next time for IPv6 + */ + ip_ver = IPV4; + do { + if (ip_ver == IPV4) { + error = fprintf(nmfile, "\n[ipv4]\n"); + if (error < 0) + goto setval_error; + } else { + error = fprintf(nmfile, "\n[ipv6]\n"); + if (error < 0) + goto setval_error; + } + + /* + * Write the configuration for ipaddress, netmask, gateway and + * name services + */ + error = process_ip_string_nm(nmfile, (char *)new_val->ip_addr, + (char *)new_val->sub_net, + ip_ver); + if (error < 0) + goto setval_error; + + /* + * As dhcp_enabled is only valid for ipv4, we do not set dhcp + * methods for ipv6 based on dhcp_enabled flag. + * + * For ipv4, set method to manual only when dhcp_enabled is + * false and specific ipv4 addresses are configured. If neither + * dhcp_enabled is true and no ipv4 addresses are configured, + * set method to 'disabled'. + * + * For ipv6, set method to manual when we configure ipv6 + * addresses. Otherwise set method to 'auto' so that SLAAC from + * RA may be used. + */ + if (ip_ver == IPV4) { + if (new_val->dhcp_enabled) { + error = kvp_write_file(nmfile, "method", "", + "auto"); + if (error < 0) + goto setval_error; + } else if (error) { + error = kvp_write_file(nmfile, "method", "", + "manual"); + if (error < 0) + goto setval_error; + } else { + error = kvp_write_file(nmfile, "method", "", + "disabled"); + if (error < 0) + goto setval_error; + } + } else if (ip_ver == IPV6) { + if (error) { + error = kvp_write_file(nmfile, "method", "", + "manual"); + if (error < 0) + goto setval_error; + } else { + error = kvp_write_file(nmfile, "method", "", + "auto"); + if (error < 0) + goto setval_error; + } + } + + error = process_dns_gateway_nm(nmfile, + (char *)new_val->gate_way, + GATEWAY, ip_ver); + if (error < 0) + goto setval_error; + + error = process_dns_gateway_nm(nmfile, + (char *)new_val->dns_addr, DNS, + ip_ver); + if (error < 0) + goto setval_error; + + ip_ver++; + } while (ip_ver < IP_TYPE_MAX); + + fclose(nmfile); + fclose(ifcfg_file); /* * Now that we have populated the configuration file, * invoke the external script to do its magic. */ - str_len = snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s", - "hv_set_ifconfig", if_file); + str_len = snprintf(cmd, sizeof(cmd), "exec %s %s %s", + KVP_SCRIPTS_PATH "hv_set_ifconfig", + if_filename, nm_filename); /* * This is a little overcautious, but it's necessary to suppress some * false warnings from gcc 8.0.1. @@ -1316,14 +1727,16 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) if (system(cmd)) { syslog(LOG_ERR, "Failed to execute cmd '%s'; error: %d %s", - cmd, errno, strerror(errno)); + cmd, errno, strerror(errno)); return HV_E_FAIL; } return 0; - +setmac_error: + free(mac_addr); setval_error: syslog(LOG_ERR, "Failed to write config file"); - fclose(file); + fclose(ifcfg_file); + fclose(nmfile); return error; } @@ -1355,6 +1768,7 @@ void print_usage(char *argv[]) fprintf(stderr, "Usage: %s [options]\n" "Options are:\n" " -n, --no-daemon stay in foreground, don't daemonize\n" + " -d, --debug Enable debug logs(syslog debug by default)\n" " -h, --help print this help\n", argv[0]); } @@ -1376,10 +1790,11 @@ int main(int argc, char *argv[]) static struct option long_options[] = { {"help", no_argument, 0, 'h' }, {"no-daemon", no_argument, 