diff options
Diffstat (limited to 'net/netfilter')
| -rw-r--r-- | net/netfilter/Kconfig | 42 | ||||
| -rw-r--r-- | net/netfilter/Makefile | 2 | ||||
| -rw-r--r-- | net/netfilter/xt_IDLETIMER.c | 78 | ||||
| -rw-r--r-- | net/netfilter/xt_qtaguid.c | 3012 | ||||
| -rw-r--r-- | net/netfilter/xt_qtaguid_internal.h | 352 | ||||
| -rw-r--r-- | net/netfilter/xt_qtaguid_print.c | 566 | ||||
| -rw-r--r-- | net/netfilter/xt_qtaguid_print.h | 120 | ||||
| -rw-r--r-- | net/netfilter/xt_quota2.c | 385 | ||||
| -rw-r--r-- | net/netfilter/xt_socket.c | 70 |
9 files changed, 4596 insertions, 31 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 56d22cae590..bdf9c60b296 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -1089,6 +1089,8 @@ config NETFILTER_XT_MATCH_OWNER based on who created the socket: the user or group. It is also possible to check whether a socket actually exists. + Conflicts with '"quota, tag, uid" match' + config NETFILTER_XT_MATCH_POLICY tristate 'IPsec "policy" match support' depends on XFRM @@ -1122,6 +1124,22 @@ config NETFILTER_XT_MATCH_PKTTYPE To compile it as a module, choose M here. If unsure, say N. +config NETFILTER_XT_MATCH_QTAGUID + bool '"quota, tag, owner" match and stats support' + depends on NETFILTER_XT_MATCH_SOCKET + depends on NETFILTER_XT_MATCH_OWNER=n + help + This option replaces the `owner' match. In addition to matching + on uid, it keeps stats based on a tag assigned to a socket. + The full tag is comprised of a UID and an accounting tag. + The tags are assignable to sockets from user space (e.g. a download + manager can assign the socket to another UID for accounting). + Stats and control are done via /proc/net/xt_qtaguid/. + It replaces owner as it takes the same arguments, but should + really be recognized by the iptables tool. + + If unsure, say `N'. + config NETFILTER_XT_MATCH_QUOTA tristate '"quota" match support' depends on NETFILTER_ADVANCED @@ -1132,6 +1150,30 @@ config NETFILTER_XT_MATCH_QUOTA If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_QUOTA2 + tristate '"quota2" match support' + depends on NETFILTER_ADVANCED + help + This option adds a `quota2' match, which allows to match on a + byte counter correctly and not per CPU. + It allows naming the quotas. + This is based on http://xtables-addons.git.sourceforge.net + + If you want to compile it as a module, say M here and read + <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. + +config NETFILTER_XT_MATCH_QUOTA2_LOG + bool '"quota2" Netfilter LOG support' + depends on NETFILTER_XT_MATCH_QUOTA2 + depends on IP_NF_TARGET_ULOG=n # not yes, not module, just no + default n + help + This option allows `quota2' to log ONCE when a quota limit + is passed. It logs via NETLINK using the NETLINK_NFLOG family. + It logs similarly to how ipt_ULOG would without data. + + If unsure, say `N'. + config NETFILTER_XT_MATCH_RATEEST tristate '"rateest" match support' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index a1abf87d43b..d9655f6f346 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -127,7 +127,9 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o +obj-$(CONFIG_NETFILTER_XT_MATCH_QTAGUID) += xt_qtaguid_print.o xt_qtaguid.o obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA) += xt_quota.o +obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA2) += xt_quota2.o obj-$(CONFIG_NETFILTER_XT_MATCH_RATEEST) += xt_rateest.o obj-$(CONFIG_NETFILTER_XT_MATCH_REALM) += xt_realm.o obj-$(CONFIG_NETFILTER_XT_MATCH_RECENT) += xt_recent.o diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index f407ebc1348..f4ba8634866 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -5,6 +5,7 @@ * After timer expires a kevent will be sent. * * Copyright (C) 2004, 2010 Nokia Corporation + * * Written by Timo Teras <ext-timo.teras@nokia.com> * * Converted to x_tables and reworked for upstream inclusion @@ -38,8 +39,10 @@ #include <linux/netfilter/xt_IDLETIMER.h> #include <linux/kdev_t.h> #include <linux/kobject.h> +#include <linux/skbuff.h> #include <linux/workqueue.h> #include <linux/sysfs.h> +#include <net/net_namespace.h> struct idletimer_tg_attr { struct attribute attr; @@ -56,6 +59,8 @@ struct idletimer_tg { struct idletimer_tg_attr attr; unsigned int refcnt; + bool send_nl_msg; + bool active; }; static LIST_HEAD(idletimer_tg_list); @@ -63,6 +68,32 @@ static DEFINE_MUTEX(list_mutex); static struct kobject *idletimer_tg_kobj; +static void notify_netlink_uevent(const char *label, struct idletimer_tg *timer) +{ + char label_msg[NLMSG_MAX_SIZE]; + char state_msg[NLMSG_MAX_SIZE]; + char *envp[] = { label_msg, state_msg, NULL }; + int res; + + res = snprintf(label_msg, NLMSG_MAX_SIZE, "LABEL=%s", + label); + if (NLMSG_MAX_SIZE <= res) { + pr_err("message too long (%d)", res); + return; + } + res = snprintf(state_msg, NLMSG_MAX_SIZE, "STATE=%s", + timer->active ? "active" : "inactive"); + if (NLMSG_MAX_SIZE <= res) { + pr_err("message too long (%d)", res); + return; + } + pr_debug("putting nlmsg: <%s> <%s>\n", label_msg, state_msg); + kobject_uevent_env(idletimer_tg_kobj, KOBJ_CHANGE, envp); + return; + + +} + static struct idletimer_tg *__idletimer_tg_find_by_label(const char *label) { @@ -83,6 +114,7 @@ static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr, { struct idletimer_tg *timer; unsigned long expires = 0; + unsigned long now = jiffies; mutex_lock(&list_mutex); @@ -92,11 +124,15 @@ static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr, mutex_unlock(&list_mutex); - if (time_after(expires, jiffies)) + if (time_after(expires, now)) return sprintf(buf, "%u\n", - jiffies_to_msecs(expires - jiffies) / 1000); + jiffies_to_msecs(expires - now) / 1000); - return sprintf(buf, "0\n"); + if (timer->send_nl_msg) + return sprintf(buf, "0 %d\n", + jiffies_to_msecs(now - expires) / 1000); + else + return sprintf(buf, "0\n"); } static void idletimer_tg_work(struct work_struct *work) @@ -105,6 +141,9 @@ static void idletimer_tg_work(struct work_struct *work) work); sysfs_notify(idletimer_tg_kobj, NULL, timer->attr.attr.name); + + if (timer->send_nl_msg) + notify_netlink_uevent(timer->attr.attr.name, timer); } static void idletimer_tg_expired(unsigned long data) @@ -113,6 +152,7 @@ static void idletimer_tg_expired(unsigned long data) pr_debug("timer %s expired\n", timer->attr.attr.name); + timer->active = false; schedule_work(&timer->work); } @@ -145,6 +185,8 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) setup_timer(&info->timer->timer, idletimer_tg_expired, (unsigned long) info->timer); info->timer->refcnt = 1; + info->timer->send_nl_msg = (info->send_nl_msg == 0) ? false : true; + info->timer->active = true; mod_timer(&info->timer->timer, msecs_to_jiffies(info->timeout * 1000) + jiffies); @@ -168,14 +210,24 @@ static unsigned int idletimer_tg_target(struct sk_buff *skb, const struct xt_action_param *par) { const struct idletimer_tg_info *info = par->targinfo; + unsigned long now = jiffies; pr_debug("resetting timer %s, timeout period %u\n", info->label, info->timeout); BUG_ON(!info->timer); + info->timer->active = true; + + if (time_before(info->timer->timer.expires, now)) { + schedule_work(&info->timer->work); + pr_debug("Starting timer %s (Expired, Jiffies): %lu, %lu\n", + info->label, info->timer->timer.expires, now); + } + + /* TODO: Avoid modifying timers on each packet */ mod_timer(&info->timer->timer, - msecs_to_jiffies(info->timeout * 1000) + jiffies); + msecs_to_jiffies(info->timeout * 1000) + now); return XT_CONTINUE; } @@ -184,8 +236,9 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) { struct idletimer_tg_info *info = par->targinfo; int ret; + unsigned long now = jiffies; - pr_debug("checkentry targinfo%s\n", info->label); + pr_debug("checkentry targinfo %s\n", info->label); if (info->timeout == 0) { pr_debug("timeout value is zero\n"); @@ -204,8 +257,16 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) info->timer = __idletimer_tg_find_by_label(info->label); if (info->timer) { info->timer->refcnt++; + info->timer->active = true; + + if (time_before(info->timer->timer.expires, now)) { + schedule_work(&info->timer->work); + pr_debug("Starting Checkentry timer (Expired, Jiffies): %lu, %lu\n", + info->timer->timer.expires, now); + } + mod_timer(&info->timer->timer, - msecs_to_jiffies(info->timeout * 1000) + jiffies); + msecs_to_jiffies(info->timeout * 1000) + now); pr_debug("increased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); @@ -219,6 +280,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) } mutex_unlock(&list_mutex); + return 0; } @@ -240,7 +302,7 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par) kfree(info->timer); } else { pr_debug("decreased refcnt of timer %s to %u\n", - info->label, info->timer->refcnt); + info->label, info->timer->refcnt); } mutex_unlock(&list_mutex); @@ -248,6 +310,7 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par) static struct xt_target idletimer_tg __read_mostly = { .name = "IDLETIMER", + .revision = 1, .family = NFPROTO_UNSPEC, .target = idletimer_tg_target, .targetsize = sizeof(struct idletimer_tg_info), @@ -313,3 +376,4 @@ MODULE_DESCRIPTION("Xtables: idle time monitor"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("ipt_IDLETIMER"); MODULE_ALIAS("ip6t_IDLETIMER"); +MODULE_ALIAS("arpt_IDLETIMER"); diff --git a/net/netfilter/xt_qtaguid.c b/net/netfilter/xt_qtaguid.c new file mode 100644 index 00000000000..7346522cf3a --- /dev/null +++ b/net/netfilter/xt_qtaguid.c @@ -0,0 +1,3012 @@ +/* + * Kernel iptables module to track stats for packets based on user tags. + * + * (C) 2011 Google, Inc + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * There are run-time debug flags enabled via the debug_mask module param, or + * via the DEFAULT_DEBUG_MASK. See xt_qtaguid_internal.h. + */ +#define DEBUG + +#include <linux/file.h> +#include <linux/inetdevice.h> +#include <linux/module.