diff options
Diffstat (limited to 'drivers/block/drbd/drbd_nl.c')
| -rw-r--r-- | drivers/block/drbd/drbd_nl.c | 4251 |
1 files changed, 2630 insertions, 1621 deletions
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 515bcd948a4..3f2e1673808 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -29,165 +29,339 @@ #include <linux/fs.h> #include <linux/file.h> #include <linux/slab.h> -#include <linux/connector.h> #include <linux/blkpg.h> #include <linux/cpumask.h> #include "drbd_int.h" +#include "drbd_protocol.h" #include "drbd_req.h" -#include "drbd_wrappers.h" #include <asm/unaligned.h> -#include <linux/drbd_tag_magic.h> #include <linux/drbd_limits.h> -#include <linux/compiler.h> #include <linux/kthread.h> -static unsigned short *tl_add_blob(unsigned short *, enum drbd_tags, const void *, int); -static unsigned short *tl_add_str(unsigned short *, enum drbd_tags, const char *); -static unsigned short *tl_add_int(unsigned short *, enum drbd_tags, const void *); - -/* see get_sb_bdev and bd_claim */ +#include <net/genetlink.h> + +/* .doit */ +// int drbd_adm_create_resource(struct sk_buff *skb, struct genl_info *info); +// int drbd_adm_delete_resource(struct sk_buff *skb, struct genl_info *info); + +int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_del_minor(struct sk_buff *skb, struct genl_info *info); + +int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_down(struct sk_buff *skb, struct genl_info *info); + +int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_pause_sync(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_suspend_io(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info); +int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info); +/* .dumpit */ +int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb); + +#include <linux/drbd_genl_api.h> +#include "drbd_nla.h" +#include <linux/genl_magic_func.h> + +/* used blkdev_get_by_path, to claim our meta data device(s) */ static char *drbd_m_holder = "Hands off! this is DRBD's meta data device."; -/* Generate the tag_list to struct functions */ -#define NL_PACKET(name, number, fields) \ -static int name ## _from_tags(struct drbd_conf *mdev, \ - unsigned short *tags, struct name *arg) __attribute__ ((unused)); \ -static int name ## _from_tags(struct drbd_conf *mdev, \ - unsigned short *tags, struct name *arg) \ -{ \ - int tag; \ - int dlen; \ - \ - while ((tag = get_unaligned(tags++)) != TT_END) { \ - dlen = get_unaligned(tags++); \ - switch (tag_number(tag)) { \ - fields \ - default: \ - if (tag & T_MANDATORY) { \ - dev_err(DEV, "Unknown tag: %d\n", tag_number(tag)); \ - return 0; \ - } \ - } \ - tags = (unsigned short *)((char *)tags + dlen); \ - } \ - return 1; \ -} -#define NL_INTEGER(pn, pr, member) \ - case pn: /* D_ASSERT( tag_type(tag) == TT_INTEGER ); */ \ - arg->member = get_unaligned((int *)(tags)); \ - break; -#define NL_INT64(pn, pr, member) \ - case pn: /* D_ASSERT( tag_type(tag) == TT_INT64 ); */ \ - arg->member = get_unaligned((u64 *)(tags)); \ +static void drbd_adm_send_reply(struct sk_buff *skb, struct genl_info *info) +{ + genlmsg_end(skb, genlmsg_data(nlmsg_data(nlmsg_hdr(skb)))); + if (genlmsg_reply(skb, info)) + printk(KERN_ERR "drbd: error sending genl reply\n"); +} + +/* Used on a fresh "drbd_adm_prepare"d reply_skb, this cannot fail: The only + * reason it could fail was no space in skb, and there are 4k available. */ +int drbd_msg_put_info(struct sk_buff *skb, const char *info) +{ + struct nlattr *nla; + int err = -EMSGSIZE; + + if (!info || !info[0]) + return 0; + + nla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY); + if (!nla) + return err; + + err = nla_put_string(skb, T_info_text, info); + if (err) { + nla_nest_cancel(skb, nla); + return err; + } else + nla_nest_end(skb, nla); + return 0; +} + +/* This would be a good candidate for a "pre_doit" hook, + * and per-family private info->pointers. + * But we need to stay compatible with older kernels. + * If it returns successfully, adm_ctx members are valid. + * + * At this point, we still rely on the global genl_lock(). + * If we want to avoid that, and allow "genl_family.parallel_ops", we may need + * to add additional synchronization against object destruction/modification. + */ +#define DRBD_ADM_NEED_MINOR 1 +#define DRBD_ADM_NEED_RESOURCE 2 +#define DRBD_ADM_NEED_CONNECTION 4 +static int drbd_adm_prepare(struct drbd_config_context *adm_ctx, + struct sk_buff *skb, struct genl_info *info, unsigned flags) +{ + struct drbd_genlmsghdr *d_in = info->userhdr; + const u8 cmd = info->genlhdr->cmd; + int err; + + memset(adm_ctx, 0, sizeof(*adm_ctx)); + + /* genl_rcv_msg only checks for CAP_NET_ADMIN on "GENL_ADMIN_PERM" :( */ + if (cmd != DRBD_ADM_GET_STATUS && !capable(CAP_NET_ADMIN)) + return -EPERM; + + adm_ctx->reply_skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!adm_ctx->reply_skb) { + err = -ENOMEM; + goto fail; + } + + adm_ctx->reply_dh = genlmsg_put_reply(adm_ctx->reply_skb, + info, &drbd_genl_family, 0, cmd); + /* put of a few bytes into a fresh skb of >= 4k will always succeed. + * but anyways */ + if (!adm_ctx->reply_dh) { + err = -ENOMEM; + goto fail; + } + + adm_ctx->reply_dh->minor = d_in->minor; + adm_ctx->reply_dh->ret_code = NO_ERROR; + + adm_ctx->volume = VOLUME_UNSPECIFIED; + if (info->attrs[DRBD_NLA_CFG_CONTEXT]) { + struct nlattr *nla; + /* parse and validate only */ + err = drbd_cfg_context_from_attrs(NULL, info); + if (err) + goto fail; + + /* It was present, and valid, + * copy it over to the reply skb. */ + err = nla_put_nohdr(adm_ctx->reply_skb, + info->attrs[DRBD_NLA_CFG_CONTEXT]->nla_len, + info->attrs[DRBD_NLA_CFG_CONTEXT]); + if (err) + goto fail; + + /* and assign stuff to the adm_ctx */ + nla = nested_attr_tb[__nla_type(T_ctx_volume)]; + if (nla) + adm_ctx->volume = nla_get_u32(nla); + nla = nested_attr_tb[__nla_type(T_ctx_resource_name)]; + if (nla) + adm_ctx->resource_name = nla_data(nla); + adm_ctx->my_addr = nested_attr_tb[__nla_type(T_ctx_my_addr)]; + adm_ctx->peer_addr = nested_attr_tb[__nla_type(T_ctx_peer_addr)]; + if ((adm_ctx->my_addr && + nla_len(adm_ctx->my_addr) > sizeof(adm_ctx->connection->my_addr)) || + (adm_ctx->peer_addr && + nla_len(adm_ctx->peer_addr) > sizeof(adm_ctx->connection->peer_addr))) { + err = -EINVAL; + goto fail; + } + } + + adm_ctx->minor = d_in->minor; + adm_ctx->device = minor_to_device(d_in->minor); + + /* We are protected by the global genl_lock(). + * But we may explicitly drop it/retake it in drbd_adm_set_role(), + * so make sure this object stays around. */ + if (adm_ctx->device) + kref_get(&adm_ctx->device->kref); + + if (adm_ctx->resource_name) { + adm_ctx->resource = drbd_find_resource(adm_ctx->resource_name); + } + + if (!adm_ctx->device && (flags & DRBD_ADM_NEED_MINOR)) { + drbd_msg_put_info(adm_ctx->reply_skb, "unknown minor"); + return ERR_MINOR_INVALID; + } + if (!adm_ctx->resource && (flags & DRBD_ADM_NEED_RESOURCE)) { + drbd_msg_put_info(adm_ctx->reply_skb, "unknown resource"); + if (adm_ctx->resource_name) + return ERR_RES_NOT_KNOWN; + return ERR_INVALID_REQUEST; + } + + if (flags & DRBD_ADM_NEED_CONNECTION) { + if (adm_ctx->resource) { + drbd_msg_put_info(adm_ctx->reply_skb, "no resource name expected"); + return ERR_INVALID_REQUEST; + } + if (adm_ctx->device) { + drbd_msg_put_info(adm_ctx->reply_skb, "no minor number expected"); + return ERR_INVALID_REQUEST; + } + if (adm_ctx->my_addr && adm_ctx->peer_addr) + adm_ctx->connection = conn_get_by_addrs(nla_data(adm_ctx->my_addr), + nla_len(adm_ctx->my_addr), + nla_data(adm_ctx->peer_addr), + nla_len(adm_ctx->peer_addr)); + if (!adm_ctx->connection) { + drbd_msg_put_info(adm_ctx->reply_skb, "unknown connection"); + return ERR_INVALID_REQUEST; + } + } + + /* some more paranoia, if the request was over-determined */ + if (adm_ctx->device && adm_ctx->resource && + adm_ctx->device->resource != adm_ctx->resource) { + pr_warning("request: minor=%u, resource=%s; but that minor belongs to resource %s\n", + adm_ctx->minor, adm_ctx->resource->name, + adm_ctx->device->resource->name); + drbd_msg_put_info(adm_ctx->reply_skb, "minor exists in different resource"); + return ERR_INVALID_REQUEST; + } + if (adm_ctx->device && + adm_ctx->volume != VOLUME_UNSPECIFIED && + adm_ctx->volume != adm_ctx->device->vnr) { + pr_warning("request: minor=%u, volume=%u; but that minor is volume %u in %s\n", + adm_ctx->minor, adm_ctx->volume, + adm_ctx->device->vnr, + adm_ctx->device->resource->name); + drbd_msg_put_info(adm_ctx->reply_skb, "minor exists as different volume"); + return ERR_INVALID_REQUEST; + } + + /* still, provide adm_ctx->resource always, if possible. */ + if (!adm_ctx->resource) { + adm_ctx->resource = adm_ctx->device ? adm_ctx->device->resource + : adm_ctx->connection ? adm_ctx->connection->resource : NULL; + if (adm_ctx->resource) + kref_get(&adm_ctx->resource->kref); + } + + return NO_ERROR; + +fail: + nlmsg_free(adm_ctx->reply_skb); + adm_ctx->reply_skb = NULL; + return err; +} + +static int drbd_adm_finish(struct drbd_config_context *adm_ctx, + struct genl_info *info, int retcode) +{ + if (adm_ctx->device) { + kref_put(&adm_ctx->device->kref, drbd_destroy_device); + adm_ctx->device = NULL; + } + if (adm_ctx->connection) { + kref_put(&adm_ctx->connection->kref, &drbd_destroy_connection); + adm_ctx->connection = NULL; + } + if (adm_ctx->resource) { + kref_put(&adm_ctx->resource->kref, drbd_destroy_resource); + adm_ctx->resource = NULL; + } + + if (!adm_ctx->reply_skb) + return -ENOMEM; + + adm_ctx->reply_dh->ret_code = retcode; + drbd_adm_send_reply(adm_ctx->reply_skb, info); + return 0; +} + +static void setup_khelper_env(struct drbd_connection *connection, char **envp) +{ + char *afs; + + /* FIXME: A future version will not allow this case. */ + if (connection->my_addr_len == 0 || connection->peer_addr_len == 0) + return; + + switch (((struct sockaddr *)&connection->peer_addr)->sa_family) { + case AF_INET6: + afs = "ipv6"; + snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI6", + &((struct sockaddr_in6 *)&connection->peer_addr)->sin6_addr); break; -#define NL_BIT(pn, pr, member) \ - case pn: /* D_ASSERT( tag_type(tag) == TT_BIT ); */ \ - arg->member = *(char *)(tags) ? 1 : 0; \ + case AF_INET: + afs = "ipv4"; + snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI4", + &((struct sockaddr_in *)&connection->peer_addr)->sin_addr); break; -#define NL_STRING(pn, pr, member, len) \ - case pn: /* D_ASSERT( tag_type(tag) == TT_STRING ); */ \ - if (dlen > len) { \ - dev_err(DEV, "arg too long: %s (%u wanted, max len: %u bytes)\n", \ - #member, dlen, (unsigned int)len); \ - return 0; \ - } \ - arg->member ## _len = dlen; \ - memcpy(arg->member, tags, min_t(size_t, dlen, len)); \ - break; -#include "linux/drbd_nl.h" - -/* Generate the struct to tag_list functions */ -#define NL_PACKET(name, number, fields) \ -static unsigned short* \ -name ## _to_tags(struct drbd_conf *mdev, \ - struct name *arg, unsigned short *tags) __attribute__ ((unused)); \ -static unsigned short* \ -name ## _to_tags(struct drbd_conf *mdev, \ - struct name *arg, unsigned short *tags) \ -{ \ - fields \ - return tags; \ -} - -#define NL_INTEGER(pn, pr, member) \ - put_unaligned(pn | pr | TT_INTEGER, tags++); \ - put_unaligned(sizeof(int), tags++); \ - put_unaligned(arg->member, (int *)tags); \ - tags = (unsigned short *)((char *)tags+sizeof(int)); -#define NL_INT64(pn, pr, member) \ - put_unaligned(pn | pr | TT_INT64, tags++); \ - put_unaligned(sizeof(u64), tags++); \ - put_unaligned(arg->member, (u64 *)tags); \ - tags = (unsigned short *)((char *)tags+sizeof(u64)); -#define NL_BIT(pn, pr, member) \ - put_unaligned(pn | pr | TT_BIT, tags++); \ - put_unaligned(sizeof(char), tags++); \ - *(char *)tags = arg->member; \ - tags = (unsigned short *)((char *)tags+sizeof(char)); -#define NL_STRING(pn, pr, member, len) \ - put_unaligned(pn | pr | TT_STRING, tags++); \ - put_unaligned(arg->member ## _len, tags++); \ - memcpy(tags, arg->member, arg->member ## _len); \ - tags = (unsigned short *)((char *)tags + arg->member ## _len); -#include "linux/drbd_nl.h" - -void drbd_bcast_ev_helper(struct drbd_conf *mdev, char *helper_name); -void drbd_nl_send_reply(struct cn_msg *, int); - -int drbd_khelper(struct drbd_conf *mdev, char *cmd) + default: + afs = "ssocks"; + snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI4", + &((struct sockaddr_in *)&connection->peer_addr)->sin_addr); + } + snprintf(envp[3], 20, "DRBD_PEER_AF=%s", afs); +} + +int drbd_khelper(struct drbd_device *device, char *cmd) { char *envp[] = { "HOME=/", "TERM=linux", "PATH=/sbin:/usr/sbin:/bin:/usr/bin", - NULL, /* Will be set to address family */ - NULL, /* Will be set to address */ + (char[20]) { }, /* address family */ + (char[60]) { }, /* address */ NULL }; - - char mb[12], af[20], ad[60], *afs; + char mb[12]; char *argv[] = {usermode_helper, cmd, mb, NULL }; + struct drbd_connection *connection = first_peer_device(device)->connection; + struct sib_info sib; int ret; - snprintf(mb, 12, "minor-%d", mdev_to_minor(mdev)); + if (current == connection->worker.task) + set_bit(CALLBACK_PENDING, &connection->flags); - if (get_net_conf(mdev)) { - switch (((struct sockaddr *)mdev->net_conf->peer_addr)->sa_family) { - case AF_INET6: - afs = "ipv6"; - snprintf(ad, 60, "DRBD_PEER_ADDRESS=%pI6", - &((struct sockaddr_in6 *)mdev->net_conf->peer_addr)->sin6_addr); - break; - case AF_INET: - afs = "ipv4"; - snprintf(ad, 60, "DRBD_PEER_ADDRESS=%pI4", - &((struct sockaddr_in *)mdev->net_conf->peer_addr)->sin_addr); - break; - default: - afs = "ssocks"; - snprintf(ad, 60, "DRBD_PEER_ADDRESS=%pI4", - &((struct sockaddr_in *)mdev->net_conf->peer_addr)->sin_addr); - } - snprintf(af, 20, "DRBD_PEER_AF=%s", afs); - envp[3]=af; - envp[4]=ad; - put_net_conf(mdev); - } + snprintf(mb, 12, "minor-%d", device_to_minor(device)); + setup_khelper_env(connection, envp); /* The helper may take some time. * write out any unsynced meta data changes now */ - drbd_md_sync(mdev); - - dev_info(DEV, "helper command: %s %s %s\n", usermode_helper, cmd, mb); + drbd_md_sync(device); - drbd_bcast_ev_helper(mdev, cmd); - ret = call_usermodehelper(usermode_helper, argv, envp, 1); + drbd_info(device, "helper command: %s %s %s\n", usermode_helper, cmd, mb); + sib.sib_reason = SIB_HELPER_PRE; + sib.helper_name = cmd; + drbd_bcast_event(device, &sib); + ret = call_usermodehelper(usermode_helper, argv, envp, UMH_WAIT_PROC); if (ret) - dev_warn(DEV, "helper command: %s %s %s exit code %u (0x%x)\n", + drbd_warn(device, "helper command: %s %s %s exit code %u (0x%x)\n", usermode_helper, cmd, mb, (ret >> 8) & 0xff, ret); else - dev_info(DEV, "helper command: %s %s %s exit code %u (0x%x)\n", + drbd_info(device, "helper command: %s %s %s exit code %u (0x%x)\n", usermode_helper, cmd, mb, (ret >> 8) & 0xff, ret); + sib.sib_reason = SIB_HELPER_POST; + sib.helper_exit_code = ret; + drbd_bcast_event(device, &sib); + + if (current == connection->worker.task) + clear_bit(CALLBACK_PENDING, &connection->flags); if (ret < 0) /* Ignore any ERRNOs we got. */ ret = 0; @@ -195,138 +369,222 @@ int drbd_khelper(struct drbd_conf *mdev, char *cmd) return ret; } -enum drbd_disk_state drbd_try_outdate_peer(struct drbd_conf *mdev) +static int conn_khelper(struct drbd_connection *connection, char *cmd) +{ + char *envp[] = { "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + (char[20]) { }, /* address family */ + (char[60]) { }, /* address */ + NULL }; + char *resource_name = connection->resource->name; + char *argv[] = {usermode_helper, cmd, resource_name, NULL }; + int ret; + + setup_khelper_env(connection, envp); + conn_md_sync(connection); + + drbd_info(connection, "helper command: %s %s %s\n", usermode_helper, cmd, resource_name); + /* TODO: conn_bcast_event() ?? */ + + ret = call_usermodehelper(usermode_helper, argv, envp, UMH_WAIT_PROC); + if (ret) + drbd_warn(connection, "helper command: %s %s %s exit code %u (0x%x)\n", + usermode_helper, cmd, resource_name, + (ret >> 8) & 0xff, ret); + else + drbd_info(connection, "helper command: %s %s %s exit code %u (0x%x)\n", + usermode_helper, cmd, resource_name, + (ret >> 8) & 0xff, ret); + /* TODO: conn_bcast_event() ?? */ + + if (ret < 0) /* Ignore any ERRNOs we got. */ + ret = 0; + + return ret; +} + +static enum drbd_fencing_p highest_fencing_policy(struct drbd_connection *connection) +{ + enum drbd_fencing_p fp = FP_NOT_AVAIL; + struct drbd_peer_device *peer_device; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { + struct drbd_device *device = peer_device->device; + if (get_ldev_if_state(device, D_CONSISTENT)) { + struct disk_conf *disk_conf = + rcu_dereference(peer_device->device->ldev->disk_conf); + fp = max_t(enum drbd_fencing_p, fp, disk_conf->fencing); + put_ldev(device); + } + } + rcu_read_unlock(); + + if (fp == FP_NOT_AVAIL) { + /* IO Suspending works on the whole resource. + Do it only for one device. */ + vnr = 0; + peer_device = idr_get_next(&connection->peer_devices, &vnr); + drbd_change_state(peer_device->device, CS_VERBOSE | CS_HARD, NS(susp_fen, 0)); + } + + return fp; +} + +bool conn_try_outdate_peer(struct drbd_connection *connection) { + unsigned int connect_cnt; + union drbd_state mask = { }; + union drbd_state val = { }; + enum drbd_fencing_p fp; char *ex_to_string; int r; - enum drbd_disk_state nps; - enum drbd_fencing_p fp; - D_ASSERT(mdev->state.pdsk == D_UNKNOWN); + spin_lock_irq(&connection->resource->req_lock); + if (connection->cstate >= C_WF_REPORT_PARAMS) { + drbd_err(connection, "Expected cstate < C_WF_REPORT_PARAMS\n"); + spin_unlock_irq(&connection->resource->req_lock); + return false; + } - if (get_ldev_if_state(mdev, D_CONSISTENT)) { - fp = mdev->ldev->dc.fencing; - put_ldev(mdev); - } else { - dev_warn(DEV, "Not fencing peer, I'm not even Consistent myself.\n"); - nps = mdev->state.pdsk; + connect_cnt = connection->connect_cnt; + spin_unlock_irq(&connection->resource->req_lock); + + fp = highest_fencing_policy(connection); + switch (fp) { + case FP_NOT_AVAIL: + drbd_warn(connection, "Not fencing peer, I'm not even Consistent myself.\n"); goto out; + case FP_DONT_CARE: + return true; + default: ; } - r = drbd_khelper(mdev, "fence-peer"); + r = conn_khelper(connection, "fence-peer"); switch ((r>>8) & 0xff) { case 3: /* peer is inconsistent */ ex_to_string = "peer is inconsistent or worse"; - nps = D_INCONSISTENT; + mask.pdsk = D_MASK; + val.pdsk = D_INCONSISTENT; break; case 4: /* peer got outdated, or was already outdated */ ex_to_string = "peer was fenced"; - nps = D_OUTDATED; + mask.pdsk = D_MASK; + val.pdsk = D_OUTDATED; break; case 5: /* peer was down */ - if (mdev->state.disk == D_UP_TO_DATE) { + if (conn_highest_disk(connection) == D_UP_TO_DATE) { /* we will(have) create(d) a new UUID anyways... */ ex_to_string = "peer is unreachable, assumed to be dead"; - nps = D_OUTDATED; + mask.pdsk = D_MASK; + val.pdsk = D_OUTDATED; } else { ex_to_string = "peer unreachable, doing nothing since disk != UpToDate"; - nps = mdev->state.pdsk; } break; case 6: /* Peer is primary, voluntarily outdate myself. * This is useful when an unconnected R_SECONDARY is asked to * become R_PRIMARY, but finds the other peer being active. */ ex_to_string = "peer is active"; - dev_warn(DEV, "Peer is primary, outdating myself.\n"); - nps = D_UNKNOWN; - _drbd_request_state(mdev, NS(disk, D_OUTDATED), CS_WAIT_COMPLETE); + drbd_warn(connection, "Peer is primary, outdating myself.\n"); + mask.disk = D_MASK; + val.disk = D_OUTDATED; break; case 7: if (fp != FP_STONITH) - dev_err(DEV, "fence-peer() = 7 && fencing != Stonith !!!\n"); + drbd_err(connection, "fence-peer() = 7 && fencing != Stonith !!!