diff options
Diffstat (limited to '')
| -rw-r--r-- | drivers/block/rnbd/Kconfig | 28 | ||||
| -rw-r--r-- | drivers/block/rnbd/Makefile | 15 | ||||
| -rw-r--r-- | drivers/block/rnbd/README | 92 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-clt-sysfs.c | 652 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-clt.c | 1736 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-clt.h | 156 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-common.c | 23 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-log.h | 41 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-proto.h | 303 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-srv-dev.c | 103 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-srv-dev.h | 83 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-srv-sysfs.c | 215 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-srv.c | 859 | ||||
| -rw-r--r-- | drivers/block/rnbd/rnbd-srv.h | 78 |
14 files changed, 4384 insertions, 0 deletions
diff --git a/drivers/block/rnbd/Kconfig b/drivers/block/rnbd/Kconfig new file mode 100644 index 000000000..4b6d3d816 --- /dev/null +++ b/drivers/block/rnbd/Kconfig @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +config BLK_DEV_RNBD + bool + +config BLK_DEV_RNBD_CLIENT + tristate "RDMA Network Block Device driver client" + depends on INFINIBAND_RTRS_CLIENT + select BLK_DEV_RNBD + help + RNBD client is a network block device driver using rdma transport. + + RNBD client allows for mapping of a remote block devices over + RTRS protocol from a target system where RNBD server is running. + + If unsure, say N. + +config BLK_DEV_RNBD_SERVER + tristate "RDMA Network Block Device driver server" + depends on INFINIBAND_RTRS_SERVER + select BLK_DEV_RNBD + help + RNBD server is the server side of RNBD using rdma transport. + + RNBD server allows for exporting local block devices to a remote client + over RTRS protocol. + + If unsure, say N. diff --git a/drivers/block/rnbd/Makefile b/drivers/block/rnbd/Makefile new file mode 100644 index 000000000..5bb1a7ad1 --- /dev/null +++ b/drivers/block/rnbd/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +ccflags-y := -I$(srctree)/drivers/infiniband/ulp/rtrs + +rnbd-client-y := rnbd-clt.o \ + rnbd-clt-sysfs.o \ + rnbd-common.o + +rnbd-server-y := rnbd-common.o \ + rnbd-srv.o \ + rnbd-srv-dev.o \ + rnbd-srv-sysfs.o + +obj-$(CONFIG_BLK_DEV_RNBD_CLIENT) += rnbd-client.o +obj-$(CONFIG_BLK_DEV_RNBD_SERVER) += rnbd-server.o diff --git a/drivers/block/rnbd/README b/drivers/block/rnbd/README new file mode 100644 index 000000000..1773c0aa0 --- /dev/null +++ b/drivers/block/rnbd/README @@ -0,0 +1,92 @@ +******************************** +RDMA Network Block Device (RNBD) +******************************** + +Introduction +------------ + +RNBD (RDMA Network Block Device) is a pair of kernel modules +(client and server) that allow for remote access of a block device on +the server over RTRS protocol using the RDMA (InfiniBand, RoCE, iWARP) +transport. After being mapped, the remote block devices can be accessed +on the client side as local block devices. + +I/O is transferred between client and server by the RTRS transport +modules. The administration of RNBD and RTRS modules is done via +sysfs entries. + +Requirements +------------ + + RTRS kernel modules + +Quick Start +----------- + +Server side: + # modprobe rnbd_server + +Client side: + # modprobe rnbd_client + # echo "sessname=blya path=ip:10.50.100.66 device_path=/dev/ram0" > \ + /sys/devices/virtual/rnbd-client/ctl/map_device + + Where "sessname=" is a session name, a string to identify the session + on client and on server sides; "path=" is a destination IP address or + a pair of a source and a destination IPs, separated by comma. Multiple + "path=" options can be specified in order to use multipath (see RTRS + description for details); "device_path=" is the block device to be + mapped from the server side. After the session to the server machine is + established, the mapped device will appear on the client side under + /dev/rnbd<N>. + + +RNBD-Server Module Parameters +============================= + +dev_search_path +--------------- + +When a device is mapped from the client, the server generates the path +to the block device on the server side by concatenating dev_search_path +and the "device_path" that was specified in the map_device operation. + +The default dev_search_path is: "/". + +dev_search_path option can also contain %SESSNAME% in order to provide +different device namespaces for different sessions. See "device_path" +option for details. + +============================ +Protocol (rnbd/rnbd-proto.h) +============================ + +1. Before mapping first device from a given server, client sends an +RNBD_MSG_SESS_INFO to the server. Server responds with +RNBD_MSG_SESS_INFO_RSP. Currently the messages only contain the protocol +version for backward compatibility. + +2. Client requests to open a device by sending RNBD_MSG_OPEN message. This +contains the path to the device and access mode (read-only or writable). +Server responds to the message with RNBD_MSG_OPEN_RSP. This contains +a 32 bit device id to be used for IOs and device "geometry" related +information: side, max_hw_sectors, etc. + +3. Client attaches RNBD_MSG_IO to each IO message send to a device. This +message contains device id, provided by server in his rnbd_msg_open_rsp, +sector to be accessed, read-write flags and bi_size. + +4. Client closes a device by sending RNBD_MSG_CLOSE which contains only the +device id provided by the server. + +========================================= +Contributors List(in alphabetical order) +========================================= +Danil Kipnis <danil.kipnis@profitbricks.com> +Fabian Holler <mail@fholler.de> +Guoqing Jiang <guoqing.jiang@cloud.ionos.com> +Jack Wang <jinpu.wang@profitbricks.com> +Kleber Souza <kleber.souza@profitbricks.com> +Lutz Pogrell <lutz.pogrell@cloud.ionos.com> +Milind Dumbare <Milind.dumbare@gmail.com> +Roman Penyaev <roman.penyaev@profitbricks.com> diff --git a/drivers/block/rnbd/rnbd-clt-sysfs.c b/drivers/block/rnbd/rnbd-clt-sysfs.c new file mode 100644 index 000000000..5613cd458 --- /dev/null +++ b/drivers/block/rnbd/rnbd-clt-sysfs.c @@ -0,0 +1,652 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ + +#undef pr_fmt +#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt + +#include <linux/types.h> +#include <linux/ctype.h> +#include <linux/parser.h> +#include <linux/module.h> +#include <linux/in6.h> +#include <linux/fs.h> +#include <linux/uaccess.h> +#include <linux/device.h> +#include <rdma/ib.h> +#include <rdma/rdma_cm.h> + +#include "rnbd-clt.h" + +static struct device *rnbd_dev; +static struct class *rnbd_dev_class; +static struct kobject *rnbd_devs_kobj; + +enum { + RNBD_OPT_ERR = 0, + RNBD_OPT_DEST_PORT = 1 << 0, + RNBD_OPT_PATH = 1 << 1, + RNBD_OPT_DEV_PATH = 1 << 2, + RNBD_OPT_ACCESS_MODE = 1 << 3, + RNBD_OPT_SESSNAME = 1 << 6, +}; + +static const unsigned int rnbd_opt_mandatory[] = { + RNBD_OPT_PATH, + RNBD_OPT_DEV_PATH, + RNBD_OPT_SESSNAME, +}; + +static const match_table_t rnbd_opt_tokens = { + {RNBD_OPT_PATH, "path=%s" }, + {RNBD_OPT_DEV_PATH, "device_path=%s"}, + {RNBD_OPT_DEST_PORT, "dest_port=%d" }, + {RNBD_OPT_ACCESS_MODE, "access_mode=%s"}, + {RNBD_OPT_SESSNAME, "sessname=%s" }, + {RNBD_OPT_ERR, NULL }, +}; + +struct rnbd_map_options { + char *sessname; + struct rtrs_addr *paths; + size_t *path_cnt; + char *pathname; + u16 *dest_port; + enum rnbd_access_mode *access_mode; +}; + +static int rnbd_clt_parse_map_options(const char *buf, size_t max_path_cnt, + struct rnbd_map_options *opt) +{ + char *options, *sep_opt; + char *p; + substring_t args[MAX_OPT_ARGS]; + int opt_mask = 0; + int token; + int ret = -EINVAL; + int i, dest_port; + int p_cnt = 0; + + options = kstrdup(buf, GFP_KERNEL); + if (!options) + return -ENOMEM; + + sep_opt = strstrip(options); + while ((p = strsep(&sep_opt, " ")) != NULL) { + if (!*p) + continue; + + token = match_token(p, rnbd_opt_tokens, args); + opt_mask |= token; + + switch (token) { + case RNBD_OPT_SESSNAME: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + if (strlen(p) > NAME_MAX) { + pr_err("map_device: sessname too long\n"); + ret = -EINVAL; + kfree(p); + goto out; + } + strlcpy(opt->sessname, p, NAME_MAX); + kfree(p); + break; + + case RNBD_OPT_PATH: + if (p_cnt >= max_path_cnt) { + pr_err("map_device: too many (> %zu) paths provided\n", + max_path_cnt); + ret = -ENOMEM; + goto out; + } + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + + ret = rtrs_addr_to_sockaddr(p, strlen(p), + *opt->dest_port, + &opt->paths[p_cnt]); + if (ret) { + pr_err("Can't parse path %s: %d\n", p, ret); + kfree(p); + goto out; + } + + p_cnt++; + + kfree(p); + break; + + case RNBD_OPT_DEV_PATH: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + if (strlen(p) > NAME_MAX) { + pr_err("map_device: Device path too long\n"); + ret = -EINVAL; + kfree(p); + goto out; + } + strlcpy(opt->pathname, p, NAME_MAX); + kfree(p); + break; + + case RNBD_OPT_DEST_PORT: + if (match_int(args, &dest_port) || dest_port < 0 || + dest_port > 65535) { + pr_err("bad destination port number parameter '%d'\n", + dest_port); + ret = -EINVAL; + goto out; + } + *opt->dest_port = dest_port; + break; + + case RNBD_OPT_ACCESS_MODE: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + + if (!strcmp(p, "ro")) { + *opt->access_mode = RNBD_ACCESS_RO; + } else if (!strcmp(p, "rw")) { + *opt->access_mode = RNBD_ACCESS_RW; + } else if (!strcmp(p, "migration")) { + *opt->access_mode = RNBD_ACCESS_MIGRATION; + } else { + pr_err("map_device: Invalid access_mode: '%s'\n", + p); + ret = -EINVAL; + kfree(p); + goto out; + } + + kfree(p); + break; + + default: + pr_err("map_device: Unknown parameter or missing value '%s'\n", + p); + ret = -EINVAL; + goto out; + } + } + + for (i = 0; i < ARRAY_SIZE(rnbd_opt_mandatory); i++) { + if ((opt_mask & rnbd_opt_mandatory[i])) { + ret = 0; + } else { + pr_err("map_device: Parameters missing\n"); + ret = -EINVAL; + break; + } + } + +out: + *opt->path_cnt = p_cnt; + kfree(options); + return ret; +} + +static ssize_t state_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + struct rnbd_clt_dev *dev; + + dev = container_of(kobj, struct rnbd_clt_dev, kobj); + + switch (dev->dev_state) { + case DEV_STATE_INIT: + return snprintf(page, PAGE_SIZE, "init\n"); + case DEV_STATE_MAPPED: + /* TODO fix cli tool before changing to proper state */ + return snprintf(page, PAGE_SIZE, "open\n"); + case DEV_STATE_MAPPED_DISCONNECTED: + /* TODO fix cli tool before changing to proper state */ + return snprintf(page, PAGE_SIZE, "closed\n"); + case DEV_STATE_UNMAPPED: + return snprintf(page, PAGE_SIZE, "unmapped\n"); + default: + return snprintf(page, PAGE_SIZE, "unknown\n"); + } +} + +static struct kobj_attribute rnbd_clt_state_attr = __ATTR_RO(state); + +static ssize_t mapping_path_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + struct rnbd_clt_dev *dev; + + dev = container_of(kobj, struct rnbd_clt_dev, kobj); + + return scnprintf(page, PAGE_SIZE, "%s\n", dev->pathname); +} + +static struct kobj_attribute rnbd_clt_mapping_path_attr = + __ATTR_RO(mapping_path); + +static ssize_t access_mode_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + struct rnbd_clt_dev *dev; + + dev = container_of(kobj, struct rnbd_clt_dev, kobj); + + return snprintf(page, PAGE_SIZE, "%s\n", + rnbd_access_mode_str(dev->access_mode)); +} + +static struct kobj_attribute rnbd_clt_access_mode = + __ATTR_RO(access_mode); + +static ssize_t rnbd_clt_unmap_dev_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return scnprintf(page, PAGE_SIZE, "Usage: echo <normal|force> > %s\n", + attr->attr.name); +} + +static ssize_t rnbd_clt_unmap_dev_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct rnbd_clt_dev *dev; + char *opt, *options; + bool force; + int err; + + opt = kstrdup(buf, GFP_KERNEL); + if (!opt) + return -ENOMEM; + + options = strstrip(opt); + dev = container_of(kobj, struct rnbd_clt_dev, kobj); + if (sysfs_streq(options, "normal")) { + force = false; + } else if (sysfs_streq(options, "force")) { + force = true; + } else { + rnbd_clt_err(dev, + "unmap_device: Invalid value: %s\n", + options); + err = -EINVAL; + goto out; + } + + rnbd_clt_info(dev, "Unmapping device, option: %s.