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_qtaguid.h> +#include <linux/ratelimit.h> +#include <linux/seq_file.h> +#include <linux/skbuff.h> +#include <linux/workqueue.h> +#include <net/addrconf.h> +#include <net/sock.h> +#include <net/tcp.h> +#include <net/udp.h> + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) +#include <linux/netfilter_ipv6/ip6_tables.h> +#endif + +#include <linux/netfilter/xt_socket.h> +#include "xt_qtaguid_internal.h" +#include "xt_qtaguid_print.h" +#include "../../fs/proc/internal.h" + +/* + * We only use the xt_socket funcs within a similar context to avoid unexpected + * return values. + */ +#define XT_SOCKET_SUPPORTED_HOOKS \ + ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN)) + + +static const char *module_procdirname = "xt_qtaguid"; +static struct proc_dir_entry *xt_qtaguid_procdir; + +static unsigned int proc_iface_perms = S_IRUGO; +module_param_named(iface_perms, proc_iface_perms, uint, S_IRUGO | S_IWUSR); + +static struct proc_dir_entry *xt_qtaguid_stats_file; +static unsigned int proc_stats_perms = S_IRUGO; +module_param_named(stats_perms, proc_stats_perms, uint, S_IRUGO | S_IWUSR); + +static struct proc_dir_entry *xt_qtaguid_ctrl_file; + +/* Everybody can write. But proc_ctrl_write_limited is true by default which + * limits what can be controlled. See the can_*() functions. + */ +static unsigned int proc_ctrl_perms = S_IRUGO | S_IWUGO; +module_param_named(ctrl_perms, proc_ctrl_perms, uint, S_IRUGO | S_IWUSR); + +/* Limited by default, so the gid of the ctrl and stats proc entries + * will limit what can be done. See the can_*() functions. + */ +static bool proc_stats_readall_limited = true; +static bool proc_ctrl_write_limited = true; + +module_param_named(stats_readall_limited, proc_stats_readall_limited, bool, + S_IRUGO | S_IWUSR); +module_param_named(ctrl_write_limited, proc_ctrl_write_limited, bool, + S_IRUGO | S_IWUSR); + +/* + * Limit the number of active tags (via socket tags) for a given UID. + * Multiple processes could share the UID. + */ +static int max_sock_tags = DEFAULT_MAX_SOCK_TAGS; +module_param(max_sock_tags, int, S_IRUGO | S_IWUSR); + +/* + * After the kernel has initiallized this module, it is still possible + * to make it passive. + * Setting passive to Y: + * - the iface stats handling will not act on notifications. + * - iptables matches will never match. + * - ctrl commands silently succeed. + * - stats are always empty. + * This is mostly usefull when a bug is suspected. + */ +static bool module_passive; +module_param_named(passive, module_passive, bool, S_IRUGO | S_IWUSR); + +/* + * Control how qtaguid data is tracked per proc/uid. + * Setting tag_tracking_passive to Y: + * - don't create proc specific structs to track tags + * - don't check that active tag stats exceed some limits. + * - don't clean up socket tags on process exits. + * This is mostly usefull when a bug is suspected. + */ +static bool qtu_proc_handling_passive; +module_param_named(tag_tracking_passive, qtu_proc_handling_passive, bool, + S_IRUGO | S_IWUSR); + +#define QTU_DEV_NAME "xt_qtaguid" + +uint qtaguid_debug_mask = DEFAULT_DEBUG_MASK; +module_param_named(debug_mask, qtaguid_debug_mask, uint, S_IRUGO | S_IWUSR); + +/*---------------------------------------------------------------------------*/ +static const char *iface_stat_procdirname = "iface_stat"; +static struct proc_dir_entry *iface_stat_procdir; +/* + * The iface_stat_all* will go away once userspace gets use to the new fields + * that have a format line. + */ +static const char *iface_stat_all_procfilename = "iface_stat_all"; +static struct proc_dir_entry *iface_stat_all_procfile; +static const char *iface_stat_fmt_procfilename = "iface_stat_fmt"; +static struct proc_dir_entry *iface_stat_fmt_procfile; + + +static LIST_HEAD(iface_stat_list); +static DEFINE_SPINLOCK(iface_stat_list_lock); + +static struct rb_root sock_tag_tree = RB_ROOT; +static DEFINE_SPINLOCK(sock_tag_list_lock); + +static struct rb_root tag_counter_set_tree = RB_ROOT; +static DEFINE_SPINLOCK(tag_counter_set_list_lock); + +static struct rb_root uid_tag_data_tree = RB_ROOT; +static DEFINE_SPINLOCK(uid_tag_data_tree_lock); + +static struct rb_root proc_qtu_data_tree = RB_ROOT; +/* No proc_qtu_data_tree_lock; use uid_tag_data_tree_lock */ + +static struct qtaguid_event_counts qtu_events; +/*----------------------------------------------*/ +static bool can_manipulate_uids(void) +{ + /* root pwnd */ + return in_egroup_p(xt_qtaguid_ctrl_file->gid) + || unlikely(!current_fsuid()) || unlikely(!proc_ctrl_write_limited) + || unlikely(current_fsuid() == xt_qtaguid_ctrl_file->uid); +} + +static bool can_impersonate_uid(uid_t uid) +{ + return uid == current_fsuid() || can_manipulate_uids(); +} + +static bool can_read_other_uid_stats(uid_t uid) +{ + /* root pwnd */ + return in_egroup_p(xt_qtaguid_stats_file->gid) + || unlikely(!current_fsuid()) || uid == current_fsuid() + || unlikely(!proc_stats_readall_limited) + || unlikely(current_fsuid() == xt_qtaguid_ctrl_file->uid); +} + +static inline void dc_add_byte_packets(struct data_counters *counters, int set, + enum ifs_tx_rx direction, + enum ifs_proto ifs_proto, + int bytes, + int packets) +{ + counters->bpc[set][direction][ifs_proto].bytes += bytes; + counters->bpc[set][direction][ifs_proto].packets += packets; +} + +static struct tag_node *tag_node_tree_search(struct rb_root *root, tag_t tag) +{ + struct rb_node *node = root->rb_node; + + while (node) { + struct tag_node *data = rb_entry(node, struct tag_node, node); + int result; + RB_DEBUG("qtaguid: tag_node_tree_search(0x%llx): " + " node=%p data=%p\n", tag, node, data); + result = tag_compare(tag, data->tag); + RB_DEBUG("qtaguid: tag_node_tree_search(0x%llx): " + " data.tag=0x%llx (uid=%u) res=%d\n", + tag, data->tag, get_uid_from_tag(data->tag), result); + if (result < 0) + node = node->rb_left; + else if (result > 0) + node = node->rb_right; + else + return data; + } + return NULL; +} + +static void tag_node_tree_insert(struct tag_node *data, struct rb_root *root) +{ + struct rb_node **new = &(root->rb_node), *parent = NULL; + + /* Figure out where to put new node */ + while (*new) { + struct tag_node *this = rb_entry(*new, struct tag_node, + node); + int result = tag_compare(data->tag, this->tag); + RB_DEBUG("qtaguid: %s(): tag=0x%llx" + " (uid=%u)\n", __func__, + this->tag, + get_uid_from_tag(this->tag)); + parent = *new; + if (result < 0) + new = &((*new)->rb_left); + else if (result > 0) + new = &((*new)->rb_right); + else + BUG(); + } + + /* Add new node and rebalance tree. */ + rb_link_node(&data->node, parent, new); + rb_insert_color(&data->node, root); +} + +static void tag_stat_tree_insert(struct tag_stat *data, struct rb_root *root) +{ + tag_node_tree_insert(&data->tn, root); +} + +static struct tag_stat *tag_stat_tree_search(struct rb_root *root, tag_t tag) +{ + struct tag_node *node = tag_node_tree_search(root, tag); + if (!node) + return NULL; + return rb_entry(&node->node, struct tag_stat, tn.node); +} + +static void tag_counter_set_tree_insert(struct tag_counter_set *data, + struct rb_root *root) +{ + tag_node_tree_insert(&data->tn, root); +} + +static struct tag_counter_set *tag_counter_set_tree_search(struct rb_root *root, + tag_t tag) +{ + struct tag_node *node = tag_node_tree_search(root, tag); + if (!node) + return NULL; + return rb_entry(&node->node, struct tag_counter_set, tn.node); + +} + +static void tag_ref_tree_insert(struct tag_ref *data, struct rb_root *root) +{ + tag_node_tree_insert(&data->tn, root); +} + +static struct tag_ref *tag_ref_tree_search(struct rb_root *root, tag_t tag) +{ + struct tag_node *node = tag_node_tree_search(root, tag); + if (!node) + return NULL; + return rb_entry(&node->node, struct tag_ref, tn.node); +} + +static struct sock_tag *sock_tag_tree_search(struct rb_root *root, + const struct sock *sk) +{ + struct rb_node *node = root->rb_node; + + while (node) { + struct sock_tag *data = rb_entry(node, struct sock_tag, + sock_node); + if (sk < data->sk) + node = node->rb_left; + else if (sk > data->sk) + node = node->rb_right; + else + return data; + } + return NULL; +} + +static void sock_tag_tree_insert(struct sock_tag *data, struct rb_root *root) +{ + struct rb_node **new = &(root->rb_node), *parent = NULL; + + /* Figure out where to put new node */ + while (*new) { + struct sock_tag *this = rb_entry(*new, struct sock_tag, + sock_node); + parent = *new; + if (data->sk < this->sk) + new = &((*new)->rb_left); + else if (data->sk > this->sk) + new = &((*new)->rb_right); + else + BUG(); + } + + /* Add new node and rebalance tree. */ + rb_link_node(&data->sock_node, parent, new); + rb_insert_color(&data->sock_node, root); +} + +static void sock_tag_tree_erase(struct rb_root *st_to_free_tree) +{ + struct rb_node *node; + struct sock_tag *st_entry; + + node = rb_first(st_to_free_tree); + while (node) { + st_entry = rb_entry(node, struct sock_tag, sock_node); + node = rb_next(node); + CT_DEBUG("qtaguid: %s(): " + "erase st: sk=%p tag=0x%llx (uid=%u)\n", __func__, + st_entry->sk, + st_entry->tag, + get_uid_from_tag(st_entry->tag)); + rb_erase(&st_entry->sock_node, st_to_free_tree); + sockfd_put(st_entry->socket); + kfree(st_entry); + } +} + +static struct proc_qtu_data *proc_qtu_data_tree_search(struct rb_root *root, + const pid_t pid) +{ + struct rb_node *node = root->rb_node; + + while (node) { + struct proc_qtu_data *data = rb_entry(node, + struct proc_qtu_data, + node); + if (pid < data->pid) + node = node->rb_left; + else if (pid > data->pid) + node = node->rb_right; + else + return data; + } + return NULL; +} + +static void proc_qtu_data_tree_insert(struct proc_qtu_data *data, + struct rb_root *root) +{ + struct rb_node **new = &(root->rb_node), *parent = NULL; + + /* Figure out where to put new node */ + while (*new) { + struct proc_qtu_data *this = rb_entry(*new, + struct