\n"); ex_to_string = "peer was stonithed"; - nps = D_OUTDATED; + mask.pdsk = D_MASK; + val.pdsk = D_OUTDATED; break; default: /* The script is broken ... */ - nps = D_UNKNOWN; - dev_err(DEV, "fence-peer helper broken, returned %d\n", (r>>8)&0xff); - return nps; + drbd_err(connection, "fence-peer helper broken, returned %d\n", (r>>8)&0xff); + return false; /* Eventually leave IO frozen */ } - dev_info(DEV, "fence-peer helper returned %d (%s)\n", - (r>>8) & 0xff, ex_to_string); + drbd_info(connection, "fence-peer helper returned %d (%s)\n", + (r>>8) & 0xff, ex_to_string); -out: - if (mdev->state.susp_fen && nps >= D_UNKNOWN) { - /* The handler was not successful... unfreeze here, the - state engine can not unfreeze... */ - _drbd_request_state(mdev, NS(susp_fen, 0), CS_VERBOSE); + out: + + /* Not using + conn_request_state(connection, mask, val, CS_VERBOSE); + here, because we might were able to re-establish the connection in the + meantime. */ + spin_lock_irq(&connection->resource->req_lock); + if (connection->cstate < C_WF_REPORT_PARAMS && !test_bit(STATE_SENT, &connection->flags)) { + if (connection->connect_cnt != connect_cnt) + /* In case the connection was established and droped + while the fence-peer handler was running, ignore it */ + drbd_info(connection, "Ignoring fence-peer exit code\n"); + else + _conn_request_state(connection, mask, val, CS_VERBOSE); } + spin_unlock_irq(&connection->resource->req_lock); - return nps; + return conn_highest_pdsk(connection) <= D_OUTDATED; } static int _try_outdate_peer_async(void *data) { - struct drbd_conf *mdev = (struct drbd_conf *)data; - enum drbd_disk_state nps; - union drbd_state ns; - - nps = drbd_try_outdate_peer(mdev); + struct drbd_connection *connection = (struct drbd_connection *)data; - /* Not using - drbd_request_state(mdev, NS(pdsk, nps)); - here, because we might were able to re-establish the connection - in the meantime. This can only partially be solved in the state's - engine is_valid_state() and is_valid_state_transition() - functions. - - nps can be D_INCONSISTENT, D_OUTDATED or D_UNKNOWN. - pdsk == D_INCONSISTENT while conn >= C_CONNECTED is valid, - therefore we have to have the pre state change check here. - */ - spin_lock_irq(&mdev->req_lock); - ns = mdev->state; - if (ns.conn < C_WF_REPORT_PARAMS) { - ns.pdsk = nps; - _drbd_set_state(mdev, ns, CS_VERBOSE, NULL); - } - spin_unlock_irq(&mdev->req_lock); + conn_try_outdate_peer(connection); + kref_put(&connection->kref, drbd_destroy_connection); return 0; } -void drbd_try_outdate_peer_async(struct drbd_conf *mdev) +void conn_try_outdate_peer_async(struct drbd_connection *connection) { struct task_struct *opa; - opa = kthread_run(_try_outdate_peer_async, mdev, "drbd%d_a_helper", mdev_to_minor(mdev)); - if (IS_ERR(opa)) - dev_err(DEV, "out of mem, failed to invoke fence-peer helper\n"); + kref_get(&connection->kref); + /* We may just have force_sig()'ed this thread + * to get it out of some blocking network function. + * Clear signals; otherwise kthread_run(), which internally uses + * wait_on_completion_killable(), will mistake our pending signal + * for a new fatal signal and fail. */ + flush_signals(current); + opa = kthread_run(_try_outdate_peer_async, connection, "drbd_async_h"); + if (IS_ERR(opa)) { + drbd_err(connection, "out of mem, failed to invoke fence-peer helper\n"); + kref_put(&connection->kref, drbd_destroy_connection); + } } enum drbd_state_rv -drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force) +drbd_set_role(struct drbd_device *device, enum drbd_role new_role, int force) { const int max_tries = 4; enum drbd_state_rv rv = SS_UNKNOWN_ERROR; + struct net_conf *nc; int try = 0; int forced = 0; union drbd_state mask, val; - enum drbd_disk_state nps; - if (new_role == R_PRIMARY) - request_ping(mdev); /* Detect a dead peer ASAP */ + if (new_role == R_PRIMARY) { + struct drbd_connection *connection; + + /* Detect dead peers as soon as possible. */ + + rcu_read_lock(); + for_each_connection(connection, device->resource) + request_ping(connection); + rcu_read_unlock(); + } - mutex_lock(&mdev->state_mutex); + mutex_lock(device->state_mutex); mask.i = 0; mask.role = R_MASK; val.i = 0; val.role = new_role; while (try++ < max_tries) { - rv = _drbd_request_state(mdev, mask, val, CS_WAIT_COMPLETE); + rv = _drbd_request_state(device, mask, val, CS_WAIT_COMPLETE); /* in case we first succeeded to outdate, * but now suddenly could establish a connection */ @@ -337,8 +595,8 @@ drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force) } if (rv == SS_NO_UP_TO_DATE_DISK && force && - (mdev->state.disk < D_UP_TO_DATE && - mdev->state.disk >= D_INCONSISTENT)) { + (device->state.disk < D_UP_TO_DATE && + device->state.disk >= D_INCONSISTENT)) { mask.disk = D_MASK; val.disk = D_UP_TO_DATE; forced = 1; @@ -346,188 +604,194 @@ drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force) } if (rv == SS_NO_UP_TO_DATE_DISK && - mdev->state.disk == D_CONSISTENT && mask.pdsk == 0) { - D_ASSERT(mdev->state.pdsk == D_UNKNOWN); - nps = drbd_try_outdate_peer(mdev); + device->state.disk == D_CONSISTENT && mask.pdsk == 0) { + D_ASSERT(device, device->state.pdsk == D_UNKNOWN); - if (nps == D_OUTDATED || nps == D_INCONSISTENT) { + if (conn_try_outdate_peer(first_peer_device(device)->connection)) { val.disk = D_UP_TO_DATE; mask.disk = D_MASK; } - - val.pdsk = nps; - mask.pdsk = D_MASK; - continue; } if (rv == SS_NOTHING_TO_DO) - goto fail; + goto out; if (rv == SS_PRIMARY_NOP && mask.pdsk == 0) { - nps = drbd_try_outdate_peer(mdev); + if (!conn_try_outdate_peer(first_peer_device(device)->connection) && force) { + drbd_warn(device, "Forced into split brain situation!\n"); + mask.pdsk = D_MASK; + val.pdsk = D_OUTDATED; - if (force && nps > D_OUTDATED) { - dev_warn(DEV, "Forced into split brain situation!\n"); - nps = D_OUTDATED; } - - mask.pdsk = D_MASK; - val.pdsk = nps; - continue; } if (rv == SS_TWO_PRIMARIES) { /* Maybe the peer is detected as dead very soon... retry at most once more in this case. */ - schedule_timeout_interruptible((mdev->net_conf->ping_timeo+1)*HZ/10); + int timeo; + rcu_read_lock(); + nc = rcu_dereference(first_peer_device(device)->connection->net_conf); + timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1; + rcu_read_unlock(); + schedule_timeout_interruptible(timeo); if (try < max_tries) try = max_tries - 1; continue; } if (rv < SS_SUCCESS) { - rv = _drbd_request_state(mdev, mask, val, + rv = _drbd_request_state(device, mask, val, CS_VERBOSE + CS_WAIT_COMPLETE); if (rv < SS_SUCCESS) - goto fail; + goto out; } break; } if (rv < SS_SUCCESS) - goto fail; + goto out; if (forced) - dev_warn(DEV, "Forced to consider local data as UpToDate!\n"); + drbd_warn(device, "Forced to consider local data as UpToDate!\n"); /* Wait until nothing is on the fly :) */ - wait_event(mdev->misc_wait, atomic_read(&mdev->ap_pending_cnt) == 0); + wait_event(device->misc_wait, atomic_read(&device->ap_pending_cnt) == 0); + + /* FIXME also wait for all pending P_BARRIER_ACK? */ if (new_role == R_SECONDARY) { - set_disk_ro(mdev->vdisk, true); - if (get_ldev(mdev)) { - mdev->ldev->md.uuid[UI_CURRENT] &= ~(u64)1; - put_ldev(mdev); + set_disk_ro(device->vdisk, true); + if (get_ldev(device)) { + device->ldev->md.uuid[UI_CURRENT] &= ~(u64)1; + put_ldev(device); } } else { - if (get_net_conf(mdev)) { - mdev->net_conf->want_lose = 0; - put_net_conf(mdev); - } - set_disk_ro(mdev->vdisk, false); - if (get_ldev(mdev)) { - if (((mdev->state.conn < C_CONNECTED || - mdev->state.pdsk <= D_FAILED) - && mdev->ldev->md.uuid[UI_BITMAP] == 0) || forced) - drbd_uuid_new_current(mdev); - - mdev->ldev->md.uuid[UI_CURRENT] |= (u64)1; - put_ldev(mdev); + /* Called from drbd_adm_set_role only. + * We are still holding the conf_update mutex. */ + nc = first_peer_device(device)->connection->net_conf; + if (nc) + nc->discard_my_data = 0; /* without copy; single bit op is atomic */ + + set_disk_ro(device->vdisk, false); + if (get_ldev(device)) { + if (((device->state.conn < C_CONNECTED || + device->state.pdsk <= D_FAILED) + && device->ldev->md.uuid[UI_BITMAP] == 0) || forced) + drbd_uuid_new_current(device); + + device->ldev->md.uuid[UI_CURRENT] |= (u64)1; + put_ldev(device); } } /* writeout of activity log covered areas of the bitmap * to stable storage done in after state change already */ - if (mdev->state.conn >= C_WF_REPORT_PARAMS) { + if (device->state.conn >= C_WF_REPORT_PARAMS) { /* if this was forced, we should consider sync */ if (forced) - drbd_send_uuids(mdev); - drbd_send_state(mdev); + drbd_send_uuids(first_peer_device(device)); + drbd_send_current_state(first_peer_device(device)); } - drbd_md_sync(mdev); + drbd_md_sync(device); - kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE); - fail: - mutex_unlock(&mdev->state_mutex); + kobject_uevent(&disk_to_dev(device->vdisk)->kobj, KOBJ_CHANGE); +out: + mutex_unlock(device->state_mutex); return rv; } -static struct drbd_conf *ensure_mdev(int minor, int create) +static const char *from_attrs_err_to_txt(int err) { - struct drbd_conf *mdev; - - if (minor >= minor_count) - return NULL; - - mdev = minor_to_mdev(minor); - - if (!mdev && create) { - struct gendisk *disk = NULL; - mdev = drbd_new_device(minor); - - spin_lock_irq(&drbd_pp_lock); - if (minor_table[minor] == NULL) { - minor_table[minor] = mdev; - disk = mdev->vdisk; - mdev = NULL; - } /* else: we lost the race */ - spin_unlock_irq(&drbd_pp_lock); - - if (disk) /* we won the race above */ - /* in case we ever add a drbd_delete_device(), - * don't forget the del_gendisk! */ - add_disk(disk); - else /* we lost the race above */ - drbd_free_mdev(mdev); - - mdev = minor_to_mdev(minor); - } - - return mdev; + return err == -ENOMSG ? "required attribute missing" : + err == -EOPNOTSUPP ? "unknown mandatory attribute" : + err == -EEXIST ? "can not change invariant setting" : + "invalid attribute value"; } -static int drbd_nl_primary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info) { - struct primary primary_args; - - memset(&primary_args, 0, sizeof(struct primary)); - if (!primary_from_tags(mdev, nlp->tag_list, &primary_args)) { - reply->ret_code = ERR_MANDATORY_TAG; - return 0; - } + struct drbd_config_context adm_ctx; + struct set_role_parms parms; + int err; + enum drbd_ret_code retcode; - reply->ret_code = - drbd_set_role(mdev, R_PRIMARY, primary_args.primary_force); + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - return 0; -} + memset(&parms, 0, sizeof(parms)); + if (info->attrs[DRBD_NLA_SET_ROLE_PARMS]) { + err = set_role_parms_from_attrs(&parms, info); + if (err) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); + goto out; + } + } + genl_unlock(); + mutex_lock(&adm_ctx.resource->adm_mutex); -static int drbd_nl_secondary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) -{ - reply->ret_code = drbd_set_role(mdev, R_SECONDARY, 0); + if (info->genlhdr->cmd == DRBD_ADM_PRIMARY) + retcode = drbd_set_role(adm_ctx.device, R_PRIMARY, parms.assume_uptodate); + else + retcode = drbd_set_role(adm_ctx.device, R_SECONDARY, 0); + mutex_unlock(&adm_ctx.resource->adm_mutex); + genl_lock(); +out: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -/* initializes the md.*_offset members, so we are able to find - * the on disk meta data */ -static void drbd_md_set_sector_offsets(struct drbd_conf *mdev, +/* Initializes the md.*_offset members, so we are able to find + * the on disk meta data. + * + * We currently have two possible layouts: + * external: + * |----------- md_size_sect ------------------| + * [ 4k superblock ][ activity log ][ Bitmap ] + * | al_offset == 8 | + * | bm_offset = al_offset + X | + * ==> bitmap sectors = md_size_sect - bm_offset + * + * internal: + * |----------- md_size_sect ------------------| + * [data.....][ Bitmap ][ activity log ][ 4k superblock ] + * | al_offset < 0 | + * | bm_offset = al_offset - Y | + * ==> bitmap sectors = Y = al_offset - bm_offset + * + * Activity log size used to be fixed 32kB, + * but is about to become configurable. + */ +static void drbd_md_set_sector_offsets(struct drbd_device *device, struct drbd_backing_dev *bdev) { sector_t md_size_sect = 0; - switch (bdev->dc.meta_dev_idx) { + unsigned int al_size_sect = bdev->md.al_size_4k * 8; + + bdev->md.md_offset = drbd_md_ss(bdev); + + switch (bdev->md.meta_dev_idx) { default: /* v07 style fixed size indexed meta data */ - bdev->md.md_size_sect = MD_RESERVED_SECT; - bdev->md.md_offset = drbd_md_ss__(mdev, bdev); - bdev->md.al_offset = MD_AL_OFFSET; - bdev->md.bm_offset = MD_BM_OFFSET; + bdev->md.md_size_sect = MD_128MB_SECT; + bdev->md.al_offset = MD_4kB_SECT; + bdev->md.bm_offset = MD_4kB_SECT + al_size_sect; break; case DRBD_MD_INDEX_FLEX_EXT: /* just occupy the full device; unit: sectors */ bdev->md.md_size_sect = drbd_get_capacity(bdev->md_bdev); - bdev->md.md_offset = 0; - bdev->md.al_offset = MD_AL_OFFSET; - bdev->md.bm_offset = MD_BM_OFFSET; + bdev->md.al_offset = MD_4kB_SECT; + bdev->md.bm_offset = MD_4kB_SECT + al_size_sect; break; case DRBD_MD_INDEX_INTERNAL: case DRBD_MD_INDEX_FLEX_INT: - bdev->md.md_offset = drbd_md_ss__(mdev, bdev); /* al size is still fixed */ - bdev->md.al_offset = -MD_AL_MAX_SIZE; + bdev->md.al_offset = -al_size_sect; /* we need (slightly less than) ~ this much bitmap sectors: */ md_size_sect = drbd_get_capacity(bdev->backing_bdev); md_size_sect = ALIGN(md_size_sect, BM_SECT_PER_EXT); @@ -536,11 +800,11 @@ static void drbd_md_set_sector_offsets(struct drbd_conf *mdev, /* plus the "drbd meta data super block", * and the activity log; */ - md_size_sect += MD_BM_OFFSET; + md_size_sect += MD_4kB_SECT + al_size_sect; bdev->md.md_size_sect = md_size_sect; /* bitmap offset is adjusted by 'super' block size */ - bdev->md.bm_offset = -md_size_sect + MD_AL_OFFSET; + bdev->md.bm_offset = -md_size_sect + MD_4kB_SECT; break; } } @@ -575,36 +839,47 @@ char *ppsize(char *buf, unsigned long long size) * R_PRIMARY D_INCONSISTENT, and C_SYNC_TARGET: * peer may not initiate a resize. */ -void drbd_suspend_io(struct drbd_conf *mdev) +/* Note these are not to be confused with + * drbd_adm_suspend_io/drbd_adm_resume_io, + * which are (sub) state changes triggered by admin (drbdsetup), + * and can be long lived. + * This changes an device->flag, is triggered by drbd internals, + * and should be short-lived. */ +void drbd_suspend_io(struct drbd_device *device) { - set_bit(SUSPEND_IO, &mdev->flags); - if (is_susp(mdev->state)) + set_bit(SUSPEND_IO, &device->flags); + if (drbd_suspended(device)) return; - wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt)); + wait_event(device->misc_wait, !atomic_read(&device->ap_bio_cnt)); } -void drbd_resume_io(struct drbd_conf *mdev) +void drbd_resume_io(struct drbd_device *device) { - clear_bit(SUSPEND_IO, &mdev->flags); - wake_up(&mdev->misc_wait); + clear_bit(SUSPEND_IO, &device->flags); + wake_up(&device->misc_wait); } /** * drbd_determine_dev_size() - Sets the right device size obeying all constraints - * @mdev: DRBD device. + * @device: DRBD device. * * Returns 0 on success, negative return values indicate errors. * You should call drbd_md_sync() after calling this function. */ -enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds_flags flags) __must_hold(local) +enum determine_dev_size +drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct resize_parms *rs) __must_hold(local) { sector_t prev_first_sect, prev_size; /* previous meta location */ - sector_t la_size; + sector_t la_size_sect, u_size; + struct drbd_md *md = &device->ldev->md; + u32 prev_al_stripe_size_4k; + u32 prev_al_stripes; sector_t size; char ppb[10]; + void *buffer; int md_moved, la_size_changed; - enum determine_dev_size rv = unchanged; + enum determine_dev_size rv = DS_UNCHANGED; /* race: * application request passes inc_ap_bio, @@ -615,101 +890,153 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds * Suspend IO right here. * still lock the act_log to not trigger ASSERTs there. */ - drbd_suspend_io(mdev); + drbd_suspend_io(device); + buffer = drbd_md_get_buffer(device); /* Lock meta-data IO */ + if (!buffer) { + drbd_resume_io(device); + return DS_ERROR; + } /* no wait necessary anymore, actually we could assert that */ - wait_event(mdev->al_wait, lc_try_lock(mdev->act_log)); + wait_event(device->al_wait, lc_try_lock(device->act_log)); + + prev_first_sect = drbd_md_first_sector(device->ldev); + prev_size = device->ldev->md.md_size_sect; + la_size_sect = device->ldev->md.la_size_sect; - prev_first_sect = drbd_md_first_sector(mdev->ldev); - prev_size = mdev->ldev->md.md_size_sect; - la_size = mdev->ldev->md.la_size_sect; + if (rs) { + /* rs is non NULL if we should change the AL layout only */ - /* TODO: should only be some assert here, not (re)init... */ - drbd_md_set_sector_offsets(mdev, mdev->ldev); + prev_al_stripes = md->al_stripes; + prev_al_stripe_size_4k = md->al_stripe_size_4k; + + md->al_stripes = rs->al_stripes; + md->al_stripe_size_4k = rs->al_stripe_size / 4; + md->al_size_4k = (u64)rs->al_stripes * rs->al_stripe_size / 4; + } - size = drbd_new_dev_size(mdev, mdev->ldev, flags & DDSF_FORCED); + drbd_md_set_sector_offsets(device, device->ldev); + + rcu_read_lock(); + u_size = rcu_dereference(device->ldev->disk_conf)->disk_size; + rcu_read_unlock(); + size = drbd_new_dev_size(device, device->ldev, u_size, flags & DDSF_FORCED); + + if (size < la_size_sect) { + if (rs && u_size == 0) { + /* Remove "rs &&" later. This check should always be active, but + right now the receiver expects the permissive behavior */ + drbd_warn(device, "Implicit shrink not allowed. " + "Use --size=%llus for explicit shrink.\n", + (unsigned long long)size); + rv = DS_ERROR_SHRINK; + } + if (u_size > size) + rv = DS_ERROR_SPACE_MD; + if (rv != DS_UNCHANGED) + goto err_out; + } - if (drbd_get_capacity(mdev->this_bdev) != size || - drbd_bm_capacity(mdev) != size) { + if (drbd_get_capacity(device->this_bdev) != size || + drbd_bm_capacity(device) != size) { int err; - err = drbd_bm_resize(mdev, size, !(flags & DDSF_NO_RESYNC)); + err = drbd_bm_resize(device, size, !(flags & DDSF_NO_RESYNC)); if (unlikely(err)) { /* currently there is only one error: ENOMEM! */ - size = drbd_bm_capacity(mdev)>>1; + size = drbd_bm_capacity(device)>>1; if (size == 0) { - dev_err(DEV, "OUT OF MEMORY! " + drbd_err(device, "OUT OF MEMORY! " "Could not allocate bitmap!\n"); } else { - dev_err(DEV, "BM resizing failed. " + drbd_err(device, "BM resizing failed. " "Leaving size unchanged at size = %lu KB\n", (unsigned long)size); } - rv = dev_size_error; + rv = DS_ERROR; } /* racy, see comments above. */ - drbd_set_my_capacity(mdev, size); - mdev->ldev->md.la_size_sect = size; - dev_info(DEV, "size = %s (%llu KB)\n", ppsize(ppb, size>>1), + drbd_set_my_capacity(device, size); + device->ldev->md.la_size_sect = size; + drbd_info(device, "size = %s (%llu KB)\n", ppsize(ppb, size>>1), (unsigned long long)size>>1); } - if (rv == dev_size_error) - goto out; + if (rv <= DS_ERROR) + goto err_out; - la_size_changed = (la_size != mdev->ldev->md.la_size_sect); + la_size_changed = (la_size_sect != device->ldev->md.la_size_sect); - md_moved = prev_first_sect != drbd_md_first_sector(mdev->ldev) - || prev_size != mdev->ldev->md.md_size_sect; + md_moved = prev_first_sect != drbd_md_first_sector(device->ldev) + || prev_size != device->ldev->md.md_size_sect; - if (la_size_changed || md_moved) { - int err; + if (la_size_changed || md_moved || rs) { + u32 prev_flags; - drbd_al_shrink(mdev); /* All extents inactive. */ - dev_info(DEV, "Writing the whole bitmap, %s\n", + drbd_al_shrink(device); /* All extents inactive. */ + + prev_flags = md->flags; + md->flags &= ~MDF_PRIMARY_IND; + drbd_md_write(device, buffer); + + drbd_info(device, "Writing the whole bitmap, %s\n", la_size_changed && md_moved ? "size changed and md moved" : la_size_changed ? "size changed" : "md moved"); /* next line implicitly does drbd_suspend_io()+drbd_resume_io() */ - err = drbd_bitmap_io(mdev, &drbd_bm_write, - "size changed", BM_LOCKED_MASK); - if (err) { - rv = dev_size_error; - goto out; - } - drbd_md_mark_dirty(mdev); + drbd_bitmap_io(device, md_moved ? &drbd_bm_write_all : &drbd_bm_write, + "size changed", BM_LOCKED_MASK); + drbd_initialize_al(device, buffer); + + md->flags = prev_flags; + drbd_md_write(device, buffer); + + if (rs) + drbd_info(device, "Changed AL layout to al-stripes = %d, al-stripe-size-kB = %d\n", + md->al_stripes, md->al_stripe_size_4k * 4); } - if (size > la_size) - rv = grew; - if (size < la_size) - rv = shrunk; -out: - lc_unlock(mdev->act_log); - wake_up(&mdev->al_wait); - drbd_resume_io(mdev); + if (size > la_size_sect) + rv = la_size_sect ? DS_GREW : DS_GREW_FROM_ZERO; + if (size < la_size_sect) + rv = DS_SHRUNK; + + if (0) { + err_out: + if (rs) { + md->al_stripes = prev_al_stripes; + md->al_stripe_size_4k = prev_al_stripe_size_4k; + md->al_size_4k = (u64)prev_al_stripes * prev_al_stripe_size_4k; + + drbd_md_set_sector_offsets(device, device->ldev); + } + } + lc_unlock(device->act_log); + wake_up(&device->al_wait); + drbd_md_put_buffer(device); + drbd_resume_io(device); return rv; } sector_t -drbd_new_dev_size(struct drbd_conf *mdev, struct drbd_backing_dev *bdev, int assume_peer_has_space) +drbd_new_dev_size(struct drbd_device *device, struct drbd_backing_dev *bdev, + sector_t u_size, int assume_peer_has_space) { - sector_t p_size = mdev->p_size; /* partner's disk size. */ - sector_t la_size = bdev->md.la_size_sect; /* last agreed size. */ + sector_t p_size = device->p_size; /* partner's disk size. */ + sector_t la_size_sect = bdev->md.la_size_sect; /* last agreed size. */ sector_t m_size; /* my size */ - sector_t u_size = bdev->dc.disk_size; /* size requested by user. */ sector_t size = 0; m_size = drbd_get_max_capacity(bdev); - if (mdev->state.conn < C_CONNECTED && assume_peer_has_space) { - dev_warn(DEV, "Resize while not connected was forced by the user!