0, 'n' }, + {"debug", no_argument, 0, 'd' }, {0, 0, 0, 0 } }; - while ((opt = getopt_long(argc, argv, "hn", long_options, + while ((opt = getopt_long(argc, argv, "hnd", long_options, &long_index)) != -1) { switch (opt) { case 'n': @@ -1388,6 +1803,9 @@ int main(int argc, char *argv[]) case 'h': print_usage(argv); exit(0); + case 'd': + debug = 1; + break; default: print_usage(argv); exit(EXIT_FAILURE); @@ -1410,6 +1828,9 @@ int main(int argc, char *argv[]) */ kvp_get_domain_name(full_domain_name, sizeof(full_domain_name)); + if (debug) + syslog(LOG_INFO, "Logging debug info in syslog(debug)"); + if (kvp_file_init()) { syslog(LOG_ERR, "Failed to initialize the pools"); exit(EXIT_FAILURE); diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index d10fe35b7f25..2f8baed2b8f7 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -18,12 +18,12 @@ # # This example script is based on a RHEL environment. # -# Here is the format of the ip configuration file: +# Here is the ifcfg format of the ip configuration file: # # HWADDR=macaddr # DEVICE=interface name # BOOTPROTO=<protocol> (where <protocol> is "dhcp" if DHCP is configured -# or "none" if no boot-time protocol should be used) +# or "none" if no boot-time protocol should be used) # # IPADDR0=ipaddr1 # IPADDR1=ipaddr2 @@ -41,6 +41,32 @@ # tagged as IPV6_DEFAULTGW and IPV6 NETMASK will be tagged as # IPV6NETMASK. # +# Here is the keyfile format of the ip configuration file: +# +# [ethernet] +# mac-address=macaddr +# [connection] +# interface-name=interface name +# +# [ipv4] +# method=<protocol> (where <protocol> is "auto" if DHCP is configured +# or "manual" if no boot-time protocol should be used) +# +# address1=ipaddr1/plen +# address2=ipaddr2/plen +# +# gateway=gateway1;gateway2 +# +# dns=dns1; +# +# [ipv6] +# address1=ipaddr1/plen +# address2=ipaddr2/plen +# +# gateway=gateway1;gateway2 +# +# dns=dns1;dns2 +# # The host can specify multiple ipv4 and ipv6 addresses to be # configured for the interface. Furthermore, the configuration # needs to be persistent. A subsequent GET call on the interface @@ -48,18 +74,19 @@ # call. # - - echo "IPV6INIT=yes" >> $1 echo "NM_CONTROLLED=no" >> $1 echo "PEERDNS=yes" >> $1 echo "ONBOOT=yes" >> $1 - cp $1 /etc/sysconfig/network-scripts/ +umask 0177 +interface=$(echo $2 | awk -F - '{ print $2 }') +filename="${2##*/}" + +sed '/\[connection\]/a autoconnect=true' $2 > /etc/NetworkManager/system-connections/${filename} -interface=$(echo $1 | awk -F - '{ print $2 }') /sbin/ifdown $interface 2>/dev/null /sbin/ifup $interface 2>/dev/null diff --git a/tools/hv/lsvmbus b/tools/hv/lsvmbus index 099f2c44dbed..f83698f14da2 100644..100755 --- a/tools/hv/lsvmbus +++ b/tools/hv/lsvmbus @@ -1,4 +1,4 @@ -#!/usr/bin/env python +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 import os diff --git a/tools/hv/vmbus_bufring.c b/tools/hv/vmbus_bufring.c new file mode 100644 index 000000000000..bac32c1109df --- /dev/null +++ b/tools/hv/vmbus_bufring.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2009-2012,2016,2023 Microsoft Corp. + * Copyright (c) 2012 NetApp Inc. + * Copyright (c) 2012 Citrix Inc. + * All rights reserved. + */ + +#include <errno.h> +#include <fcntl.h> +#include <emmintrin.h> +#include <linux/limits.