proc_qtu_data, + node); + parent = *new; + if (data->pid < this->pid) + new = &((*new)->rb_left); + else if (data->pid > this->pid) + new = &((*new)->rb_right); + else + BUG(); + } + + /* Add new node and rebalance tree. */ + rb_link_node(&data->node, parent, new); + rb_insert_color(&data->node, root); +} + +static void uid_tag_data_tree_insert(struct uid_tag_data *data, + struct rb_root *root) +{ + struct rb_node **new = &(root->rb_node), *parent = NULL; + + /* Figure out where to put new node */ + while (*new) { + struct uid_tag_data *this = rb_entry(*new, + struct uid_tag_data, + node); + parent = *new; + if (data->uid < this->uid) + new = &((*new)->rb_left); + else if (data->uid > this->uid) + new = &((*new)->rb_right); + else + BUG(); + } + + /* Add new node and rebalance tree. */ + rb_link_node(&data->node, parent, new); + rb_insert_color(&data->node, root); +} + +static struct uid_tag_data *uid_tag_data_tree_search(struct rb_root *root, + uid_t uid) +{ + struct rb_node *node = root->rb_node; + + while (node) { + struct uid_tag_data *data = rb_entry(node, + struct uid_tag_data, + node); + if (uid < data->uid) + node = node->rb_left; + else if (uid > data->uid) + node = node->rb_right; + else + return data; + } + return NULL; +} + +/* + * Allocates a new uid_tag_data struct if needed. + * Returns a pointer to the found or allocated uid_tag_data. + * Returns a PTR_ERR on failures, and lock is not held. + * If found is not NULL: + * sets *found to true if not allocated. + * sets *found to false if allocated. + */ +struct uid_tag_data *get_uid_data(uid_t uid, bool *found_res) +{ + struct uid_tag_data *utd_entry; + + /* Look for top level uid_tag_data for the UID */ + utd_entry = uid_tag_data_tree_search(&uid_tag_data_tree, uid); + DR_DEBUG("qtaguid: get_uid_data(%u) utd=%p\n", uid, utd_entry); + + if (found_res) + *found_res = utd_entry; + if (utd_entry) + return utd_entry; + + utd_entry = kzalloc(sizeof(*utd_entry), GFP_ATOMIC); + if (!utd_entry) { + pr_err("qtaguid: get_uid_data(%u): " + "tag data alloc failed\n", uid); + return ERR_PTR(-ENOMEM); + } + + utd_entry->uid = uid; + utd_entry->tag_ref_tree = RB_ROOT; + uid_tag_data_tree_insert(utd_entry, &uid_tag_data_tree); + DR_DEBUG("qtaguid: get_uid_data(%u) new utd=%p\n", uid, utd_entry); + return utd_entry; +} + +/* Never returns NULL. Either PTR_ERR or a valid ptr. */ +static struct tag_ref *new_tag_ref(tag_t new_tag, + struct uid_tag_data *utd_entry) +{ + struct tag_ref *tr_entry; + int res; + + if (utd_entry->num_active_tags + 1 > max_sock_tags) { + pr_info("qtaguid: new_tag_ref(0x%llx): " + "tag ref alloc quota exceeded. max=%d\n", + new_tag, max_sock_tags); + res = -EMFILE; + goto err_res; + + } + + tr_entry = kzalloc(sizeof(*tr_entry), GFP_ATOMIC); + if (!tr_entry) { + pr_err("qtaguid: new_tag_ref(0x%llx): " + "tag ref alloc failed\n", + new_tag); + res = -ENOMEM; + goto err_res; + } + tr_entry->tn.tag = new_tag; + /* tr_entry->num_sock_tags handled by caller */ + utd_entry->num_active_tags++; + tag_ref_tree_insert(tr_entry, &utd_entry->tag_ref_tree); + DR_DEBUG("qtaguid: new_tag_ref(0x%llx): " + " inserted new tag ref %p\n", + new_tag, tr_entry); + return tr_entry; + +err_res: + return ERR_PTR(res); +} + +static struct tag_ref *lookup_tag_ref(tag_t full_tag, + struct uid_tag_data **utd_res) +{ + struct uid_tag_data *utd_entry; + struct tag_ref *tr_entry; + bool found_utd; + uid_t uid = get_uid_from_tag(full_tag); + + DR_DEBUG("qtaguid: lookup_tag_ref(tag=0x%llx (uid=%u))\n", + full_tag, uid); + + utd_entry = get_uid_data(uid, &found_utd); + if (IS_ERR_OR_NULL(utd_entry)) { + if (utd_res) + *utd_res = utd_entry; + return NULL; + } + + tr_entry = tag_ref_tree_search(&utd_entry->tag_ref_tree, full_tag); + if (utd_res) + *utd_res = utd_entry; + DR_DEBUG("qtaguid: lookup_tag_ref(0x%llx) utd_entry=%p tr_entry=%p\n", + full_tag, utd_entry, tr_entry); + return tr_entry; +} + +/* Never returns NULL. Either PTR_ERR or a valid ptr. */ +static struct tag_ref *get_tag_ref(tag_t full_tag, + struct uid_tag_data **utd_res) +{ + struct uid_tag_data *utd_entry; + struct tag_ref *tr_entry; + + DR_DEBUG("qtaguid: get_tag_ref(0x%llx)\n", + full_tag); + spin_lock_bh(&uid_tag_data_tree_lock); + tr_entry = lookup_tag_ref(full_tag, &utd_entry); + BUG_ON(IS_ERR_OR_NULL(utd_entry)); + if (!tr_entry) + tr_entry = new_tag_ref(full_tag, utd_entry); + + spin_unlock_bh(&uid_tag_data_tree_lock); + if (utd_res) + *utd_res = utd_entry; + DR_DEBUG("qtaguid: get_tag_ref(0x%llx) utd=%p tr=%p\n", + full_tag, utd_entry, tr_entry); + return tr_entry; +} + +/* Checks and maybe frees the UID Tag Data entry */ +static void put_utd_entry(struct uid_tag_data *utd_entry) +{ + /* Are we done with the UID tag data entry? */ + if (RB_EMPTY_ROOT(&utd_entry->tag_ref_tree) && + !utd_entry->num_pqd) { + DR_DEBUG("qtaguid: %s(): " + "erase utd_entry=%p uid=%u " + "by pid=%u tgid=%u uid=%u\n", __func__, + utd_entry, utd_entry->uid, + current->pid, current->tgid, current_fsuid()); + BUG_ON(utd_entry->num_active_tags); + rb_erase(&utd_entry->node, &uid_tag_data_tree); + kfree(utd_entry); + } else { + DR_DEBUG("qtaguid: %s(): " + "utd_entry=%p still has %d tags %d proc_qtu_data\n", + __func__, utd_entry, utd_entry->num_active_tags, + utd_entry->num_pqd); + BUG_ON(!