\n", + force ? "force" : "normal"); + + /* + * We take explicit module reference only for one reason: do not + * race with lockless rnbd_destroy_sessions(). + */ + if (!try_module_get(THIS_MODULE)) { + err = -ENODEV; + goto out; + } + err = rnbd_clt_unmap_device(dev, force, &attr->attr); + if (err) { + if (err != -EALREADY) + rnbd_clt_err(dev, "unmap_device: %d\n", err); + goto module_put; + } + + /* + * Here device can be vanished! + */ + + err = count; + +module_put: + module_put(THIS_MODULE); +out: + kfree(opt); + + return err; +} + +static struct kobj_attribute rnbd_clt_unmap_device_attr = + __ATTR(unmap_device, 0644, rnbd_clt_unmap_dev_show, + rnbd_clt_unmap_dev_store); + +static ssize_t rnbd_clt_resize_dev_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *page) +{ + return scnprintf(page, PAGE_SIZE, + "Usage: echo <new size in sectors> > %s\n", + attr->attr.name); +} + +static ssize_t rnbd_clt_resize_dev_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int ret; + unsigned long sectors; + struct rnbd_clt_dev *dev; + + dev = container_of(kobj, struct rnbd_clt_dev, kobj); + + ret = kstrtoul(buf, 0, §ors); + if (ret) + return ret; + + ret = rnbd_clt_resize_disk(dev, (size_t)sectors); + if (ret) + return ret; + + return count; +} + +static struct kobj_attribute rnbd_clt_resize_dev_attr = + __ATTR(resize, 0644, rnbd_clt_resize_dev_show, + rnbd_clt_resize_dev_store); + +static ssize_t rnbd_clt_remap_dev_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return scnprintf(page, PAGE_SIZE, "Usage: echo <1> > %s\n", + attr->attr.name); +} + +static ssize_t rnbd_clt_remap_dev_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct rnbd_clt_dev *dev; + char *opt, *options; + int err; + + opt = kstrdup(buf, GFP_KERNEL); + if (!opt) + return -ENOMEM; + + options = strstrip(opt); + dev = container_of(kobj, struct rnbd_clt_dev, kobj); + if (!sysfs_streq(options, "1")) { + rnbd_clt_err(dev, + "remap_device: Invalid value: %s\n", + options); + err = -EINVAL; + goto out; + } + err = rnbd_clt_remap_device(dev); + if (likely(!err)) + err = count; + +out: + kfree(opt); + + return err; +} + +static struct kobj_attribute rnbd_clt_remap_device_attr = + __ATTR(remap_device, 0644, rnbd_clt_remap_dev_show, + rnbd_clt_remap_dev_store); + +static ssize_t session_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + struct rnbd_clt_dev *dev; + + dev = container_of(kobj, struct rnbd_clt_dev, kobj); + + return scnprintf(page, PAGE_SIZE, "%s\n", dev->sess->sessname); +} + +static struct kobj_attribute rnbd_clt_session_attr = + __ATTR_RO(session); + +static struct attribute *rnbd_dev_attrs[] = { + &rnbd_clt_unmap_device_attr.attr, + &rnbd_clt_resize_dev_attr.attr, + &rnbd_clt_remap_device_attr.attr, + &rnbd_clt_mapping_path_attr.attr, + &rnbd_clt_state_attr.attr, + &rnbd_clt_session_attr.attr, + &rnbd_clt_access_mode.attr, + NULL, +}; + +void rnbd_clt_remove_dev_symlink(struct rnbd_clt_dev *dev) +{ + /* + * The module unload rnbd_client_exit path is racing with unmapping of + * the last single device from the sysfs manually + * i.e. rnbd_clt_unmap_dev_store() leading to a sysfs warning because + * of sysfs link already was removed already. + */ + if (dev->blk_symlink_name) { + if (try_module_get(THIS_MODULE)) { + sysfs_remove_link(rnbd_devs_kobj, dev->blk_symlink_name); + module_put(THIS_MODULE); + } + /* It should be freed always. */ + kfree(dev->blk_symlink_name); + dev->blk_symlink_name = NULL; + } +} + +static struct kobj_type rnbd_dev_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .default_attrs = rnbd_dev_attrs, +}; + +static int rnbd_clt_add_dev_kobj(struct rnbd_clt_dev *dev) +{ + int ret; + struct kobject *gd_kobj = &disk_to_dev(dev->gd)->kobj; + + ret = kobject_init_and_add(&dev->kobj, &rnbd_dev_ktype, gd_kobj, "%s", + "rnbd"); + if (ret) + rnbd_clt_err(dev, "Failed to create device sysfs dir, err: %d\n", + ret); + + return ret; +} + +static ssize_t rnbd_clt_map_device_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *page) +{ + return scnprintf(page, PAGE_SIZE, + "Usage: echo \"[dest_port=server port number] sessname=<name of the rtrs session> path=<[srcaddr@]dstaddr> [path=<[srcaddr@]dstaddr>] device_path=<full path on remote side> [access_mode=<ro|rw|migration>]\" > %s\n\naddr ::= [ ip:<ipv4> | ip:<ipv6> | gid:<gid> ]\n", + attr->attr.name); +} + +static int rnbd_clt_get_path_name(struct rnbd_clt_dev *dev, char *buf, + size_t len) +{ + int ret; + char pathname[NAME_MAX], *s; + + strlcpy(pathname, dev->pathname, sizeof(pathname)); + while ((s = strchr(pathname, '/'))) + s[0] = '!'; + + ret = snprintf(buf, len, "%s", pathname); + if (ret >= len) + return -ENAMETOOLONG; + + return 0; +} + +static int rnbd_clt_add_dev_symlink(struct rnbd_clt_dev *dev) +{ + struct kobject *gd_kobj = &disk_to_dev(dev->gd)->kobj; + int ret, len; + + len = strlen(dev->pathname) + strlen(dev->sess->sessname) + 2; + dev->blk_symlink_name = kzalloc(len, GFP_KERNEL); + if (!dev->blk_symlink_name) { + rnbd_clt_err(dev, "Failed to allocate memory for blk_symlink_name\n"); + return -ENOMEM; + } + + ret = rnbd_clt_get_path_name(dev, dev->blk_symlink_name, + len); + if (ret) { + rnbd_clt_err(dev, "Failed to get /sys/block symlink path, err: %d\n", + ret); + goto out_err; + } + + ret = sysfs_create_link(rnbd_devs_kobj, gd_kobj, + dev->blk_symlink_name); + if (ret) { + rnbd_clt_err(dev, "Creating /sys/block symlink failed, err: %d\n", + ret); + goto out_err; + } + + return 0; + +out_err: + kfree(dev->blk_symlink_name); + dev->blk_symlink_name = NULL ; + return ret; +} + +static ssize_t rnbd_clt_map_device_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct rnbd_clt_dev *dev; + struct rnbd_map_options opt; + int ret; + char pathname[NAME_MAX]; + char sessname[NAME_MAX]; + enum rnbd_access_mode access_mode = RNBD_ACCESS_RW; + u16 port_nr = RTRS_PORT; + + struct sockaddr_storage *addrs; + struct rtrs_addr paths[6]; + size_t path_cnt; + + opt.sessname = sessname; + opt.paths = paths; + opt.path_cnt = &path_cnt; + opt.pathname = pathname; + opt.dest_port = &port_nr; + opt.access_mode = &access_mode; + addrs = kcalloc(ARRAY_SIZE(paths) * 2, sizeof(*addrs), GFP_KERNEL); + if (!addrs) + return -ENOMEM; + + for (path_cnt = 0; path_cnt < ARRAY_SIZE(paths); path_cnt++) { + paths[path_cnt].src = &addrs[path_cnt * 2]; + paths[path_cnt].dst = &addrs[path_cnt * 2 + 1]; + } + + ret = rnbd_clt_parse_map_options(buf, ARRAY_SIZE(paths), &opt); + if (ret) + goto out; + + pr_info("Mapping device %s on session %s, (access_mode: %s)\n", + pathname, sessname, + rnbd_access_mode_str(access_mode)); + + dev = rnbd_clt_map_device(sessname, paths, path_cnt, port_nr, pathname, + access_mode); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + + ret = rnbd_clt_add_dev_kobj(dev); + if (ret) + goto unmap_dev; + + ret = rnbd_clt_add_dev_symlink(dev); + if (ret) + goto unmap_dev; + + kfree(addrs); + return count; + +unmap_dev: + rnbd_clt_unmap_device(dev, true, NULL); +out: + kfree(addrs); + return ret; +} + +static struct kobj_attribute rnbd_clt_map_device_attr = + __ATTR(map_device, 0644, + rnbd_clt_map_device_show, rnbd_clt_map_device_store); + +static struct attribute *default_attrs[] = { + &rnbd_clt_map_device_attr.attr, + NULL, +}; + +static struct attribute_group default_attr_group = { + .attrs = default_attrs, +}; + +static const struct attribute_group *default_attr_groups[] = { + &default_attr_group, + NULL, +}; + +int rnbd_clt_create_sysfs_files(void) +{ + int err; + + rnbd_dev_class = class_create(THIS_MODULE, "rnbd-client"); + if (IS_ERR(rnbd_dev_class)) + return PTR_ERR(rnbd_dev_class); + + rnbd_dev = device_create_with_groups(rnbd_dev_class, NULL, + MKDEV(0, 0), NULL, + default_attr_groups, "ctl"); + if (IS_ERR(rnbd_dev)) { + err = PTR_ERR(rnbd_dev); + goto cls_destroy; + } + rnbd_devs_kobj = kobject_create_and_add("devices", &rnbd_dev->kobj); + if (!rnbd_devs_kobj) { + err = -ENOMEM; + goto dev_destroy; + } + + return 0; + +dev_destroy: + device_destroy(rnbd_dev_class, MKDEV(0, 0)); +cls_destroy: + class_destroy(rnbd_dev_class); + + return err; +} + +void rnbd_clt_destroy_default_group(void) +{ + sysfs_remove_group(&rnbd_dev->kobj, &default_attr_group); +} + +void rnbd_clt_destroy_sysfs_files(void) +{ + kobject_del(rnbd_devs_kobj); + kobject_put(rnbd_devs_kobj); + device_destroy(rnbd_dev_class, MKDEV(0, 0)); + class_destroy(rnbd_dev_class); +} diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c new file mode 100644 index 000000000..71b86fee8 --- /dev/null +++ b/drivers/block/rnbd/rnbd-clt.c @@ -0,0 +1,1736 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ + +#undef pr_fmt +#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt + +#include <linux/module.h> +#include <linux/blkdev.h> +#include <linux/hdreg.h> +#include <linux/scatterlist.h> +#include <linux/idr.h> + +#include "rnbd-clt.h" + +MODULE_DESCRIPTION("RDMA Network Block Device Client"); +MODULE_LICENSE("GPL"); + +static int rnbd_client_major; +static DEFINE_IDA(index_ida); +static DEFINE_MUTEX(ida_lock); +static DEFINE_MUTEX(sess_lock); +static LIST_HEAD(sess_list); + +/* + * Maximum number of partitions an instance can have. + * 6 bits = 64 minors = 63 partitions (one minor is used for the device itself) + */ +#define RNBD_PART_BITS 6 + +static inline bool rnbd_clt_get_sess(struct rnbd_clt_session *sess) +{ + return refcount_inc_not_zero(&sess->refcount); +} + +static void free_sess(struct rnbd_clt_session *sess); + +static void rnbd_clt_put_sess(struct rnbd_clt_session *sess) +{ + might_sleep(); + + if (refcount_dec_and_test(&sess->refcount)) + free_sess(sess); +} + +static void rnbd_clt_put_dev(struct rnbd_clt_dev *dev) +{ + might_sleep(); + + if (!refcount_dec_and_test(&dev->refcount)) + return; + + mutex_lock(&ida_lock); + ida_simple_remove(&index_ida, dev->clt_device_id); + mutex_unlock(&ida_lock); + kfree(dev->hw_queues); + kfree(dev->pathname); + rnbd_clt_put_sess(dev->sess); + mutex_destroy(&dev->lock); + kfree(dev); +} + +static inline bool rnbd_clt_get_dev(struct rnbd_clt_dev *dev) +{ + return refcount_inc_not_zero(&dev->refcount); +} + +static int rnbd_clt_set_dev_attr(struct rnbd_clt_dev *dev, + const struct rnbd_msg_open_rsp *rsp) +{ + struct rnbd_clt_session *sess = dev->sess; + + if (!rsp->logical_block_size) + return -EINVAL; + + dev->device_id = le32_to_cpu(rsp->device_id); + dev->nsectors = le64_to_cpu(rsp->nsectors); + dev->logical_block_size = le16_to_cpu(rsp->logical_block_size); + dev->physical_block_size = le16_to_cpu(rsp->physical_block_size); + dev->max_write_same_sectors = le32_to_cpu(rsp->max_write_same_sectors); + dev->max_discard_sectors = le32_to_cpu(rsp->max_discard_sectors); + dev->discard_granularity = le32_to_cpu(rsp->discard_granularity); + dev->discard_alignment = le32_to_cpu(rsp->discard_alignment); + dev->secure_discard = le16_to_cpu(rsp->secure_discard); + dev->rotational = rsp->rotational; + + dev->max_hw_sectors = sess->max_io_size / SECTOR_SIZE; + dev->max_segments = BMAX_SEGMENTS; + + return 0; +} + +static int rnbd_clt_change_capacity(struct rnbd_clt_dev *dev, + size_t new_nsectors) +{ + rnbd_clt_info(dev, "Device size changed from %zu to %zu sectors\n", + dev->nsectors, new_nsectors); + dev->nsectors = new_nsectors; + set_capacity(dev->gd, dev->nsectors); + revalidate_disk_size(dev->gd, true); + return 0; +} + +static int process_msg_open_rsp(struct rnbd_clt_dev *dev, + struct rnbd_msg_open_rsp *rsp) +{ + int err = 0; + + mutex_lock(&dev->lock); + if (dev->dev_state == DEV_STATE_UNMAPPED) { + rnbd_clt_info(dev, + "Ignoring Open-Response message from server for unmapped device\n"); + err = -ENOENT; + goto out; + } + if (dev->dev_state == DEV_STATE_MAPPED_DISCONNECTED) { + u64 nsectors = le64_to_cpu(rsp->nsectors); + + /* + * If the device was remapped and the size changed in the + * meantime we need to revalidate it + */ + if (dev->nsectors != nsectors) + rnbd_clt_change_capacity(dev, nsectors); + rnbd_clt_info(dev, "Device online, device remapped successfully\n"); + } + err = rnbd_clt_set_dev_attr(dev, rsp); + if (err) + goto out; + dev->dev_state = DEV_STATE_MAPPED; + +out: + mutex_unlock(&dev->lock); + + return err; +} + +int rnbd_clt_resize_disk(struct rnbd_clt_dev *dev, size_t newsize) +{ + int ret = 0; + + mutex_lock(&dev->lock); + if (dev->dev_state != DEV_STATE_MAPPED) { + pr_err("Failed to set new size of the device, device is not opened\n"); + ret = -ENOENT; + goto out; + } + ret = rnbd_clt_change_capacity(dev, newsize); + +out: + mutex_unlock(&dev->lock); + + return ret; +} + +static inline void rnbd_clt_dev_requeue(struct rnbd_queue *q) +{ + if (WARN_ON(!q->hctx)) + return; + + /* We can come here from interrupt, thus async=true */ + blk_mq_run_hw_queue(q->hctx, true); +} + +enum { + RNBD_DELAY_IFBUSY = -1, +}; + +/** + * rnbd_get_cpu_qlist() - finds a list with HW queues to be rerun + * @sess: Session to find a queue for + * @cpu: Cpu to start the search from + * + * Description: + * Each CPU has a list of HW queues, which needs to be rerun. If a list + * is not empty - it is marked with a bit. This function finds first + * set bit in a bitmap and returns corresponding CPU list. + */ +static struct rnbd_cpu_qlist * +rnbd_get_cpu_qlist(struct rnbd_clt_session *sess, int cpu) +{ + int bit; + + /* Search from cpu to nr_cpu_ids */ + bit = find_next_bit(sess->cpu_queues_bm, nr_cpu_ids, cpu); + if (bit < nr_cpu_ids) { + return per_cpu_ptr(sess->cpu_queues, bit); + } else if (cpu != 0) { + /* Search from 0 to cpu */ + bit = find_next_bit(sess->cpu_queues_bm, cpu, 0); + if (bit < cpu) + return per_cpu_ptr(sess->cpu_queues, bit); + } + + return NULL; +} + +static inline int nxt_cpu(int cpu) +{ + return (cpu + 1) % nr_cpu_ids; +} + +/** + * rnbd_rerun_if_needed() - rerun next queue marked as stopped + * @sess: Session to rerun a queue on + * + * Description: + * Each CPU has it's own list of HW queues, which should be rerun. + * Function finds such list with HW queues, takes a list lock, picks up + * the first HW queue out of the list and requeues it. + * + * Return: + * True if the queue was requeued, false otherwise. + * + * Context: + * Does not matter. + */ +static bool rnbd_rerun_if_needed(struct rnbd_clt_session *sess) +{ + struct rnbd_queue *q = NULL; + struct rnbd_cpu_qlist *cpu_q; + unsigned long flags; + int *cpup; + + /* + * To keep fairness and not to let other queues starve we always + * try to wake up someone else in round-robin manner. That of course + * increases latency but queues always have a chance to be executed. + */ + cpup = get_cpu_ptr(sess->cpu_rr); + for (cpu_q = rnbd_get_cpu_qlist(sess, nxt_cpu(*cpup)); cpu_q; + cpu_q = rnbd_get_cpu_qlist(sess, nxt_cpu(cpu_q->cpu))) { + if (!spin_trylock_irqsave(&cpu_q->requeue_lock, flags)) + continue; + if (unlikely(!test_bit(cpu_q->cpu, sess->cpu_queues_bm))) + goto unlock; + q = list_first_entry_or_null(&cpu_q->requeue_list, + typeof(*q), requeue_list); + if (WARN_ON(!q)) + goto clear_bit; + list_del_init(&q->requeue_list); + clear_bit_unlock(0, &q->in_list); + + if (list_empty(&cpu_q->requeue_list)) { + /* Clear bit if nothing is left */ +clear_bit: + clear_bit(cpu_q->cpu, sess->cpu_queues_bm); + } +unlock: + spin_unlock_irqrestore(&cpu_q->requeue_lock, flags); + + if (q) + break; + } + + /** + * Saves the CPU that is going to be requeued on the per-cpu var. Just + * incrementing it doesn't work because rnbd_get_cpu_qlist() will + * always return the first CPU with something on the queue list when the + * value stored on the var is greater than the last CPU with something + * on the list. + */ + if (cpu_q) + *cpup = cpu_q->cpu; + put_cpu_var(sess->cpu_rr); + + if (q) + rnbd_clt_dev_requeue(q); + + return q; +} + +/** + * rnbd_rerun_all_if_idle() - rerun all queues left in the list if + * session is idling (there are no requests + * in-flight). + * @sess: Session to rerun the queues on + * + * Description: + * This function tries to rerun all stopped queues if there are no + * requests in-flight anymore. This function tries to solve an obvious + * problem, when number of tags < than number of queues (hctx), which + * are stopped and put to sleep. If last permit, which has been just put, + * does not wake up all left queues (hctxs), IO requests hang forever. + * + * That can happen when all number of permits, say N, have been exhausted + * from one CPU, and we have many block devices per session, say M. + * Each block device has it's own queue (hctx) for each CPU, so eventually + * we can put that number of queues (hctxs) to sleep: M x nr_cpu_ids. + * If number of permits N < M x nr_cpu_ids finally we will get an IO hang. + * + * To avoid this hang last caller of rnbd_put_permit() (last caller is the + * one who observes sess->busy == 0) must wake up all remaining queues. + * + * Context: + * Does not matter. + */ +static void rnbd_rerun_all_if_idle(struct rnbd_clt_session *sess) +{ + bool requeued; + + do { + requeued = rnbd_rerun_if_needed(sess); + } while (atomic_read(&sess->busy) == 0 && requeued); +} + +static struct rtrs_permit *rnbd_get_permit(struct rnbd_clt_session *sess, + enum rtrs_clt_con_type con_type, + int wait) +{ + struct rtrs_permit *permit; + + permit = rtrs_clt_get_permit(sess->rtrs, con_type, + wait ? RTRS_PERMIT_WAIT : + RTRS_PERMIT_NOWAIT); + if (likely(permit)) + /* We have a subtle rare case here, when all permits can be + * consumed before busy counter increased. This is safe, + * because loser will get NULL as a permit, observe 0 busy + * counter and immediately restart the queue himself. + */ + atomic_inc(&sess->busy); + + return permit; +} + +static void rnbd_put_permit(struct rnbd_clt_session *sess, + struct rtrs_permit *permit) +{ + rtrs_clt_put_permit(sess->rtrs, permit); + atomic_dec(&sess->busy); + /* Paired with rnbd_clt_dev_add_to_requeue(). Decrement first + * and then check queue bits. + */ + smp_mb__after_atomic(); + rnbd_rerun_all_if_idle(sess); +} + +static struct rnbd_iu *rnbd_get_iu(struct rnbd_clt_session *sess, + enum rtrs_clt_con_type con_type, + int wait) +{ + struct rnbd_iu *iu; + struct rtrs_permit *permit; + + permit = rnbd_get_permit(sess, con_type, + wait ? RTRS_PERMIT_WAIT : + RTRS_PERMIT_NOWAIT); + if (unlikely(!permit)) + return NULL; + iu = rtrs_permit_to_pdu(permit); + iu->permit = permit; + /* + * 1st reference is dropped after finishing sending a "user" message, + * 2nd reference is dropped after confirmation with the response is + * returned. + * 1st and 2nd can happen in any order, so the rnbd_iu should be + * released (rtrs_permit returned to ibbtrs) only leased after both + * are finished. + */ + atomic_set(&iu->refcount, 2); + init_waitqueue_head(&iu->comp.wait); + iu->comp.errno = INT_MAX; + + return iu; +} + +static void rnbd_put_iu(struct rnbd_clt_session *sess, struct rnbd_iu *iu) +{ + if (atomic_dec_and_test(&iu->refcount)) + rnbd_put_permit(sess, iu->permit); +} + +static void rnbd_softirq_done_fn(struct request *rq) +{ + struct rnbd_clt_dev *dev = rq->rq_disk->private_data; + struct rnbd_clt_session *sess = dev->sess; + struct rnbd_iu *iu; + + iu = blk_mq_rq_to_pdu(rq); + rnbd_put_permit(sess, iu->permit); + blk_mq_end_request(rq, errno_to_blk_status(iu->errno)); +} + +static void msg_io_conf(void *priv, int errno) +{ + struct rnbd_iu *iu = priv; + struct rnbd_clt_dev *dev = iu->dev; + struct request *rq = iu->rq; + int rw = rq_data_dir(rq); + + iu->errno = errno; + + blk_mq_complete_request(rq); + + if (errno) + rnbd_clt_info_rl(dev, "%s I/O failed with err: %d\n", + rw == READ ? "read" : "write", errno); +} + +static void wake_up_iu_comp(struct rnbd_iu *iu, int errno) +{ + iu->comp.errno = errno; + wake_up(&iu->comp.wait); +} + +static void msg_conf(void *priv, int errno) +{ + struct rnbd_iu *iu = priv; + + iu->errno = errno; + schedule_work(&iu->work); +} + +enum wait_type { + NO_WAIT = 0, + WAIT = 1 +}; + +static int send_usr_msg(struct rtrs_clt *rtrs, int dir, + struct rnbd_iu *iu, struct kvec *vec, + size_t len, struct scatterlist *sg, unsigned int sg_len, + void (*conf)(struct work_struct *work), + int *errno, enum wait_type wait) +{ + int err; + struct rtrs_clt_req_ops req_ops; + + INIT_WORK(&iu->work, conf); + req_ops = (struct rtrs_clt_req_ops) { + .priv = iu, + .conf_fn = msg_conf, + }; + err = rtrs_clt_request(dir, &req_ops, rtrs, iu->permit, + vec, 1, len, sg, sg_len); + if (!err && wait) { + wait_event(iu->comp.wait, iu->comp.errno != INT_MAX); + *errno = iu->comp.errno; + } else { + *errno = 0; + } + + return err; +} + +static void msg_close_conf(struct work_struct *work) +{ + struct rnbd_iu *iu = container_of(work, struct rnbd_iu, work); + struct rnbd_clt_dev *dev = iu->dev; + + wake_up_iu_comp(iu, iu->errno); + rnbd_put_iu(dev->sess, iu); + rnbd_clt_put_dev(dev); +} + +static int send_msg_close(struct rnbd_clt_dev *dev, u32 device_id, bool wait) +{ + struct rnbd_clt_session *sess = dev->sess; + struct rnbd_msg_close msg; + struct rnbd_iu *iu; + struct kvec vec = { + .iov_base = &msg, + .iov_len = sizeof(msg) + }; + int err, errno; + + iu = rnbd_get_iu(sess, RTRS_ADMIN_CON, RTRS_PERMIT_WAIT); + if (!iu) + return -ENOMEM; + + iu->buf = NULL; + iu->dev = dev; + + sg_mark_end(&iu->sglist[0]); + + msg.hdr.type = cpu_to_le16(RNBD_MSG_CLOSE); + msg.device_id = cpu_to_le32(device_id); + + WARN_ON(!rnbd_clt_get_dev(dev)); + err = send_usr_msg(sess->rtrs, WRITE, iu, &vec, 0, NULL, 0, + msg_close_conf, &errno, wait); + if (err) { + rnbd_clt_put_dev(dev); + rnbd_put_iu(sess, iu); + } else { + err = errno; + } + + rnbd_put_iu(sess, iu); + return err; +} + +static void msg_open_conf(struct work_struct *work) +{ + struct rnbd_iu *iu = container_of(work, struct rnbd_iu, work); + struct rnbd_msg_open_rsp *rsp = iu->buf; + struct rnbd_clt_dev *dev = iu->dev; + int errno = iu->errno; + + if (errno) { + rnbd_clt_err(dev, + "Opening failed, server responded: %d\n", + errno); + } else { + errno = process_msg_open_rsp(dev, rsp); + if (errno) { + u32 device_id = le32_to_cpu(rsp->device_id); + /* + * If server thinks its fine, but we fail to process + * then be nice and send a close to server. + */ + (void)send_msg_close(dev, device_id, NO_WAIT); + } + } + kfree(rsp); + wake_up_iu_comp(iu, errno); + rnbd_put_iu(dev->sess, iu); + rnbd_clt_put_dev(dev); +} + +static void msg_sess_info_conf(struct work_struct *work) +{ + struct rnbd_iu *iu = container_of(work, struct rnbd_iu, work); + struct rnbd_msg_sess_info_rsp *rsp = iu->buf; + struct rnbd_clt_session *sess = iu->sess; + + if (!iu->errno) + sess->ver = min_t(u8, rsp->ver, RNBD_PROTO_VER_MAJOR); + + kfree(rsp); + wake_up_iu_comp(iu, iu->errno); + rnbd_put_iu(sess, iu); + rnbd_clt_put_sess(sess); +} + +static int send_msg_open(struct rnbd_clt_dev *dev, bool wait) +{ + struct rnbd_clt_session *sess = dev->sess; + struct rnbd_msg_open_rsp *rsp; + struct rnbd_msg_open msg; + struct rnbd_iu *iu; + struct kvec vec = { + .iov_base = &msg, + .iov_len = sizeof(msg) + }; + int err, errno; + + rsp = kzalloc(sizeof(*rsp), GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + iu = rnbd_get_iu(sess, RTRS_ADMIN_CON, RTRS_PERMIT_WAIT); + if (!iu) { + kfree(rsp); + return -ENOMEM; + } + + iu->buf = rsp; + iu->dev = dev; + + sg_init_one(iu->sglist, rsp, sizeof(*rsp)); + + msg.hdr.type = cpu_to_le16(RNBD_MSG_OPEN); + msg.access_mode = dev->access_mode; + strlcpy(msg.dev_name, dev->pathname, sizeof(msg.dev_name)); + + WARN_ON(!rnbd_clt_get_dev(dev)); + err = send_usr_msg(sess->rtrs, READ, iu, + &vec, sizeof(*rsp), iu->sglist, 1, + msg_open_conf, &errno, wait); + if (err) { + rnbd_clt_put_dev(dev); + rnbd_put_iu(sess, iu); + kfree(rsp); + } else { + err = errno; + } + + rnbd_put_iu(sess, iu); + return err; +} + +static int send_msg_sess_info(struct rnbd_clt_session *sess, bool wait) +{ + struct rnbd_msg_sess_info_rsp *rsp; + struct rnbd_msg_sess_info msg; + struct rnbd_iu *iu; + struct kvec vec = { + .iov_base = &msg, + .iov_len = sizeof(msg) + }; + int err, errno; + + rsp = kzalloc(sizeof(*rsp), GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + iu = rnbd_get_iu(sess, RTRS_ADMIN_CON, RTRS_PERMIT_WAIT); + if (!iu) { + kfree(rsp); + return -ENOMEM; + } + + iu->buf = rsp; + iu->sess = sess; + + sg_init_one(iu->sglist, rsp, sizeof(*rsp)); + + msg.hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO); + msg.ver = RNBD_PROTO_VER_MAJOR; + + if (!rnbd_clt_get_sess(sess)) { + /* + * That can happen only in one case, when RTRS has restablished + * the connection and link_ev() is called, but session is almost + * dead, last reference on session is put and caller is waiting + * for RTRS to close everything. + */ + err = -ENODEV; + goto put_iu; + } + err = send_usr_msg(sess->rtrs, READ, iu, + &vec, sizeof(*rsp), iu->sglist, 1, + msg_sess_info_conf, &errno, wait); + if (err) { + rnbd_clt_put_sess(sess); +put_iu: + rnbd_put_iu(sess, iu); + kfree(rsp); + } else { + err = errno; + } + + rnbd_put_iu(sess, iu); + return err; +} + +static void set_dev_states_to_disconnected(struct rnbd_clt_session *sess) +{ + struct rnbd_clt_dev *dev; + + mutex_lock(&sess->lock); + list_for_each_entry(dev, &sess->devs_list, list) { + rnbd_clt_err(dev, "Device disconnected.\n"); + + mutex_lock(&dev->lock); + if (dev->dev_state == DEV_STATE_MAPPED) + dev->dev_state = DEV_STATE_MAPPED_DISCONNECTED; + mutex_unlock(&dev->lock); + } + mutex_unlock(&sess->lock); +} + +static void remap_devs(struct rnbd_clt_session *sess) +{ + struct rnbd_clt_dev *dev; + struct rtrs_attrs attrs; + int err; + + /* + * Careful here: we are called from RTRS link event directly, + * thus we can't send any RTRS request and wait for response + * or RTRS will not be able to complete request with failure + * if something goes wrong (failing of outstanding requests + * happens exactly from the context where we are blocking now). + * + * So to avoid deadlocks each usr message sent from here must + * be asynchronous. + */ + + err = send_msg_sess_info(sess, NO_WAIT); + if (err) { + pr_err("send_msg_sess_info(\"%s\"): %d\n", sess->sessname, err); + return; + } + + err = rtrs_clt_query(sess->rtrs, &attrs); + if (err) { + pr_err("rtrs_clt_query(\"%s\"): %d\n", sess->sessname, err); + return; + } + mutex_lock(&sess->lock); + sess->max_io_size = attrs.max_io_size; + + list_for_each_entry(dev, &sess->devs_list, list) { + bool skip; + + mutex_lock(&dev->lock); + skip = (dev->dev_state == DEV_STATE_INIT); + mutex_unlock(&dev->lock); + if (skip) + /* + * When device is establishing connection for the first + * time - do not remap, it will be closed soon. + */ + continue; + + rnbd_clt_info(dev, "session reconnected, remapping device\n"); + err = send_msg_open(dev, NO_WAIT); + if (err) { + rnbd_clt_err(dev, "send_msg_open(): %d\n", err); + break; + } + } + mutex_unlock(&sess->lock); +} + +static void rnbd_clt_link_ev(void *priv, enum rtrs_clt_link_ev ev) +{ + struct rnbd_clt_session *sess = priv; + + switch (ev) { + case RTRS_CLT_LINK_EV_DISCONNECTED: + set_dev_states_to_disconnected(sess); + break; + case RTRS_CLT_LINK_EV_RECONNECTED: + remap_devs(sess); + break; + default: + pr_err("Unknown session event received (%d), session: %s\n", + ev, sess->sessname); + } +} + +static void rnbd_init_cpu_qlists(struct rnbd_cpu_qlist __percpu *cpu_queues) +{ + unsigned int cpu; + struct rnbd_cpu_qlist *cpu_q; + + for_each_possible_cpu(cpu) { + cpu_q = per_cpu_ptr(cpu_queues, cpu); + + cpu_q->cpu = cpu; + INIT_LIST_HEAD(&cpu_q->requeue_list); + spin_lock_init(&cpu_q->requeue_lock); + } +} + +static void destroy_mq_tags(struct rnbd_clt_session *sess) +{ + if (sess->tag_set.tags) + blk_mq_free_tag_set(&sess->tag_set); +} + +static inline void wake_up_rtrs_waiters(struct rnbd_clt_session *sess) +{ + sess->rtrs_ready = true; + wake_up_all(&sess->rtrs_waitq); +} + +static void close_rtrs(struct rnbd_clt_session *sess) +{ + might_sleep(); + + if (!IS_ERR_OR_NULL(sess->rtrs)) { + rtrs_clt_close(sess->rtrs); + sess->rtrs = NULL; + wake_up_rtrs_waiters(sess); + } +} + +static void free_sess(struct rnbd_clt_session *sess) +{ + WARN_ON(!list_empty(&sess->devs_list)); + + might_sleep(); + + close_rtrs(sess); + destroy_mq_tags(sess); + if (!list_empty(&sess->list)) { + mutex_lock(&sess_lock); + list_del(&sess->list); + mutex_unlock(&sess_lock); + } + free_percpu(sess->cpu_queues); + free_percpu(sess->cpu_rr); + mutex_destroy(&sess->lock); + kfree(sess); +} + +static struct rnbd_clt_session *alloc_sess(const char *sessname) +{ + struct rnbd_clt_session *sess; + int err, cpu; + + sess = kzalloc_node(sizeof(*sess), GFP_KERNEL, NUMA_NO_NODE); + if (!sess) + return ERR_PTR(-ENOMEM); + strlcpy(sess->sessname, sessname, sizeof(sess->sessname)); + atomic_set(&sess->busy, 0); + mutex_init(&sess->lock); + INIT_LIST_HEAD(&sess->devs_list); + INIT_LIST_HEAD(&sess->list); + bitmap_zero(sess->cpu_queues_bm, NR_CPUS); + init_waitqueue_head(&sess->rtrs_waitq); + refcount_set(&sess->refcount, 1); + + sess->cpu_queues = alloc_percpu(struct rnbd_cpu_qlist); + if (!sess->cpu_queues) { + err = -ENOMEM; + goto err; + } + rnbd_init_cpu_qlists(sess->cpu_queues); + + /* + * That is simple percpu variable which stores cpu indeces, which are + * incremented on each access. We need that for the sake of fairness + * to wake up queues in a round-robin manner. + */ + sess->cpu_rr = alloc_percpu(int); + if (!sess->cpu_rr) { + err = -ENOMEM; + goto err; + } + for_each_possible_cpu(cpu) + * per_cpu_ptr(sess->cpu_rr, cpu) = cpu; + + return sess; + +err: + free_sess(sess); + + return ERR_PTR(err); +} + +static int wait_for_rtrs_connection(struct rnbd_clt_session *sess) +{ + wait_event(sess->rtrs_waitq, sess->rtrs_ready); + if (IS_ERR_OR_NULL(sess->rtrs)) + return -ECONNRESET; + + return 0; +} + +static void wait_for_rtrs_disconnection(struct rnbd_clt_session *sess) + __releases(&sess_lock) + __acquires(&sess_lock) +{ + DEFINE_WAIT(wait); + + prepare_to_wait(&sess->rtrs_waitq, &wait, TASK_UNINTERRUPTIBLE); + if (IS_ERR_OR_NULL(sess->rtrs)) { + finish_wait(&sess->rtrs_waitq, &wait); + return; + } + mutex_unlock(&sess_lock); + /* loop in caller, see __find_and_get_sess(). + * You can't leave mutex locked and call schedule(), you will catch a + * deadlock with a caller of free_sess(), which has just put the last + * reference and is about to take the sess_lock in order to delete + * the session from the list. + */ + schedule(); + mutex_lock(&sess_lock); +} + +static struct rnbd_clt_session *__find_and_get_sess(const char *sessname) + __releases(&sess_lock) + __acquires(&sess_lock) +{ + struct rnbd_clt_session *sess, *sn; + int err; + +again: + list_for_each_entry_safe(sess, sn, &sess_list, list) { + if (strcmp(sessname, sess->sessname)) + continue; + + if (sess->rtrs_ready && IS_ERR_OR_NULL(sess->rtrs)) + /* + * No RTRS connection, session is dying. + */ + continue; + + if (rnbd_clt_get_sess(sess)) { + /* + * Alive session is found, wait for RTRS connection. + */ + mutex_unlock(&sess_lock); + err = wait_for_rtrs_connection(sess); + if (err) + rnbd_clt_put_sess(sess); + mutex_lock(&sess_lock); + + if (err) + /* Session is dying, repeat the loop */ + goto again; + + return sess; + } + /* + * Ref is 0, session is dying, wait for RTRS disconnect + * in order to avoid session names clashes. + */ + wait_for_rtrs_disconnection(sess); + /* + * RTRS is disconnected and soon session will be freed, + * so repeat a loop. + */ + goto again; + } + + return NULL; +} + +static struct +rnbd_clt_session *find_or_create_sess(const char *sessname, bool *first) +{ + struct rnbd_clt_session *sess = NULL; + + mutex_lock(&sess_lock); + sess = __find_and_get_sess(sessname); + if (!sess) { + sess = alloc_sess(sessname); + if (IS_ERR(sess)) { + mutex_unlock(&sess_lock); + return sess; + } + list_add(&sess->list, &sess_list); + *first = true; + } else + *first = false; + mutex_unlock(&sess_lock); + + return sess; +} + +static int rnbd_client_open(struct block_device *block_device, fmode_t mode) +{ + struct rnbd_clt_dev *dev = block_device->bd_disk->private_data; + + if (dev->read_only && (mode & FMODE_WRITE)) + return -EPERM; + + if (dev->dev_state == DEV_STATE_UNMAPPED || + !rnbd_clt_get_dev(dev)) + return -EIO; + + return 0; +} + +static void rnbd_client_release(struct gendisk *gen, fmode_t mode) +{ + struct rnbd_clt_dev *dev = gen->private_data; + + rnbd_clt_put_dev(dev); +} + +static int rnbd_client_getgeo(struct block_device *block_device, + struct hd_geometry *geo) +{ + u64 size; + struct rnbd_clt_dev *dev; + + dev = block_device->bd_disk->private_data; + size = dev->size * (dev->logical_block_size / SECTOR_SIZE); + geo->cylinders = size >> 6; /* size/64 */ + geo->heads = 4; + geo->sectors = 16; + geo->start = 0; + + return 0; +} + +static const struct block_device_operations rnbd_client_ops = { + .owner = THIS_MODULE, + .open = rnbd_client_open, + .release = rnbd_client_release, + .getgeo = rnbd_client_getgeo +}; + +/* The amount of data that belongs to an I/O and the amount of data that + * should be read or written to the disk (bi_size) can differ. + * + * E.g. When WRITE_SAME is used, only a small amount of data is + * transferred that is then written repeatedly over a lot of sectors. + * + * Get the size of data to be transferred via RTRS by summing up the size + * of the scather-gather list entries. + */ +static size_t rnbd_clt_get_sg_size(struct scatterlist *sglist, u32 len) +{ + struct scatterlist *sg; + size_t tsize = 0; + int i; + + for_each_sg(sglist, sg, len, i) + tsize += sg->length; + return tsize; +} + +static int rnbd_client_xfer_request(struct rnbd_clt_dev *dev, + struct request *rq, + struct rnbd_iu *iu) +{ + struct rtrs_clt *rtrs = dev->sess->rtrs; + struct rtrs_permit *permit = iu->permit; + struct rnbd_msg_io msg; + struct rtrs_clt_req_ops req_ops; + unsigned int sg_cnt = 0; + struct kvec vec; + size_t size; + int err; + + iu->rq = rq; + iu->dev = dev; + msg.sector = cpu_to_le64(blk_rq_pos(rq)); + msg.bi_size = cpu_to_le32(blk_rq_bytes(rq)); + msg.rw = cpu_to_le32(rq_to_rnbd_flags(rq)); + msg.prio = cpu_to_le16(req_get_ioprio(rq)); + + /* + * We only support discards with single segment for now. + * See queue limits. + */ + if (req_op(rq) != REQ_OP_DISCARD) + sg_cnt = blk_rq_map_sg(dev->queue, rq, iu->sglist); + + if (sg_cnt == 0) + /* Do not forget to mark the end */ + sg_mark_end(&iu->sglist[0]); + + msg.hdr.type = cpu_to_le16(RNBD_MSG_IO); + msg.device_id = cpu_to_le32(dev->device_id); + + vec = (struct kvec) { + .iov_base = &msg, + .iov_len = sizeof(msg) + }; + size = rnbd_clt_get_sg_size(iu->sglist, sg_cnt); + req_ops = (struct rtrs_clt_req_ops) { + .priv = iu, + .conf_fn = msg_io_conf, + }; + err = rtrs_clt_request(rq_data_dir(rq), &req_ops, rtrs, permit, + &vec, 1, size, iu->sglist, sg_cnt); + if (unlikely(err)) { + rnbd_clt_err_rl(dev, "RTRS failed to transfer IO, err: %d\n", + err); + return err; + } + + return 0; +} + +/** + * rnbd_clt_dev_add_to_requeue() - add device to requeue if session is busy + * @dev: Device to be checked + * @q: Queue to be added to the requeue list if required + * + * Description: + * If session is busy, that means someone will requeue us when resources + * are freed. If session is not doing anything - device is not added to + * the list and @false is returned. + */ +static bool rnbd_clt_dev_add_to_requeue(struct rnbd_clt_dev *dev, + struct rnbd_queue *q) +{ + struct rnbd_clt_session *sess = dev->sess; + struct rnbd_cpu_qlist *cpu_q; + unsigned long flags; + bool added = true; + bool need_set; + + cpu_q = get_cpu_ptr(sess->cpu_queues); + spin_lock_irqsave(&cpu_q->requeue_lock, flags); + + if (likely(!test_and_set_bit_lock(0, &q->in_list))) { + if (WARN_ON(!list_empty(&q->requeue_list))) + goto unlock; + + need_set = !test_bit(cpu_q->cpu, sess->cpu_queues_bm); + if (need_set) { + set_bit(cpu_q->cpu, sess->cpu_queues_bm); + /* Paired with rnbd_put_permit(). Set a bit first + * and then observe the busy counter. + */ + smp_mb__before_atomic(); + } + if (likely(atomic_read(&sess->busy))) { + list_add_tail(&q->requeue_list, &cpu_q->requeue_list); + } else { + /* Very unlikely, but possible: busy counter was + * observed as zero. Drop all bits and return + * false to restart the queue by ourselves. + */ + if (need_set) + clear_bit(cpu_q->cpu, sess->cpu_queues_bm); + clear_bit_unlock(0, &q->in_list); + added = false; + } + } +unlock: + spin_unlock_irqrestore(&cpu_q->requeue_lock, flags); + put_cpu_ptr(sess->cpu_queues); + + return added; +} + +static void rnbd_clt_dev_kick_mq_queue(struct rnbd_clt_dev *dev, + struct blk_mq_hw_ctx *hctx, + int delay) +{ + struct rnbd_queue *q = hctx->driver_data; + + if (delay != RNBD_DELAY_IFBUSY) + blk_mq_delay_run_hw_queue(hctx, delay); + else if (unlikely(!rnbd_clt_dev_add_to_requeue(dev, q))) + /* + * If session is not busy we have to restart + * the queue ourselves. + */ + blk_mq_delay_run_hw_queue(hctx, 10/*ms*/); +} + +static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + struct request *rq = bd->rq; + struct rnbd_clt_dev *dev = rq->rq_disk->private_data; + struct rnbd_iu *iu = blk_mq_rq_to_pdu(rq); + int err; + + if (unlikely(dev->dev_state != DEV_STATE_MAPPED)) + return BLK_STS_IOERR; + + iu->permit = rnbd_get_permit(dev->sess, RTRS_IO_CON, + RTRS_PERMIT_NOWAIT); + if (unlikely(!iu->permit)) { + rnbd_clt_dev_kick_mq_queue(dev, hctx, RNBD_DELAY_IFBUSY); + return BLK_STS_RESOURCE; + } + + blk_mq_start_request(rq); + err = rnbd_client_xfer_request(dev, rq, iu); + if (likely(err == 0)) + return BLK_STS_OK; + if (unlikely(err == -EAGAIN || err == -ENOMEM)) { + rnbd_clt_dev_kick_mq_queue(dev, hctx, 10/*ms*/); + rnbd_put_permit(dev->sess, iu->permit); + return BLK_STS_RESOURCE; + } + + rnbd_put_permit(dev->sess, iu->permit); + return BLK_STS_IOERR; +} + +static int rnbd_init_request(struct blk_mq_tag_set *set, struct request *rq, + unsigned int hctx_idx, unsigned int numa_node) +{ + struct rnbd_iu *iu = blk_mq_rq_to_pdu(rq); + + sg_init_table(iu->sglist, BMAX_SEGMENTS); + return 0; +} + +static struct blk_mq_ops rnbd_mq_ops = { + .queue_rq = rnbd_queue_rq, + .init_request = rnbd_init_request, + .complete = rnbd_softirq_done_fn, +}; + +static int setup_mq_tags(struct rnbd_clt_session *sess) +{ + struct blk_mq_tag_set *tag_set = &sess->tag_set; + + memset(tag_set, 0, sizeof(*tag_set)); + tag_set->ops = &rnbd_mq_ops; + tag_set->queue_depth = sess->queue_depth; + tag_set->numa_node = NUMA_NO_NODE; + tag_set->flags = BLK_MQ_F_SHOULD_MERGE | + BLK_MQ_F_TAG_QUEUE_SHARED; + tag_set->cmd_size = sizeof(struct rnbd_iu); + tag_set->nr_hw_queues = num_online_cpus(); + + return blk_mq_alloc_tag_set(tag_set); +} + +static struct rnbd_clt_session * +find_and_get_or_create_sess(const char *sessname, + const struct rtrs_addr *paths, + size_t path_cnt, u16 port_nr) +{ + struct rnbd_clt_session *sess; + struct rtrs_attrs attrs; + int err; + bool first; + struct rtrs_clt_ops rtrs_ops; + + sess = find_or_create_sess(sessname, &first); + if (sess == ERR_PTR(-ENOMEM)) + return ERR_PTR(-ENOMEM); + else if (!first) + return sess; + + rtrs_ops = (struct rtrs_clt_ops) { + .priv = sess, + .link_ev = rnbd_clt_link_ev, + }; + /* + * Nothing was found, establish rtrs connection and proceed further. + */ + sess->rtrs = rtrs_clt_open(&rtrs_ops, sessname, + paths, path_cnt, port_nr, + sizeof(struct rnbd_iu), + RECONNECT_DELAY, BMAX_SEGMENTS, + BLK_MAX_SEGMENT_SIZE, + MAX_RECONNECTS); + if (IS_ERR(sess->rtrs)) { + err = PTR_ERR(sess->rtrs); + goto wake_up_and_put; + } + + err = rtrs_clt_query(sess->rtrs, &attrs); + if (err) + goto close_rtrs; + + sess->max_io_size = attrs.max_io_size; + sess->queue_depth = attrs.queue_depth; + + err = setup_mq_tags(sess); + if (err) + goto close_rtrs; + + err = send_msg_sess_info(sess, WAIT); + if (err) + goto close_rtrs; + + wake_up_rtrs_waiters(sess); + + return sess; + +close_rtrs: + close_rtrs(sess); +put_sess: + rnbd_clt_put_sess(sess); + + return ERR_PTR(err); + +wake_up_and_put: + wake_up_rtrs_waiters(sess); + goto put_sess; +} + +static inline void rnbd_init_hw_queue(struct rnbd_clt_dev *dev, + struct rnbd_queue *q, + struct blk_mq_hw_ctx *hctx) +{ + INIT_LIST_HEAD(&q->requeue_list); + q->dev = dev; + q->hctx = hctx; +} + +static void rnbd_init_mq_hw_queues(struct rnbd_clt_dev *dev) +{ + int i; + struct blk_mq_hw_ctx *hctx; + struct rnbd_queue *q; + + queue_for_each_hw_ctx(dev->queue, hctx, i) { + q = &dev->hw_queues[i]; + rnbd_init_hw_queue(dev, q, hctx); + hctx->driver_data = q; + } +} + +static int setup_mq_dev(struct rnbd_clt_dev *dev) +{ + dev->queue = blk_mq_init_queue(&dev->sess->tag_set); + if (IS_ERR(dev->queue)) { + rnbd_clt_err(dev, "Initializing multiqueue queue failed, err: %ld\n", + PTR_ERR(dev->queue)); + return PTR_ERR(dev->queue); + } + rnbd_init_mq_hw_queues(dev); + return 0; +} + +static void setup_request_queue(struct rnbd_clt_dev *dev) +{ + blk_queue_logical_block_size(dev->queue, dev->logical_block_size); + blk_queue_physical_block_size(dev->queue, dev->physical_block_size); + blk_queue_max_hw_sectors(dev->queue, dev->max_hw_sectors); + blk_queue_max_write_same_sectors(dev->queue, + dev->max_write_same_sectors); + + /* + * we don't support discards to "discontiguous" segments + * in on request + */ + blk_queue_max_discard_segments(dev->queue, 1); + + blk_queue_max_discard_sectors(dev->queue, dev->max_discard_sectors); + dev->queue->limits.discard_granularity = dev->discard_granularity; + dev->queue->limits.discard_alignment = dev->discard_alignment; + if (dev->max_discard_sectors) + blk_queue_flag_set(QUEUE_FLAG_DISCARD, dev->queue); + if (dev->secure_discard) + blk_queue_flag_set(QUEUE_FLAG_SECERASE, dev->queue); + + blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue); + blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue); + blk_queue_max_segments(dev->queue, dev->max_segments); + blk_queue_io_opt(dev->queue, dev->sess->max_io_size); + blk_queue_virt_boundary(dev->queue, SZ_4K - 1); + blk_queue_write_cache(dev->queue, true, true); + dev->queue->queuedata = dev; +} + +static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) +{ + dev->gd->major = rnbd_client_major; + dev->gd->first_minor = idx << RNBD_PART_BITS; + dev->gd->fops = &rnbd_client_ops; + dev->gd->queue = dev->queue; + dev->gd->private_data = dev; + snprintf(dev->gd->disk_name, sizeof(dev->gd->disk_name), "rnbd%d", + idx); + pr_debug("disk_name=%s, capacity=%zu\n", + dev->gd->disk_name, + dev->nsectors * (dev->logical_block_size / SECTOR_SIZE) + ); + + set_capacity(dev->gd, dev->nsectors); + + if (dev->access_mode == RNBD_ACCESS_RO) { + dev->read_only = true; + set_disk_ro(dev->gd, true); + } else { + dev->read_only = false; + } + + if (!dev->rotational) + blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue); +} + +static int rnbd_client_setup_device(struct rnbd_clt_session *sess, + struct rnbd_clt_dev *dev, int idx) +{ + int err; + + dev->size = dev->nsectors * dev->logical_block_size; + + err = setup_mq_dev(dev); + if (err) + return err; + + setup_request_queue(dev); + + dev->gd = alloc_disk_node(1 << RNBD_PART_BITS, NUMA_NO_NODE); + if (!dev->gd) { + blk_cleanup_queue(dev->queue); + return -ENOMEM; + } + + rnbd_clt_setup_gen_disk(dev, idx); + + return 0; +} + +static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, + enum rnbd_access_mode access_mode, + const char *pathname) +{ + struct rnbd_clt_dev *dev; + int ret; + + dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, NUMA_NO_NODE); + if (!dev) + return ERR_PTR(-ENOMEM); + + dev->hw_queues = kcalloc(nr_cpu_ids, sizeof(*dev->hw_queues), + GFP_KERNEL); + if (!dev->hw_queues) { + ret = -ENOMEM; + goto out_alloc; + } + + mutex_lock(&ida_lock); + ret = ida_simple_get(&index_ida, 0, 1 << (MINORBITS - RNBD_PART_BITS), + GFP_KERNEL); + mutex_unlock(&ida_lock); + if (ret < 0) { + pr_err("Failed to initialize device '%s' from session %s, allocating idr failed, err: %d\n", + pathname, sess->sessname, ret); + goto out_queues; + } + + dev->pathname = kstrdup(pathname, GFP_KERNEL); + if (!dev->pathname) { + ret = -ENOMEM; + goto out_queues; + } + + dev->clt_device_id = ret; + dev->sess = sess; + dev->access_mode = access_mode; + mutex_init(&dev->lock); + refcount_set(&dev->refcount, 1); + dev->dev_state = DEV_STATE_INIT; + + /* + * Here we called from sysfs entry, thus clt-sysfs is + * responsible that session will not disappear. + */ + WARN_ON(!rnbd_clt_get_sess(sess)); + + return dev; + +out_queues: + kfree(dev->hw_queues); +out_alloc: + kfree(dev); + return ERR_PTR(ret); +} + +static bool __exists_dev(const char *pathname) +{ + struct rnbd_clt_session *sess; + struct rnbd_clt_dev *dev; + bool found = false; + + list_for_each_entry(sess, &sess_list, list) { + mutex_lock(&sess->lock); + list_for_each_entry(dev, &sess->devs_list, list) { + if (strlen(dev->pathname) == strlen(pathname) && + !strcmp(dev->pathname, pathname)) { + found = true; + break; + } + } + mutex_unlock(&sess->lock); + if (found) + break; + } + + return found; +} + +static bool exists_devpath(const char *pathname) +{ + bool found; + + mutex_lock(&sess_lock); + found = __exists_dev(pathname); + mutex_unlock(&sess_lock); + + return found; +} + +static bool insert_dev_if_not_exists_devpath(const char *pathname, + struct rnbd_clt_session *sess, + struct rnbd_clt_dev *dev) +{ + bool found; + + mutex_lock(&sess_lock); + found = __exists_dev(pathname); + if (!found) { + mutex_lock(&sess->lock); + list_add_tail(&dev->list, &sess->devs_list); + mutex_unlock(&sess->lock); + } + mutex_unlock(&sess_lock); + + return found; +} + +static void delete_dev(struct rnbd_clt_dev *dev) +{ + struct rnbd_clt_session *sess = dev->sess; + + mutex_lock(&sess->lock); + list_del(&dev->list); + mutex_unlock(&sess->lock); +} + +struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, + struct rtrs_addr *paths, + size_t path_cnt, u16 port_nr, + const char *pathname, + enum rnbd_access_mode access_mode) +{ + struct rnbd_clt_session *sess; + struct rnbd_clt_dev *dev; + int ret; + + if (exists_devpath(pathname)) + return ERR_PTR(-EEXIST); + + sess = find_and_get_or_create_sess(sessname, paths, path_cnt, port_nr); + if (IS_ERR(sess)) + return ERR_CAST(sess); + + dev = init_dev(sess, access_mode, pathname); + if (IS_ERR(dev)) { + pr_err("map_device: failed to map device '%s' from session %s, can't initialize device, err: %ld\n", + pathname, sess->sessname, PTR_ERR(dev)); + ret = PTR_ERR(dev); + goto put_sess; + } + if (insert_dev_if_not_exists_devpath(pathname, sess, dev)) { + ret = -EEXIST; + goto put_dev; + } + ret = send_msg_open(dev, WAIT); + if (ret) { + rnbd_clt_err(dev, + "map_device: failed, can't open remote device, err: %d\n", + ret); + goto del_dev; + } + mutex_lock(&dev->lock); + pr_debug("Opened remote device: session=%s, path='%s'\n", + sess->sessname, pathname); + ret = rnbd_client_setup_device(sess, dev, dev->clt_device_id); + if (ret) { + rnbd_clt_err(dev, + "map_device: Failed to configure device, err: %d\n", + ret); + mutex_unlock(&dev->lock); + goto send_close; + } + + rnbd_clt_info(dev, + "map_device: Device mapped as %s (nsectors: %zu, logical_block_size: %d, physical_block_size: %d, max_write_same_sectors: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, rotational: %d)\n", + dev->gd->disk_name, dev->nsectors, + dev->logical_block_size, dev->physical_block_size, + dev->max_write_same_sectors, dev->max_discard_sectors, + dev->discard_granularity, dev->discard_alignment, + dev->secure_discard, dev->max_segments, + dev->max_hw_sectors, dev->rotational); + + mutex_unlock(&dev->lock); + + add_disk(dev->gd); + rnbd_clt_put_sess(sess); + + return dev; + +send_close: + send_msg_close(dev, dev->device_id, WAIT); +del_dev: + delete_dev(dev); +put_dev: + rnbd_clt_put_dev(dev); +put_sess: + rnbd_clt_put_sess(sess); + + return ERR_PTR(ret); +} + +static void destroy_gen_disk(struct rnbd_clt_dev *dev) +{ + del_gendisk(dev->gd); + blk_cleanup_queue(dev->queue); + put_disk(dev->gd); +} + +static void destroy_sysfs(struct rnbd_clt_dev *dev, + const struct attribute *sysfs_self) +{ + rnbd_clt_remove_dev_symlink(dev); + if (dev->kobj.state_initialized) { + if (sysfs_self) + /* To avoid deadlock firstly remove itself */ + sysfs_remove_file_self(&dev->kobj, sysfs_self); + kobject_del(&dev->kobj); + kobject_put(&dev->kobj); + } +} + +int rnbd_clt_unmap_device(struct rnbd_clt_dev *dev, bool force, + const struct attribute *sysfs_self) +{ + struct rnbd_clt_session *sess = dev->sess; + int refcount, ret = 0; + bool was_mapped; + + mutex_lock(&dev->lock); + if (dev->dev_state == DEV_STATE_UNMAPPED) { + rnbd_clt_info(dev, "Device is already being unmapped\n"); + ret = -EALREADY; + goto err; + } + refcount = refcount_read(&dev->refcount); + if (!force && refcount > 1) { + rnbd_clt_err(dev, + "Closing device failed, device is in use, (%d device users)\n", + refcount - 1); + ret = -EBUSY; + goto err; + } + was_mapped = (dev->dev_state == DEV_STATE_MAPPED); + dev->dev_state = DEV_STATE_UNMAPPED; + mutex_unlock(&dev->lock); + + delete_dev(dev); + destroy_sysfs(dev, sysfs_self); + destroy_gen_disk(dev); + if (was_mapped && sess->rtrs) + send_msg_close(dev, dev->device_id, WAIT); + + rnbd_clt_info(dev, "Device is unmapped\n"); + + /* Likely last reference put */ + rnbd_clt_put_dev(dev); + + /* + * Here device and session can be vanished! + */ + + return 0; +err: + mutex_unlock(&dev->lock); + + return ret; +} + +int rnbd_clt_remap_device(struct rnbd_clt_dev *dev) +{ + int err; + + mutex_lock(&dev->lock); + if (dev->dev_state == DEV_STATE_MAPPED_DISCONNECTED) + err = 0; + else if (dev->dev_state == DEV_STATE_UNMAPPED) + err = -ENODEV; + else if (dev->dev_state == DEV_STATE_MAPPED) + err = -EALREADY; + else + err = -EBUSY; + mutex_unlock(&dev->lock); + if (!err) { + rnbd_clt_info(dev, "Remapping device.\n"); + err = send_msg_open(dev, WAIT); + if (err) + rnbd_clt_err(dev, "remap_device: %d\n", err); + } + + return err; +} + +static void unmap_device_work(struct work_struct *work) +{ + struct rnbd_clt_dev *dev; + + dev = container_of(work, typeof(*dev), unmap_on_rmmod_work); + rnbd_clt_unmap_device(dev, true, NULL); +} + +static void rnbd_destroy_sessions(void) +{ + struct rnbd_clt_session *sess, *sn; + struct rnbd_clt_dev *dev, *tn; + + /* Firstly forbid access through sysfs interface */ + rnbd_clt_destroy_default_group(); + rnbd_clt_destroy_sysfs_files(); + + /* + * Here at this point there is no any concurrent access to sessions + * list and devices list: + * 1. New session or device can'be be created - session sysfs files + * are removed. + * 2. Device or session can't be removed - module reference is taken + * into account in unmap device sysfs callback. + * 3. No IO requests inflight - each file open of block_dev increases + * module reference in get_disk(). + * + * But still there can be user requests inflights, which are sent by + * asynchronous send_msg_*() functions, thus before unmapping devices + * RTRS session must be explicitly closed. + */ + + list_for_each_entry_safe(sess, sn, &sess_list, list) { + if (!rnbd_clt_get_sess(sess)) + continue; + close_rtrs(sess); + list_for_each_entry_safe(dev, tn, &sess->devs_list, list) { + /* + * Here unmap happens in parallel for only one reason: + * blk_cleanup_queue() takes around half a second, so + * on huge amount of devices the whole module unload + * procedure takes minutes. + */ + INIT_WORK(&dev->unmap_on_rmmod_work, unmap_device_work); + queue_work(system_long_wq, &dev->unmap_on_rmmod_work); + } + rnbd_clt_put_sess(sess); + } + /* Wait for all scheduled unmap works */ + flush_workqueue(system_long_wq); + WARN_ON(!list_empty(&sess_list)); +} + +static int __init rnbd_client_init(void) +{ + int err = 0; + + BUILD_BUG_ON(sizeof(struct rnbd_msg_hdr) != 4); + BUILD_BUG_ON(sizeof(struct rnbd_msg_sess_info) != 36); + BUILD_BUG_ON(sizeof(struct rnbd_msg_sess_info_rsp) != 36); + BUILD_BUG_ON(sizeof(struct rnbd_msg_open) != 264); + BUILD_BUG_ON(sizeof(struct rnbd_msg_close) != 8); + BUILD_BUG_ON(sizeof(struct rnbd_msg_open_rsp) != 56); + rnbd_client_major = register_blkdev(rnbd_client_major, "rnbd"); + if (rnbd_client_major <= 0) { + pr_err("Failed to load module, block device registration failed\n"); + return -EBUSY; + } + + err = rnbd_clt_create_sysfs_files(); + if (err) { + pr_err("Failed to load module, creating sysfs device files failed, err: %d\n", + err); + unregister_blkdev(rnbd_client_major, "rnbd"); + } + + return err; +} + +static void __exit rnbd_client_exit(void) +{ + rnbd_destroy_sessions(); + unregister_blkdev(rnbd_client_major, "rnbd"); + ida_destroy(&index_ida); +} + +module_init(rnbd_client_init); +module_exit(rnbd_client_exit); diff --git a/drivers/block/rnbd/rnbd-clt.h b/drivers/block/rnbd/rnbd-clt.h new file mode 100644 index 000000000..2941e3862 --- /dev/null +++ b/drivers/block/rnbd/rnbd-clt.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ + +#ifndef RNBD_CLT_H +#define RNBD_CLT_H + +#include <linux/wait.h> +#include <linux/in.h> +#include <linux/inet.h> +#include <linux/blk-mq.h> +#include <linux/refcount.h> + +#include <rtrs.h> +#include "rnbd-proto.h" +#include "rnbd-log.h" + +/* Max. number of segments per IO request, Mellanox Connect X ~ Connect X5, + * choose minimial 30 for all, minus 1 for internal protocol, so 29. + */ +#define BMAX_SEGMENTS 29 +/* time in seconds between reconnect tries, default to 30 s */ +#define RECONNECT_DELAY 30 +/* + * Number of times to reconnect on error before giving up, 0 for * disabled, + * -1 for forever + */ +#define MAX_RECONNECTS -1 + +enum rnbd_clt_dev_state { + DEV_STATE_INIT, + DEV_STATE_MAPPED, + DEV_STATE_MAPPED_DISCONNECTED, + DEV_STATE_UNMAPPED, +}; + +struct rnbd_iu_comp { + wait_queue_head_t wait; + int errno; +}; + +struct rnbd_iu { + union { + struct request *rq; /* for block io */ + void *buf; /* for user messages */ + }; + struct rtrs_permit *permit; + union { + /* use to send msg associated with a dev */ + struct rnbd_clt_dev *dev; + /* use to send msg associated with a sess */ + struct rnbd_clt_session *sess; + }; + struct scatterlist sglist[BMAX_SEGMENTS]; + struct work_struct work; + int errno; + struct rnbd_iu_comp comp; + atomic_t refcount; +}; + +struct rnbd_cpu_qlist { + struct list_head requeue_list; + spinlock_t requeue_lock; + unsigned int cpu; +}; + +struct rnbd_clt_session { + struct list_head list; + struct rtrs_clt *rtrs; + wait_queue_head_t rtrs_waitq; + bool rtrs_ready; + struct rnbd_cpu_qlist __percpu + *cpu_queues; + DECLARE_BITMAP(cpu_queues_bm, NR_CPUS); + int __percpu *cpu_rr; /* per-cpu var for CPU round-robin */ + atomic_t busy; + size_t queue_depth; + u32 max_io_size; + struct blk_mq_tag_set tag_set; + struct mutex lock; /* protects state and devs_list */ + struct list_head devs_list; /* list of struct rnbd_clt_dev */ + refcount_t refcount; + char sessname[NAME_MAX]; + u8 ver; /* protocol version */ +}; + +/** + * Submission queues. + */ +struct rnbd_queue { + struct list_head requeue_list; + unsigned long in_list; + struct rnbd_clt_dev *dev; + struct blk_mq_hw_ctx *hctx; +}; + +struct rnbd_clt_dev { + struct rnbd_clt_session *sess; + struct request_queue *queue; + struct rnbd_queue *hw_queues; + u32 device_id; + /* local Idr index - used to track minor number allocations. */ + u32 clt_device_id; + struct mutex lock; + enum rnbd_clt_dev_state dev_state; + char *pathname; + enum rnbd_access_mode access_mode; + bool read_only; + bool rotational; + u32 max_hw_sectors; + u32 max_write_same_sectors; + u32 max_discard_sectors; + u32 discard_granularity; + u32 discard_alignment; + u16 secure_discard; + u16 physical_block_size; + u16 logical_block_size; + u16 max_segments; + size_t nsectors; + u64 size; /* device size in bytes */ + struct list_head list; + struct gendisk *gd; + struct kobject kobj; + char *blk_symlink_name; + refcount_t refcount; + struct work_struct unmap_on_rmmod_work; +}; + +/* rnbd-clt.c */ + +struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, + struct rtrs_addr *paths, + size_t path_cnt, u16 port_nr, + const char *pathname, + enum rnbd_access_mode access_mode); +int rnbd_clt_unmap_device(struct rnbd_clt_dev *dev, bool force, + const struct attribute *sysfs_self); + +int rnbd_clt_remap_device(struct rnbd_clt_dev *dev); +int rnbd_clt_resize_disk(struct rnbd_clt_dev *dev, size_t newsize); + +/* rnbd-clt-sysfs.c */ + +int rnbd_clt_create_sysfs_files(void); + +void rnbd_clt_destroy_sysfs_files(void); +void rnbd_clt_destroy_default_group(void); + +void rnbd_clt_remove_dev_symlink(struct rnbd_clt_dev *dev); + +#endif /* RNBD_CLT_H */ diff --git a/drivers/block/rnbd/rnbd-common.c b/drivers/block/rnbd/rnbd-common.c new file mode 100644 index 000000000..596c3f732 --- /dev/null +++ b/drivers/block/rnbd/rnbd-common.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ +#include "rnbd-proto.h" + +const char *rnbd_access_mode_str(enum rnbd_access_mode mode) +{ + switch (mode) { + case RNBD_ACCESS_RO: + return "ro"; + case RNBD_ACCESS_RW: + return "rw"; + case RNBD_ACCESS_MIGRATION: + return "migration"; + default: + return "unknown"; + } +} diff --git a/drivers/block/rnbd/rnbd-log.h b/drivers/block/rnbd/rnbd-log.h new file mode 100644 index 000000000..136e7d6c3 --- /dev/null +++ b/drivers/block/rnbd/rnbd-log.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ +#ifndef RNBD_LOG_H +#define RNBD_LOG_H + +#include "rnbd-clt.h" +#include "rnbd-srv.h" + +#define rnbd_clt_log(fn, dev, fmt, ...) ( \ + fn("<%s@%s> " fmt, (dev)->pathname, \ + (dev)->sess->sessname, \ + ##__VA_ARGS__)) +#define rnbd_srv_log(fn, dev, fmt, ...) ( \ + fn("<%s@%s>: " fmt, (dev)->pathname, \ + (dev)->sess->sessname, ##__VA_ARGS__)) + +#define rnbd_clt_err(dev, fmt, ...) \ + rnbd_clt_log(pr_err, dev, fmt, ##__VA_ARGS__) +#define rnbd_clt_err_rl(dev, fmt, ...) \ + rnbd_clt_log(pr_err_ratelimited, dev, fmt, ##__VA_ARGS__) +#define rnbd_clt_info(dev, fmt, ...) \ + rnbd_clt_log(pr_info, dev, fmt, ##__VA_ARGS__) +#define rnbd_clt_info_rl(dev, fmt, ...) \ + rnbd_clt_log(pr_info_ratelimited, dev, fmt, ##__VA_ARGS__) + +#define rnbd_srv_err(dev, fmt, ...) \ + rnbd_srv_log(pr_err, dev, fmt, ##__VA_ARGS__) +#define rnbd_srv_err_rl(dev, fmt, ...) \ + rnbd_srv_log(pr_err_ratelimited, dev, fmt, ##__VA_ARGS__) +#define rnbd_srv_info(dev, fmt, ...) \ + rnbd_srv_log(pr_info, dev, fmt, ##__VA_ARGS__) +#define rnbd_srv_info_rl(dev, fmt, ...) \ + rnbd_srv_log(pr_info_ratelimited, dev, fmt, ##__VA_ARGS__) + +#endif /* RNBD_LOG_H */ diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h new file mode 100644 index 000000000..cb1185545 --- /dev/null +++ b/drivers/block/rnbd/rnbd-proto.h @@ -0,0 +1,303 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ +#ifndef RNBD_PROTO_H +#define RNBD_PROTO_H + +#include <linux/types.h> +#include <linux/blkdev.h> +#include <linux/limits.h> +#include <linux/inet.