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/uio.h> +#include <unistd.h> +#include "vmbus_bufring.h" + +/** + * Compiler barrier. + * + * Guarantees that operation reordering does not occur at compile time + * for operations directly before and after the barrier. + */ +#define rte_compiler_barrier() ({ asm volatile ("" : : : "memory"); }) + +#define VMBUS_RQST_ERROR 0xFFFFFFFFFFFFFFFF +#define ALIGN(val, align) ((typeof(val))((val) & (~((typeof(val))((align) - 1))))) + +void *vmbus_uio_map(int *fd, int size) +{ + void *map; + + map = mmap(NULL, 2 * size, PROT_READ | PROT_WRITE, MAP_SHARED, *fd, 0); + if (map == MAP_FAILED) + return NULL; + + return map; +} + +/* Increase bufring index by inc with wraparound */ +static inline uint32_t vmbus_br_idxinc(uint32_t idx, uint32_t inc, uint32_t sz) +{ + idx += inc; + if (idx >= sz) + idx -= sz; + + return idx; +} + +void vmbus_br_setup(struct vmbus_br *br, void *buf, unsigned int blen) +{ + br->vbr = buf; + br->windex = br->vbr->windex; + br->dsize = blen - sizeof(struct vmbus_bufring); +} + +static inline __always_inline void +rte_smp_mb(void) +{ + asm volatile("lock addl $0, -128(%%rsp); " ::: "memory"); +} + +static inline int +rte_atomic32_cmpset(volatile uint32_t *dst, uint32_t exp, uint32_t src) +{ + uint8_t res; + + asm volatile("lock ; " + "cmpxchgl %[src], %[dst];" + "sete %[res];" + : [res] "=a" (res), /* output */ + [dst] "=m" (*dst) + : [src] "r" (src), /* input */ + "a" (exp), + "m" (*dst) + : "memory"); /* no-clobber list */ + return res; +} + +static inline uint32_t +vmbus_txbr_copyto(const struct vmbus_br *tbr, uint32_t windex, + const void *src0, uint32_t cplen) +{ + uint8_t *br_data = tbr->vbr->data; + uint32_t br_dsize = tbr->dsize; + const uint8_t *src = src0; + + /* XXX use double mapping like Linux kernel? */ + if (cplen > br_dsize - windex) { + uint32_t fraglen = br_dsize - windex; + + /* Wrap-around detected */ + memcpy(br_data + windex, src, fraglen); + memcpy(br_data, src + fraglen, cplen - fraglen); + } else { + memcpy(br_data + windex, src, cplen); + } + + return vmbus_br_idxinc(windex, cplen, br_dsize); +} + +/* + * Write scattered channel packet to TX bufring. + * + * The offset of this channel packet is written as a 64bits value + * immediately after this channel packet. + * + * The write goes through three stages: + * 1. Reserve space in ring buffer for the new data. + * Writer atomically moves priv_write_index. + * 2. Copy the new data into the ring. + * 3. Update the tail of the ring (visible to host) that indicates + * next read location. Writer updates write_index + */ +static int +vmbus_txbr_write(struct vmbus_br *tbr, const struct iovec iov[], int iovlen) +{ + struct vmbus_bufring *vbr = tbr->vbr; + uint32_t ring_size = tbr->dsize; + uint32_t old_windex, next_windex, windex, total; + uint64_t save_windex; + int i; + + total = 0; + for (i = 0; i < iovlen; i++) + total += iov[i].iov_len; + total += sizeof(save_windex); + + /* Reserve space in ring */ + do { + uint32_t avail; + + /* Get current free location */ + old_windex = tbr->windex; + + /* Prevent compiler reordering this with calculation */ + rte_compiler_barrier(); + + avail = vmbus_br_availwrite(tbr, old_windex); + + /* If not enough space in ring, then