(utd_entry->num_active_tags || + utd_entry->num_pqd)); + } +} + +/* + * If no sock_tags are using this tag_ref, + * decrements refcount of utd_entry, removes tr_entry + * from utd_entry->tag_ref_tree and frees. + */ +static void free_tag_ref_from_utd_entry(struct tag_ref *tr_entry, + struct uid_tag_data *utd_entry) +{ + DR_DEBUG("qtaguid: %s(): %p tag=0x%llx (uid=%u)\n", __func__, + tr_entry, tr_entry->tn.tag, + get_uid_from_tag(tr_entry->tn.tag)); + if (!tr_entry->num_sock_tags) { + BUG_ON(!utd_entry->num_active_tags); + utd_entry->num_active_tags--; + rb_erase(&tr_entry->tn.node, &utd_entry->tag_ref_tree); + DR_DEBUG("qtaguid: %s(): erased %p\n", __func__, tr_entry); + kfree(tr_entry); + } +} + +static void put_tag_ref_tree(tag_t full_tag, struct uid_tag_data *utd_entry) +{ + struct rb_node *node; + struct tag_ref *tr_entry; + tag_t acct_tag; + + DR_DEBUG("qtaguid: %s(tag=0x%llx (uid=%u))\n", __func__, + full_tag, get_uid_from_tag(full_tag)); + acct_tag = get_atag_from_tag(full_tag); + node = rb_first(&utd_entry->tag_ref_tree); + while (node) { + tr_entry = rb_entry(node, struct tag_ref, tn.node); + node = rb_next(node); + if (!acct_tag || tr_entry->tn.tag == full_tag) + free_tag_ref_from_utd_entry(tr_entry, utd_entry); + } +} + +static ssize_t read_proc_u64(struct file *file, char __user *buf, + size_t size, loff_t *ppos) +{ + uint64_t *valuep = PDE_DATA(file_inode(file)); + char tmp[24]; + size_t tmp_size; + + tmp_size = scnprintf(tmp, sizeof(tmp), "%llu\n", *valuep); + return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size); +} + +static ssize_t read_proc_bool(struct file *file, char __user *buf, + size_t size, loff_t *ppos) +{ + bool *valuep = PDE_DATA(file_inode(file)); + char tmp[24]; + size_t tmp_size; + + tmp_size = scnprintf(tmp, sizeof(tmp), "%u\n", *valuep); + return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size); +} + +static int get_active_counter_set(tag_t tag) +{ + int active_set = 0; + struct tag_counter_set *tcs; + + MT_DEBUG("qtaguid: get_active_counter_set(tag=0x%llx)" + " (uid=%u)\n", + tag, get_uid_from_tag(tag)); + /* For now we only handle UID tags for active sets */ + tag = get_utag_from_tag(tag); + spin_lock_bh(&tag_counter_set_list_lock); + tcs = tag_counter_set_tree_search(&tag_counter_set_tree, tag); + if (tcs) + active_set = tcs->active_set; + spin_unlock_bh(&tag_counter_set_list_lock); + return active_set; +} + +/* + * Find the entry for tracking the specified interface. + * Caller must hold iface_stat_list_lock + */ +static struct iface_stat *get_iface_entry(const char *ifname) +{ + struct iface_stat *iface_entry; + + /* Find the entry for tracking the specified tag within the interface */ + if (ifname == NULL) { + pr_info("qtaguid: iface_stat: get() NULL device name\n"); + return NULL; + } + + /* Iterate over interfaces */ + list_for_each_entry(iface_entry, &iface_stat_list, list) { + if (!strcmp(ifname, iface_entry->ifname)) + goto done; + } + iface_entry = NULL; +done: + return iface_entry; +} + +/* This is for fmt2 only */ +static void pp_iface_stat_header(struct seq_file *m) +{ + seq_puts(m, + "ifname " + "total_skb_rx_bytes total_skb_rx_packets " + "total_skb_tx_bytes total_skb_tx_packets " + "rx_tcp_bytes rx_tcp_packets " + "rx_udp_bytes rx_udp_packets " + "rx_other_bytes rx_other_packets " + "tx_tcp_bytes tx_tcp_packets " + "tx_udp_bytes tx_udp_packets " + "tx_other_bytes tx_other_packets\n" + ); +} + +static void pp_iface_stat_line(struct seq_file *m, + struct iface_stat *iface_entry) +{ + struct data_counters *cnts; + int cnt_set = 0; /* We only use one set for the device */ + cnts = &iface_entry->totals_via_skb; + seq_printf(m, "%s %llu %llu %llu %llu %llu %llu %llu %llu " + "%llu %llu %llu %llu %llu %llu %llu %llu\n", + iface_entry->ifname, + dc_sum_bytes(cnts, cnt_set, IFS_RX), + dc_sum_packets(cnts, cnt_set, IFS_RX), + dc_sum_bytes(cnts, cnt_set, IFS_TX), + dc_sum_packets(cnts, cnt_set, IFS_TX), + cnts->bpc[cnt_set][IFS_RX][IFS_TCP].bytes, + cnts->bpc[cnt_set][IFS_RX][IFS_TCP].packets, + cnts->bpc[cnt_set][IFS_RX][IFS_UDP].bytes, + cnts->bpc[cnt_set][IFS_RX][IFS_UDP].packets, + cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].bytes, + cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].packets, + cnts->bpc[cnt_set][IFS_TX][IFS_TCP].bytes, + cnts->bpc[cnt_set][IFS_TX][IFS_TCP].packets, + cnts->bpc[cnt_set][IFS_TX][IFS_UDP].bytes, + cnts->bpc[cnt_set][IFS_TX][IFS_UDP].packets, + cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].bytes, + cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].packets); +} + +struct