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <rdma/ib.h> + +#define RNBD_PROTO_VER_MAJOR 2 +#define RNBD_PROTO_VER_MINOR 0 + +/* The default port number the RTRS server is listening on. */ +#define RTRS_PORT 1234 + +/** + * enum rnbd_msg_types - RNBD message types + * @RNBD_MSG_SESS_INFO: initial session info from client to server + * @RNBD_MSG_SESS_INFO_RSP: initial session info from server to client + * @RNBD_MSG_OPEN: open (map) device request + * @RNBD_MSG_OPEN_RSP: response to an @RNBD_MSG_OPEN + * @RNBD_MSG_IO: block IO request operation + * @RNBD_MSG_CLOSE: close (unmap) device request + */ +enum rnbd_msg_type { + RNBD_MSG_SESS_INFO, + RNBD_MSG_SESS_INFO_RSP, + RNBD_MSG_OPEN, + RNBD_MSG_OPEN_RSP, + RNBD_MSG_IO, + RNBD_MSG_CLOSE, +}; + +/** + * struct rnbd_msg_hdr - header of RNBD messages + * @type: Message type, valid values see: enum rnbd_msg_types + */ +struct rnbd_msg_hdr { + __le16 type; + __le16 __padding; +}; + +/** + * We allow to map RO many times and RW only once. We allow to map yet another + * time RW, if MIGRATION is provided (second RW export can be required for + * example for VM migration) + */ +enum rnbd_access_mode { + RNBD_ACCESS_RO, + RNBD_ACCESS_RW, + RNBD_ACCESS_MIGRATION, +}; + +/** + * struct rnbd_msg_sess_info - initial session info from client to server + * @hdr: message header + * @ver: RNBD protocol version + */ +struct rnbd_msg_sess_info { + struct rnbd_msg_hdr hdr; + u8 ver; + u8 reserved[31]; +}; + +/** + * struct rnbd_msg_sess_info_rsp - initial session info from server to client + * @hdr: message header + * @ver: RNBD protocol version + */ +struct rnbd_msg_sess_info_rsp { + struct rnbd_msg_hdr hdr; + u8 ver; + u8 reserved[31]; +}; + +/** + * struct rnbd_msg_open - request to open a remote device. + * @hdr: message header + * @access_mode: the mode to open remote device, valid values see: + * enum rnbd_access_mode + * @device_name: device path on remote side + */ +struct rnbd_msg_open { + struct rnbd_msg_hdr hdr; + u8 access_mode; + u8 resv1; + s8 dev_name[NAME_MAX]; + u8 reserved[3]; +}; + +/** + * struct rnbd_msg_close - request to close a remote device. + * @hdr: message header + * @device_id: device_id on server side to identify the device + */ +struct rnbd_msg_close { + struct rnbd_msg_hdr hdr; + __le32 device_id; +}; + +/** + * struct rnbd_msg_open_rsp - response message to RNBD_MSG_OPEN + * @hdr: message header + * @device_id: device_id on server side to identify the device + * @nsectors: number of sectors in the usual 512b unit + * @max_hw_sectors: max hardware sectors in the usual 512b unit + * @max_write_same_sectors: max sectors for WRITE SAME in the 512b unit + * @max_discard_sectors: max. sectors that can be discarded at once in 512b + * unit. + * @discard_granularity: size of the internal discard allocation unit in bytes + * @discard_alignment: offset from internal allocation assignment in bytes + * @physical_block_size: physical block size device supports in bytes + * @logical_block_size: logical block size device supports in bytes + * @max_segments: max segments hardware support in one transfer + * @secure_discard: supports secure discard + * @rotation: is a rotational disc? + */ +struct rnbd_msg_open_rsp { + struct rnbd_msg_hdr hdr; + __le32 device_id; + __le64 nsectors; + __le32 max_hw_sectors; + __le32 max_write_same_sectors; + __le32 max_discard_sectors; + __le32 discard_granularity; + __le32 discard_alignment; + __le16 physical_block_size; + __le16 logical_block_size; + __le16 max_segments; + __le16 secure_discard; + u8 rotational; + u8 reserved[11]; +}; + +/** + * struct rnbd_msg_io - message for I/O read/write + * @hdr: message header + * @device_id: device_id on server side to find the right device + * @sector: bi_sector attribute from struct bio + * @rw: valid values are defined in enum rnbd_io_flags + * @bi_size: number of bytes for I/O read/write + * @prio: priority + */ +struct rnbd_msg_io { + struct rnbd_msg_hdr hdr; + __le32 device_id; + __le64 sector; + __le32 rw; + __le32 bi_size; + __le16 prio; +}; + +#define RNBD_OP_BITS 8 +#define RNBD_OP_MASK ((1 << RNBD_OP_BITS) - 1) + +/** + * enum rnbd_io_flags - RNBD request types from rq_flag_bits + * @RNBD_OP_READ: read sectors from the device + * @RNBD_OP_WRITE: write sectors to the device + * @RNBD_OP_FLUSH: flush the volatile write cache + * @RNBD_OP_DISCARD: discard sectors + * @RNBD_OP_SECURE_ERASE: securely erase sectors + * @RNBD_OP_WRITE_SAME: write the same sectors many times + + * @RNBD_F_SYNC: request is sync (sync write or read) + * @RNBD_F_FUA: forced unit access + */ +enum rnbd_io_flags { + + /* Operations */ + + RNBD_OP_READ = 0, + RNBD_OP_WRITE = 1, + RNBD_OP_FLUSH = 2, + RNBD_OP_DISCARD = 3, + RNBD_OP_SECURE_ERASE = 4, + RNBD_OP_WRITE_SAME = 5, + + RNBD_OP_LAST, + + /* Flags */ + + RNBD_F_SYNC = 1<<(RNBD_OP_BITS + 0), + RNBD_F_FUA = 1<<(RNBD_OP_BITS + 1), + + RNBD_F_ALL = (RNBD_F_SYNC | RNBD_F_FUA) + +}; + +static inline u32 rnbd_op(u32 flags) +{ + return flags & RNBD_OP_MASK; +} + +static inline u32 rnbd_flags(u32 flags) +{ + return flags & ~RNBD_OP_MASK; +} + +static inline bool rnbd_flags_supported(u32 flags) +{ + u32 op; + + op = rnbd_op(flags); + flags = rnbd_flags(flags); + + if (op >= RNBD_OP_LAST) + return false; + if (flags & ~RNBD_F_ALL) + return false; + + return true; +} + +static inline u32 rnbd_to_bio_flags(u32 rnbd_opf) +{ + u32 bio_opf; + + switch (rnbd_op(rnbd_opf)) { + case RNBD_OP_READ: + bio_opf = REQ_OP_READ; + break; + case RNBD_OP_WRITE: + bio_opf = REQ_OP_WRITE; + break; + case RNBD_OP_FLUSH: + bio_opf = REQ_OP_WRITE | REQ_PREFLUSH; + break; + case RNBD_OP_DISCARD: + bio_opf = REQ_OP_DISCARD; + break; + case RNBD_OP_SECURE_ERASE: + bio_opf = REQ_OP_SECURE_ERASE; + break; + case RNBD_OP_WRITE_SAME: + bio_opf = REQ_OP_WRITE_SAME; + break; + default: + WARN(1, "Unknown RNBD type: %d (flags %d)\n", + rnbd_op(rnbd_opf), rnbd_opf); + bio_opf = 0; + } + + if (rnbd_opf & RNBD_F_SYNC) + bio_opf |= REQ_SYNC; + + if (rnbd_opf & RNBD_F_FUA) + bio_opf |= REQ_FUA; + + return bio_opf; +} + +static inline u32 rq_to_rnbd_flags(struct request *rq) +{ + u32 rnbd_opf; + + switch (req_op(rq)) { + case REQ_OP_READ: + rnbd_opf = RNBD_OP_READ; + break; + case REQ_OP_WRITE: + rnbd_opf = RNBD_OP_WRITE; + break; + case REQ_OP_DISCARD: + rnbd_opf = RNBD_OP_DISCARD; + break; + case REQ_OP_SECURE_ERASE: + rnbd_opf = RNBD_OP_SECURE_ERASE; + break; + case REQ_OP_WRITE_SAME: + rnbd_opf = RNBD_OP_WRITE_SAME; + break; + case REQ_OP_FLUSH: + rnbd_opf = RNBD_OP_FLUSH; + break; + default: + WARN(1, "Unknown request type %d (flags %llu)\n", + req_op(rq), (unsigned long long)rq->cmd_flags); + rnbd_opf = 0; + } + + if (op_is_sync(rq->cmd_flags)) + rnbd_opf |= RNBD_F_SYNC; + + if (op_is_flush(rq->cmd_flags)) + rnbd_opf |= RNBD_F_FUA; + + return rnbd_opf; +} + +const char *rnbd_access_mode_str(enum rnbd_access_mode mode); + +#endif /* RNBD_PROTO_H */ diff --git a/drivers/block/rnbd/rnbd-srv-dev.c b/drivers/block/rnbd/rnbd-srv-dev.c new file mode 100644 index 000000000..b241a099a --- /dev/null +++ b/drivers/block/rnbd/rnbd-srv-dev.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ +#undef pr_fmt +#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt + +#include "rnbd-srv-dev.h" +#include "rnbd-log.h" + +struct rnbd_dev *rnbd_dev_open(const char *path, fmode_t flags, + struct bio_set *bs) +{ + struct rnbd_dev *dev; + int ret; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return ERR_PTR(-ENOMEM); + + dev->blk_open_flags = flags; + dev->bdev = blkdev_get_by_path(path, flags, THIS_MODULE); + ret = PTR_ERR_OR_ZERO(dev->bdev); + if (ret) + goto err; + + dev->blk_open_flags = flags; + bdevname(dev->bdev, dev->name); + dev->ibd_bio_set = bs; + + return dev; + +err: + kfree(dev); + return ERR_PTR(ret); +} + +void rnbd_dev_close(struct rnbd_dev *dev) +{ + blkdev_put(dev->bdev, dev->blk_open_flags); + kfree(dev); +} + +void rnbd_dev_bi_end_io(struct bio *bio) +{ + struct rnbd_dev_blk_io *io = bio->bi_private; + + rnbd_endio(io->priv, blk_status_to_errno(bio->bi_status)); + bio_put(bio); +} + +/** + * rnbd_bio_map_kern - map kernel address into bio + * @data: pointer to buffer to map + * @bs: bio_set to use. + * @len: length in bytes + * @gfp_mask: allocation flags for bio allocation + * + * Map the kernel address into a bio suitable for io to a block + * device. Returns an error pointer in case of error. + */ +struct bio *rnbd_bio_map_kern(void *data, struct bio_set *bs, + unsigned int len, gfp_t gfp_mask) +{ + unsigned long kaddr = (unsigned long)data; + unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; + unsigned long start = kaddr >> PAGE_SHIFT; + const int nr_pages = end - start; + int offset, i; + struct bio *bio; + + bio = bio_alloc_bioset(gfp_mask, nr_pages, bs); + if (!bio) + return ERR_PTR(-ENOMEM); + + offset = offset_in_page(kaddr); + for (i = 0; i < nr_pages; i++) { + unsigned int bytes = PAGE_SIZE - offset; + + if (len <= 0) + break; + + if (bytes > len) + bytes = len; + + if (bio_add_page(bio, virt_to_page(data), bytes, + offset) < bytes) { + /* we don't support partial mappings */ + bio_put(bio); + return ERR_PTR(-EINVAL); + } + + data += bytes; + len -= bytes; + offset = 0; + } + + return bio; +} diff --git a/drivers/block/rnbd/rnbd-srv-dev.h b/drivers/block/rnbd/rnbd-srv-dev.h new file mode 100644 index 000000000..0eb23850a --- /dev/null +++ b/drivers/block/rnbd/rnbd-srv-dev.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ +#ifndef RNBD_SRV_DEV_H +#define RNBD_SRV_DEV_H + +#include <linux/fs.h> +#include "rnbd-proto.h" + +struct rnbd_dev { + struct block_device *bdev; + struct bio_set *ibd_bio_set; + fmode_t blk_open_flags; + char name[BDEVNAME_SIZE]; +}; + +struct rnbd_dev_blk_io { + struct rnbd_dev *dev; + void *priv; + /* have to be last member for front_pad usage of bioset_init */ + struct bio bio; +}; + +/** + * rnbd_dev_open() - Open a device + * @flags: open flags + * @bs: bio_set to use during block io, + */ +struct rnbd_dev *rnbd_dev_open(const char *path, fmode_t flags, + struct bio_set *bs); + +/** + * rnbd_dev_close() - Close a device + */ +void rnbd_dev_close(struct rnbd_dev *dev); + +void rnbd_endio(void *priv, int error); + +void rnbd_dev_bi_end_io(struct bio *bio); + +struct bio *rnbd_bio_map_kern(void *data, struct bio_set *bs, + unsigned int len, gfp_t gfp_mask); + +static inline int rnbd_dev_get_max_segs(const struct rnbd_dev *dev) +{ + return queue_max_segments(bdev_get_queue(dev->bdev)); +} + +static inline int rnbd_dev_get_max_hw_sects(const struct rnbd_dev *dev) +{ + return queue_max_hw_sectors(bdev_get_queue(dev->bdev)); +} + +static inline int rnbd_dev_get_secure_discard(const struct rnbd_dev *dev) +{ + return blk_queue_secure_erase(bdev_get_queue(dev->bdev)); +} + +static inline int rnbd_dev_get_max_discard_sects(const struct rnbd_dev *dev) +{ + if (!blk_queue_discard(bdev_get_queue(dev->bdev))) + return 0; + + return blk_queue_get_max_sectors(bdev_get_queue(dev->bdev), + REQ_OP_DISCARD); +} + +static inline int rnbd_dev_get_discard_granularity(const struct rnbd_dev *dev) +{ + return bdev_get_queue(dev->bdev)->limits.discard_granularity; +} + +static inline int rnbd_dev_get_discard_alignment(const struct rnbd_dev *dev) +{ + return bdev_get_queue(dev->bdev)->limits.discard_alignment; +} + +#endif /* RNBD_SRV_DEV_H */ diff --git a/drivers/block/rnbd/rnbd-srv-sysfs.c b/drivers/block/rnbd/rnbd-srv-sysfs.c new file mode 100644 index 000000000..106775c07 --- /dev/null +++ b/drivers/block/rnbd/rnbd-srv-sysfs.c @@ -0,0 +1,215 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ +#undef pr_fmt +#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt + +#include <uapi/linux/limits.h> +#include <linux/kobject.h> +#include <linux/sysfs.h> +#include <linux/stat.h> +#include <linux/genhd.h> +#include <linux/list.h> +#include <linux/moduleparam.h> +#include <linux/device.h> + +#include "rnbd-srv.h" + +static struct device *rnbd_dev; +static struct class *rnbd_dev_class; +static struct kobject *rnbd_devs_kobj; + +static void rnbd_srv_dev_release(struct kobject *kobj) +{ + struct rnbd_srv_dev *dev; + + dev = container_of(kobj, struct rnbd_srv_dev, dev_kobj); + + kfree(dev); +} + +static struct kobj_type dev_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .release = rnbd_srv_dev_release +}; + +int rnbd_srv_create_dev_sysfs(struct rnbd_srv_dev *dev, + struct block_device *bdev, + const char *dev_name) +{ + struct kobject *bdev_kobj; + int ret; + + ret = kobject_init_and_add(&dev->dev_kobj, &dev_ktype, + rnbd_devs_kobj, dev_name); + if (ret) + return ret; + + dev->dev_sessions_kobj = kobject_create_and_add("sessions", + &dev->dev_kobj); + if (!dev->dev_sessions_kobj) + goto put_dev_kobj; + + bdev_kobj = &disk_to_dev(bdev->bd_disk)->kobj; + ret = sysfs_create_link(&dev->dev_kobj, bdev_kobj, "block_dev"); + if (ret) + goto put_sess_kobj; + + return 0; + +put_sess_kobj: + kobject_put(dev->dev_sessions_kobj); +put_dev_kobj: + kobject_put(&dev->dev_kobj); + return ret; +} + +void rnbd_srv_destroy_dev_sysfs(struct rnbd_srv_dev *dev) +{ + sysfs_remove_link(&dev->dev_kobj, "block_dev"); + kobject_del(dev->dev_sessions_kobj); + kobject_put(dev->dev_sessions_kobj); + kobject_del(&dev->dev_kobj); + kobject_put(&dev->dev_kobj); +} + +static ssize_t read_only_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + struct rnbd_srv_sess_dev *sess_dev; + + sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj); + + return scnprintf(page, PAGE_SIZE, "%d\n", + !