tell caller. */ + if (avail <= total) + return -EAGAIN; + + next_windex = vmbus_br_idxinc(old_windex, total, ring_size); + + /* Atomic update of next write_index for other threads */ + } while (!rte_atomic32_cmpset(&tbr->windex, old_windex, next_windex)); + + /* Space from old..new is now reserved */ + windex = old_windex; + for (i = 0; i < iovlen; i++) + windex = vmbus_txbr_copyto(tbr, windex, iov[i].iov_base, iov[i].iov_len); + + /* Set the offset of the current channel packet. */ + save_windex = ((uint64_t)old_windex) << 32; + windex = vmbus_txbr_copyto(tbr, windex, &save_windex, + sizeof(save_windex)); + + /* The region reserved should match region used */ + if (windex != next_windex) + return -EINVAL; + + /* Ensure that data is available before updating host index */ + rte_compiler_barrier(); + + /* Checkin for our reservation. wait for our turn to update host */ + while (!rte_atomic32_cmpset(&vbr->windex, old_windex, next_windex)) + _mm_pause(); + + return 0; +} + +int rte_vmbus_chan_send(struct vmbus_br *txbr, uint16_t type, void *data, + uint32_t dlen, uint32_t flags) +{ + struct vmbus_chanpkt pkt; + unsigned int pktlen, pad_pktlen; + const uint32_t hlen = sizeof(pkt); + uint64_t pad = 0; + struct iovec iov[3]; + int error; + + pktlen = hlen + dlen; + pad_pktlen = ALIGN(pktlen, sizeof(uint64_t)); + + pkt.hdr.type = type; + pkt.hdr.flags = flags; + pkt.hdr.hlen = hlen >> VMBUS_CHANPKT_SIZE_SHIFT; + pkt.hdr.tlen = pad_pktlen >> VMBUS_CHANPKT_SIZE_SHIFT; + pkt.hdr.xactid = VMBUS_RQST_ERROR; + + iov[0].iov_base = &pkt; + iov[0].iov_len = hlen; + iov[1].iov_base = data; + iov[1].iov_len = dlen; + iov[2].iov_base = &pad; + iov[2].iov_len = pad_pktlen - pktlen; + + error = vmbus_txbr_write(txbr, iov, 3); + + return error; +} + +static inline uint32_t +vmbus_rxbr_copyfrom(const struct vmbus_br *rbr, uint32_t rindex, + void *dst0, size_t cplen) +{ + const uint8_t *br_data = rbr->vbr->data; + uint32_t br_dsize = rbr->dsize; + uint8_t *dst = dst0; + + if (cplen > br_dsize - rindex) { + uint32_t fraglen = br_dsize - rindex; + + /* Wrap-around detected. */ + memcpy(dst, br_data + rindex, fraglen); + memcpy(dst + fraglen, br_data, cplen - fraglen); + } else { + memcpy(dst, br_data + rindex, cplen); + } + + return vmbus_br_idxinc(rindex, cplen, br_dsize); +} + +/* Copy data from receive ring but don't change index */ +static int +vmbus_rxbr_peek(const struct vmbus_br *rbr, void *data, size_t dlen) +{ + uint32_t avail; + + /* + * The requested data and the 64bits channel packet + * offset should be there at least. + */ + avail = vmbus_br_availread(rbr); + if (avail < dlen + sizeof(uint64_t)) + return -EAGAIN; + + vmbus_rxbr_copyfrom(rbr, rbr->vbr->rindex, data, dlen); + return 0; +} + +/* + * Copy data from receive ring and change index + * NOTE: + * We assume (dlen + skip) == sizeof(channel packet). + */ +static int +vmbus_rxbr_read(struct vmbus_br *rbr, void *data, size_t dlen, size_t skip) +{ + struct vmbus_bufring *vbr = rbr->vbr; + uint32_t br_dsize = rbr->dsize; + uint32_t rindex; + + if (vmbus_br_availread(rbr) < dlen + skip + sizeof(uint64_t)) + return -EAGAIN; + + /* Record where host was when we started read (for debug) */ + rbr->windex = rbr->vbr->windex; + + /* + * Copy channel packet