proc_iface_stat_fmt_info { + long fmt; +}; + +static void *iface_stat_fmt_proc_start(struct seq_file *m, loff_t *pos) +{ + struct proc_iface_stat_fmt_info *p = m->private; + loff_t n = *pos; + + /* + * This lock will prevent iface_stat_update() from changing active, + * and in turn prevent an interface from unregistering itself. + */ + spin_lock_bh(&iface_stat_list_lock); + + if (unlikely(module_passive)) + return NULL; + + if (!n && p->fmt == 2) + pp_iface_stat_header(m); + + return seq_list_start(&iface_stat_list, n); +} + +static void *iface_stat_fmt_proc_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next(p, &iface_stat_list, pos); +} + +static void iface_stat_fmt_proc_stop(struct seq_file *m, void *p) +{ + spin_unlock_bh(&iface_stat_list_lock); +} + +static int iface_stat_fmt_proc_show(struct seq_file *m, void *v) +{ + struct proc_iface_stat_fmt_info *p = m->private; + struct iface_stat *iface_entry; + struct rtnl_link_stats64 dev_stats, *stats; + struct rtnl_link_stats64 no_dev_stats = {0}; + + + CT_DEBUG("qtaguid:proc iface_stat_fmt pid=%u tgid=%u uid=%u\n", + current->pid, current->tgid, current_fsuid()); + + iface_entry = list_entry(v, struct iface_stat, list); + + if (iface_entry->active) { + stats = dev_get_stats(iface_entry->net_dev, + &dev_stats); + } else { + stats = &no_dev_stats; + } + /* + * If the meaning of the data changes, then update the fmtX + * string. + */ + if (p->fmt == 1) { + seq_printf(m, "%s %d %llu %llu %llu %llu %llu %llu %llu %llu\n", + iface_entry->ifname, + iface_entry->active, + iface_entry->totals_via_dev[IFS_RX].bytes, + iface_entry->totals_via_dev[IFS_RX].packets, + iface_entry->totals_via_dev[IFS_TX].bytes, + iface_entry->totals_via_dev[IFS_TX].packets, + stats->rx_bytes, stats->rx_packets, + stats->tx_bytes, stats->tx_packets + ); + } else { + pp_iface_stat_line(m, iface_entry); + } + return 0; +} + +static const struct file_operations read_u64_fops = { + .read = read_proc_u64, + .llseek = default_llseek, +}; + +static const struct file_operations read_bool_fops = { + .read = read_proc_bool, + .llseek = default_llseek, +}; + +static void iface_create_proc_worker(struct work_struct *work) +{ + struct proc_dir_entry *proc_entry; + struct iface_stat_work *isw = container_of(work, struct iface_stat_work, + iface_work); + struct iface_stat *new_iface = isw->iface_entry; + + /* iface_entries are not deleted, so safe to manipulate. */ + proc_entry = proc_mkdir(new_iface->ifname, iface_stat_procdir); + if (IS_ERR_OR_NULL(proc_entry)) { + pr_err("qtaguid: iface_stat: create_proc(): alloc failed.\n"); + kfree(isw); + return; + } + + new_iface->proc_ptr = proc_entry; + + proc_create_data("tx_bytes", proc_iface_perms, proc_entry, + &read_u64_fops, + &new_iface->totals_via_dev[IFS_TX].bytes); + proc_create_data("rx_bytes", proc_iface_perms, proc_entry, + &read_u64_fops, + &new_iface->totals_via_dev[IFS_RX].bytes); + proc_create_data("tx_packets", proc_iface_perms, proc_entry, + &read_u64_fops, + &new_iface->totals_via_dev[IFS_TX].packets); + proc_create_data("rx_packets", proc_iface_perms, proc_entry, + &read_u64_fops, + &new_iface->totals_via_dev[IFS_RX].packets); + proc_create_data("active", proc_iface_perms, proc_entry, + &read_bool_fops, &new_iface->active); + + IF_DEBUG("qtaguid: iface_stat: create_proc(): done " + "entry=%p dev=%s\n", new_iface, new_iface->ifname); + kfree(isw); +} + +/* + * Will set the entry's active state, and + * update the net_dev accordingly also. + */ +static void _iface_stat_set_active(struct iface_stat *entry, + struct net_device *net_dev, + bool activate) +{ + if (activate) { + entry->net_dev = net_dev; + entry->active = true; + IF_DEBUG("qtaguid: %s(%s): " + "enable tracking. rfcnt=%d\n", __func__, + entry->ifname, + __this_cpu_read(*net_dev->pcpu_refcnt)); + } else { + entry->active = false; + entry->net_dev = NULL; + IF_DEBUG("qtaguid: %s(%s): " + "disable tracking. rfcnt=%d\n", __func__, + entry->ifname, + __this_cpu_read(*net_dev->pcpu_refcnt)); + + } +} + +/* Caller must hold iface_stat_list_lock */ +static struct iface_stat *iface_alloc(struct net_device *net_dev) +{ + struct iface_stat *new_iface; + struct iface_stat_work *isw; + + new_iface = kzalloc(sizeof(*new_iface), GFP_ATOMIC); + if (new_iface == NULL) { + pr_err("qtaguid: iface_stat: create(%s): " + "iface_stat alloc failed\n", net_dev->name); + return NULL; + } + new_iface->ifname = kstrdup(net_dev->name, GFP_ATOMIC); + if (new_iface->ifname == NULL) { + pr_err("qtaguid: iface_stat: create(%s): " + "ifname alloc failed\n", net_dev->name); + kfree(new_iface); + return NULL; + } + spin_lock_init(&new_iface->tag_stat_list_lock); + new_iface->tag_stat_tree = RB_ROOT; + _iface_stat_set_active(new_iface, net_dev, true); + + /* + * ipv6 notifier chains are atomic :( + * No create_proc_read_entry() for you! + */ + isw = kmalloc(sizeof(*isw), GFP_ATOMIC); + if (!isw) { + pr_err("qtaguid: iface_stat: create(%s): " + "work alloc