\n"); + if (device->state.conn < C_CONNECTED && assume_peer_has_space) { + drbd_warn(device, "Resize while not connected was forced by the user!\n"); p_size = m_size; } if (p_size && m_size) { size = min_t(sector_t, p_size, m_size); } else { - if (la_size) { - size = la_size; + if (la_size_sect) { + size = la_size_sect; if (m_size && m_size < size) size = m_size; if (p_size && p_size < size) @@ -723,11 +1050,11 @@ drbd_new_dev_size(struct drbd_conf *mdev, struct drbd_backing_dev *bdev, int ass } if (size == 0) - dev_err(DEV, "Both nodes diskless!\n"); + drbd_err(device, "Both nodes diskless!\n"); if (u_size) { if (u_size > size) - dev_err(DEV, "Requested disk size is too big (%lu > %lu)\n", + drbd_err(device, "Requested disk size is too big (%lu > %lu)\n", (unsigned long)u_size>>1, (unsigned long)size>>1); else size = u_size; @@ -738,72 +1065,74 @@ drbd_new_dev_size(struct drbd_conf *mdev, struct drbd_backing_dev *bdev, int ass /** * drbd_check_al_size() - Ensures that the AL is of the right size - * @mdev: DRBD device. + * @device: DRBD device. * * Returns -EBUSY if current al lru is still used, -ENOMEM when allocation * failed, and 0 on success. You should call drbd_md_sync() after you called * this function. */ -static int drbd_check_al_size(struct drbd_conf *mdev) +static int drbd_check_al_size(struct drbd_device *device, struct disk_conf *dc) { struct lru_cache *n, *t; struct lc_element *e; unsigned int in_use; int i; - ERR_IF(mdev->sync_conf.al_extents < 7) - mdev->sync_conf.al_extents = 127; - - if (mdev->act_log && - mdev->act_log->nr_elements == mdev->sync_conf.al_extents) + if (device->act_log && + device->act_log->nr_elements == dc->al_extents) return 0; in_use = 0; - t = mdev->act_log; - n = lc_create("act_log", drbd_al_ext_cache, - mdev->sync_conf.al_extents, sizeof(struct lc_element), 0); + t = device->act_log; + n = lc_create("act_log", drbd_al_ext_cache, AL_UPDATES_PER_TRANSACTION, + dc->al_extents, sizeof(struct lc_element), 0); if (n == NULL) { - dev_err(DEV, "Cannot allocate act_log lru!\n"); + drbd_err(device, "Cannot allocate act_log lru!\n"); return -ENOMEM; } - spin_lock_irq(&mdev->al_lock); + spin_lock_irq(&device->al_lock); if (t) { for (i = 0; i < t->nr_elements; i++) { e = lc_element_by_index(t, i); if (e->refcnt) - dev_err(DEV, "refcnt(%d)==%d\n", + drbd_err(device, "refcnt(%d)==%d\n", e->lc_number, e->refcnt); in_use += e->refcnt; } } if (!in_use) - mdev->act_log = n; - spin_unlock_irq(&mdev->al_lock); + device->act_log = n; + spin_unlock_irq(&device->al_lock); if (in_use) { - dev_err(DEV, "Activity log still in use!\n"); + drbd_err(device, "Activity log still in use!\n"); lc_destroy(n); return -EBUSY; } else { if (t) lc_destroy(t); } - drbd_md_mark_dirty(mdev); /* we changed mdev->act_log->nr_elemens */ + drbd_md_mark_dirty(device); /* we changed device->act_log->nr_elemens */ return 0; } -static void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_bio_size) +static void drbd_setup_queue_param(struct drbd_device *device, unsigned int max_bio_size) { - struct request_queue * const q = mdev->rq_queue; - int max_hw_sectors = max_bio_size >> 9; - int max_segments = 0; + struct request_queue * const q = device->rq_queue; + unsigned int max_hw_sectors = max_bio_size >> 9; + unsigned int max_segments = 0; + struct request_queue *b = NULL; - if (get_ldev_if_state(mdev, D_ATTACHING)) { - struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue; + if (get_ldev_if_state(device, D_ATTACHING)) { + b = device->ldev->backing_bdev->bd_disk->queue; max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9); - max_segments = mdev->ldev->dc.max_bio_bvecs; - put_ldev(mdev); + rcu_read_lock(); + max_segments = rcu_dereference(device->ldev->disk_conf)->max_bio_bvecs; + rcu_read_unlock(); + + blk_set_stacking_limits(&q->limits); + blk_queue_max_write_same_sectors(q, 0); } blk_queue_logical_block_size(q, 512); @@ -812,134 +1141,331 @@ static void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_bio_ blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS); blk_queue_segment_boundary(q, PAGE_CACHE_SIZE-1); - if (get_ldev_if_state(mdev, D_ATTACHING)) { - struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue; + if (b) { + struct drbd_connection *connection = first_peer_device(device)->connection; + + if (blk_queue_discard(b) && + (connection->cstate < C_CONNECTED || connection->agreed_features & FF_TRIM)) { + /* For now, don't allow more than one activity log extent worth of data + * to be discarded in one go. We may need to rework drbd_al_begin_io() + * to allow for even larger discard ranges */ + q->limits.max_discard_sectors = DRBD_MAX_DISCARD_SECTORS; + + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); + /* REALLY? Is stacking secdiscard "legal"? */ + if (blk_queue_secdiscard(b)) + queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q); + } else { + q->limits.max_discard_sectors = 0; + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); + queue_flag_clear_unlocked(QUEUE_FLAG_SECDISCARD, q); + } blk_queue_stack_limits(q, b); if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) { - dev_info(DEV, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n", + drbd_info(device, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n", q->backing_dev_info.ra_pages, b->backing_dev_info.ra_pages); q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages; } - put_ldev(mdev); + put_ldev(device); } } -void drbd_reconsider_max_bio_size(struct drbd_conf *mdev) +void drbd_reconsider_max_bio_size(struct drbd_device *device) { - int now, new, local, peer; + unsigned int now, new, local, peer; - now = queue_max_hw_sectors(mdev->rq_queue) << 9; - local = mdev->local_max_bio_size; /* Eventually last known value, from volatile memory */ - peer = mdev->peer_max_bio_size; /* Eventually last known value, from meta data */ + now = queue_max_hw_sectors(device->rq_queue) << 9; + local = device->local_max_bio_size; /* Eventually last known value, from volatile memory */ + peer = device->peer_max_bio_size; /* Eventually last known value, from meta data */ - if (get_ldev_if_state(mdev, D_ATTACHING)) { - local = queue_max_hw_sectors(mdev->ldev->backing_bdev->bd_disk->queue) << 9; - mdev->local_max_bio_size = local; - put_ldev(mdev); + if (get_ldev_if_state(device, D_ATTACHING)) { + local = queue_max_hw_sectors(device->ldev->backing_bdev->bd_disk->queue) << 9; + device->local_max_bio_size = local; + put_ldev(device); } + local = min(local, DRBD_MAX_BIO_SIZE); /* We may ignore peer limits if the peer is modern enough. Because new from 8.3.8 onwards the peer can use multiple BIOs for a single peer_request */ - if (mdev->state.conn >= C_CONNECTED) { - if (mdev->agreed_pro_version < 94) - peer = mdev->peer_max_bio_size; - else if (mdev->agreed_pro_version == 94) + if (device->state.conn >= C_WF_REPORT_PARAMS) { + if (first_peer_device(device)->connection->agreed_pro_version < 94) + peer = min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET); + /* Correct old drbd (up to 8.3.7) if it believes it can do more than 32KiB */ + else if (first_peer_device(device)->connection->agreed_pro_version == 94) peer = DRBD_MAX_SIZE_H80_PACKET; - else /* drbd 8.3.8 onwards */ + else if (first_peer_device(device)->connection->agreed_pro_version < 100) + peer = DRBD_MAX_BIO_SIZE_P95; /* drbd 8.3.8 onwards, before 8.4.0 */ + else peer = DRBD_MAX_BIO_SIZE; - } - new = min_t(int, local, peer); + /* We may later detach and re-attach on a disconnected Primary. + * Avoid this setting to jump back in that case. + * We want to store what we know the peer DRBD can handle, + * not what the peer IO backend can handle. */ + if (peer > device->peer_max_bio_size) + device->peer_max_bio_size = peer; + } + new = min(local, peer); - if (mdev->state.role == R_PRIMARY && new < now) - dev_err(DEV, "ASSERT FAILED new < now; (%d < %d)\n", new, now); + if (device->state.role == R_PRIMARY && new < now) + drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n", new, now); if (new != now) - dev_info(DEV, "max BIO size = %u\n", new); + drbd_info(device, "max BIO size = %u\n", new); - drbd_setup_queue_param(mdev, new); + drbd_setup_queue_param(device, new); } -/* serialize deconfig (worker exiting, doing cleanup) - * and reconfig (drbdsetup disk, drbdsetup net) - * - * Wait for a potentially exiting worker, then restart it, - * or start a new one. Flush any pending work, there may still be an - * after_state_change queued. - */ -static void drbd_reconfig_start(struct drbd_conf *mdev) +/* Starts the worker thread */ +static void conn_reconfig_start(struct drbd_connection *connection) { - wait_event(mdev->state_wait, !test_and_set_bit(CONFIG_PENDING, &mdev->flags)); - wait_event(mdev->state_wait, !test_bit(DEVICE_DYING, &mdev->flags)); - drbd_thread_start(&mdev->worker); - drbd_flush_workqueue(mdev); + drbd_thread_start(&connection->worker); + drbd_flush_workqueue(&connection->sender_work); } -/* if still unconfigured, stops worker again. - * if configured now, clears CONFIG_PENDING. - * wakes potential waiters */ -static void drbd_reconfig_done(struct drbd_conf *mdev) +/* if still unconfigured, stops worker again. */ +static void conn_reconfig_done(struct drbd_connection *connection) { - spin_lock_irq(&mdev->req_lock); - if (mdev->state.disk == D_DISKLESS && - mdev->state.conn == C_STANDALONE && - mdev->state.role == R_SECONDARY) { - set_bit(DEVICE_DYING, &mdev->flags); - drbd_thread_stop_nowait(&mdev->worker); - } else - clear_bit(CONFIG_PENDING, &mdev->flags); - spin_unlock_irq(&mdev->req_lock); - wake_up(&mdev->state_wait); + bool stop_threads; + spin_lock_irq(&connection->resource->req_lock); + stop_threads = conn_all_vols_unconf(connection) && + connection->cstate == C_STANDALONE; + spin_unlock_irq(&connection->resource->req_lock); + if (stop_threads) { + /* asender is implicitly stopped by receiver + * in conn_disconnect() */ + drbd_thread_stop(&connection->receiver); + drbd_thread_stop(&connection->worker); + } } /* Make sure IO is suspended before calling this function(). */ -static void drbd_suspend_al(struct drbd_conf *mdev) +static void drbd_suspend_al(struct drbd_device *device) { int s = 0; - if (lc_try_lock(mdev->act_log)) { - drbd_al_shrink(mdev); - lc_unlock(mdev->act_log); - } else { - dev_warn(DEV, "Failed to lock al in drbd_suspend_al()\n"); + if (!lc_try_lock(device->act_log)) { + drbd_warn(device, "Failed to lock al in drbd_suspend_al()\n"); return; } - spin_lock_irq(&mdev->req_lock); - if (mdev->state.conn < C_CONNECTED) - s = !test_and_set_bit(AL_SUSPENDED, &mdev->flags); - - spin_unlock_irq(&mdev->req_lock); + drbd_al_shrink(device); + spin_lock_irq(&device->resource->req_lock); + if (device->state.conn < C_CONNECTED) + s = !test_and_set_bit(AL_SUSPENDED, &device->flags); + spin_unlock_irq(&device->resource->req_lock); + lc_unlock(device->act_log); if (s) - dev_info(DEV, "Suspended AL updates\n"); + drbd_info(device, "Suspended AL updates\n"); +} + + +static bool should_set_defaults(struct genl_info *info) +{ + unsigned flags = ((struct drbd_genlmsghdr*)info->userhdr)->flags; + return 0 != (flags & DRBD_GENL_F_SET_DEFAULTS); } -/* does always return 0; - * interesting return code is in reply->ret_code */ -static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +static unsigned int drbd_al_extents_max(struct drbd_backing_dev *bdev) { + /* This is limited by 16 bit "slot" numbers, + * and by available on-disk context storage. + * + * Also (u16)~0 is special (denotes a "free" extent). + * + * One transaction occupies one 4kB on-disk block, + * we have n such blocks in the on disk ring buffer, + * the "current" transaction may fail (n-1), + * and there is 919 slot numbers context information per transaction. + * + * 72 transaction blocks amounts to more than 2**16 context slots, + * so cap there first. + */ + const unsigned int max_al_nr = DRBD_AL_EXTENTS_MAX; + const unsigned int sufficient_on_disk = + (max_al_nr + AL_CONTEXT_PER_TRANSACTION -1) + /AL_CONTEXT_PER_TRANSACTION; + + unsigned int al_size_4k = bdev->md.al_size_4k; + + if (al_size_4k > sufficient_on_disk) + return max_al_nr; + + return (al_size_4k - 1) * AL_CONTEXT_PER_TRANSACTION; +} + +int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) +{ + struct drbd_config_context adm_ctx; + enum drbd_ret_code retcode; + struct drbd_device *device; + struct disk_conf *new_disk_conf, *old_disk_conf; + struct fifo_buffer *old_plan = NULL, *new_plan = NULL; + int err, fifo_size; + + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto finish; + + device = adm_ctx.device; + mutex_lock(&adm_ctx.resource->adm_mutex); + + /* we also need a disk + * to change the options on */ + if (!get_ldev(device)) { + retcode = ERR_NO_DISK; + goto out; + } + + new_disk_conf = kmalloc(sizeof(struct disk_conf), GFP_KERNEL); + if (!new_disk_conf) { + retcode = ERR_NOMEM; + goto fail; + } + + mutex_lock(&device->resource->conf_update); + old_disk_conf = device->ldev->disk_conf; + *new_disk_conf = *old_disk_conf; + if (should_set_defaults(info)) + set_disk_conf_defaults(new_disk_conf); + + err = disk_conf_from_attrs_for_change(new_disk_conf, info); + if (err && err != -ENOMSG) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); + goto fail_unlock; + } + + if (!expect(new_disk_conf->resync_rate >= 1)) + new_disk_conf->resync_rate = 1; + + if (new_disk_conf->al_extents < DRBD_AL_EXTENTS_MIN) + new_disk_conf->al_extents = DRBD_AL_EXTENTS_MIN; + if (new_disk_conf->al_extents > drbd_al_extents_max(device->ldev)) + new_disk_conf->al_extents = drbd_al_extents_max(device->ldev); + + if (new_disk_conf->c_plan_ahead > DRBD_C_PLAN_AHEAD_MAX) + new_disk_conf->c_plan_ahead = DRBD_C_PLAN_AHEAD_MAX; + + fifo_size = (new_disk_conf->c_plan_ahead * 10 * SLEEP_TIME) / HZ; + if (fifo_size != device->rs_plan_s->size) { + new_plan = fifo_alloc(fifo_size); + if (!new_plan) { + drbd_err(device, "kmalloc of fifo_buffer failed"); + retcode = ERR_NOMEM; + goto fail_unlock; + } + } + + drbd_suspend_io(device); + wait_event(device->al_wait, lc_try_lock(device->act_log)); + drbd_al_shrink(device); + err = drbd_check_al_size(device, new_disk_conf); + lc_unlock(device->act_log); + wake_up(&device->al_wait); + drbd_resume_io(device); + + if (err) { + retcode = ERR_NOMEM; + goto fail_unlock; + } + + write_lock_irq(&global_state_lock); + retcode = drbd_resync_after_valid(device, new_disk_conf->resync_after); + if (retcode == NO_ERROR) { + rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); + drbd_resync_after_changed(device); + } + write_unlock_irq(&global_state_lock); + + if (retcode != NO_ERROR) + goto fail_unlock; + + if (new_plan) { + old_plan = device->rs_plan_s; + rcu_assign_pointer(device->rs_plan_s, new_plan); + } + + mutex_unlock(&device->resource->conf_update); + + if (new_disk_conf->al_updates) + device->ldev->md.flags &= ~MDF_AL_DISABLED; + else + device->ldev->md.flags |= MDF_AL_DISABLED; + + if (new_disk_conf->md_flushes) + clear_bit(MD_NO_FUA, &device->flags); + else + set_bit(MD_NO_FUA, &device->flags); + + drbd_bump_write_ordering(first_peer_device(device)->connection, WO_bdev_flush); + + drbd_md_sync(device); + + if (device->state.conn >= C_CONNECTED) { + struct drbd_peer_device *peer_device; + + for_each_peer_device(peer_device, device) + drbd_send_sync_param(peer_device); + } + + synchronize_rcu(); + kfree(old_disk_conf); + kfree(old_plan); + mod_timer(&device->request_timer, jiffies + HZ); + goto success; + +fail_unlock: + mutex_unlock(&device->resource->conf_update); + fail: + kfree(new_disk_conf); + kfree(new_plan); +success: + put_ldev(device); + out: + mutex_unlock(&adm_ctx.resource->adm_mutex); + finish: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; +} + +int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) +{ + struct drbd_config_context adm_ctx; + struct drbd_device *device; + int err; enum drbd_ret_code retcode; enum determine_dev_size dd; sector_t max_possible_sectors; sector_t min_md_device_sectors; struct drbd_backing_dev *nbc = NULL; /* new_backing_conf */ + struct disk_conf *new_disk_conf = NULL; struct block_device *bdev; struct lru_cache *resync_lru = NULL; + struct fifo_buffer *new_plan = NULL; union drbd_state ns, os; enum drbd_state_rv rv; - int cp_discovered = 0; - int logical_block_size; + struct net_conf *nc; - drbd_reconfig_start(mdev); + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto finish; + + device = adm_ctx.device; + mutex_lock(&adm_ctx.resource->adm_mutex); + conn_reconfig_start(first_peer_device(device)->connection); /* if you want to reconfigure, please tear down first */ - if (mdev->state.disk > D_DISKLESS) { + if (device->state.disk > D_DISKLESS) { retcode = ERR_DISK_CONFIGURED; goto fail; } @@ -947,43 +1473,76 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp * drbd_ldev_destroy is done already, we may end up here very fast, * e.g. if someone calls attach from the on-io-error handler, * to realize a "hot spare" feature (not that I'd recommend that) */ - wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt)); + wait_event(device->misc_wait, !atomic_read(&device->local_cnt)); + + /* make sure there is no leftover from previous force-detach attempts */ + clear_bit(FORCE_DETACH, &device->flags); + clear_bit(WAS_IO_ERROR, &device->flags); + clear_bit(WAS_READ_ERROR, &device->flags); - /* allocation not in the IO path, cqueue thread context */ + /* and no leftover from previously aborted resync or verify, either */ + device->rs_total = 0; + device->rs_failed = 0; + atomic_set(&device->rs_pending_cnt, 0); + + /* allocation not in the IO path, drbdsetup context */ nbc = kzalloc(sizeof(struct drbd_backing_dev), GFP_KERNEL); if (!nbc) { retcode = ERR_NOMEM; goto fail; } + spin_lock_init(&nbc->md.uuid_lock); - nbc->dc.disk_size = DRBD_DISK_SIZE_SECT_DEF; - nbc->dc.on_io_error = DRBD_ON_IO_ERROR_DEF; - nbc->dc.fencing = DRBD_FENCING_DEF; - nbc->dc.max_bio_bvecs = DRBD_MAX_BIO_BVECS_DEF; + new_disk_conf = kzalloc(sizeof(struct disk_conf), GFP_KERNEL); + if (!new_disk_conf) { + retcode = ERR_NOMEM; + goto fail; + } + nbc->disk_conf = new_disk_conf; - if (!disk_conf_from_tags(mdev, nlp->tag_list, &nbc->dc)) { + set_disk_conf_defaults(new_disk_conf); + err = disk_conf_from_attrs(new_disk_conf, info); + if (err) { retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); goto fail; } - if (nbc->dc.meta_dev_idx < DRBD_MD_INDEX_FLEX_INT) { + if (new_disk_conf->c_plan_ahead > DRBD_C_PLAN_AHEAD_MAX) + new_disk_conf->c_plan_ahead = DRBD_C_PLAN_AHEAD_MAX; + + new_plan = fifo_alloc((new_disk_conf->c_plan_ahead * 10 * SLEEP_TIME) / HZ); + if (!new_plan) { + retcode = ERR_NOMEM; + goto fail; + } + + if (new_disk_conf->meta_dev_idx < DRBD_MD_INDEX_FLEX_INT) { retcode = ERR_MD_IDX_INVALID; goto fail; } - if (get_net_conf(mdev)) { - int prot = mdev->net_conf->wire_protocol; - put_net_conf(mdev); - if (nbc->dc.fencing == FP_STONITH && prot == DRBD_PROT_A) { + write_lock_irq(&global_state_lock); + retcode = drbd_resync_after_valid(device, new_disk_conf->resync_after); + write_unlock_irq(&global_state_lock); + if (retcode != NO_ERROR) + goto fail; + + rcu_read_lock(); + nc = rcu_dereference(first_peer_device(device)->connection->net_conf); + if (nc) { + if (new_disk_conf->fencing == FP_STONITH && nc->wire_protocol == DRBD_PROT_A) { + rcu_read_unlock(); retcode = ERR_STONITH_AND_PROT_A; goto fail; } } + rcu_read_unlock(); - bdev = blkdev_get_by_path(nbc->dc.backing_dev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, mdev); + bdev = blkdev_get_by_path(new_disk_conf->backing_dev, + FMODE_READ | FMODE_WRITE | FMODE_EXCL, device); if (IS_ERR(bdev)) { - dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.backing_dev, + drbd_err(device, "open(\"%s\") failed with %ld\n", new_disk_conf->backing_dev, PTR_ERR(bdev)); retcode = ERR_OPEN_DISK; goto fail; @@ -998,12 +1557,12 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp * should check it for you already; but if you don't, or * someone fooled it, we need to double check here) */ - bdev = blkdev_get_by_path(nbc->dc.meta_dev, + bdev = blkdev_get_by_path(new_disk_conf->meta_dev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, - (nbc->dc.meta_dev_idx < 0) ? - (void *)mdev : (void *)drbd_m_holder); + (new_disk_conf->meta_dev_idx < 0) ? + (void *)device : (void *)drbd_m_holder); if (IS_ERR(bdev)) { - dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.meta_dev, + drbd_err(device, "open(\"%s\") failed with %ld\n", new_disk_conf->meta_dev, PTR_ERR(bdev)); retcode = ERR_OPEN_MD_DISK; goto fail; @@ -1011,43 +1570,51 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp nbc->md_bdev = bdev; if ((nbc->backing_bdev == nbc->md_bdev) != - (nbc->dc.meta_dev_idx == DRBD_MD_INDEX_INTERNAL || - nbc->dc.meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)) { + (new_disk_conf->meta_dev_idx == DRBD_MD_INDEX_INTERNAL || + new_disk_conf->meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)) { retcode = ERR_MD_IDX_INVALID; goto fail; } resync_lru = lc_create("resync", drbd_bm_ext_cache, - 61, sizeof(struct bm_extent), + 1, 61, sizeof(struct bm_extent), offsetof(struct bm_extent, lce)); if (!resync_lru) { retcode = ERR_NOMEM; goto fail; } - /* RT - for drbd_get_max_capacity() DRBD_MD_INDEX_FLEX_INT */ - drbd_md_set_sector_offsets(mdev, nbc); + /* Read our meta data super block early. + * This also sets other on-disk offsets. */ + retcode = drbd_md_read(device, nbc); + if (retcode != NO_ERROR) + goto fail; + + if (new_disk_conf->al_extents < DRBD_AL_EXTENTS_MIN) + new_disk_conf->al_extents = DRBD_AL_EXTENTS_MIN; + if (new_disk_conf->al_extents > drbd_al_extents_max(nbc)) + new_disk_conf->al_extents = drbd_al_extents_max(nbc); - if (drbd_get_max_capacity(nbc) < nbc->dc.disk_size) { - dev_err(DEV, "max capacity %llu smaller than disk size %llu\n", + if (drbd_get_max_capacity(nbc) < new_disk_conf->disk_size) { + drbd_err(device, "max capacity %llu smaller than disk size %llu\n", (unsigned long long) drbd_get_max_capacity(nbc), - (unsigned long long) nbc->dc.disk_size); - retcode = ERR_DISK_TO_SMALL; + (unsigned long long) new_disk_conf->disk_size); + retcode = ERR_DISK_TOO_SMALL; goto fail; } - if (nbc->dc.meta_dev_idx < 0) { + if (new_disk_conf->meta_dev_idx < 0) { max_possible_sectors = DRBD_MAX_SECTORS_FLEX; /* at least one MB, otherwise it does not make sense */ min_md_device_sectors = (2<<10); } else { max_possible_sectors = DRBD_MAX_SECTORS; - min_md_device_sectors = MD_RESERVED_SECT * (nbc->dc.meta_dev_idx + 1); + min_md_device_sectors = MD_128MB_SECT * (new_disk_conf->meta_dev_idx + 1); } if (drbd_get_capacity(nbc->md_bdev) < min_md_device_sectors) { - retcode = ERR_MD_DISK_TO_SMALL; - dev_warn(DEV, "refusing attach: md-device too small, " + retcode = ERR_MD_DISK_TOO_SMALL; + drbd_warn(device, "refusing attach: md-device too small, " "at least %llu sectors needed for this meta-disk type\n", (unsigned long long) min_md_device_sectors); goto fail; @@ -1056,134 +1623,110 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp /* Make sure the new disk is big enough * (we may currently be R_PRIMARY with no local disk...) */ if (drbd_get_max_capacity(nbc) < - drbd_get_capacity(mdev->this_bdev)) { - retcode = ERR_DISK_TO_SMALL; + drbd_get_capacity(device->this_bdev)) { + retcode = ERR_DISK_TOO_SMALL; goto fail; } nbc->known_size = drbd_get_capacity(nbc->backing_bdev); if (nbc->known_size > max_possible_sectors) { - dev_warn(DEV, "==> truncating very big lower level device " + drbd_warn(device, "==> truncating very big lower level device " "to currently maximum possible %llu sectors <==\n", (unsigned long long) max_possible_sectors); - if (nbc->dc.meta_dev_idx >= 0) - dev_warn(DEV, "==>> using internal or flexible " + if (new_disk_conf->meta_dev_idx >= 0) + drbd_warn(device, "==>> using internal or flexible " "meta data may help <<==\n"); } - drbd_suspend_io(mdev); + drbd_suspend_io(device); /* also wait for the last barrier ack. */ - wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_pending_cnt) || is_susp(mdev->state)); + /* FIXME see also https://daiquiri.linbit/cgi-bin/bugzilla/show_bug.cgi?id=171 + * We need a way to either ignore barrier acks for barriers sent before a device + * was attached, or a way to wait for all pending barrier acks to come in. + * As barriers are counted per resource, + * we'd need to suspend io on all devices of a resource. + */ + wait_event(device->misc_wait, !atomic_read(&device->ap_pending_cnt) || drbd_suspended(device)); /* and for any other previously queued work */ - drbd_flush_workqueue(mdev); + drbd_flush_workqueue(&first_peer_device(device)->connection->sender_work); - rv = _drbd_request_state(mdev, NS(disk, D_ATTACHING), CS_VERBOSE); + rv = _drbd_request_state(device, NS(disk, D_ATTACHING), CS_VERBOSE); retcode = rv; /* FIXME: Type mismatch. */ - drbd_resume_io(mdev); + drbd_resume_io(device); if (rv < SS_SUCCESS) goto fail; - if (!get_ldev_if_state(mdev, D_ATTACHING)) + if (!get_ldev_if_state(device, D_ATTACHING)) goto force_diskless; - drbd_md_set_sector_offsets(mdev, nbc); - - /* allocate a second IO page if logical_block_size != 512 */ - logical_block_size = bdev_logical_block_size(nbc->md_bdev); - if (logical_block_size == 0) - logical_block_size = MD_SECTOR_SIZE; - - if (logical_block_size != MD_SECTOR_SIZE) { - if (!mdev->md_io_tmpp) { - struct page *page = alloc_page(GFP_NOIO); - if (!page) - goto force_diskless_dec; - - dev_warn(DEV, "Meta data's bdev logical_block_size = %d != %d\n", - logical_block_size, MD_SECTOR_SIZE); - dev_warn(DEV, "Workaround engaged (has performance impact).\n"); - - mdev->md_io_tmpp = page; - } - } - - if (!mdev->bitmap) { - if (drbd_bm_init(mdev)) { + if (!device->bitmap) { + if (drbd_bm_init(device)) { retcode = ERR_NOMEM; goto force_diskless_dec; } } - retcode = drbd_md_read(mdev, nbc); - if (retcode != NO_ERROR) - goto force_diskless_dec; - - if (mdev->state.conn < C_CONNECTED && - mdev->state.role == R_PRIMARY && - (mdev->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) { - dev_err(DEV, "Can only attach to data with current UUID=%016llX\n", - (unsigned long long)mdev->ed_uuid); + if (device->state.conn < C_CONNECTED && + device->state.role == R_PRIMARY && device->ed_uuid && + (device->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) { + drbd_err(device, "Can only attach to data with current UUID=%016llX\n", + (unsigned long long)device->ed_uuid); retcode = ERR_DATA_NOT_CURRENT; goto force_diskless_dec; } /* Since we are diskless, fix the activity log first... */ - if (drbd_check_al_size(mdev)) { + if (drbd_check_al_size(device, new_disk_conf)) { retcode = ERR_NOMEM; goto force_diskless_dec; } /* Prevent shrinking of consistent devices ! */ if (drbd_md_test_flag(nbc, MDF_CONSISTENT) && - drbd_new_dev_size(mdev, nbc, 0) < nbc->md.la_size_sect) { - dev_warn(DEV, "refusing to truncate a consistent device\n"); - retcode = ERR_DISK_TO_SMALL; - goto force_diskless_dec; - } - - if (!drbd_al_read_log(mdev, nbc)) { - retcode = ERR_IO_MD_DISK; + drbd_new_dev_size(device, nbc, nbc->disk_conf->disk_size, 0) < nbc->md.la_size_sect) { + drbd_warn(device, "refusing to truncate a consistent device\n"); + retcode = ERR_DISK_TOO_SMALL; goto force_diskless_dec; } /* Reset the "barriers don't work" bits here, then force meta data to * be written, to ensure we determine if barriers are supported. */ - if (nbc->dc.no_md_flush) - set_bit(MD_NO_FUA, &mdev->flags); + if (new_disk_conf->md_flushes) + clear_bit(MD_NO_FUA, &device->flags); else - clear_bit(MD_NO_FUA, &mdev->flags); + set_bit(MD_NO_FUA, &device->flags); /* Point of no return reached. * Devices and memory are no longer released by error cleanup below. - * now mdev takes over responsibility, and the state engine should + * now device takes over responsibility, and the state engine should * clean it up somewhere. */ - D_ASSERT(mdev->ldev == NULL); - mdev->ldev = nbc; - mdev->resync = resync_lru; + D_ASSERT(device, device->ldev == NULL); + device->ldev = nbc; + device->resync = resync_lru; + device->rs_plan_s = new_plan; nbc = NULL; resync_lru = NULL; + new_disk_conf = NULL; + new_plan = NULL; - mdev->write_ordering = WO_bdev_flush; - drbd_bump_write_ordering(mdev, WO_bdev_flush); + drbd_bump_write_ordering(first_peer_device(device)->connection, WO_bdev_flush); - if (drbd_md_test_flag(mdev->ldev, MDF_CRASHED_PRIMARY)) - set_bit(CRASHED_PRIMARY, &mdev->flags); + if (drbd_md_test_flag(device->ldev, MDF_CRASHED_PRIMARY)) + set_bit(CRASHED_PRIMARY, &device->flags); else - clear_bit(CRASHED_PRIMARY, &mdev->flags); + clear_bit(CRASHED_PRIMARY, &device->flags); - if (drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND) && - !(mdev->state.role == R_PRIMARY && mdev->state.susp_nod)) { - set_bit(CRASHED_PRIMARY, &mdev->flags); - cp_discovered = 1; - } + if (drbd_md_test_flag(device->ldev, MDF_PRIMARY_IND) && + !(device->state.role == R_PRIMARY && device->resource->susp_nod)) + set_bit(CRASHED_PRIMARY, &device->flags); - mdev->send_cnt = 0; - mdev->recv_cnt = 0; - mdev->read_cnt = 0; - mdev->writ_cnt = 0; + device->send_cnt = 0; + device->recv_cnt = 0; + device->read_cnt = 0; + device->writ_cnt = 0; - drbd_reconsider_max_bio_size(mdev); + drbd_reconsider_max_bio_size(device); /* If I am currently not R_PRIMARY, * but meta data primary indicator is set, @@ -1199,57 +1742,50 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp * so we can automatically recover from a crash of a * degraded but active "cluster" after a certain timeout. */ - clear_bit(USE_DEGR_WFC_T, &mdev->flags); - if (mdev->state.role != R_PRIMARY && - drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND) && - !drbd_md_test_flag(mdev->ldev, MDF_CONNECTED_IND)) - set_bit(USE_DEGR_WFC_T, &mdev->flags); - - dd = drbd_determine_dev_size(mdev, 0); - if (dd == dev_size_error) { + clear_bit(USE_DEGR_WFC_T, &device->flags); + if (device->state.role != R_PRIMARY && + drbd_md_test_flag(device->ldev, MDF_PRIMARY_IND) && + !drbd_md_test_flag(device->ldev, MDF_CONNECTED_IND)) + set_bit(USE_DEGR_WFC_T, &device->flags); + + dd = drbd_determine_dev_size(device, 0, NULL); + if (dd <= DS_ERROR) { retcode = ERR_NOMEM_BITMAP; goto force_diskless_dec; - } else if (dd == grew) - set_bit(RESYNC_AFTER_NEG, &mdev->flags); + } else if (dd == DS_GREW) + set_bit(RESYNC_AFTER_NEG, &device->flags); - if (drbd_md_test_flag(mdev->ldev, MDF_FULL_SYNC)) { - dev_info(DEV, "Assuming that all blocks are out of sync " + if (drbd_md_test_flag(device->ldev, MDF_FULL_SYNC) || + (test_bit(CRASHED_PRIMARY, &device->flags) && + drbd_md_test_flag(device->ldev, MDF_AL_DISABLED))) { + drbd_info(device, "Assuming that all blocks are out of sync " "(aka FullSync)\n"); - if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write, + if (drbd_bitmap_io(device, &drbd_bmio_set_n_write, "set_n_write from attaching", BM_LOCKED_MASK)) { retcode = ERR_IO_MD_DISK; goto force_diskless_dec; } } else { - if (drbd_bitmap_io(mdev, &drbd_bm_read, - "read from attaching", BM_LOCKED_MASK) < 0) { - retcode = ERR_IO_MD_DISK; - goto force_diskless_dec; - } - } - - if (cp_discovered) { - drbd_al_apply_to_bm(mdev); - if (drbd_bitmap_io(mdev, &drbd_bm_write, - "crashed primary apply AL", BM_LOCKED_MASK)) { + if (drbd_bitmap_io(device, &drbd_bm_read, + "read from attaching", BM_LOCKED_MASK)) { retcode = ERR_IO_MD_DISK; goto force_diskless_dec; } } - if (_drbd_bm_total_weight(mdev) == drbd_bm_bits(mdev)) - drbd_suspend_al(mdev); /* IO is still suspended here... */ + if (_drbd_bm_total_weight(device) == drbd_bm_bits(device)) + drbd_suspend_al(device); /* IO is still suspended here... */ - spin_lock_irq(&mdev->req_lock); - os = mdev->state; - ns.i = os.i; + spin_lock_irq(&device->resource->req_lock); + os = drbd_read_state(device); + ns = os; /* If MDF_CONSISTENT is not set go into inconsistent state, otherwise investigate MDF_WasUpToDate... If MDF_WAS_UP_TO_DATE is not set go into D_OUTDATED disk state, otherwise into D_CONSISTENT state. */ - if (drbd_md_test_flag(mdev->ldev, MDF_CONSISTENT)) { - if (drbd_md_test_flag(mdev->ldev, MDF_WAS_UP_TO_DATE)) + if (drbd_md_test_flag(device->ldev, MDF_CONSISTENT)) { + if (drbd_md_test_flag(device->ldev, MDF_WAS_UP_TO_DATE)) ns.disk = D_CONSISTENT; else ns.disk = D_OUTDATED; @@ -1257,11 +1793,12 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp ns.disk = D_INCONSISTENT; } - if (drbd_md_test_flag(mdev->ldev, MDF_PEER_OUT_DATED)) + if (drbd_md_test_flag(device->ldev, MDF_PEER_OUT_DATED)) ns.pdsk = D_OUTDATED; - if ( ns.disk == D_CONSISTENT && - (ns.pdsk == D_OUTDATED || mdev->ldev->dc.fencing == FP_DONT_CARE)) + rcu_read_lock(); + if (ns.disk == D_CONSISTENT && + (ns.pdsk == D_OUTDATED || rcu_dereference(device->ldev->disk_conf)->fencing == FP_DONT_CARE)) ns.disk = D_UP_TO_DATE; /* All tests on MDF_PRIMARY_IND, MDF_CONNECTED_IND, @@ -1269,47 +1806,57 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp this point, because drbd_request_state() modifies these flags. */ + if (rcu_dereference(device->ldev->disk_conf)->al_updates) + device->ldev->md.flags &= ~MDF_AL_DISABLED; + else + device->ldev->md.flags |= MDF_AL_DISABLED; + + rcu_read_unlock(); + /* In case we are C_CONNECTED postpone any decision on the new disk state after the negotiation phase. */ - if (mdev->state.conn == C_CONNECTED) { - mdev->new_state_tmp.i = ns.i; + if (device->state.conn == C_CONNECTED) { + device->new_state_tmp.i = ns.i; ns.i = os.i; ns.disk = D_NEGOTIATING; /* We expect to receive up-to-date UUIDs soon. To avoid a race in receive_state, free p_uuid while holding req_lock. I.e. atomic with the state change */ - kfree(mdev->p_uuid); - mdev->p_uuid = NULL; + kfree(device->p_uuid); + device->p_uuid = NULL; } - rv = _drbd_set_state(mdev, ns, CS_VERBOSE, NULL); - ns = mdev->state; - spin_unlock_irq(&mdev->req_lock); + rv = _drbd_set_state(device, ns, CS_VERBOSE, NULL); + spin_unlock_irq(&device->resource->req_lock); if (rv < SS_SUCCESS) goto force_diskless_dec; - if (mdev->state.role == R_PRIMARY) - mdev->ldev->md.uuid[UI_CURRENT] |= (u64)1; + mod_timer(&device->request_timer, jiffies + HZ); + + if (device->state.role == R_PRIMARY) + device->ldev->md.uuid[UI_CURRENT] |= (u64)1; else - mdev->ldev->md.uuid[UI_CURRENT] &= ~(u64)1; + device->ldev->md.uuid[UI_CURRENT] &= ~(u64)1; - drbd_md_mark_dirty(mdev); - drbd_md_sync(mdev); + drbd_md_mark_dirty(device); + drbd_md_sync(device); - kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE); - put_ldev(mdev); - reply->ret_code = retcode; - drbd_reconfig_done(mdev); + kobject_uevent(&disk_to_dev(device->vdisk)->kobj, KOBJ_CHANGE); + put_ldev(device); + conn_reconfig_done(first_peer_device(device)->connection); + mutex_unlock(&adm_ctx.resource->adm_mutex); + drbd_adm_finish(&adm_ctx, info, retcode); return 0; force_diskless_dec: - put_ldev(mdev); + put_ldev(device); force_diskless: - drbd_force_state(mdev, NS(disk, D_FAILED)); - drbd_md_sync(mdev); + drbd_force_state(device, NS(disk, D_DISKLESS)); + drbd_md_sync(device); fail: + conn_reconfig_done(first_peer_device(device)->connection); if (nbc) { if (nbc->backing_bdev) blkdev_put(nbc->backing_bdev, @@ -1319,710 +1866,933 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp FMODE_READ | FMODE_WRITE | FMODE_EXCL); kfree(nbc); } + kfree(new_disk_conf); lc_destroy(resync_lru); - - reply->ret_code = retcode; - drbd_reconfig_done(mdev); + kfree(new_plan); + mutex_unlock(&adm_ctx.resource->adm_mutex); + finish: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -/* Detaching the disk is a process in multiple stages. First we need to lock - * out application IO, in-flight IO, IO stuck in drbd_al_begin_io. - * Then we transition to D_DISKLESS, and wait for put_ldev() to return all - * internal references as well. - * Only then we have finally detached. */ -static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +static int adm_detach(struct drbd_device *device, int force) { - enum drbd_ret_code retcode; + enum drbd_state_rv retcode; int ret; - drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */ - retcode = drbd_request_state(mdev, NS(disk, D_FAILED)); + + if (force) { + set_bit(FORCE_DETACH, &device->flags); + drbd_force_state(device, NS(disk, D_FAILED)); + retcode = SS_SUCCESS; + goto out; + } + + drbd_suspend_io(device); /* so no-one is stuck in drbd_al_begin_io */ + drbd_md_get_buffer(device); /* make sure there is no in-flight meta-data IO */ + retcode = drbd_request_state(device, NS(disk, D_FAILED)); + drbd_md_put_buffer(device); /* D_FAILED will transition to DISKLESS. */ - ret = wait_event_interruptible(mdev->misc_wait, - mdev->state.disk != D_FAILED); - drbd_resume_io(mdev); + ret = wait_event_interruptible(device->misc_wait, + device->state.disk != D_FAILED); + drbd_resume_io(device); if ((int)retcode == (int)SS_IS_DISKLESS) retcode = SS_NOTHING_TO_DO; if (ret) retcode = ERR_INTR; - reply->ret_code = retcode; - return 0; +out: + return retcode; } -static int drbd_nl_net_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +/* Detaching the disk is a process in multiple stages. First we need to lock + * out application IO, in-flight IO, IO stuck in drbd_al_begin_io. + * Then we transition to D_DISKLESS, and wait for put_ldev() to return all + * internal references as well. + * Only then we have finally detached. */ +int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info) { - int i, ns; + struct drbd_config_context adm_ctx; enum drbd_ret_code retcode; - struct net_conf *new_conf = NULL; - struct crypto_hash *tfm = NULL; - struct crypto_hash *integrity_w_tfm = NULL; - struct crypto_hash *integrity_r_tfm = NULL; - struct hlist_head *new_tl_hash = NULL; - struct hlist_head *new_ee_hash = NULL; - struct drbd_conf *odev; - char hmac_name[CRYPTO_MAX_ALG_NAME]; - void *int_dig_out = NULL; - void *int_dig_in = NULL; - void *int_dig_vv = NULL; - struct sockaddr *new_my_addr, *new_peer_addr, *taken_addr; + struct detach_parms parms = { }; + int err; - drbd_reconfig_start(mdev); + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - if (mdev->state.conn > C_STANDALONE) { - retcode = ERR_NET_CONFIGURED; - goto fail; + if (info->attrs[DRBD_NLA_DETACH_PARMS]) { + err = detach_parms_from_attrs(&parms, info); + if (err) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); + goto out; + } } - /* allocation not in the IO path, cqueue thread context */ - new_conf = kzalloc(sizeof(struct net_conf), GFP_KERNEL); - if (!new_conf) { - retcode = ERR_NOMEM; - goto fail; - } + mutex_lock(&adm_ctx.resource->adm_mutex); + retcode = adm_detach(adm_ctx.device, parms.force_detach); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; +} - new_conf->timeout = DRBD_TIMEOUT_DEF; - new_conf->try_connect_int = DRBD_CONNECT_INT_DEF; - new_conf->ping_int = DRBD_PING_INT_DEF; - new_conf->max_epoch_size = DRBD_MAX_EPOCH_SIZE_DEF; - new_conf->max_buffers = DRBD_MAX_BUFFERS_DEF; - new_conf->unplug_watermark = DRBD_UNPLUG_WATERMARK_DEF; - new_conf->sndbuf_size = DRBD_SNDBUF_SIZE_DEF; - new_conf->rcvbuf_size = DRBD_RCVBUF_SIZE_DEF; - new_conf->ko_count = DRBD_KO_COUNT_DEF; - new_conf->after_sb_0p = DRBD_AFTER_SB_0P_DEF; - new_conf->after_sb_1p = DRBD_AFTER_SB_1P_DEF; - new_conf->after_sb_2p = DRBD_AFTER_SB_2P_DEF; - new_conf->want_lose = 0; - new_conf->two_primaries = 0; - new_conf->wire_protocol = DRBD_PROT_C; - new_conf->ping_timeo = DRBD_PING_TIMEO_DEF; - new_conf->rr_conflict = DRBD_RR_CONFLICT_DEF; - new_conf->on_congestion = DRBD_ON_CONGESTION_DEF; - new_conf->cong_extents = DRBD_CONG_EXTENTS_DEF; - - if (!net_conf_from_tags(mdev, nlp->tag_list, new_conf)) { - retcode = ERR_MANDATORY_TAG; - goto fail; +static bool conn_resync_running(struct drbd_connection *connection) +{ + struct drbd_peer_device *peer_device; + bool rv = false; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { + struct drbd_device *device = peer_device->device; + if (device->state.conn == C_SYNC_SOURCE || + device->state.conn == C_SYNC_TARGET || + device->state.conn == C_PAUSED_SYNC_S || + device->state.conn == C_PAUSED_SYNC_T) { + rv = true; + break; + } } + rcu_read_unlock(); - if (new_conf->two_primaries - && (new_conf->wire_protocol != DRBD_PROT_C)) { - retcode = ERR_NOT_PROTO_C; - goto fail; - } + return rv; +} - if (get_ldev(mdev)) { - enum drbd_fencing_p fp = mdev->ldev->dc.fencing; - put_ldev(mdev); - if (new_conf->wire_protocol == DRBD_PROT_A && fp == FP_STONITH) { - retcode = ERR_STONITH_AND_PROT_A; - goto fail; +static bool conn_ov_running(struct drbd_connection *connection) +{ + struct drbd_peer_device *peer_device; + bool rv = false; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { + struct drbd_device *device = peer_device->device; + if (device->state.conn == C_VERIFY_S || + device->state.conn == C_VERIFY_T) { + rv = true; + break; } } + rcu_read_unlock(); - if (new_conf->on_congestion != OC_BLOCK && new_conf->wire_protocol != DRBD_PROT_A) { - retcode = ERR_CONG_NOT_PROTO_A; - goto fail; - } - - if (mdev->state.role == R_PRIMARY && new_conf->want_lose) { - retcode = ERR_DISCARD; - goto fail; - } + return rv; +} - retcode = NO_ERROR; +static enum drbd_ret_code +_check_net_options(struct drbd_connection *connection, struct net_conf *old_net_conf, struct net_conf *new_net_conf) +{ + struct drbd_peer_device *peer_device; + int i; - new_my_addr = (struct sockaddr *)&new_conf->my_addr; - new_peer_addr = (struct sockaddr *)&new_conf->peer_addr; - for (i = 0; i < minor_count; i++) { - odev = minor_to_mdev(i); - if (!odev || odev == mdev) - continue; - if (get_net_conf(odev)) { - taken_addr = (struct sockaddr *)&odev->net_conf->my_addr; - if (new_conf->my_addr_len == odev->net_conf->my_addr_len && - !memcmp(new_my_addr, taken_addr, new_conf->my_addr_len)) - retcode = ERR_LOCAL_ADDR; + if (old_net_conf && connection->cstate == C_WF_REPORT_PARAMS && connection->agreed_pro_version < 100) { + if (new_net_conf->wire_protocol != old_net_conf->wire_protocol) + return ERR_NEED_APV_100; - taken_addr = (struct sockaddr *)&odev->net_conf->peer_addr; - if (new_conf->peer_addr_len == odev->net_conf->peer_addr_len && - !memcmp(new_peer_addr, taken_addr, new_conf->peer_addr_len)) - retcode = ERR_PEER_ADDR; + if (new_net_conf->two_primaries != old_net_conf->two_primaries) + return ERR_NEED_APV_100; - put_net_conf(odev); - if (retcode != NO_ERROR) - goto fail; - } + if (strcmp(new_net_conf->integrity_alg, old_net_conf->integrity_alg)) + return ERR_NEED_APV_100; } - if (new_conf->cram_hmac_alg[0] != 0) { - snprintf(hmac_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)", - new_conf->cram_hmac_alg); - tfm = crypto_alloc_hash(hmac_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) { - tfm = NULL; - retcode = ERR_AUTH_ALG; - goto fail; - } + if (!new_net_conf->two_primaries && + conn_highest_role(connection) == R_PRIMARY && + conn_highest_peer(connection) == R_PRIMARY) + return ERR_NEED_ALLOW_TWO_PRI; - if (!drbd_crypto_is_hash(crypto_hash_tfm(tfm))) { - retcode = ERR_AUTH_ALG_ND; - goto fail; + if (new_net_conf->two_primaries && + (new_net_conf->wire_protocol != DRBD_PROT_C)) + return ERR_NOT_PROTO_C; + + idr_for_each_entry(&connection->peer_devices, peer_device, i) { + struct drbd_device *device = peer_device->device; + if (get_ldev(device)) { + enum drbd_fencing_p fp = rcu_dereference(device->ldev->disk_conf)->fencing; + put_ldev(device); + if (new_net_conf->wire_protocol == DRBD_PROT_A && fp == FP_STONITH) + return ERR_STONITH_AND_PROT_A; } + if (device->state.role == R_PRIMARY && new_net_conf->discard_my_data) + return ERR_DISCARD_IMPOSSIBLE; } - if (new_conf->integrity_alg[0]) { - integrity_w_tfm = crypto_alloc_hash(new_conf->integrity_alg, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(integrity_w_tfm)) { - integrity_w_tfm = NULL; - retcode=ERR_INTEGRITY_ALG; - goto fail; - } + if (new_net_conf->on_congestion != OC_BLOCK && new_net_conf->wire_protocol != DRBD_PROT_A) + return ERR_CONG_NOT_PROTO_A; - if (!drbd_crypto_is_hash(crypto_hash_tfm(integrity_w_tfm))) { - retcode=ERR_INTEGRITY_ALG_ND; - goto fail; - } + return NO_ERROR; +} - integrity_r_tfm = crypto_alloc_hash(new_conf->integrity_alg, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(integrity_r_tfm)) { - integrity_r_tfm = NULL; - retcode=ERR_INTEGRITY_ALG; - goto fail; - } - } +static enum drbd_ret_code +check_net_options(struct drbd_connection *connection, struct net_conf *new_net_conf) +{ + static enum drbd_ret_code rv; + struct drbd_peer_device *peer_device; + int i; - ns = new_conf->max_epoch_size/8; - if (mdev->tl_hash_s != ns) { - new_tl_hash = kzalloc(ns*sizeof(void *), GFP_KERNEL); - if (!new_tl_hash) { - retcode = ERR_NOMEM; - goto fail; - } - } + rcu_read_lock(); + rv = _check_net_options(connection, rcu_dereference(connection->net_conf), new_net_conf); + rcu_read_unlock(); - ns = new_conf->max_buffers/8; - if (new_conf->two_primaries && (mdev->ee_hash_s != ns)) { - new_ee_hash = kzalloc(ns*sizeof(void *), GFP_KERNEL); - if (!new_ee_hash) { - retcode = ERR_NOMEM; - goto fail; + /* connection->volumes protected by genl_lock() here */ + idr_for_each_entry(&connection->peer_devices, peer_device, i) { + struct drbd_device *device = peer_device->device; + if (!device->bitmap) { + if (drbd_bm_init(device)) + return ERR_NOMEM; } } - ((char *)new_conf->shared_secret)[SHARED_SECRET_MAX-1] = 0; + return rv; +} - if (integrity_w_tfm) { - i = crypto_hash_digestsize(integrity_w_tfm); - int_dig_out = kmalloc(i, GFP_KERNEL); - if (!int_dig_out) { - retcode = ERR_NOMEM; - goto fail; - } - int_dig_in = kmalloc(i, GFP_KERNEL); - if (!int_dig_in) { - retcode = ERR_NOMEM; - goto fail; - } - int_dig_vv = kmalloc(i, GFP_KERNEL); - if (!int_dig_vv) { - retcode = ERR_NOMEM; - goto fail; - } - } +struct crypto { + struct crypto_hash *verify_tfm; + struct crypto_hash *csums_tfm; + struct crypto_hash *cram_hmac_tfm; + struct crypto_hash *integrity_tfm; +}; - if (!mdev->bitmap) { - if(drbd_bm_init(mdev)) { - retcode = ERR_NOMEM; - goto fail; - } - } +static int +alloc_hash(struct crypto_hash **tfm, char *tfm_name, int err_alg) +{ + if (!tfm_name[0]) + return NO_ERROR; - drbd_flush_workqueue(mdev); - spin_lock_irq(&mdev->req_lock); - if (mdev->net_conf != NULL) { - retcode = ERR_NET_CONFIGURED; - spin_unlock_irq(&mdev->req_lock); - goto fail; + *tfm = crypto_alloc_hash(tfm_name, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(*tfm)) { + *tfm = NULL; + return err_alg; } - mdev->net_conf = new_conf; - mdev->send_cnt = 0; - mdev->recv_cnt = 0; + return NO_ERROR; +} - if (new_tl_hash) { - kfree(mdev->tl_hash); - mdev->tl_hash_s = mdev->net_conf->max_epoch_size/8; - mdev->tl_hash = new_tl_hash; - } +static enum drbd_ret_code +alloc_crypto(struct crypto *crypto, struct net_conf *new_net_conf) +{ + char hmac_name[CRYPTO_MAX_ALG_NAME]; + enum drbd_ret_code rv; + + rv = alloc_hash(&crypto->csums_tfm, new_net_conf->csums_alg, + ERR_CSUMS_ALG); + if (rv != NO_ERROR) + return rv; + rv = alloc_hash(&crypto->verify_tfm, new_net_conf->verify_alg, + ERR_VERIFY_ALG); + if (rv != NO_ERROR) + return rv; + rv = alloc_hash(&crypto->integrity_tfm, new_net_conf->integrity_alg, + ERR_INTEGRITY_ALG); + if (rv != NO_ERROR) + return rv; + if (new_net_conf->cram_hmac_alg[0] != 0) { + snprintf(hmac_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)", + new_net_conf->cram_hmac_alg); - if (new_ee_hash) { - kfree(mdev->ee_hash); - mdev->ee_hash_s = mdev->net_conf->max_buffers/8; - mdev->ee_hash = new_ee_hash; + rv = alloc_hash(&crypto->cram_hmac_tfm, hmac_name, + ERR_AUTH_ALG); } - crypto_free_hash(mdev->cram_hmac_tfm); - mdev->cram_hmac_tfm = tfm; + return rv; +} - crypto_free_hash(mdev->integrity_w_tfm); - mdev->integrity_w_tfm = integrity_w_tfm; +static void free_crypto(struct crypto *crypto) +{ + crypto_free_hash(crypto->cram_hmac_tfm); + crypto_free_hash(crypto->integrity_tfm); + crypto_free_hash(crypto->csums_tfm); + crypto_free_hash(crypto->verify_tfm); +} - crypto_free_hash(mdev->integrity_r_tfm); - mdev->integrity_r_tfm = integrity_r_tfm; +int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info) +{ + struct drbd_config_context adm_ctx; + enum drbd_ret_code retcode; + struct drbd_connection *connection; + struct net_conf *old_net_conf, *new_net_conf = NULL; + int err; + int ovr; /* online verify running */ + int rsr; /* re-sync running */ + struct crypto crypto = { }; - kfree(mdev->int_dig_out); - kfree(mdev->int_dig_in); - kfree(mdev->int_dig_vv); - mdev->int_dig_out=int_dig_out; - mdev->int_dig_in=int_dig_in; - mdev->int_dig_vv=int_dig_vv; - retcode = _drbd_set_state(_NS(mdev, conn, C_UNCONNECTED), CS_VERBOSE, NULL); - spin_unlock_irq(&mdev->req_lock); + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_CONNECTION); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto finish; - kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE); - reply->ret_code = retcode; - drbd_reconfig_done(mdev); - return 0; + connection = adm_ctx.connection; + mutex_lock(&adm_ctx.resource->adm_mutex); -fail: - kfree(int_dig_out); - kfree(int_dig_in); - kfree(int_dig_vv); - crypto_free_hash(tfm); - crypto_free_hash(integrity_w_tfm); - crypto_free_hash(integrity_r_tfm); - kfree(new_tl_hash); - kfree(new_ee_hash); - kfree(new_conf); - - reply->ret_code = retcode; - drbd_reconfig_done(mdev); - return 0; -} + new_net_conf = kzalloc(sizeof(struct net_conf), GFP_KERNEL); + if (!new_net_conf) { + retcode = ERR_NOMEM; + goto out; + } -static int drbd_nl_disconnect(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) -{ - int retcode; - struct disconnect dc; + conn_reconfig_start(connection); - memset(&dc, 0, sizeof(struct disconnect)); - if (!disconnect_from_tags(mdev, nlp->tag_list, &dc)) { - retcode = ERR_MANDATORY_TAG; + mutex_lock(&connection->data.mutex); + mutex_lock(&connection->resource->conf_update); + old_net_conf = connection->net_conf; + + if (!old_net_conf) { + drbd_msg_put_info(adm_ctx.reply_skb, "net conf missing, try connect"); + retcode = ERR_INVALID_REQUEST; goto fail; } - if (dc.force) { - spin_lock_irq(&mdev->req_lock); - if (mdev->state.conn >= C_WF_CONNECTION) - _drbd_set_state(_NS(mdev, conn, C_DISCONNECTING), CS_HARD, NULL); - spin_unlock_irq(&mdev->req_lock); - goto done; + *new_net_conf = *old_net_conf; + if (should_set_defaults(info)) + set_net_conf_defaults(new_net_conf); + + err = net_conf_from_attrs_for_change(new_net_conf, info); + if (err && err != -ENOMSG) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); + goto fail; } - retcode = _drbd_request_state(mdev, NS(conn, C_DISCONNECTING), CS_ORDERED); + retcode = check_net_options(connection, new_net_conf); + if (retcode != NO_ERROR) + goto fail; - if (retcode == SS_NOTHING_TO_DO) - goto done; - else if (retcode == SS_ALREADY_STANDALONE) - goto done; - else if (retcode == SS_PRIMARY_NOP) { - /* Our statche checking code wants to see the peer outdated. */ - retcode = drbd_request_state(mdev, NS2(conn, C_DISCONNECTING, - pdsk, D_OUTDATED)); - } else if (retcode == SS_CW_FAILED_BY_PEER) { - /* The peer probably wants to see us outdated. */ - retcode = _drbd_request_state(mdev, NS2(conn, C_DISCONNECTING, - disk, D_OUTDATED), - CS_ORDERED); - if (retcode == SS_IS_DISKLESS || retcode == SS_LOWER_THAN_OUTDATED) { - drbd_force_state(mdev, NS(conn, C_DISCONNECTING)); - retcode = SS_SUCCESS; - } + /* re-sync running */ + rsr = conn_resync_running(connection); + if (rsr && strcmp(new_net_conf->csums_alg, old_net_conf->csums_alg)) { + retcode = ERR_CSUMS_RESYNC_RUNNING; + goto fail; } - if (retcode < SS_SUCCESS) + /* online verify running */ + ovr = conn_ov_running(connection); + if (ovr && strcmp(new_net_conf->verify_alg, old_net_conf->verify_alg)) { + retcode = ERR_VERIFY_RUNNING; goto fail; + } - if (wait_event_interruptible(mdev->state_wait, - mdev->state.conn != C_DISCONNECTING)) { - /* Do not test for mdev->state.conn == C_STANDALONE, since - someone else might connect us in the mean time! */ - retcode = ERR_INTR; + retcode = alloc_crypto(&crypto, new_net_conf); + if (retcode != NO_ERROR) goto fail; + + rcu_assign_pointer(connection->net_conf, new_net_conf); + + if (!rsr) { + crypto_free_hash(connection->csums_tfm); + connection->csums_tfm = crypto.csums_tfm; + crypto.csums_tfm = NULL; + } + if (!ovr) { + crypto_free_hash(connection->verify_tfm); + connection->verify_tfm = crypto.verify_tfm; + crypto.verify_tfm = NULL; } - done: - retcode = NO_ERROR; + crypto_free_hash(connection->integrity_tfm); + connection->integrity_tfm = crypto.integrity_tfm; + if (connection->cstate >= C_WF_REPORT_PARAMS && connection->agreed_pro_version >= 100) + /* Do this without trying to take connection->data.mutex again. */ + __drbd_send_protocol(connection, P_PROTOCOL_UPDATE); + + crypto_free_hash(connection->cram_hmac_tfm); + connection->cram_hmac_tfm = crypto.cram_hmac_tfm; + + mutex_unlock(&connection->resource->conf_update); + mutex_unlock(&connection->data.mutex); + synchronize_rcu(); + kfree(old_net_conf); + + if (connection->cstate >= C_WF_REPORT_PARAMS) { + struct drbd_peer_device *peer_device; + int vnr; + + idr_for_each_entry(&connection->peer_devices, peer_device, vnr) + drbd_send_sync_param(peer_device); + } + + goto done; + fail: - drbd_md_sync(mdev); - reply->ret_code = retcode; + mutex_unlock(&connection->resource->conf_update); + mutex_unlock(&connection->data.mutex); + free_crypto(&crypto); + kfree(new_net_conf); + done: + conn_reconfig_done(connection); + out: + mutex_unlock(&adm_ctx.resource->adm_mutex); + finish: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -void resync_after_online_grow(struct drbd_conf *mdev) +int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) { - int iass; /* I am sync source */ + struct drbd_config_context adm_ctx; + struct drbd_peer_device *peer_device; + struct net_conf *old_net_conf, *new_net_conf = NULL; + struct crypto crypto = { }; + struct drbd_resource *resource; + struct drbd_connection *connection; + enum drbd_ret_code retcode; + int i; + int err; - dev_info(DEV, "Resync of new storage after online grow\n"); - if (mdev->state.role != mdev->state.peer) - iass = (mdev->state.role == R_PRIMARY); - else - iass = test_bit(DISCARD_CONCURRENT, &mdev->flags); + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE); - if (iass) - drbd_start_resync(mdev, C_SYNC_SOURCE); - else - _drbd_request_state(mdev, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE + CS_SERIALIZE); -} + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; + if (!(adm_ctx.my_addr && adm_ctx.peer_addr)) { + drbd_msg_put_info(adm_ctx.reply_skb, "connection endpoint(s) missing"); + retcode = ERR_INVALID_REQUEST; + goto out; + } -static int drbd_nl_resize(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) -{ - struct resize rs; - int retcode = NO_ERROR; - enum determine_dev_size dd; - enum dds_flags ddsf; + /* No need for _rcu here. All reconfiguration is + * strictly serialized on genl_lock(). We are protected against + * concurrent reconfiguration/addition/deletion */ + for_each_resource(resource, &drbd_resources) { + for_each_connection(connection, resource) { + if (nla_len(adm_ctx.my_addr) == connection->my_addr_len && + !memcmp(nla_data(adm_ctx.my_addr), &connection->my_addr, + connection->my_addr_len)) { + retcode = ERR_LOCAL_ADDR; + goto out; + } - memset(&rs, 0, sizeof(struct resize)); - if (!resize_from_tags(mdev, nlp->tag_list, &rs)) { - retcode = ERR_MANDATORY_TAG; - goto fail; + if (nla_len(adm_ctx.peer_addr) == connection->peer_addr_len && + !memcmp(nla_data(adm_ctx.peer_addr), &connection->peer_addr, + connection->peer_addr_len)) { + retcode = ERR_PEER_ADDR; + goto out; + } + } } - if (mdev->state.conn > C_CONNECTED) { - retcode = ERR_RESIZE_RESYNC; + mutex_lock(&adm_ctx.resource->adm_mutex); + connection = first_connection(adm_ctx.resource); + conn_reconfig_start(connection); + + if (connection->cstate > C_STANDALONE) { + retcode = ERR_NET_CONFIGURED; goto fail; } - if (mdev->state.role == R_SECONDARY && - mdev->state.peer == R_SECONDARY) { - retcode = ERR_NO_PRIMARY; + /* allocation not in the IO path, drbdsetup / netlink process context */ + new_net_conf = kzalloc(sizeof(*new_net_conf), GFP_KERNEL); + if (!new_net_conf) { + retcode = ERR_NOMEM; goto fail; } - if (!get_ldev(mdev)) { - retcode = ERR_NO_DISK; + set_net_conf_defaults(new_net_conf); + + err = net_conf_from_attrs(new_net_conf, info); + if (err && err != -ENOMSG) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); goto fail; } - if (rs.no_resync && mdev->agreed_pro_version < 93) { - retcode = ERR_NEED_APV_93; + retcode = check_net_options(connection, new_net_conf); + if (retcode != NO_ERROR) goto fail; - } - if (mdev->ldev->known_size != drbd_get_capacity(mdev->ldev->backing_bdev)) - mdev->ldev->known_size = drbd_get_capacity(mdev->ldev->backing_bdev); + retcode = alloc_crypto(&crypto, new_net_conf); + if (retcode != NO_ERROR) + goto fail; - mdev->ldev->dc.disk_size = (sector_t)rs.resize_size; - ddsf = (rs.resize_force ? DDSF_FORCED : 0) | (rs.no_resync ? DDSF_NO_RESYNC : 0); - dd = drbd_determine_dev_size(mdev, ddsf); - drbd_md_sync(mdev); - put_ldev(mdev); - if (dd == dev_size_error) { - retcode = ERR_NOMEM_BITMAP; + ((char *)new_net_conf->shared_secret)[SHARED_SECRET_MAX-1] = 0; + + drbd_flush_workqueue(&connection->sender_work); + + mutex_lock(&adm_ctx.resource->conf_update); + old_net_conf = connection->net_conf; + if (old_net_conf) { + retcode = ERR_NET_CONFIGURED; + mutex_unlock(&adm_ctx.resource->conf_update); goto fail; } + rcu_assign_pointer(connection->net_conf, new_net_conf); + + conn_free_crypto(connection); + connection->cram_hmac_tfm = crypto.cram_hmac_tfm; + connection->integrity_tfm = crypto.integrity_tfm; + connection->csums_tfm = crypto.csums_tfm; + connection->verify_tfm = crypto.verify_tfm; + + connection->my_addr_len = nla_len(adm_ctx.my_addr); + memcpy(&connection->my_addr, nla_data(adm_ctx.my_addr), connection->my_addr_len); + connection->peer_addr_len = nla_len(adm_ctx.peer_addr); + memcpy(&connection->peer_addr, nla_data(adm_ctx.peer_addr), connection->peer_addr_len); - if (mdev->state.conn == C_CONNECTED) { - if (dd == grew) - set_bit(RESIZE_PENDING, &mdev->flags); + mutex_unlock(&adm_ctx.resource->conf_update); - drbd_send_uuids(mdev); - drbd_send_sizes(mdev, 1, ddsf); + rcu_read_lock(); + idr_for_each_entry(&connection->peer_devices, peer_device, i) { + struct drbd_device *device = peer_device->device; + device->send_cnt = 0; + device->recv_cnt = 0; } + rcu_read_unlock(); - fail: - reply->ret_code = retcode; + retcode = conn_request_state(connection, NS(conn, C_UNCONNECTED), CS_VERBOSE); + + conn_reconfig_done(connection); + mutex_unlock(&adm_ctx.resource->adm_mutex); + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; + +fail: + free_crypto(&crypto); + kfree(new_net_conf); + + conn_reconfig_done(connection); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +static enum drbd_state_rv conn_try_disconnect(struct drbd_connection *connection, bool force) { - int retcode = NO_ERROR; - int err; - int ovr; /* online verify running */ - int rsr; /* re-sync running */ - struct crypto_hash *verify_tfm = NULL; - struct crypto_hash *csums_tfm = NULL; - struct syncer_conf sc; - cpumask_var_t new_cpu_mask; - int *rs_plan_s = NULL; - int fifo_size; - - if (!zalloc_cpumask_var(&new_cpu_mask, GFP_KERNEL)) { - retcode = ERR_NOMEM; - goto fail; - } + enum drbd_state_rv rv; - if (nlp->flags & DRBD_NL_SET_DEFAULTS) { - memset(&sc, 0, sizeof(struct syncer_conf)); - sc.rate = DRBD_RATE_DEF; - sc.after = DRBD_AFTER_DEF; - sc.al_extents = DRBD_AL_EXTENTS_DEF; - sc.on_no_data = DRBD_ON_NO_DATA_DEF; - sc.c_plan_ahead = DRBD_C_PLAN_AHEAD_DEF; - sc.c_delay_target = DRBD_C_DELAY_TARGET_DEF; - sc.c_fill_target = DRBD_C_FILL_TARGET_DEF; - sc.c_max_rate = DRBD_C_MAX_RATE_DEF; - sc.c_min_rate = DRBD_C_MIN_RATE_DEF; - } else - memcpy(&sc, &mdev->sync_conf, sizeof(struct syncer_conf)); + rv = conn_request_state(connection, NS(conn, C_DISCONNECTING), + force ? CS_HARD : 0); - if (!syncer_conf_from_tags(mdev, nlp->tag_list, &sc)) { - retcode = ERR_MANDATORY_TAG; - goto fail; - } + switch (rv) { + case SS_NOTHING_TO_DO: + break; + case SS_ALREADY_STANDALONE: + return SS_SUCCESS; + case SS_PRIMARY_NOP: + /* Our state checking code wants to see the peer outdated. */ + rv = conn_request_state(connection, NS2(conn, C_DISCONNECTING, pdsk, D_OUTDATED), 0); - /* re-sync running */ - rsr = ( mdev->state.conn == C_SYNC_SOURCE || - mdev->state.conn == C_SYNC_TARGET || - mdev->state.conn == C_PAUSED_SYNC_S || - mdev->state.conn == C_PAUSED_SYNC_T ); + if (rv == SS_OUTDATE_WO_CONN) /* lost connection before graceful disconnect succeeded */ + rv = conn_request_state(connection, NS(conn, C_DISCONNECTING), CS_VERBOSE); - if (rsr && strcmp(sc.csums_alg, mdev->sync_conf.csums_alg)) { - retcode = ERR_CSUMS_RESYNC_RUNNING; - goto fail; + break; + case SS_CW_FAILED_BY_PEER: + /* The peer probably wants to see us outdated. */ + rv = conn_request_state(connection, NS2(conn, C_DISCONNECTING, + disk, D_OUTDATED), 0); + if (rv == SS_IS_DISKLESS || rv == SS_LOWER_THAN_OUTDATED) { + rv = conn_request_state(connection, NS(conn, C_DISCONNECTING), + CS_HARD); + } + break; + default:; + /* no special handling necessary */ + } + + if (rv >= SS_SUCCESS) { + enum drbd_state_rv rv2; + /* No one else can reconfigure the network while I am here. + * The state handling only uses drbd_thread_stop_nowait(), + * we want to really wait here until the receiver is no more. + */ + drbd_thread_stop(&connection->receiver); + + /* Race breaker. This additional state change request may be + * necessary, if this was a forced disconnect during a receiver + * restart. We may have "killed" the receiver thread just + * after drbd_receiver() returned. Typically, we should be + * C_STANDALONE already, now, and this becomes a no-op. + */ + rv2 = conn_request_state(connection, NS(conn, C_STANDALONE), + CS_VERBOSE | CS_HARD); + if (rv2 < SS_SUCCESS) + drbd_err(connection, + "unexpected rv2=%d in conn_try_disconnect()\n", + rv2); } + return rv; +} - if (!rsr && sc.csums_alg[0]) { - csums_tfm = crypto_alloc_hash(sc.csums_alg, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(csums_tfm)) { - csums_tfm = NULL; - retcode = ERR_CSUMS_ALG; - goto fail; - } +int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info) +{ + struct drbd_config_context adm_ctx; + struct disconnect_parms parms; + struct drbd_connection *connection; + enum drbd_state_rv rv; + enum drbd_ret_code retcode; + int err; + + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_CONNECTION); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto fail; - if (!drbd_crypto_is_hash(crypto_hash_tfm(csums_tfm))) { - retcode = ERR_CSUMS_ALG_ND; + connection = adm_ctx.connection; + memset(&parms, 0, sizeof(parms)); + if (info->attrs[DRBD_NLA_DISCONNECT_PARMS]) { + err = disconnect_parms_from_attrs(&parms, info); + if (err) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); goto fail; } } - /* online verify running */ - ovr = (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T); + mutex_lock(&adm_ctx.resource->adm_mutex); + rv = conn_try_disconnect(connection, parms.force_disconnect); + if (rv < SS_SUCCESS) + retcode = rv; /* FIXME: Type mismatch. */ + else + retcode = NO_ERROR; + mutex_unlock(&adm_ctx.resource->adm_mutex); + fail: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; +} - if (ovr) { - if (strcmp(sc.verify_alg, mdev->sync_conf.verify_alg)) { - retcode = ERR_VERIFY_RUNNING; - goto fail; - } - } +void resync_after_online_grow(struct drbd_device *device) +{ + int iass; /* I am sync source */ - if (!ovr && sc.verify_alg[0]) { - verify_tfm = crypto_alloc_hash(sc.verify_alg, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(verify_tfm)) { - verify_tfm = NULL; - retcode = ERR_VERIFY_ALG; - goto fail; - } + drbd_info(device, "Resync of new storage after online grow\n"); + if (device->state.role != device->state.peer) + iass = (device->state.role == R_PRIMARY); + else + iass = test_bit(RESOLVE_CONFLICTS, &first_peer_device(device)->connection->flags); - if (!drbd_crypto_is_hash(crypto_hash_tfm(verify_tfm))) { - retcode = ERR_VERIFY_ALG_ND; - goto fail; - } + if (iass) + drbd_start_resync(device, C_SYNC_SOURCE); + else + _drbd_request_state(device, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE + CS_SERIALIZE); +} + +int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info) +{ + struct drbd_config_context adm_ctx; + struct disk_conf *old_disk_conf, *new_disk_conf = NULL; + struct resize_parms rs; + struct drbd_device *device; + enum drbd_ret_code retcode; + enum determine_dev_size dd; + bool change_al_layout = false; + enum dds_flags ddsf; + sector_t u_size; + int err; + + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto finish; + + mutex_lock(&adm_ctx.resource->adm_mutex); + device = adm_ctx.device; + if (!get_ldev(device)) { + retcode = ERR_NO_DISK; + goto fail; } - /* silently ignore cpu mask on UP kernel */ - if (nr_cpu_ids > 1 && sc.cpu_mask[0] != 0) { - err = __bitmap_parse(sc.cpu_mask, 32, 0, - cpumask_bits(new_cpu_mask), nr_cpu_ids); + memset(&rs, 0, sizeof(struct resize_parms)); + rs.al_stripes = device->ldev->md.al_stripes; + rs.al_stripe_size = device->ldev->md.al_stripe_size_4k * 4; + if (info->attrs[DRBD_NLA_RESIZE_PARMS]) { + err = resize_parms_from_attrs(&rs, info); if (err) { - dev_warn(DEV, "__bitmap_parse() failed with %d\n", err); - retcode = ERR_CPU_MASK_PARSE; - goto fail; + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); + goto fail_ldev; } } - ERR_IF (sc.rate < 1) sc.rate = 1; - ERR_IF (sc.al_extents < 7) sc.al_extents = 127; /* arbitrary minimum */ -#define AL_MAX ((MD_AL_MAX_SIZE-1) * AL_EXTENTS_PT) - if (sc.al_extents > AL_MAX) { - dev_err(DEV, "sc.al_extents > %d\n", AL_MAX); - sc.al_extents = AL_MAX; + if (device->state.conn > C_CONNECTED) { + retcode = ERR_RESIZE_RESYNC; + goto fail_ldev; } -#undef AL_MAX - /* to avoid spurious errors when configuring minors before configuring - * the minors they depend on: if necessary, first create the minor we - * depend on */ - if (sc.after >= 0) - ensure_mdev(sc.after, 1); + if (device->state.role == R_SECONDARY && + device->state.peer == R_SECONDARY) { + retcode = ERR_NO_PRIMARY; + goto fail_ldev; + } - /* most sanity checks done, try to assign the new sync-after - * dependency. need to hold the global lock in there, - * to avoid a race in the dependency loop check. */ - retcode = drbd_alter_sa(mdev, sc.after); - if (retcode != NO_ERROR) - goto fail; + if (rs.no_resync && first_peer_device(device)->connection->agreed_pro_version < 93) { + retcode = ERR_NEED_APV_93; + goto fail_ldev; + } - fifo_size = (sc.c_plan_ahead * 10 * SLEEP_TIME) / HZ; - if (fifo_size != mdev->rs_plan_s.size && fifo_size > 0) { - rs_plan_s = kzalloc(sizeof(int) * fifo_size, GFP_KERNEL); - if (!rs_plan_s) { - dev_err(DEV, "kmalloc of fifo_buffer failed"); + rcu_read_lock(); + u_size = rcu_dereference(device->ldev->disk_conf)->disk_size; + rcu_read_unlock(); + if (u_size != (sector_t)rs.resize_size) { + new_disk_conf = kmalloc(sizeof(struct disk_conf), GFP_KERNEL); + if (!new_disk_conf) { retcode = ERR_NOMEM; - goto fail; + goto fail_ldev; } } - /* ok, assign the rest of it as well. - * lock against receive_SyncParam() */ - spin_lock(&mdev->peer_seq_lock); - mdev->sync_conf = sc; + if (device->ldev->md.al_stripes != rs.al_stripes || + device->ldev->md.al_stripe_size_4k != rs.al_stripe_size / 4) { + u32 al_size_k = rs.al_stripes * rs.al_stripe_size; - if (!rsr) { - crypto_free_hash(mdev->csums_tfm); - mdev->csums_tfm = csums_tfm; - csums_tfm = NULL; + if (al_size_k > (16 * 1024 * 1024)) { + retcode = ERR_MD_LAYOUT_TOO_BIG; + goto fail_ldev; + } + + if (al_size_k < MD_32kB_SECT/2) { + retcode = ERR_MD_LAYOUT_TOO_SMALL; + goto fail_ldev; + } + + if (device->state.conn != C_CONNECTED && !rs.resize_force) { + retcode = ERR_MD_LAYOUT_CONNECTED; + goto fail_ldev; + } + + change_al_layout = true; } - if (!ovr) { - crypto_free_hash(mdev->verify_tfm); - mdev->verify_tfm = verify_tfm; - verify_tfm = NULL; + if (device->ldev->known_size != drbd_get_capacity(device->ldev->backing_bdev)) + device->ldev->known_size = drbd_get_capacity(device->ldev->backing_bdev); + + if (new_disk_conf) { + mutex_lock(&device->resource->conf_update); + old_disk_conf = device->ldev->disk_conf; + *new_disk_conf = *old_disk_conf; + new_disk_conf->disk_size = (sector_t)rs.resize_size; + rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); + mutex_unlock(&device->resource->conf_update); + synchronize_rcu(); + kfree(old_disk_conf); + } + + ddsf = (rs.resize_force ? DDSF_FORCED : 0) | (rs.no_resync ? DDSF_NO_RESYNC : 0); + dd = drbd_determine_dev_size(device, ddsf, change_al_layout ? &rs : NULL); + drbd_md_sync(device); + put_ldev(device); + if (dd == DS_ERROR) { + retcode = ERR_NOMEM_BITMAP; + goto fail; + } else if (dd == DS_ERROR_SPACE_MD) { + retcode = ERR_MD_LAYOUT_NO_FIT; + goto fail; + } else if (dd == DS_ERROR_SHRINK) { + retcode = ERR_IMPLICIT_SHRINK; + goto fail; } - if (fifo_size != mdev->rs_plan_s.size) { - kfree(mdev->rs_plan_s.values); - mdev->rs_plan_s.values = rs_plan_s; - mdev->rs_plan_s.size = fifo_size; - mdev->rs_planed = 0; - rs_plan_s = NULL; + if (device->state.conn == C_CONNECTED) { + if (dd == DS_GREW) + set_bit(RESIZE_PENDING, &device->flags); + + drbd_send_uuids(first_peer_device(device)); + drbd_send_sizes(first_peer_device(device), 1, ddsf); } - spin_unlock(&mdev->peer_seq_lock); + fail: + mutex_unlock(&adm_ctx.resource->adm_mutex); + finish: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; - if (get_ldev(mdev)) { - wait_event(mdev->al_wait, lc_try_lock(mdev->act_log)); - drbd_al_shrink(mdev); - err = drbd_check_al_size(mdev); - lc_unlock(mdev->act_log); - wake_up(&mdev->al_wait); + fail_ldev: + put_ldev(device); + goto fail; +} - put_ldev(mdev); - drbd_md_sync(mdev); +int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info) +{ + struct drbd_config_context adm_ctx; + enum drbd_ret_code retcode; + struct res_opts res_opts; + int err; - if (err) { - retcode = ERR_NOMEM; - goto fail; - } - } + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto fail; - if (mdev->state.conn >= C_CONNECTED) - drbd_send_sync_param(mdev, &sc); + res_opts = adm_ctx.resource->res_opts; + if (should_set_defaults(info)) + set_res_opts_defaults(&res_opts); - if (!cpumask_equal(mdev->cpu_mask, new_cpu_mask)) { - cpumask_copy(mdev->cpu_mask, new_cpu_mask); - drbd_calc_cpu_mask(mdev); - mdev->receiver.reset_cpu_mask = 1; - mdev->asender.reset_cpu_mask = 1; - mdev->worker.reset_cpu_mask = 1; + err = res_opts_from_attrs(&res_opts, info); + if (err && err != -ENOMSG) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); + goto fail; + } + + mutex_lock(&adm_ctx.resource->adm_mutex); + err = set_resource_options(adm_ctx.resource, &res_opts); + if (err) { + retcode = ERR_INVALID_REQUEST; + if (err == -ENOMEM) + retcode = ERR_NOMEM; } + mutex_unlock(&adm_ctx.resource->adm_mutex); - kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE); fail: - kfree(rs_plan_s); - free_cpumask_var(new_cpu_mask); - crypto_free_hash(csums_tfm); - crypto_free_hash(verify_tfm); - reply->ret_code = retcode; + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -static int drbd_nl_invalidate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info) { - int retcode; + struct drbd_config_context adm_ctx; + struct drbd_device *device; + int retcode; /* enum drbd_ret_code rsp. enum drbd_state_rv */ - /* If there is still bitmap IO pending, probably because of a previous - * resync just being finished, wait for it before requesting a new resync. */ - wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags)); - - retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T), CS_ORDERED); + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - if (retcode < SS_SUCCESS && retcode != SS_NEED_CONNECTION) - retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T)); + mutex_lock(&adm_ctx.resource->adm_mutex); + device = adm_ctx.device; - while (retcode == SS_NEED_CONNECTION) { - spin_lock_irq(&mdev->req_lock); - if (mdev->state.conn < C_CONNECTED) - retcode = _drbd_set_state(_NS(mdev, disk, D_INCONSISTENT), CS_VERBOSE, NULL); - spin_unlock_irq(&mdev->req_lock); + /* If there is still bitmap IO pending, probably because of a previous + * resync just being finished, wait for it before requesting a new resync. + * Also wait for it's after_state_ch(). */ + drbd_suspend_io(device); + wait_event(device->misc_wait, !test_bit(BITMAP_IO, &device->flags)); + drbd_flush_workqueue(&first_peer_device(device)->connection->sender_work); + + /* If we happen to be C_STANDALONE R_SECONDARY, just change to + * D_INCONSISTENT, and set all bits in the bitmap. Otherwise, + * try to start a resync handshake as sync target for full sync. + */ + if (device->state.conn == C_STANDALONE && device->state.role == R_SECONDARY) { + retcode = drbd_request_state(device, NS(disk, D_INCONSISTENT)); + if (retcode >= SS_SUCCESS) { + if (drbd_bitmap_io(device, &drbd_bmio_set_n_write, + "set_n_write from invalidate", BM_LOCKED_MASK)) + retcode = ERR_IO_MD_DISK; + } + } else + retcode = drbd_request_state(device, NS(conn, C_STARTING_SYNC_T)); + drbd_resume_io(device); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; +} - if (retcode != SS_NEED_CONNECTION) - break; +static int drbd_adm_simple_request_state(struct sk_buff *skb, struct genl_info *info, + union drbd_state mask, union drbd_state val) +{ + struct drbd_config_context adm_ctx; + enum drbd_ret_code retcode; - retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T)); - } + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - reply->ret_code = retcode; + mutex_lock(&adm_ctx.resource->adm_mutex); + retcode = drbd_request_state(adm_ctx.device, mask, val); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -static int drbd_bmio_set_susp_al(struct drbd_conf *mdev) +static int drbd_bmio_set_susp_al(struct drbd_device *device) { int rv; - rv = drbd_bmio_set_n_write(mdev); - drbd_suspend_al(mdev); + rv = drbd_bmio_set_n_write(device); + drbd_suspend_al(device); return rv; } -static int drbd_nl_invalidate_peer(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info) { - int retcode; + struct drbd_config_context adm_ctx; + int retcode; /* drbd_ret_code, drbd_state_rv */ + struct drbd_device *device; - /* If there is still bitmap IO pending, probably because of a previous - * resync just being finished, wait for it before requesting a new resync. */ - wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags)); - - retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S), CS_ORDERED); - - if (retcode < SS_SUCCESS) { - if (retcode == SS_NEED_CONNECTION && mdev->state.role == R_PRIMARY) { - /* The peer will get a resync upon connect anyways. Just make that - into a full resync. */ - retcode = drbd_request_state(mdev, NS(pdsk, D_INCONSISTENT)); - if (retcode >= SS_SUCCESS) { - if (drbd_bitmap_io(mdev, &drbd_bmio_set_susp_al, - "set_n_write from invalidate_peer", - BM_LOCKED_SET_ALLOWED)) - retcode = ERR_IO_MD_DISK; - } - } else - retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S)); - } + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - reply->ret_code = retcode; + mutex_lock(&adm_ctx.resource->adm_mutex); + device = adm_ctx.device; + + /* If there is still bitmap IO pending, probably because of a previous + * resync just being finished, wait for it before requesting a new resync. + * Also wait for it's after_state_ch(). */ + drbd_suspend_io(device); + wait_event(device->misc_wait, !test_bit(BITMAP_IO, &device->flags)); + drbd_flush_workqueue(&first_peer_device(device)->connection->sender_work); + + /* If we happen to be C_STANDALONE R_PRIMARY, just set all bits + * in the bitmap. Otherwise, try to start a resync handshake + * as sync source for full sync. + */ + if (device->state.conn == C_STANDALONE && device->state.role == R_PRIMARY) { + /* The peer will get a resync upon connect anyways. Just make that + into a full resync. */ + retcode = drbd_request_state(device, NS(pdsk, D_INCONSISTENT)); + if (retcode >= SS_SUCCESS) { + if (drbd_bitmap_io(device, &drbd_bmio_set_susp_al, + "set_n_write from invalidate_peer", + BM_LOCKED_SET_ALLOWED)) + retcode = ERR_IO_MD_DISK; + } + } else + retcode = drbd_request_state(device, NS(conn, C_STARTING_SYNC_S)); + drbd_resume_io(device); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -static int drbd_nl_pause_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_pause_sync(struct sk_buff *skb, struct genl_info *info) { - int retcode = NO_ERROR; + struct drbd_config_context adm_ctx; + enum drbd_ret_code retcode; - if (drbd_request_state(mdev, NS(user_isp, 1)) == SS_NOTHING_TO_DO) - retcode = ERR_PAUSE_IS_SET; + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - reply->ret_code = retcode; + mutex_lock(&adm_ctx.resource->adm_mutex); + if (drbd_request_state(adm_ctx.device, NS(user_isp, 1)) == SS_NOTHING_TO_DO) + retcode = ERR_PAUSE_IS_SET; + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -static int drbd_nl_resume_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info) { - int retcode = NO_ERROR; - union drbd_state s; + struct drbd_config_context adm_ctx; + union drbd_dev_state s; + enum drbd_ret_code retcode; - if (drbd_request_state(mdev, NS(user_isp, 0)) == SS_NOTHING_TO_DO) { - s = mdev->state; + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; + + mutex_lock(&adm_ctx.resource->adm_mutex); + if (drbd_request_state(adm_ctx.device, NS(user_isp, 0)) == SS_NOTHING_TO_DO) { + s = adm_ctx.device->state; if (s.conn == C_PAUSED_SYNC_S || s.conn == C_PAUSED_SYNC_T) { retcode = s.aftr_isp ? ERR_PIC_AFTER_DEP : s.peer_isp ? ERR_PIC_PEER_DEP : ERR_PAUSE_IS_CLEAR; @@ -2030,622 +2800,861 @@ static int drbd_nl_resume_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n retcode = ERR_PAUSE_IS_CLEAR; } } - - reply->ret_code = retcode; + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -static int drbd_nl_suspend_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_suspend_io(struct sk_buff *skb, struct genl_info *info) { - reply->ret_code = drbd_request_state(mdev, NS(susp, 1)); - - return 0; + return drbd_adm_simple_request_state(skb, info, NS(susp, 1)); } -static int drbd_nl_resume_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info) { - if (test_bit(NEW_CUR_UUID, &mdev->flags)) { - drbd_uuid_new_current(mdev); - clear_bit(NEW_CUR_UUID, &mdev->flags); - } - drbd_suspend_io(mdev); - reply->ret_code = drbd_request_state(mdev, NS3(susp, 0, susp_nod, 0, susp_fen, 0)); - if (reply->ret_code == SS_SUCCESS) { - if (mdev->state.conn < C_CONNECTED) - tl_clear(mdev); - if (mdev->state.disk == D_DISKLESS || mdev->state.disk == D_FAILED) - tl_restart(mdev, fail_frozen_disk_io); - } - drbd_resume_io(mdev); + struct drbd_config_context adm_ctx; + struct drbd_device *device; + int retcode; /* enum drbd_ret_code rsp. enum drbd_state_rv */ + + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; + mutex_lock(&adm_ctx.resource->adm_mutex); + device = adm_ctx.device; + if (test_bit(NEW_CUR_UUID, &device->flags)) { + drbd_uuid_new_current(device); + clear_bit(NEW_CUR_UUID, &device->flags); + } + drbd_suspend_io(device); + retcode = drbd_request_state(device, NS3(susp, 0, susp_nod, 0, susp_fen, 0)); + if (retcode == SS_SUCCESS) { + if (device->state.conn < C_CONNECTED) + tl_clear(first_peer_device(device)->connection); + if (device->state.disk == D_DISKLESS || device->state.disk == D_FAILED) + tl_restart(first_peer_device(device)->connection, FAIL_FROZEN_DISK_IO); + } + drbd_resume_io(device); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -static int drbd_nl_outdate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info) +{ + return drbd_adm_simple_request_state(skb, info, NS(disk, D_OUTDATED)); +} + +static int nla_put_drbd_cfg_context(struct sk_buff *skb, + struct drbd_resource *resource, + struct drbd_connection *connection, + struct drbd_device *device) { - reply->ret_code = drbd_request_state(mdev, NS(disk, D_OUTDATED)); + struct nlattr *nla; + nla = nla_nest_start(skb, DRBD_NLA_CFG_CONTEXT); + if (!nla) + goto nla_put_failure; + if (device && + nla_put_u32(skb, T_ctx_volume, device->vnr)) + goto nla_put_failure; + if (nla_put_string(skb, T_ctx_resource_name, resource->name)) + goto nla_put_failure; + if (connection) { + if (connection->my_addr_len && + nla_put(skb, T_ctx_my_addr, connection->my_addr_len, &connection->my_addr)) + goto nla_put_failure; + if (connection->peer_addr_len && + nla_put(skb, T_ctx_peer_addr, connection->peer_addr_len, &connection->peer_addr)) + goto nla_put_failure; + } + nla_nest_end(skb, nla); return 0; + +nla_put_failure: + if (nla) + nla_nest_cancel(skb, nla); + return -EMSGSIZE; } -static int drbd_nl_get_config(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +/* + * Return the connection of @resource if @resource has exactly one connection. + */ +static struct drbd_connection *the_only_connection(struct drbd_resource *resource) { - unsigned short *tl; + struct list_head *connections = &resource->connections; - tl = reply->tag_list; + if (list_empty(connections) || connections->next->next != connections) + return NULL; + return list_first_entry(&resource->connections, struct drbd_connection, connections); +} - if (get_ldev(mdev)) { - tl = disk_conf_to_tags(mdev, &mdev->ldev->dc, tl); - put_ldev(mdev); - } +int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device, + const struct sib_info *sib) +{ + struct drbd_resource *resource = device->resource; + struct state_info *si = NULL; /* for sizeof(si->member); */ + struct nlattr *nla; + int got_ldev; + int err = 0; + int exclude_sensitive; + + /* If sib != NULL, this is drbd_bcast_event, which anyone can listen + * to. So we better exclude_sensitive information. + * + * If sib == NULL, this is drbd_adm_get_status, executed synchronously + * in the context of the requesting user process. Exclude sensitive + * information, unless current has superuser. + * + * NOTE: for drbd_adm_get_status_all(), this is a netlink dump, and + * relies on the current implementation of netlink_dump(), which + * executes the dump callback successively from netlink_recvmsg(), + * always in the context of the receiving process */ + exclude_sensitive = sib || !capable(CAP_SYS_ADMIN); + + got_ldev = get_ldev(device); + + /* We need to add connection name and volume number information still. + * Minor number is in drbd_genlmsghdr. */ + if (nla_put_drbd_cfg_context(skb, resource, the_only_connection(resource), device)) + goto nla_put_failure; + + if (res_opts_to_skb(skb, &device->resource->res_opts, exclude_sensitive)) + goto nla_put_failure; + + rcu_read_lock(); + if (got_ldev) { + struct disk_conf *disk_conf; + + disk_conf = rcu_dereference(device->ldev->disk_conf); + err = disk_conf_to_skb(skb, disk_conf, exclude_sensitive); + } + if (!err) { + struct net_conf *nc; + + nc = rcu_dereference(first_peer_device(device)->connection->net_conf); + if (nc) + err = net_conf_to_skb(skb, nc, exclude_sensitive); + } + rcu_read_unlock(); + if (err) + goto nla_put_failure; + + nla = nla_nest_start(skb, DRBD_NLA_STATE_INFO); + if (!nla) + goto nla_put_failure; + if (nla_put_u32(skb, T_sib_reason, sib ? sib->sib_reason : SIB_GET_STATUS_REPLY) || + nla_put_u32(skb, T_current_state, device->state.i) || + nla_put_u64(skb, T_ed_uuid, device->ed_uuid) || + nla_put_u64(skb, T_capacity, drbd_get_capacity(device->this_bdev)) || + nla_put_u64(skb, T_send_cnt, device->send_cnt) || + nla_put_u64(skb, T_recv_cnt, device->recv_cnt) || + nla_put_u64(skb, T_read_cnt, device->read_cnt) || + nla_put_u64(skb, T_writ_cnt, device->writ_cnt) || + nla_put_u64(skb, T_al_writ_cnt, device->al_writ_cnt) || + nla_put_u64(skb, T_bm_writ_cnt, device->bm_writ_cnt) || + nla_put_u32(skb, T_ap_bio_cnt, atomic_read(&device->ap_bio_cnt)) || + nla_put_u32(skb, T_ap_pending_cnt, atomic_read(&device->ap_pending_cnt)) || + nla_put_u32(skb, T_rs_pending_cnt, atomic_read(&device->rs_pending_cnt))) + goto nla_put_failure; + + if (got_ldev) { + int err; - if (get_net_conf(mdev)) { - tl = net_conf_to_tags(mdev, mdev->net_conf, tl); - put_net_conf(mdev); + spin_lock_irq(&device->ldev->md.uuid_lock); + err = nla_put(skb, T_uuids, sizeof(si->uuids), device->ldev->md.uuid); + spin_unlock_irq(&device->ldev->md.uuid_lock); + + if (err) + goto nla_put_failure; + + if (nla_put_u32(skb, T_disk_flags, device->ldev->md.flags) || + nla_put_u64(skb, T_bits_total, drbd_bm_bits(device)) || + nla_put_u64(skb, T_bits_oos, drbd_bm_total_weight(device))) + goto nla_put_failure; + if (C_SYNC_SOURCE <= device->state.conn && + C_PAUSED_SYNC_T >= device->state.conn) { + if (nla_put_u64(skb, T_bits_rs_total, device->rs_total) || + nla_put_u64(skb, T_bits_rs_failed, device->rs_failed)) + goto nla_put_failure; + } } - tl = syncer_conf_to_tags(mdev, &mdev->sync_conf, tl); - put_unaligned(TT_END, tl++); /* Close the tag list */ + if (sib) { + switch(sib->sib_reason) { + case SIB_SYNC_PROGRESS: + case SIB_GET_STATUS_REPLY: + break; + case SIB_STATE_CHANGE: + if (nla_put_u32(skb, T_prev_state, sib->os.i) || + nla_put_u32(skb, T_new_state, sib->ns.i)) + goto nla_put_failure; + break; + case SIB_HELPER_POST: + if (nla_put_u32(skb, T_helper_exit_code, + sib->helper_exit_code)) + goto nla_put_failure; + /* fall through */ + case SIB_HELPER_PRE: + if (nla_put_string(skb, T_helper, sib->helper_name)) + goto nla_put_failure; + break; + } + } + nla_nest_end(skb, nla); - return (int)((char *)tl - (char *)reply->tag_list); + if (0) +nla_put_failure: + err = -EMSGSIZE; + if (got_ldev) + put_ldev(device); + return err; } -static int drbd_nl_get_state(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info) { - unsigned short *tl = reply->tag_list; - union drbd_state s = mdev->state; - unsigned long rs_left; - unsigned int res; + struct drbd_config_context adm_ctx; + enum drbd_ret_code retcode; + int err; - tl = get_state_to_tags(mdev, (struct get_state *)&s, tl); + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - /* no local ref, no bitmap, no syncer progress. */ - if (s.conn >= C_SYNC_SOURCE && s.conn <= C_PAUSED_SYNC_T) { - if (get_ldev(mdev)) { - drbd_get_syncer_progress(mdev, &rs_left, &res); - tl = tl_add_int(tl, T_sync_progress, &res); - put_ldev(mdev); - } + err = nla_put_status_info(adm_ctx.reply_skb, adm_ctx.device, NULL); + if (err) { + nlmsg_free(adm_ctx.reply_skb); + return err; } - put_unaligned(TT_END, tl++); /* Close the tag list */ - - return (int)((char *)tl - (char *)reply->tag_list); +out: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; } -static int drbd_nl_get_uuids(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +static int get_one_status(struct sk_buff *skb, struct netlink_callback *cb) { - unsigned short *tl; + struct drbd_device *device; + struct drbd_genlmsghdr *dh; + struct drbd_resource *pos = (struct drbd_resource *)cb->args[0]; + struct drbd_resource *resource = NULL; + struct drbd_resource *tmp; + unsigned volume = cb->args[1]; + + /* Open coded, deferred, iteration: + * for_each_resource_safe(resource, tmp, &drbd_resources) { + * connection = "first connection of resource or undefined"; + * idr_for_each_entry(&resource->devices, device, i) { + * ... + * } + * } + * where resource is cb->args[0]; + * and i is cb->args[1]; + * + * cb->args[2] indicates if we shall loop over all resources, + * or just dump all volumes of a single resource. + * + * This may miss entries inserted after this dump started, + * or entries deleted before they are reached. + * + * We need to make sure the device won't disappear while + * we are looking at it, and revalidate our iterators + * on each iteration. + */ - tl = reply->tag_list; + /* synchronize with conn_create()/drbd_destroy_connection() */ + rcu_read_lock(); + /* revalidate iterator position */ + for_each_resource_rcu(tmp, &drbd_resources) { + if (pos == NULL) { + /* first iteration */ + pos = tmp; + resource = pos; + break; + } + if (tmp == pos) { + resource = pos; + break; + } + } + if (resource) { +next_resource: + device = idr_get_next(&resource->devices, &volume); + if (!device) { + /* No more volumes to dump on this resource. + * Advance resource iterator. */ + pos = list_entry_rcu(resource->resources.next, + struct drbd_resource, resources); + /* Did we dump any volume of this resource yet? */ + if (volume != 0) { + /* If we reached the end of the list, + * or only a single resource dump was requested, + * we are done. */ + if (&pos->resources == &drbd_resources || cb->args[2]) + goto out; + volume = 0; + resource = pos; + goto next_resource; + } + } - if (get_ldev(mdev)) { - tl = tl_add_blob(tl, T_uuids, mdev->ldev->md.uuid, UI_SIZE*sizeof(u64)); - tl = tl_add_int(tl, T_uuids_flags, &mdev->ldev->md.flags); - put_ldev(mdev); + dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &drbd_genl_family, + NLM_F_MULTI, DRBD_ADM_GET_STATUS); + if (!dh) + goto out; + + if (!device) { + /* This is a connection without a single volume. + * Suprisingly enough, it may have a network + * configuration. */ + struct drbd_connection *connection; + + dh->minor = -1U; + dh->ret_code = NO_ERROR; + connection = the_only_connection(resource); + if (nla_put_drbd_cfg_context(skb, resource, connection, NULL)) + goto cancel; + if (connection) { + struct net_conf *nc; + + nc = rcu_dereference(connection->net_conf); + if (nc && net_conf_to_skb(skb, nc, 1) != 0) + goto cancel; + } + goto done; + } + + D_ASSERT(device, device->vnr == volume); + D_ASSERT(device, device->resource == resource); + + dh->minor = device_to_minor(device); + dh->ret_code = NO_ERROR; + + if (nla_put_status_info(skb, device, NULL)) { +cancel: + genlmsg_cancel(skb, dh); + goto out; + } +done: + genlmsg_end(skb, dh); } - put_unaligned(TT_END, tl++); /* Close the tag list */ - return (int)((char *)tl - (char *)reply->tag_list); +out: + rcu_read_unlock(); + /* where to start the next iteration */ + cb->args[0] = (long)pos; + cb->args[1] = (pos == resource) ? volume + 1 : 0; + + /* No more resources/volumes/minors found results in an empty skb. + * Which will terminate the dump. */ + return skb->len; } -/** - * drbd_nl_get_timeout_flag() - Used by drbdsetup to find out which timeout value to use - * @mdev: DRBD device. - * @nlp: Netlink/connector packet from drbdsetup - * @reply: Reply packet for drbdsetup +/* + * Request status of all resources, or of all volumes within a single resource. + * + * This is a dump, as the answer may not fit in a single reply skb otherwise. + * Which means we cannot use the family->attrbuf or other such members, because + * dump is NOT protected by the genl_lock(). During dump, we only have access + * to the incoming skb, and need to opencode "parsing" of the nlattr payload. + * + * Once things are setup properly, we call into get_one_status(). */ -static int drbd_nl_get_timeout_flag(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb) { - unsigned short *tl; - char rv; + const unsigned hdrlen = GENL_HDRLEN + GENL_MAGIC_FAMILY_HDRSZ; + struct nlattr *nla; + const char *resource_name; + struct drbd_resource *resource; + int maxtype; + + /* Is this a followup call? */ + if (cb->args[0]) { + /* ... of a single resource dump, + * and the resource iterator has been advanced already? */ + if (cb->args[2] && cb->args[2] != cb->args[0]) + return 0; /* DONE. */ + goto dump; + } + + /* First call (from netlink_dump_start). We need to figure out + * which resource(s) the user wants us to dump. */ + nla = nla_find(nlmsg_attrdata(cb->nlh, hdrlen), + nlmsg_attrlen(cb->nlh, hdrlen), + DRBD_NLA_CFG_CONTEXT); + + /* No explicit context given. Dump all. */ + if (!nla) + goto dump; + maxtype = ARRAY_SIZE(drbd_cfg_context_nl_policy) - 1; + nla = drbd_nla_find_nested(maxtype, nla, __nla_type(T_ctx_resource_name)); + if (IS_ERR(nla)) + return PTR_ERR(nla); + /* context given, but no name present? */ + if (!nla) + return -EINVAL; + resource_name = nla_data(nla); + if (!*resource_name) + return -ENODEV; + resource = drbd_find_resource(resource_name); + if (!resource) + return -ENODEV; + + kref_put(&resource->kref, drbd_destroy_resource); /* get_one_status() revalidates the resource */ + + /* prime iterators, and set "filter" mode mark: + * only dump this connection. */ + cb->args[0] = (long)resource; + /* cb->args[1] = 0; passed in this way. */ + cb->args[2] = (long)resource; + +dump: + return get_one_status(skb, cb); +} - tl = reply->tag_list; +int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info) +{ + struct drbd_config_context adm_ctx; + enum drbd_ret_code retcode; + struct timeout_parms tp; + int err; - rv = mdev->state.pdsk == D_OUTDATED ? UT_PEER_OUTDATED : - test_bit(USE_DEGR_WFC_T, &mdev->flags) ? UT_DEGRADED : UT_DEFAULT; + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - tl = tl_add_blob(tl, T_use_degraded, &rv, sizeof(rv)); - put_unaligned(TT_END, tl++); /* Close the tag list */ + tp.timeout_type = + adm_ctx.device->state.pdsk == D_OUTDATED ? UT_PEER_OUTDATED : + test_bit(USE_DEGR_WFC_T, &adm_ctx.device->flags) ? UT_DEGRADED : + UT_DEFAULT; - return (int)((char *)tl - (char *)reply->tag_list); + err = timeout_parms_to_priv_skb(adm_ctx.reply_skb, &tp); + if (err) { + nlmsg_free(adm_ctx.reply_skb); + return err; + } +out: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; } -static int drbd_nl_start_ov(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info) { - /* default to resume from last known position, if possible */ - struct start_ov args = - { .start_sector = mdev->ov_start_sector }; + struct drbd_config_context adm_ctx; + struct drbd_device *device; + enum drbd_ret_code retcode; + struct start_ov_parms parms; - if (!start_ov_from_tags(mdev, nlp->tag_list, &args)) { - reply->ret_code = ERR_MANDATORY_TAG; - return 0; + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; + + device = adm_ctx.device; + + /* resume from last known position, if possible */ + parms.ov_start_sector = device->ov_start_sector; + parms.ov_stop_sector = ULLONG_MAX; + if (info->attrs[DRBD_NLA_START_OV_PARMS]) { + int err = start_ov_parms_from_attrs(&parms, info); + if (err) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); + goto out; + } } + mutex_lock(&adm_ctx.resource->adm_mutex); + + /* w_make_ov_request expects position to be aligned */ + device->ov_start_sector = parms.ov_start_sector & ~(BM_SECT_PER_BIT-1); + device->ov_stop_sector = parms.ov_stop_sector; /* If there is still bitmap IO pending, e.g. previous resync or verify * just being finished, wait for it before requesting a new resync. */ - wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags)); + drbd_suspend_io(device); + wait_event(device->misc_wait, !test_bit(BITMAP_IO, &device->flags)); + retcode = drbd_request_state(device, NS(conn, C_VERIFY_S)); + drbd_resume_io(device); - /* w_make_ov_request expects position to be aligned */ - mdev->ov_start_sector = args.start_sector & ~BM_SECT_PER_BIT; - reply->ret_code = drbd_request_state(mdev,NS(conn,C_VERIFY_S)); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -static int drbd_nl_new_c_uuid(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, - struct drbd_nl_cfg_reply *reply) +int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info) { - int retcode = NO_ERROR; + struct drbd_config_context adm_ctx; + struct drbd_device *device; + enum drbd_ret_code retcode; int skip_initial_sync = 0; int err; + struct new_c_uuid_parms args; - struct new_c_uuid args; + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out_nolock; - memset(&args, 0, sizeof(struct new_c_uuid)); - if (!new_c_uuid_from_tags(mdev, nlp->tag_list, &args)) { - reply->ret_code = ERR_MANDATORY_TAG; - return 0; + device = adm_ctx.device; + memset(&args, 0, sizeof(args)); + if (info->attrs[DRBD_NLA_NEW_C_UUID_PARMS]) { + err = new_c_uuid_parms_from_attrs(&args, info); + if (err) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); + goto out_nolock; + } } - mutex_lock(&mdev->state_mutex); /* Protects us against serialized state changes. */ + mutex_lock(&adm_ctx.resource->adm_mutex); + mutex_lock(device->state_mutex); /* Protects us against serialized state changes. */ - if (!get_ldev(mdev)) { + if (!get_ldev(device)) { retcode = ERR_NO_DISK; goto out; } /* this is "skip initial sync", assume to be clean */ - if (mdev->state.conn == C_CONNECTED && mdev->agreed_pro_version >= 90 && - mdev->ldev->md.uuid[UI_CURRENT] == UUID_JUST_CREATED && args.clear_bm) { - dev_info(DEV, "Preparing to skip initial sync\n"); + if (device->state.conn == C_CONNECTED && + first_peer_device(device)->connection->agreed_pro_version >= 90 && + device->ldev->md.uuid[UI_CURRENT] == UUID_JUST_CREATED && args.clear_bm) { + drbd_info(device, "Preparing to skip initial sync\n"); skip_initial_sync = 1; - } else if (mdev->state.conn != C_STANDALONE) { + } else if (device->state.conn != C_STANDALONE) { retcode = ERR_CONNECTED; goto out_dec; } - drbd_uuid_set(mdev, UI_BITMAP, 0); /* Rotate UI_BITMAP to History 1, etc... */ - drbd_uuid_new_current(mdev); /* New current, previous to UI_BITMAP */ + drbd_uuid_set(device, UI_BITMAP, 0); /* Rotate UI_BITMAP to History 1, etc... */ + drbd_uuid_new_current(device); /* New current, previous to UI_BITMAP */ if (args.clear_bm) { - err = drbd_bitmap_io(mdev, &drbd_bmio_clear_n_write, + err = drbd_bitmap_io(device, &drbd_bmio_clear_n_write, "clear_n_write from new_c_uuid", BM_LOCKED_MASK); if (err) { - dev_err(DEV, "Writing bitmap failed with %d\n",err); + drbd_err(device, "Writing bitmap failed with %d\n", err); retcode = ERR_IO_MD_DISK; } if (skip_initial_sync) { - drbd_send_uuids_skip_initial_sync(mdev); - _drbd_uuid_set(mdev, UI_BITMAP, 0); - drbd_print_uuids(mdev, "cleared bitmap UUID"); - spin_lock_irq(&mdev->req_lock); - _drbd_set_state(_NS2(mdev, disk, D_UP_TO_DATE, pdsk, D_UP_TO_DATE), + drbd_send_uuids_skip_initial_sync(first_peer_device(device)); + _drbd_uuid_set(device, UI_BITMAP, 0); + drbd_print_uuids(device, "cleared bitmap UUID"); + spin_lock_irq(&device->resource->req_lock); + _drbd_set_state(_NS2(device, disk, D_UP_TO_DATE, pdsk, D_UP_TO_DATE), CS_VERBOSE, NULL); - spin_unlock_irq(&mdev->req_lock); + spin_unlock_irq(&device->resource->req_lock); } } - drbd_md_sync(mdev); + drbd_md_sync(device); out_dec: - put_ldev(mdev); + put_ldev(device); out: - mutex_unlock(&mdev->state_mutex); - - reply->ret_code = retcode; + mutex_unlock(device->state_mutex); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out_nolock: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -struct cn_handler_struct { - int (*function)(struct drbd_conf *, - struct drbd_nl_cfg_req *, - struct drbd_nl_cfg_reply *); - int reply_body_size; -}; - -static struct cn_handler_struct cnd_table[] = { - [ P_primary ] = { &drbd_nl_primary, 0 }, - [ P_secondary ] = { &drbd_nl_secondary, 0 }, - [ P_disk_conf ] = { &drbd_nl_disk_conf, 0 }, - [ P_detach ] = { &drbd_nl_detach, 0 }, - [ P_net_conf ] = { &drbd_nl_net_conf, 0 }, - [ P_disconnect ] = { &drbd_nl_disconnect, 0 }, - [ P_resize ] = { &drbd_nl_resize, 0 }, - [ P_syncer_conf ] = { &drbd_nl_syncer_conf, 0 }, - [ P_invalidate ] = { &drbd_nl_invalidate, 0 }, - [ P_invalidate_peer ] = { &drbd_nl_invalidate_peer, 0 }, - [ P_pause_sync ] = { &drbd_nl_pause_sync, 0 }, - [ P_resume_sync ] = { &drbd_nl_resume_sync, 0 }, - [ P_suspend_io ] = { &drbd_nl_suspend_io, 0 }, - [ P_resume_io ] = { &drbd_nl_resume_io, 0 }, - [ P_outdate ] = { &drbd_nl_outdate, 0 }, - [ P_get_config ] = { &drbd_nl_get_config, - sizeof(struct syncer_conf_tag_len_struct) + - sizeof(struct disk_conf_tag_len_struct) + - sizeof(struct net_conf_tag_len_struct) }, - [ P_get_state ] = { &drbd_nl_get_state, - sizeof(struct get_state_tag_len_struct) + - sizeof(struct sync_progress_tag_len_struct) }, - [ P_get_uuids ] = { &drbd_nl_get_uuids, - sizeof(struct get_uuids_tag_len_struct) }, - [ P_get_timeout_flag ] = { &drbd_nl_get_timeout_flag, - sizeof(struct get_timeout_flag_tag_len_struct)}, - [ P_start_ov ] = { &drbd_nl_start_ov, 0 }, - [ P_new_c_uuid ] = { &drbd_nl_new_c_uuid, 0 }, -}; - -static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms *nsp) +static enum drbd_ret_code +drbd_check_resource_name(struct drbd_config_context *adm_ctx) { - struct drbd_nl_cfg_req *nlp = (struct drbd_nl_cfg_req *)req->data; - struct cn_handler_struct *cm; - struct cn_msg *cn_reply; - struct drbd_nl_cfg_reply *reply; - struct drbd_conf *mdev; - int retcode, rr; - int reply_size = sizeof(struct cn_msg) - + sizeof(struct drbd_nl_cfg_reply) - + sizeof(short int); - - if (!try_module_get(THIS_MODULE)) { - printk(KERN_ERR "drbd: try_module_get() failed!