from RX bufring. + */ + rindex = vmbus_br_idxinc(rbr->vbr->rindex, skip, br_dsize); + rindex = vmbus_rxbr_copyfrom(rbr, rindex, data, dlen); + + /* + * Discard this channel packet's 64bits offset, which is useless to us. + */ + rindex = vmbus_br_idxinc(rindex, sizeof(uint64_t), br_dsize); + + /* Update the read index _after_ the channel packet is fetched. */ + rte_compiler_barrier(); + + vbr->rindex = rindex; + + return 0; +} + +int rte_vmbus_chan_recv_raw(struct vmbus_br *rxbr, + void *data, uint32_t *len) +{ + struct vmbus_chanpkt_hdr pkt; + uint32_t dlen, bufferlen = *len; + int error; + + error = vmbus_rxbr_peek(rxbr, &pkt, sizeof(pkt)); + if (error) + return error; + + if (unlikely(pkt.hlen < VMBUS_CHANPKT_HLEN_MIN)) + /* XXX this channel is dead actually. */ + return -EIO; + + if (unlikely(pkt.hlen > pkt.tlen)) + return -EIO; + + /* Length are in quad words */ + dlen = pkt.tlen << VMBUS_CHANPKT_SIZE_SHIFT; + *len = dlen; + + /* If caller buffer is not large enough */ + if (unlikely(dlen > bufferlen)) + return -ENOBUFS; + + /* Read data and skip packet header */ + error = vmbus_rxbr_read(rxbr, data, dlen, 0); + if (error) + return error; + + /* Return the number of bytes read */ + return dlen + sizeof(uint64_t); +} diff --git a/tools/hv/vmbus_bufring.h b/tools/hv/vmbus_bufring.h new file mode 100644 index 000000000000..6e7caacfff57 --- /dev/null +++ b/tools/hv/vmbus_bufring.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ + +#ifndef _VMBUS_BUF_H_ +#define _VMBUS_BUF_H_ + +#include <stdbool.h> +#include <stdint.h> + +#define __packed __attribute__((__packed__)) +#define unlikely(x) __builtin_expect(!!(x), 0) + +#define ICMSGHDRFLAG_TRANSACTION 1 +#define ICMSGHDRFLAG_REQUEST 2 +#define ICMSGHDRFLAG_RESPONSE 4 + +#define IC_VERSION_NEGOTIATION_MAX_VER_COUNT 100 +#define ICMSG_HDR (sizeof(struct vmbuspipe_hdr) + sizeof(struct icmsg_hdr)) +#define ICMSG_NEGOTIATE_PKT_SIZE(icframe_vercnt, icmsg_vercnt) \ + (ICMSG_HDR + sizeof(struct icmsg_negotiate) + \ + (((icframe_vercnt) + (icmsg_vercnt)) * sizeof(struct ic_version))) + +/* + * Channel packets + */ + +/* Channel packet flags */ +#define VMBUS_CHANPKT_TYPE_INBAND 0x0006 +#define VMBUS_CHANPKT_TYPE_RXBUF 0x0007 +#define VMBUS_CHANPKT_TYPE_GPA 0x0009 +#define VMBUS_CHANPKT_TYPE_COMP 0x000b + +#define VMBUS_CHANPKT_FLAG_NONE 0 +#define VMBUS_CHANPKT_FLAG_RC 0x0001 /* report completion */ + +#define VMBUS_CHANPKT_SIZE_SHIFT 3 +#define VMBUS_CHANPKT_SIZE_ALIGN BIT(VMBUS_CHANPKT_SIZE_SHIFT) +#define VMBUS_CHANPKT_HLEN_MIN \ + (sizeof(struct vmbus_chanpkt_hdr) >> VMBUS_CHANPKT_SIZE_SHIFT) + +/* + * Buffer ring + */ +struct vmbus_bufring { + volatile uint32_t windex; + volatile uint32_t rindex; + + /* + * Interrupt mask {0,1} + * + * For TX bufring, host set this to 1, when it is processing + * the TX bufring, so that we can safely skip the TX event + * notification to host. + * + * For RX bufring, once this is set to 1 by us, host will not + * further dispatch interrupts to us, even if there are data + * pending on the RX bufring. This effectively disables the + * interrupt of the channel to which this RX bufring is attached. + */ + volatile uint32_t imask; + + /* + * Win8 uses some of the reserved bits to implement + * interrupt driven flow