(sess_dev->open_flags & FMODE_WRITE)); +} + +static struct kobj_attribute rnbd_srv_dev_session_ro_attr = + __ATTR_RO(read_only); + +static ssize_t access_mode_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *page) +{ + struct rnbd_srv_sess_dev *sess_dev; + + sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj); + + return scnprintf(page, PAGE_SIZE, "%s\n", + rnbd_access_mode_str(sess_dev->access_mode)); +} + +static struct kobj_attribute rnbd_srv_dev_session_access_mode_attr = + __ATTR_RO(access_mode); + +static ssize_t mapping_path_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + struct rnbd_srv_sess_dev *sess_dev; + + sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj); + + return scnprintf(page, PAGE_SIZE, "%s\n", sess_dev->pathname); +} + +static struct kobj_attribute rnbd_srv_dev_session_mapping_path_attr = + __ATTR_RO(mapping_path); + +static struct attribute *rnbd_srv_default_dev_sessions_attrs[] = { + &rnbd_srv_dev_session_access_mode_attr.attr, + &rnbd_srv_dev_session_ro_attr.attr, + &rnbd_srv_dev_session_mapping_path_attr.attr, + NULL, +}; + +static struct attribute_group rnbd_srv_default_dev_session_attr_group = { + .attrs = rnbd_srv_default_dev_sessions_attrs, +}; + +void rnbd_srv_destroy_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev) +{ + sysfs_remove_group(&sess_dev->kobj, + &rnbd_srv_default_dev_session_attr_group); + + kobject_del(&sess_dev->kobj); + kobject_put(&sess_dev->kobj); +} + +static void rnbd_srv_sess_dev_release(struct kobject *kobj) +{ + struct rnbd_srv_sess_dev *sess_dev; + + sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj); + rnbd_destroy_sess_dev(sess_dev); +} + +static struct kobj_type rnbd_srv_sess_dev_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .release = rnbd_srv_sess_dev_release, +}; + +int rnbd_srv_create_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev) +{ + int ret; + + ret = kobject_init_and_add(&sess_dev->kobj, &rnbd_srv_sess_dev_ktype, + sess_dev->dev->dev_sessions_kobj, "%s", + sess_dev->sess->sessname); + if (ret) + return ret; + + ret = sysfs_create_group(&sess_dev->kobj, + &rnbd_srv_default_dev_session_attr_group); + if (ret) + goto err; + + return 0; + +err: + kobject_put(&sess_dev->kobj); + + return ret; +} + +int rnbd_srv_create_sysfs_files(void) +{ + int err; + + rnbd_dev_class = class_create(THIS_MODULE, "rnbd-server"); + if (IS_ERR(rnbd_dev_class)) + return PTR_ERR(rnbd_dev_class); + + rnbd_dev = device_create(rnbd_dev_class, NULL, + MKDEV(0, 0), NULL, "ctl"); + if (IS_ERR(rnbd_dev)) { + err = PTR_ERR(rnbd_dev); + goto cls_destroy; + } + rnbd_devs_kobj = kobject_create_and_add("devices", &rnbd_dev->kobj); + if (!rnbd_devs_kobj) { + err = -ENOMEM; + goto dev_destroy; + } + + return 0; + +dev_destroy: + device_destroy(rnbd_dev_class, MKDEV(0, 0)); +cls_destroy: + class_destroy(rnbd_dev_class); + + return err; +} + +void rnbd_srv_destroy_sysfs_files(void) +{ + kobject_del(rnbd_devs_kobj); + kobject_put(rnbd_devs_kobj); + device_destroy(rnbd_dev_class, MKDEV(0, 0)); + class_destroy(rnbd_dev_class); +} diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c new file mode 100644 index 000000000..e1bc8b4cd --- /dev/null +++ b/drivers/block/rnbd/rnbd-srv.c @@ -0,0 +1,859 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ +#undef pr_fmt +#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt + +#include <linux/module.h> +#include <linux/blkdev.h> + +#include "rnbd-srv.h" +#include "rnbd-srv-dev.h" + +MODULE_DESCRIPTION("RDMA Network Block Device Server"); +MODULE_LICENSE("GPL"); + +static u16 port_nr = RTRS_PORT; + +module_param_named(port_nr, port_nr, ushort, 0444); +MODULE_PARM_DESC(port_nr, + "The port number the server is listening on (default: " + __stringify(RTRS_PORT)")"); + +#define DEFAULT_DEV_SEARCH_PATH "/" + +static char dev_search_path[PATH_MAX] = DEFAULT_DEV_SEARCH_PATH; + +static int dev_search_path_set(const char *val, const struct kernel_param *kp) +{ + const char *p = strrchr(val, '\n') ? : val + strlen(val); + + if (strlen(val) >= sizeof(dev_search_path)) + return -EINVAL; + + snprintf(dev_search_path, sizeof(dev_search_path), "%.*s", + (int)(p - val), val); + + pr_info("dev_search_path changed to '%s'\n", dev_search_path); + + return 0; +} + +static struct kparam_string dev_search_path_kparam_str = { + .maxlen = sizeof(dev_search_path), + .string = dev_search_path +}; + +static const struct kernel_param_ops dev_search_path_ops = { + .set = dev_search_path_set, + .get = param_get_string, +}; + +module_param_cb(dev_search_path, &dev_search_path_ops, + &dev_search_path_kparam_str, 0444); +MODULE_PARM_DESC(dev_search_path, + "Sets the dev_search_path. When a device is mapped this path is prepended to the device path from the map device operation. If %SESSNAME% is specified in a path, then device will be searched in a session namespace. (default: " + DEFAULT_DEV_SEARCH_PATH ")"); + +static DEFINE_MUTEX(sess_lock); +static DEFINE_SPINLOCK(dev_lock); + +static LIST_HEAD(sess_list); +static LIST_HEAD(dev_list); + +struct rnbd_io_private { + struct rtrs_srv_op *id; + struct rnbd_srv_sess_dev *sess_dev; +}; + +static void rnbd_sess_dev_release(struct kref *kref) +{ + struct rnbd_srv_sess_dev *sess_dev; + + sess_dev = container_of(kref, struct rnbd_srv_sess_dev, kref); + complete(sess_dev->destroy_comp); +} + +static inline void rnbd_put_sess_dev(struct rnbd_srv_sess_dev *sess_dev) +{ + kref_put(&sess_dev->kref, rnbd_sess_dev_release); +} + +void rnbd_endio(void *priv, int error) +{ + struct rnbd_io_private *rnbd_priv = priv; + struct rnbd_srv_sess_dev *sess_dev = rnbd_priv->sess_dev; + + rnbd_put_sess_dev(sess_dev); + + rtrs_srv_resp_rdma(rnbd_priv->id, error); + + kfree(priv); +} + +static struct rnbd_srv_sess_dev * +rnbd_get_sess_dev(int dev_id, struct rnbd_srv_session *srv_sess) +{ + struct rnbd_srv_sess_dev *sess_dev; + int ret = 0; + + rcu_read_lock(); + sess_dev = xa_load(&srv_sess->index_idr, dev_id); + if (likely(sess_dev)) + ret = kref_get_unless_zero(&sess_dev->kref); + rcu_read_unlock(); + + if (!sess_dev || !ret) + return ERR_PTR(-ENXIO); + + return sess_dev; +} + +static int process_rdma(struct rtrs_srv *sess, + struct rnbd_srv_session *srv_sess, + struct rtrs_srv_op *id, void *data, u32 datalen, + const void *usr, size_t usrlen) +{ + const struct rnbd_msg_io *msg = usr; + struct rnbd_io_private *priv; + struct rnbd_srv_sess_dev *sess_dev; + u32 dev_id; + int err; + struct rnbd_dev_blk_io *io; + struct bio *bio; + short prio; + + priv = kmalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + dev_id = le32_to_cpu(msg->device_id); + + sess_dev = rnbd_get_sess_dev(dev_id, srv_sess); + if (IS_ERR(sess_dev)) { + pr_err_ratelimited("Got I/O request on session %s for unknown device id %d\n", + srv_sess->sessname, dev_id); + err = -ENOTCONN; + goto err; + } + + priv->sess_dev = sess_dev; + priv->id = id; + + /* Generate bio with pages pointing to the rdma buffer */ + bio = rnbd_bio_map_kern(data, sess_dev->rnbd_dev->ibd_bio_set, datalen, GFP_KERNEL); + if (IS_ERR(bio)) { + err = PTR_ERR(bio); + rnbd_srv_err(sess_dev, "Failed to generate bio, err: %d\n", err); + goto sess_dev_put; + } + + io = container_of(bio, struct rnbd_dev_blk_io, bio); + io->dev = sess_dev->rnbd_dev; + io->priv = priv; + + bio->bi_end_io = rnbd_dev_bi_end_io; + bio->bi_private = io; + bio->bi_opf = rnbd_to_bio_flags(le32_to_cpu(msg->rw)); + bio->bi_iter.bi_sector = le64_to_cpu(msg->sector); + bio->bi_iter.bi_size = le32_to_cpu(msg->bi_size); + prio = srv_sess->ver < RNBD_PROTO_VER_MAJOR || + usrlen < sizeof(*msg) ? 0 : le16_to_cpu(msg->prio); + bio_set_prio(bio, prio); + bio_set_dev(bio, sess_dev->rnbd_dev->bdev); + + submit_bio(bio); + + return 0; + +sess_dev_put: + rnbd_put_sess_dev(sess_dev); +err: + kfree(priv); + return err; +} + +static void destroy_device(struct rnbd_srv_dev *dev) +{ + WARN_ONCE(!list_empty(&dev->sess_dev_list), + "Device %s is being destroyed but still in use!\n", + dev->id); + + spin_lock(&dev_lock); + list_del(&dev->list); + spin_unlock(&dev_lock); + + mutex_destroy(&dev->lock); + if (dev->dev_kobj.state_in_sysfs) + /* + * Destroy kobj only if it was really created. + */ + rnbd_srv_destroy_dev_sysfs(dev); + else + kfree(dev); +} + +static void destroy_device_cb(struct kref *kref) +{ + struct rnbd_srv_dev *dev; + + dev = container_of(kref, struct rnbd_srv_dev, kref); + + destroy_device(dev); +} + +static void rnbd_put_srv_dev(struct rnbd_srv_dev *dev) +{ + kref_put(&dev->kref, destroy_device_cb); +} + +void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev) +{ + DECLARE_COMPLETION_ONSTACK(dc); + + xa_erase(&sess_dev->sess->index_idr, sess_dev->device_id); + synchronize_rcu(); + sess_dev->destroy_comp = &dc; + rnbd_put_sess_dev(sess_dev); + wait_for_completion(&dc); /* wait for inflights to drop to zero */ + + rnbd_dev_close(sess_dev->rnbd_dev); + list_del(&sess_dev->sess_list); + mutex_lock(&sess_dev->dev->lock); + list_del(&sess_dev->dev_list); + if (sess_dev->open_flags & FMODE_WRITE) + sess_dev->dev->open_write_cnt--; + mutex_unlock(&sess_dev->dev->lock); + + rnbd_put_srv_dev(sess_dev->dev); + + rnbd_srv_info(sess_dev, "Device closed\n"); + kfree(sess_dev); +} + +static void destroy_sess(struct rnbd_srv_session *srv_sess) +{ + struct rnbd_srv_sess_dev *sess_dev, *tmp; + + if (list_empty(&srv_sess->sess_dev_list)) + goto out; + + mutex_lock(&srv_sess->lock); + list_for_each_entry_safe(sess_dev, tmp, &srv_sess->sess_dev_list, + sess_list) + rnbd_srv_destroy_dev_session_sysfs(sess_dev); + mutex_unlock(&srv_sess->lock); + +out: + xa_destroy(&srv_sess->index_idr); + bioset_exit(&srv_sess->sess_bio_set); + + pr_info("RTRS Session %s disconnected\n", srv_sess->sessname); + + mutex_lock(&sess_lock); + list_del(&srv_sess->list); + mutex_unlock(&sess_lock); + + mutex_destroy(&srv_sess->lock); + kfree(srv_sess); +} + +static int create_sess(struct rtrs_srv *rtrs) +{ + struct rnbd_srv_session *srv_sess; + char sessname[NAME_MAX]; + int err; + + err = rtrs_srv_get_sess_name(rtrs, sessname, sizeof(sessname)); + if (err) { + pr_err("rtrs_srv_get_sess_name(%s): %d\n", sessname, err); + + return err; + } + srv_sess = kzalloc(sizeof(*srv_sess), GFP_KERNEL); + if (!srv_sess) + return -ENOMEM; + + srv_sess->queue_depth = rtrs_srv_get_queue_depth(rtrs); + err = bioset_init(&srv_sess->sess_bio_set, srv_sess->queue_depth, + offsetof(struct rnbd_dev_blk_io, bio), + BIOSET_NEED_BVECS); + if (err) { + pr_err("Allocating srv_session for session %s failed\n", + sessname); + kfree(srv_sess); + return err; + } + + xa_init_flags(&srv_sess->index_idr, XA_FLAGS_ALLOC); + INIT_LIST_HEAD(&srv_sess->sess_dev_list); + mutex_init(&srv_sess->lock); + mutex_lock(&sess_lock); + list_add(&srv_sess->list, &sess_list); + mutex_unlock(&sess_lock); + + srv_sess->rtrs = rtrs; + strlcpy(srv_sess->sessname, sessname, sizeof(srv_sess->sessname)); + + rtrs_srv_set_sess_priv(rtrs, srv_sess); + + return 0; +} + +static int rnbd_srv_link_ev(struct rtrs_srv *rtrs, + enum rtrs_srv_link_ev ev, void *priv) +{ + struct rnbd_srv_session *srv_sess = priv; + + switch (ev) { + case RTRS_SRV_LINK_EV_CONNECTED: + return create_sess(rtrs); + + case RTRS_SRV_LINK_EV_DISCONNECTED: + if (WARN_ON_ONCE(!srv_sess)) + return -EINVAL; + + destroy_sess(srv_sess); + return 0; + + default: + pr_warn("Received unknown RTRS session event %d from session %s\n", + ev, srv_sess->sessname); + return -EINVAL; + } +} + +static int process_msg_close(struct rtrs_srv *rtrs, + struct rnbd_srv_session *srv_sess, + void *data, size_t datalen, const void *usr, + size_t usrlen) +{ + const struct rnbd_msg_close *close_msg = usr; + struct rnbd_srv_sess_dev *sess_dev; + + sess_dev = rnbd_get_sess_dev(le32_to_cpu(close_msg->device_id), + srv_sess); + if (IS_ERR(sess_dev)) + return 0; + + rnbd_put_sess_dev(sess_dev); + mutex_lock(&srv_sess->lock); + rnbd_srv_destroy_dev_session_sysfs(sess_dev); + mutex_unlock(&srv_sess->lock); + return 0; +} + +static int process_msg_open(struct rtrs_srv *rtrs, + struct rnbd_srv_session *srv_sess, + const void *msg, size_t len, + void *data, size_t datalen); + +static int process_msg_sess_info(struct rtrs_srv *rtrs, + struct rnbd_srv_session *srv_sess, + const void *msg, size_t len, + void *data, size_t datalen); + +static int rnbd_srv_rdma_ev(struct rtrs_srv *rtrs, void *priv, + struct rtrs_srv_op *id, int dir, + void *data, size_t datalen, const void *usr, + size_t usrlen) +{ + struct rnbd_srv_session *srv_sess = priv; + const struct rnbd_msg_hdr *hdr = usr; + int ret = 0; + u16 type; + + if (WARN_ON_ONCE(!srv_sess)) + return -ENODEV; + + type = le16_to_cpu(hdr->type); + + switch (type) { + case RNBD_MSG_IO: + return process_rdma(rtrs, srv_sess, id, data, datalen, usr, + usrlen); + case RNBD_MSG_CLOSE: + ret = process_msg_close(rtrs, srv_sess, data, datalen, + usr, usrlen); + break; + case RNBD_MSG_OPEN: + ret = process_msg_open(rtrs, srv_sess, usr, usrlen, + data, datalen); + break; + case RNBD_MSG_SESS_INFO: + ret = process_msg_sess_info(rtrs, srv_sess, usr, usrlen, + data, datalen); + break; + default: + pr_warn("Received unexpected message type %d with dir %d from session %s\n", + type, dir, srv_sess->sessname); + return -EINVAL; + } + + rtrs_srv_resp_rdma(id, ret); + return 0; +} + +static struct rnbd_srv_sess_dev +*rnbd_sess_dev_alloc(struct rnbd_srv_session *srv_sess) +{ + struct rnbd_srv_sess_dev *sess_dev; + int error; + + sess_dev = kzalloc(sizeof(*sess_dev), GFP_KERNEL); + if (!sess_dev) + return ERR_PTR(-ENOMEM); + + error = xa_alloc(&srv_sess->index_idr, &sess_dev->device_id, sess_dev, + xa_limit_32b, GFP_NOWAIT); + if (error < 0) { + pr_warn("Allocating idr failed, err: %d\n", error); + kfree(sess_dev); + return ERR_PTR(error); + } + + return sess_dev; +} + +static struct rnbd_srv_dev *rnbd_srv_init_srv_dev(const char *id) +{ + struct rnbd_srv_dev *dev; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return ERR_PTR(-ENOMEM); + + strlcpy(dev->id, id, sizeof(dev->id)); + kref_init(&dev->kref); + INIT_LIST_HEAD(&dev->sess_dev_list); + mutex_init(&dev->lock); + + return dev; +} + +static struct rnbd_srv_dev * +rnbd_srv_find_or_add_srv_dev(struct rnbd_srv_dev *new_dev) +{ + struct rnbd_srv_dev *dev; + + spin_lock(&dev_lock); + list_for_each_entry(dev, &dev_list, list) { + if (!strncmp(dev->id, new_dev->id, sizeof(dev->id))) { + if (!kref_get_unless_zero(&dev->kref)) + /* + * We lost the race, device is almost dead. + * Continue traversing to find a valid one. + */ + continue; + spin_unlock(&dev_lock); + return dev; + } + } + list_add(&new_dev->list, &dev_list); + spin_unlock(&dev_lock); + + return new_dev; +} + +static int rnbd_srv_check_update_open_perm(struct rnbd_srv_dev *srv_dev, + struct rnbd_srv_session *srv_sess, + enum rnbd_access_mode access_mode) +{ + int ret = -EPERM; + + mutex_lock(&srv_dev->lock); + + switch (access_mode) { + case RNBD_ACCESS_RO: + ret = 0; + break; + case RNBD_ACCESS_RW: + if (srv_dev->open_write_cnt == 0) { + srv_dev->open_write_cnt++; + ret = 0; + } else { + pr_err("Mapping device '%s' for session %s with RW permissions failed. Device already opened as 'RW' by %d client(s), access mode %s.