\n"); - return; - } + const char *name = adm_ctx->resource_name; + if (!name || !name[0]) { + drbd_msg_put_info(adm_ctx->reply_skb, "resource name missing"); + return ERR_MANDATORY_TAG; + } + /* if we want to use these in sysfs/configfs/debugfs some day, + * we must not allow slashes */ + if (strchr(name, '/')) { + drbd_msg_put_info(adm_ctx->reply_skb, "invalid resource name"); + return ERR_INVALID_REQUEST; + } + return NO_ERROR; +} - if (!cap_raised(current_cap(), CAP_SYS_ADMIN)) { - retcode = ERR_PERM; - goto fail; - } +int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info) +{ + struct drbd_config_context adm_ctx; + enum drbd_ret_code retcode; + struct res_opts res_opts; + int err; - mdev = ensure_mdev(nlp->drbd_minor, - (nlp->flags & DRBD_NL_CREATE_DEVICE)); - if (!mdev) { - retcode = ERR_MINOR_INVALID; - goto fail; - } + retcode = drbd_adm_prepare(&adm_ctx, skb, info, 0); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - if (nlp->packet_type >= P_nl_after_last_packet || - nlp->packet_type == P_return_code_only) { - retcode = ERR_PACKET_NR; - goto fail; + set_res_opts_defaults(&res_opts); + err = res_opts_from_attrs(&res_opts, info); + if (err && err != -ENOMSG) { + retcode = ERR_MANDATORY_TAG; + drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err)); + goto out; } - cm = cnd_table + nlp->packet_type; + retcode = drbd_check_resource_name(&adm_ctx); + if (retcode != NO_ERROR) + goto out; - /* This may happen if packet number is 0: */ - if (cm->function == NULL) { - retcode = ERR_PACKET_NR; - goto fail; + if (adm_ctx.resource) { + if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) { + retcode = ERR_INVALID_REQUEST; + drbd_msg_put_info(adm_ctx.reply_skb, "resource exists"); + } + /* else: still NO_ERROR */ + goto out; } - reply_size += cm->reply_body_size; - - /* allocation not in the IO path, cqueue thread context */ - cn_reply = kzalloc(reply_size, GFP_KERNEL); - if (!cn_reply) { + /* not yet safe for genl_family.parallel_ops */ + if (!conn_create(adm_ctx.resource_name, &res_opts)) retcode = ERR_NOMEM; - goto fail; - } - reply = (struct drbd_nl_cfg_reply *) cn_reply->data; - - reply->packet_type = - cm->reply_body_size ? nlp->packet_type : P_return_code_only; - reply->minor = nlp->drbd_minor; - reply->ret_code = NO_ERROR; /* Might by modified by cm->function. */ - /* reply->tag_list; might be modified by cm->function. */ - - rr = cm->function(mdev, nlp, reply); - - cn_reply->id = req->id; - cn_reply->seq = req->seq; - cn_reply->ack = req->ack + 1; - cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + rr; - cn_reply->flags = 0; - - rr = cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_KERNEL); - if (rr && rr != -ESRCH) - printk(KERN_INFO "drbd: cn_netlink_send()=%d\n", rr); - - kfree(cn_reply); - module_put(THIS_MODULE); - return; - fail: - drbd_nl_send_reply(req, retcode); - module_put(THIS_MODULE); +out: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; } -static atomic_t drbd_nl_seq = ATOMIC_INIT(2); /* two. */ - -static unsigned short * -__tl_add_blob(unsigned short *tl, enum drbd_tags tag, const void *data, - unsigned short len, int nul_terminated) +int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info) { - unsigned short l = tag_descriptions[tag_number(tag)].max_len; - len = (len < l) ? len : l; - put_unaligned(tag, tl++); - put_unaligned(len, tl++); - memcpy(tl, data, len); - tl = (unsigned short*)((char*)tl + len); - if (nul_terminated) - *((char*)tl - 1) = 0; - return tl; -} + struct drbd_config_context adm_ctx; + struct drbd_genlmsghdr *dh = info->userhdr; + enum drbd_ret_code retcode; -static unsigned short * -tl_add_blob(unsigned short *tl, enum drbd_tags tag, const void *data, int len) -{ - return __tl_add_blob(tl, tag, data, len, 0); -} + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; -static unsigned short * -tl_add_str(unsigned short *tl, enum drbd_tags tag, const char *str) -{ - return __tl_add_blob(tl, tag, str, strlen(str)+1, 0); -} + if (dh->minor > MINORMASK) { + drbd_msg_put_info(adm_ctx.reply_skb, "requested minor out of range"); + retcode = ERR_INVALID_REQUEST; + goto out; + } + if (adm_ctx.volume > DRBD_VOLUME_MAX) { + drbd_msg_put_info(adm_ctx.reply_skb, "requested volume id out of range"); + retcode = ERR_INVALID_REQUEST; + goto out; + } -static unsigned short * -tl_add_int(unsigned short *tl, enum drbd_tags tag, const void *val) -{ - put_unaligned(tag, tl++); - switch(tag_type(tag)) { - case TT_INTEGER: - put_unaligned(sizeof(int), tl++); - put_unaligned(*(int *)val, (int *)tl); - tl = (unsigned short*)((char*)tl+sizeof(int)); - break; - case TT_INT64: - put_unaligned(sizeof(u64), tl++); - put_unaligned(*(u64 *)val, (u64 *)tl); - tl = (unsigned short*)((char*)tl+sizeof(u64)); - break; - default: - /* someone did something stupid. */ - ; + /* drbd_adm_prepare made sure already + * that first_peer_device(device)->connection and device->vnr match the request. */ + if (adm_ctx.device) { + if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) + retcode = ERR_MINOR_EXISTS; + /* else: still NO_ERROR */ + goto out; } - return tl; + + mutex_lock(&adm_ctx.resource->adm_mutex); + retcode = drbd_create_device(&adm_ctx, dh->minor); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; } -void drbd_bcast_state(struct drbd_conf *mdev, union drbd_state state) +static enum drbd_ret_code adm_del_minor(struct drbd_device *device) { - char buffer[sizeof(struct cn_msg)+ - sizeof(struct drbd_nl_cfg_reply)+ - sizeof(struct get_state_tag_len_struct)+ - sizeof(short int)]; - struct cn_msg *cn_reply = (struct cn_msg *) buffer; - struct drbd_nl_cfg_reply *reply = - (struct drbd_nl_cfg_reply *)cn_reply->data; - unsigned short *tl = reply->tag_list; - - /* dev_warn(DEV, "drbd_bcast_state() got called\n"); */ - - tl = get_state_to_tags(mdev, (struct get_state *)&state, tl); - - put_unaligned(TT_END, tl++); /* Close the tag list */ - - cn_reply->id.idx = CN_IDX_DRBD; - cn_reply->id.val = CN_VAL_DRBD; - - cn_reply->seq = atomic_add_return(1, &drbd_nl_seq); - cn_reply->ack = 0; /* not used here. */ - cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + - (int)((char *)tl - (char *)reply->tag_list); - cn_reply->flags = 0; - - reply->packet_type = P_get_state; - reply->minor = mdev_to_minor(mdev); - reply->ret_code = NO_ERROR; - - cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); + if (device->state.disk == D_DISKLESS && + /* no need to be device->state.conn == C_STANDALONE && + * we may want to delete a minor from a live replication group. + */ + device->state.role == R_SECONDARY) { + _drbd_request_state(device, NS(conn, C_WF_REPORT_PARAMS), + CS_VERBOSE + CS_WAIT_COMPLETE); + drbd_delete_device(device); + return NO_ERROR; + } else + return ERR_MINOR_CONFIGURED; } -void drbd_bcast_ev_helper(struct drbd_conf *mdev, char *helper_name) +int drbd_adm_del_minor(struct sk_buff *skb, struct genl_info *info) { - char buffer[sizeof(struct cn_msg)+ - sizeof(struct drbd_nl_cfg_reply)+ - sizeof(struct call_helper_tag_len_struct)+ - sizeof(short int)]; - struct cn_msg *cn_reply = (struct cn_msg *) buffer; - struct drbd_nl_cfg_reply *reply = - (struct drbd_nl_cfg_reply *)cn_reply->data; - unsigned short *tl = reply->tag_list; - - /* dev_warn(DEV, "drbd_bcast_state() got called\n"); */ - - tl = tl_add_str(tl, T_helper, helper_name); - put_unaligned(TT_END, tl++); /* Close the tag list */ - - cn_reply->id.idx = CN_IDX_DRBD; - cn_reply->id.val = CN_VAL_DRBD; - - cn_reply->seq = atomic_add_return(1, &drbd_nl_seq); - cn_reply->ack = 0; /* not used here. */ - cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + - (int)((char *)tl - (char *)reply->tag_list); - cn_reply->flags = 0; + struct drbd_config_context adm_ctx; + enum drbd_ret_code retcode; - reply->packet_type = P_call_helper; - reply->minor = mdev_to_minor(mdev); - reply->ret_code = NO_ERROR; + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto out; - cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); + mutex_lock(&adm_ctx.resource->adm_mutex); + retcode = adm_del_minor(adm_ctx.device); + mutex_unlock(&adm_ctx.resource->adm_mutex); +out: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; } -void drbd_bcast_ee(struct drbd_conf *mdev, - const char *reason, const int dgs, - const char* seen_hash, const char* calc_hash, - const struct drbd_epoch_entry* e) +int drbd_adm_down(struct sk_buff *skb, struct genl_info *info) { - struct cn_msg *cn_reply; - struct drbd_nl_cfg_reply *reply; - unsigned short *tl; - struct page *page; - unsigned len; - - if (!e) - return; - if (!reason || !reason[0]) - return; + struct drbd_config_context adm_ctx; + struct drbd_resource *resource; + struct drbd_connection *connection; + struct drbd_device *device; + int retcode; /* enum drbd_ret_code rsp. enum drbd_state_rv */ + unsigned i; + + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto finish; + + resource = adm_ctx.resource; + mutex_lock(&resource->adm_mutex); + /* demote */ + for_each_connection(connection, resource) { + struct drbd_peer_device *peer_device; + + idr_for_each_entry(&connection->peer_devices, peer_device, i) { + retcode = drbd_set_role(peer_device->device, R_SECONDARY, 0); + if (retcode < SS_SUCCESS) { + drbd_msg_put_info(adm_ctx.reply_skb, "failed to demote"); + goto out; + } + } - /* apparently we have to memcpy twice, first to prepare the data for the - * struct cn_msg, then within cn_netlink_send from the cn_msg to the - * netlink skb. */ - /* receiver thread context, which is not in the writeout path (of this node), - * but may be in the writeout path of the _other_ node. - * GFP_NOIO to avoid potential "distributed deadlock". */ - cn_reply = kzalloc( - sizeof(struct cn_msg)+ - sizeof(struct drbd_nl_cfg_reply)+ - sizeof(struct dump_ee_tag_len_struct)+ - sizeof(short int), - GFP_NOIO); - - if (!cn_reply) { - dev_err(DEV, "could not kmalloc buffer for drbd_bcast_ee, sector %llu, size %u\n", - (unsigned long long)e->sector, e->size); - return; + retcode = conn_try_disconnect(connection, 0); + if (retcode < SS_SUCCESS) { + drbd_msg_put_info(adm_ctx.reply_skb, "failed to disconnect"); + goto out; + } } - reply = (struct drbd_nl_cfg_reply*)cn_reply->data; - tl = reply->tag_list; - - tl = tl_add_str(tl, T_dump_ee_reason, reason); - tl = tl_add_blob(tl, T_seen_digest, seen_hash, dgs); - tl = tl_add_blob(tl, T_calc_digest, calc_hash, dgs); - tl = tl_add_int(tl, T_ee_sector, &e->sector); - tl = tl_add_int(tl, T_ee_block_id, &e->block_id); - - /* dump the first 32k */ - len = min_t(unsigned, e->size, 32 << 10); - put_unaligned(T_ee_data, tl++); - put_unaligned(len, tl++); - - page = e->pages; - page_chain_for_each(page) { - void *d = kmap_atomic(page, KM_USER0); - unsigned l = min_t(unsigned, len, PAGE_SIZE); - memcpy(tl, d, l); - kunmap_atomic(d, KM_USER0); - tl = (unsigned short*)((char*)tl + l); - len -= l; - if (len == 0) - break; + /* detach */ + idr_for_each_entry(&resource->devices, device, i) { + retcode = adm_detach(device, 0); + if (retcode < SS_SUCCESS || retcode > NO_ERROR) { + drbd_msg_put_info(adm_ctx.reply_skb, "failed to detach"); + goto out; + } } - put_unaligned(TT_END, tl++); /* Close the tag list */ - - cn_reply->id.idx = CN_IDX_DRBD; - cn_reply->id.val = CN_VAL_DRBD; - cn_reply->seq = atomic_add_return(1,&drbd_nl_seq); - cn_reply->ack = 0; // not used here. - cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + - (int)((char*)tl - (char*)reply->tag_list); - cn_reply->flags = 0; - - reply->packet_type = P_dump_ee; - reply->minor = mdev_to_minor(mdev); - reply->ret_code = NO_ERROR; - - cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); - kfree(cn_reply); -} - -void drbd_bcast_sync_progress(struct drbd_conf *mdev) -{ - char buffer[sizeof(struct cn_msg)+ - sizeof(struct drbd_nl_cfg_reply)+ - sizeof(struct sync_progress_tag_len_struct)+ - sizeof(short int)]; - struct cn_msg *cn_reply = (struct cn_msg *) buffer; - struct drbd_nl_cfg_reply *reply = - (struct drbd_nl_cfg_reply *)cn_reply->data; - unsigned short *tl = reply->tag_list; - unsigned long rs_left; - unsigned int res; - - /* no local ref, no bitmap, no syncer progress, no broadcast. */ - if (!get_ldev(mdev)) - return; - drbd_get_syncer_progress(mdev, &rs_left, &res); - put_ldev(mdev); + /* If we reach this, all volumes (of this connection) are Secondary, + * Disconnected, Diskless, aka Unconfigured. Make sure all threads have + * actually stopped, state handling only does drbd_thread_stop_nowait(). */ + for_each_connection(connection, resource) + drbd_thread_stop(&connection->worker); - tl = tl_add_int(tl, T_sync_progress, &res); - put_unaligned(TT_END, tl++); /* Close the tag list */ + /* Now, nothing can fail anymore */ - cn_reply->id.idx = CN_IDX_DRBD; - cn_reply->id.val = CN_VAL_DRBD; - - cn_reply->seq = atomic_add_return(1, &drbd_nl_seq); - cn_reply->ack = 0; /* not used here. */ - cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + - (int)((char *)tl - (char *)reply->tag_list); - cn_reply->flags = 0; - - reply->packet_type = P_sync_progress; - reply->minor = mdev_to_minor(mdev); - reply->ret_code = NO_ERROR; + /* delete volumes */ + idr_for_each_entry(&resource->devices, device, i) { + retcode = adm_del_minor(device); + if (retcode != NO_ERROR) { + /* "can not happen" */ + drbd_msg_put_info(adm_ctx.reply_skb, "failed to delete volume"); + goto out; + } + } - cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); + list_del_rcu(&resource->resources); + synchronize_rcu(); + drbd_free_resource(resource); + retcode = NO_ERROR; +out: + mutex_unlock(&resource->adm_mutex); +finish: + drbd_adm_finish(&adm_ctx, info, retcode); + return 0; } -int __init drbd_nl_init(void) +int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info) { - static struct cb_id cn_id_drbd; - int err, try=10; + struct drbd_config_context adm_ctx; + struct drbd_resource *resource; + struct drbd_connection *connection; + enum drbd_ret_code retcode; - cn_id_drbd.val = CN_VAL_DRBD; - do { - cn_id_drbd.idx = cn_idx; - err = cn_add_callback(&cn_id_drbd, "cn_drbd", &drbd_connector_callback); - if (!err) - break; - cn_idx = (cn_idx + CN_IDX_STEP); - } while (try--); + retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE); + if (!adm_ctx.reply_skb) + return retcode; + if (retcode != NO_ERROR) + goto finish; - if (err) { - printk(KERN_ERR "drbd: cn_drbd failed to register\n"); - return err; + resource = adm_ctx.resource; + mutex_lock(&resource->adm_mutex); + for_each_connection(connection, resource) { + if (connection->cstate > C_STANDALONE) { + retcode = ERR_NET_CONFIGURED; + goto out; + } + } + if (!idr_is_empty(&resource->devices)) { + retcode = ERR_RES_IN_USE; + goto out; } + list_del_rcu(&resource->resources); + for_each_connection(connection, resource) + drbd_thread_stop(&connection->worker); + synchronize_rcu(); + drbd_free_resource(resource); + retcode = NO_ERROR; +out: + mutex_unlock(&resource->adm_mutex); +finish: + drbd_adm_finish(&adm_ctx, info, retcode); return 0; } -void drbd_nl_cleanup(void) +void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib) { - static struct cb_id cn_id_drbd; - - cn_id_drbd.idx = cn_idx; - cn_id_drbd.val = CN_VAL_DRBD; - - cn_del_callback(&cn_id_drbd); -} + static atomic_t drbd_genl_seq = ATOMIC_INIT(2); /* two. */ + struct sk_buff *msg; + struct drbd_genlmsghdr *d_out; + unsigned seq; + int err = -ENOMEM; + + if (sib->sib_reason == SIB_SYNC_PROGRESS) { + if (time_after(jiffies, device->rs_last_bcast + HZ)) + device->rs_last_bcast = jiffies; + else + return; + } -void drbd_nl_send_reply(struct cn_msg *req, int ret_code) -{ - char buffer[sizeof(struct cn_msg)+sizeof(struct drbd_nl_cfg_reply)]; - struct cn_msg *cn_reply = (struct cn_msg *) buffer; - struct drbd_nl_cfg_reply *reply = - (struct drbd_nl_cfg_reply *)cn_reply->data; - int rr; + seq = atomic_inc_return(&drbd_genl_seq); + msg = genlmsg_new(NLMSG_GOODSIZE, GFP_NOIO); + if (!msg) + goto failed; - memset(buffer, 0, sizeof(buffer)); - cn_reply->id = req->id; + err = -EMSGSIZE; + d_out = genlmsg_put(msg, 0, seq, &drbd_genl_family, 0, DRBD_EVENT); + if (!d_out) /* cannot happen, but anyways. */ + goto nla_put_failure; + d_out->minor = device_to_minor(device); + d_out->ret_code = NO_ERROR; - cn_reply->seq = req->seq; - cn_reply->ack = req->ack + 1; - cn_reply->len = sizeof(struct drbd_nl_cfg_reply); - cn_reply->flags = 0; + if (nla_put_status_info(msg, device, sib)) + goto nla_put_failure; + genlmsg_end(msg, d_out); + err = drbd_genl_multicast_events(msg, 0); + /* msg has been consumed or freed in netlink_broadcast() */ + if (err && err != -ESRCH) + goto failed; - reply->packet_type = P_return_code_only; - reply->minor = ((struct drbd_nl_cfg_req *)req->data)->drbd_minor; - reply->ret_code = ret_code; + return; - rr = cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO); - if (rr && rr != -ESRCH) - printk(KERN_INFO "drbd: cn_netlink_send()=%d\n", rr); +nla_put_failure: + nlmsg_free(msg); +failed: + drbd_err(device, "Error %d while broadcasting event. " + "Event seq:%u sib_reason:%u\n", + err, seq, sib->sib_reason); } - |