management. On the send side + * we can request that the receiver interrupt the sender + * when the ring transitions from being full to being able + * to handle a message of size "pending_send_sz". + * + * Add necessary state for this enhancement. + */ + volatile uint32_t pending_send; + uint32_t reserved1[12]; + + union { + struct { + uint32_t feat_pending_send_sz:1; + }; + uint32_t value; + } feature_bits; + + /* Pad it to rte_mem_page_size() so that data starts on page boundary */ + uint8_t reserved2[4028]; + + /* + * Ring data starts here + RingDataStartOffset + * !!! DO NOT place any fields below this !!! + */ + uint8_t data[]; +} __packed; + +struct vmbus_br { + struct vmbus_bufring *vbr; + uint32_t dsize; + uint32_t windex; /* next available location */ +}; + +struct vmbus_chanpkt_hdr { + uint16_t type; /* VMBUS_CHANPKT_TYPE_ */ + uint16_t hlen; /* header len, in 8 bytes */ + uint16_t tlen; /* total len, in 8 bytes */ + uint16_t flags; /* VMBUS_CHANPKT_FLAG_ */ + uint64_t xactid; +} __packed; + +struct vmbus_chanpkt { + struct vmbus_chanpkt_hdr hdr; +} __packed; + +struct vmbuspipe_hdr { + unsigned int flags; + unsigned int msgsize; +} __packed; + +struct ic_version { + unsigned short major; + unsigned short minor; +} __packed; + +struct icmsg_negotiate { + unsigned short icframe_vercnt; + unsigned short icmsg_vercnt; + unsigned int reserved; + struct ic_version icversion_data[]; /* any size array */ +} __packed; + +struct icmsg_hdr { + struct ic_version icverframe; + unsigned short icmsgtype; + struct ic_version icvermsg; + unsigned short icmsgsize; + unsigned int status; + unsigned char ictransaction_id; + unsigned char icflags; + unsigned char reserved[2]; +} __packed; + +int rte_vmbus_chan_recv_raw(struct vmbus_br *rxbr, void *data, uint32_t *len); +int rte_vmbus_chan_send(struct vmbus_br *txbr, uint16_t type, void *data, + uint32_t dlen, uint32_t flags); +void vmbus_br_setup(struct vmbus_br *br, void *buf, unsigned int blen); +void *vmbus_uio_map(int *fd, int size); + +/* Amount of space available for write */ +static inline uint32_t vmbus_br_availwrite(const struct vmbus_br *br, uint32_t windex) +{ + uint32_t rindex = br->vbr->rindex; + + if (windex >= rindex) + return br->dsize - (windex - rindex); + else + return rindex - windex; +} + +static inline uint32_t vmbus_br_availread(const struct vmbus_br *br) +{ + return br->dsize - vmbus_br_availwrite(br, br->vbr->windex); +} + +#endif /* !_VMBUS_BUF_H_ */ diff --git a/tools/hv/vmbus_testing b/tools/hv/vmbus_testing index e7212903dd1d..4467979d8f69 100755 --- a/tools/hv/vmbus_testing +++ b/tools/hv/vmbus_testing @@ -164,7 +164,7 @@ def recursive_file_lookup(path, file_map): def get_all_devices_test_status(file_map): for device in file_map: - if (get_test_state(locate_state(device, file_map)) is 1): + if (get_test_state(locate_state(device, file_map)) == 1): print("Testing = ON for: {}" .format(device.split("/")[5])) else: @@ -203,7 +203,7 @@ def write_test_files(path, value): def set_test_state(state_path, state_value, quiet): write_test_files(state_path, state_value) - if (get_test_state(state_path) is 1): + if (get_test_state(state_path) == 1): if (not quiet): print("Testing = ON for device: {}" .format(state_path.split("/")[5])) |