\n", + srv_dev->id, srv_sess->sessname, + srv_dev->open_write_cnt, + rnbd_access_mode_str(access_mode)); + } + break; + case RNBD_ACCESS_MIGRATION: + if (srv_dev->open_write_cnt < 2) { + srv_dev->open_write_cnt++; + ret = 0; + } else { + pr_err("Mapping device '%s' for session %s with migration permissions failed. Device already opened as 'RW' by %d client(s), access mode %s.\n", + srv_dev->id, srv_sess->sessname, + srv_dev->open_write_cnt, + rnbd_access_mode_str(access_mode)); + } + break; + default: + pr_err("Received mapping request for device '%s' on session %s with invalid access mode: %d\n", + srv_dev->id, srv_sess->sessname, access_mode); + ret = -EINVAL; + } + + mutex_unlock(&srv_dev->lock); + + return ret; +} + +static struct rnbd_srv_dev * +rnbd_srv_get_or_create_srv_dev(struct rnbd_dev *rnbd_dev, + struct rnbd_srv_session *srv_sess, + enum rnbd_access_mode access_mode) +{ + int ret; + struct rnbd_srv_dev *new_dev, *dev; + + new_dev = rnbd_srv_init_srv_dev(rnbd_dev->name); + if (IS_ERR(new_dev)) + return new_dev; + + dev = rnbd_srv_find_or_add_srv_dev(new_dev); + if (dev != new_dev) + kfree(new_dev); + + ret = rnbd_srv_check_update_open_perm(dev, srv_sess, access_mode); + if (ret) { + rnbd_put_srv_dev(dev); + return ERR_PTR(ret); + } + + return dev; +} + +static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, + struct rnbd_srv_sess_dev *sess_dev) +{ + struct rnbd_dev *rnbd_dev = sess_dev->rnbd_dev; + + rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP); + rsp->device_id = + cpu_to_le32(sess_dev->device_id); + rsp->nsectors = + cpu_to_le64(get_capacity(rnbd_dev->bdev->bd_disk)); + rsp->logical_block_size = + cpu_to_le16(bdev_logical_block_size(rnbd_dev->bdev)); + rsp->physical_block_size = + cpu_to_le16(bdev_physical_block_size(rnbd_dev->bdev)); + rsp->max_segments = + cpu_to_le16(rnbd_dev_get_max_segs(rnbd_dev)); + rsp->max_hw_sectors = + cpu_to_le32(rnbd_dev_get_max_hw_sects(rnbd_dev)); + rsp->max_write_same_sectors = + cpu_to_le32(bdev_write_same(rnbd_dev->bdev)); + rsp->max_discard_sectors = + cpu_to_le32(rnbd_dev_get_max_discard_sects(rnbd_dev)); + rsp->discard_granularity = + cpu_to_le32(rnbd_dev_get_discard_granularity(rnbd_dev)); + rsp->discard_alignment = + cpu_to_le32(rnbd_dev_get_discard_alignment(rnbd_dev)); + rsp->secure_discard = + cpu_to_le16(rnbd_dev_get_secure_discard(rnbd_dev)); + rsp->rotational = + !blk_queue_nonrot(bdev_get_queue(rnbd_dev->bdev)); +} + +static struct rnbd_srv_sess_dev * +rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess, + const struct rnbd_msg_open *open_msg, + struct rnbd_dev *rnbd_dev, fmode_t open_flags, + struct rnbd_srv_dev *srv_dev) +{ + struct rnbd_srv_sess_dev *sdev = rnbd_sess_dev_alloc(srv_sess); + + if (IS_ERR(sdev)) + return sdev; + + kref_init(&sdev->kref); + + strlcpy(sdev->pathname, open_msg->dev_name, sizeof(sdev->pathname)); + + sdev->rnbd_dev = rnbd_dev; + sdev->sess = srv_sess; + sdev->dev = srv_dev; + sdev->open_flags = open_flags; + sdev->access_mode = open_msg->access_mode; + + return sdev; +} + +static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess, + const char *dev_name) +{ + char *full_path; + char *a, *b; + + full_path = kmalloc(PATH_MAX, GFP_KERNEL); + if (!full_path) + return ERR_PTR(-ENOMEM); + + /* + * Replace %SESSNAME% with a real session name in order to + * create device namespace. + */ + a = strnstr(dev_search_path, "%SESSNAME%", sizeof(dev_search_path)); + if (a) { + int len = a - dev_search_path; + + len = snprintf(full_path, PATH_MAX, "%.*s/%s/%s", len, + dev_search_path, srv_sess->sessname, dev_name); + if (len >= PATH_MAX) { + pr_err("Too long path: %s, %s, %s\n", + dev_search_path, srv_sess->sessname, dev_name); + kfree(full_path); + return ERR_PTR(-EINVAL); + } + } else { + snprintf(full_path, PATH_MAX, "%s/%s", + dev_search_path, dev_name); + } + + /* eliminitate duplicated slashes */ + a = strchr(full_path, '/'); + b = a; + while (*b != '\0') { + if (*b == '/' && *a == '/') { + b++; + } else { + a++; + *a = *b; + b++; + } + } + a++; + *a = '\0'; + + return full_path; +} + +static int process_msg_sess_info(struct rtrs_srv *rtrs, + struct rnbd_srv_session *srv_sess, + const void *msg, size_t len, + void *data, size_t datalen) +{ + const struct rnbd_msg_sess_info *sess_info_msg = msg; + struct rnbd_msg_sess_info_rsp *rsp = data; + + srv_sess->ver = min_t(u8, sess_info_msg->ver, RNBD_PROTO_VER_MAJOR); + pr_debug("Session %s using protocol version %d (client version: %d, server version: %d)\n", + srv_sess->sessname, srv_sess->ver, + sess_info_msg->ver, RNBD_PROTO_VER_MAJOR); + + rsp->hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO_RSP); + rsp->ver = srv_sess->ver; + + return 0; +} + +/** + * find_srv_sess_dev() - a dev is already opened by this name + * @srv_sess: the session to search. + * @dev_name: string containing the name of the device. + * + * Return struct rnbd_srv_sess_dev if srv_sess already opened the dev_name + * NULL if the session didn't open the device yet. + */ +static struct rnbd_srv_sess_dev * +find_srv_sess_dev(struct rnbd_srv_session *srv_sess, const char *dev_name) +{ + struct rnbd_srv_sess_dev *sess_dev; + + if (list_empty(&srv_sess->sess_dev_list)) + return NULL; + + list_for_each_entry(sess_dev, &srv_sess->sess_dev_list, sess_list) + if (!strcmp(sess_dev->pathname, dev_name)) + return sess_dev; + + return NULL; +} + +static int process_msg_open(struct rtrs_srv *rtrs, + struct rnbd_srv_session *srv_sess, + const void *msg, size_t len, + void *data, size_t datalen) +{ + int ret; + struct rnbd_srv_dev *srv_dev; + struct rnbd_srv_sess_dev *srv_sess_dev; + const struct rnbd_msg_open *open_msg = msg; + fmode_t open_flags; + char *full_path; + struct rnbd_dev *rnbd_dev; + struct rnbd_msg_open_rsp *rsp = data; + + pr_debug("Open message received: session='%s' path='%s' access_mode=%d\n", + srv_sess->sessname, open_msg->dev_name, + open_msg->access_mode); + open_flags = FMODE_READ; + if (open_msg->access_mode != RNBD_ACCESS_RO) + open_flags |= FMODE_WRITE; + + mutex_lock(&srv_sess->lock); + + srv_sess_dev = find_srv_sess_dev(srv_sess, open_msg->dev_name); + if (srv_sess_dev) + goto fill_response; + + if ((strlen(dev_search_path) + strlen(open_msg->dev_name)) + >= PATH_MAX) { + pr_err("Opening device for session %s failed, device path too long. '%s/%s' is longer than PATH_MAX (%d)\n", + srv_sess->sessname, dev_search_path, open_msg->dev_name, + PATH_MAX); + ret = -EINVAL; + goto reject; + } + if (strstr(open_msg->dev_name, "..")) { + pr_err("Opening device for session %s failed, device path %s contains relative path ..\n", + srv_sess->sessname, open_msg->dev_name); + ret = -EINVAL; + goto reject; + } + full_path = rnbd_srv_get_full_path(srv_sess, open_msg->dev_name); + if (IS_ERR(full_path)) { + ret = PTR_ERR(full_path); + pr_err("Opening device '%s' for client %s failed, failed to get device full path, err: %d\n", + open_msg->dev_name, srv_sess->sessname, ret); + goto reject; + } + + rnbd_dev = rnbd_dev_open(full_path, open_flags, + &srv_sess->sess_bio_set); + if (IS_ERR(rnbd_dev)) { + pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %ld\n", + full_path, srv_sess->sessname, PTR_ERR(rnbd_dev)); + ret = PTR_ERR(rnbd_dev); + goto free_path; + } + + srv_dev = rnbd_srv_get_or_create_srv_dev(rnbd_dev, srv_sess, + open_msg->access_mode); + if (IS_ERR(srv_dev)) { + pr_err("Opening device '%s' on session %s failed, creating srv_dev failed, err: %ld\n", + full_path, srv_sess->sessname, PTR_ERR(srv_dev)); + ret = PTR_ERR(srv_dev); + goto rnbd_dev_close; + } + + srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg, + rnbd_dev, open_flags, + srv_dev); + if (IS_ERR(srv_sess_dev)) { + pr_err("Opening device '%s' on session %s failed, creating sess_dev failed, err: %ld\n", + full_path, srv_sess->sessname, PTR_ERR(srv_sess_dev)); + ret = PTR_ERR(srv_sess_dev); + goto srv_dev_put; + } + + /* Create the srv_dev sysfs files if they haven't been created yet. The + * reason to delay the creation is not to create the sysfs files before + * we are sure the device can be opened. + */ + mutex_lock(&srv_dev->lock); + if (!srv_dev->dev_kobj.state_in_sysfs) { + ret = rnbd_srv_create_dev_sysfs(srv_dev, rnbd_dev->bdev, + rnbd_dev->name); + if (ret) { + mutex_unlock(&srv_dev->lock); + rnbd_srv_err(srv_sess_dev, + "Opening device failed, failed to create device sysfs files, err: %d\n", + ret); + goto free_srv_sess_dev; + } + } + + ret = rnbd_srv_create_dev_session_sysfs(srv_sess_dev); + if (ret) { + mutex_unlock(&srv_dev->lock); + rnbd_srv_err(srv_sess_dev, + "Opening device failed, failed to create dev client sysfs files, err: %d\n", + ret); + goto free_srv_sess_dev; + } + + list_add(&srv_sess_dev->dev_list, &srv_dev->sess_dev_list); + mutex_unlock(&srv_dev->lock); + + list_add(&srv_sess_dev->sess_list, &srv_sess->sess_dev_list); + + rnbd_srv_info(srv_sess_dev, "Opened device '%s'\n", srv_dev->id); + + kfree(full_path); + +fill_response: + rnbd_srv_fill_msg_open_rsp(rsp, srv_sess_dev); + mutex_unlock(&srv_sess->lock); + return 0; + +free_srv_sess_dev: + xa_erase(&srv_sess->index_idr, srv_sess_dev->device_id); + synchronize_rcu(); + kfree(srv_sess_dev); +srv_dev_put: + if (open_msg->access_mode != RNBD_ACCESS_RO) { + mutex_lock(&srv_dev->lock); + srv_dev->open_write_cnt--; + mutex_unlock(&srv_dev->lock); + } + rnbd_put_srv_dev(srv_dev); +rnbd_dev_close: + rnbd_dev_close(rnbd_dev); +free_path: + kfree(full_path); +reject: + mutex_unlock(&srv_sess->lock); + return ret; +} + +static struct rtrs_srv_ctx *rtrs_ctx; + +static struct rtrs_srv_ops rtrs_ops; +static int __init rnbd_srv_init_module(void) +{ + int err; + + BUILD_BUG_ON(sizeof(struct rnbd_msg_hdr) != 4); + BUILD_BUG_ON(sizeof(struct rnbd_msg_sess_info) != 36); + BUILD_BUG_ON(sizeof(struct rnbd_msg_sess_info_rsp) != 36); + BUILD_BUG_ON(sizeof(struct rnbd_msg_open) != 264); + BUILD_BUG_ON(sizeof(struct rnbd_msg_close) != 8); + BUILD_BUG_ON(sizeof(struct rnbd_msg_open_rsp) != 56); + rtrs_ops = (struct rtrs_srv_ops) { + .rdma_ev = rnbd_srv_rdma_ev, + .link_ev = rnbd_srv_link_ev, + }; + rtrs_ctx = rtrs_srv_open(&rtrs_ops, port_nr); + if (IS_ERR(rtrs_ctx)) { + err = PTR_ERR(rtrs_ctx); + pr_err("rtrs_srv_open(), err: %d\n", err); + return err; + } + + err = rnbd_srv_create_sysfs_files(); + if (err) { + pr_err("rnbd_srv_create_sysfs_files(), err: %d\n", err); + rtrs_srv_close(rtrs_ctx); + return err; + } + + return 0; +} + +static void __exit rnbd_srv_cleanup_module(void) +{ + rtrs_srv_close(rtrs_ctx); + WARN_ON(!list_empty(&sess_list)); + rnbd_srv_destroy_sysfs_files(); +} + +module_init(rnbd_srv_init_module); +module_exit(rnbd_srv_cleanup_module); diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h new file mode 100644 index 000000000..5a8544b5e --- /dev/null +++ b/drivers/block/rnbd/rnbd-srv.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * RDMA Network Block Driver + * + * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. + * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. + * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. + */ +#ifndef RNBD_SRV_H +#define RNBD_SRV_H + +#include <linux/types.h> +#include <linux/idr.h> +#include <linux/kref.h> + +#include <rtrs.h> +#include "rnbd-proto.h" +#include "rnbd-log.h" + +struct rnbd_srv_session { + /* Entry inside global sess_list */ + struct list_head list; + struct rtrs_srv *rtrs; + char sessname[NAME_MAX]; + int queue_depth; + struct bio_set sess_bio_set; + + struct xarray index_idr; + /* List of struct rnbd_srv_sess_dev */ + struct list_head sess_dev_list; + struct mutex lock; + u8 ver; +}; + +struct rnbd_srv_dev { + /* Entry inside global dev_list */ + struct list_head list; + struct kobject dev_kobj; + struct kobject *dev_sessions_kobj; + struct kref kref; + char id[NAME_MAX]; + /* List of rnbd_srv_sess_dev structs */ + struct list_head sess_dev_list; + struct mutex lock; + int open_write_cnt; +}; + +/* Structure which binds N devices and N sessions */ +struct rnbd_srv_sess_dev { + /* Entry inside rnbd_srv_dev struct */ + struct list_head dev_list; + /* Entry inside rnbd_srv_session struct */ + struct list_head sess_list; + struct rnbd_dev *rnbd_dev; + struct rnbd_srv_session *sess; + struct rnbd_srv_dev *dev; + struct kobject kobj; + u32 device_id; + fmode_t open_flags; + struct kref kref; + struct completion *destroy_comp; + char pathname[NAME_MAX]; + enum rnbd_access_mode access_mode; +}; + +/* rnbd-srv-sysfs.c */ + +int rnbd_srv_create_dev_sysfs(struct rnbd_srv_dev *dev, + struct block_device *bdev, + const char *dir_name); +void rnbd_srv_destroy_dev_sysfs(struct rnbd_srv_dev *dev); +int rnbd_srv_create_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev); +void rnbd_srv_destroy_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev); +int rnbd_srv_create_sysfs_files(void); +void rnbd_srv_destroy_sysfs_files(void); +void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev); + +#endif /* RNBD_SRV_H */ |