failed\n", new_iface->ifname); + _iface_stat_set_active(new_iface, net_dev, false); + kfree(new_iface->ifname); + kfree(new_iface); + return NULL; + } + isw->iface_entry = new_iface; + INIT_WORK(&isw->iface_work, iface_create_proc_worker); + schedule_work(&isw->iface_work); + list_add(&new_iface->list, &iface_stat_list); + return new_iface; +} + +static void iface_check_stats_reset_and_adjust(struct net_device *net_dev, + struct iface_stat *iface) +{ + struct rtnl_link_stats64 dev_stats, *stats; + bool stats_rewound; + + stats = dev_get_stats(net_dev, &dev_stats); + /* No empty packets */ + stats_rewound = + (stats->rx_bytes < iface->last_known[IFS_RX].bytes) + || (stats->tx_bytes < iface->last_known[IFS_TX].bytes); + + IF_DEBUG("qtaguid: %s(%s): iface=%p netdev=%p " + "bytes rx/tx=%llu/%llu " + "active=%d last_known=%d " + "stats_rewound=%d\n", __func__, + net_dev ? net_dev->name : "?", + iface, net_dev, + stats->rx_bytes, stats->tx_bytes, + iface->active, iface->last_known_valid, stats_rewound); + + if (iface->active && iface->last_known_valid && stats_rewound) { + pr_warn_once("qtaguid: iface_stat: %s(%s): " + "iface reset its stats unexpectedly\n", __func__, + net_dev->name); + + iface->totals_via_dev[IFS_TX].bytes += + iface->last_known[IFS_TX].bytes; + iface->totals_via_dev[IFS_TX].packets += + iface->last_known[IFS_TX].packets; + iface->totals_via_dev[IFS_RX].bytes += + iface->last_known[IFS_RX].bytes; + iface->totals_via_dev[IFS_RX].packets += + iface->last_known[IFS_RX].packets; + iface->last_known_valid = false; + IF_DEBUG("qtaguid: %s(%s): iface=%p " + "used last known bytes rx/tx=%llu/%llu\n", __func__, + iface->ifname, iface, iface->last_known[IFS_RX].bytes, + iface->last_known[IFS_TX].bytes); + } +} + +/* + * Create a new entry for tracking the specified interface. + * Do nothing if the entry already exists. + * Called when an interface is configured with a valid IP address. + */ +static void iface_stat_create(struct net_device *net_dev, + struct in_ifaddr *ifa) +{ + struct in_device *in_dev = NULL; + const char *ifname; + struct iface_stat *entry; + __be32 ipaddr = 0; + struct iface_stat *new_iface; + + IF_DEBUG("qtaguid: iface_stat: create(%s): ifa=%p netdev=%p\n", + net_dev ? net_dev->name : "?", + ifa, net_dev); + if (!net_dev) { + pr_err("qtaguid: iface_stat: create(): no net dev\n"); + return; + } + + ifname = net_dev->name; + if (!ifa) { + in_dev = in_dev_get(net_dev); + if (!in_dev) { + pr_err("qtaguid: iface_stat: create(%s): no inet dev\n", + ifname); + return; + } + IF_DEBUG("qtaguid: iface_stat: create(%s): in_dev=%p\n", + ifname, in_dev); + for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { + IF_DEBUG("qtaguid: iface_stat: create(%s): " + "ifa=%p ifa_label=%s\n", + ifname, ifa, + ifa->ifa_label ? ifa->ifa_label : "(null)"); + if (ifa->ifa_label && !strcmp(ifname, ifa->ifa_label)) + break; + } + } + + if (!ifa) { + IF_DEBUG("qtaguid: iface_stat: create(%s): no matching IP\n", + ifname); + goto done_put; + } + ipaddr = ifa->ifa_local; + + spin_lock_bh(&iface_stat_list_lock); + entry = get_iface_entry(ifname); + if (entry != NULL) { + IF_DEBUG("qtaguid: iface_stat: create(%s): entry=%p\n", + ifname, entry); + iface_check_stats_reset_and_adjust(net_dev, entry); + _iface_stat_set_active(entry, net_dev, true); + IF_DEBUG("qtaguid: %s(%s): " + "tracking now %d on ip=%pI4\n", __func__, + entry->ifname, true, &ipaddr); + goto done_unlock_put; + } + + new_iface = iface_alloc(net_dev); + IF_DEBUG("qtaguid: iface_stat: create(%s): done " + "entry=%p ip=%pI4\n", ifname, new_iface, &ipaddr); +done_unlock_put: + spin_unlock_bh(&iface_stat_list_lock); +done_put: + if (in_dev) + in_dev_put(in_dev); +} + +static void iface_stat_create_ipv6(struct net_device *net_dev, + struct inet6_ifaddr *ifa) +{ + struct in_device *in_dev; + const char *ifname; + struct iface_stat *entry; + struct iface_stat *new_iface; + int addr_type; + + IF_DEBUG("qtaguid: iface_stat: create6(): ifa=%p netdev=%p->name=%s\n", + ifa, net_dev, net_dev ? net_dev->name : ""); + if (!net_dev) { + pr_err("qtaguid: iface_stat: create6(): no net dev!\n"); + return; + } + ifname = net_dev->name; + + in_dev = in_dev_get(net_dev); + if (!in_dev) { + pr_err("qtaguid: iface_stat: create6(%s): no inet dev\n", + ifname); + return; + } + + IF_DEBUG("qtaguid: iface_stat: create6(%s): in_dev=%p\n", + ifname, in_dev); + + if (!ifa) { + IF_DEBUG("qtaguid: iface_stat: create6(%s): no matching IP\n", + ifname); + goto done_put; + } + addr_type = ipv6_addr_type(&ifa->addr); + + spin_lock_bh(&iface_stat_list_lock); + entry = get_iface_entry(ifname); + if (entry != NULL) { + IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__, + ifname, entry); + iface_check_stats_reset_and_adjust(net_dev, entry); + _iface_stat_set_active(entry, net_dev, true); + IF_DEBUG("qtaguid: %s(%s): " + "tracking now %d on ip=%pI6c\n", __func__, + entry->ifname, true, &ifa->addr); + goto done_unlock_put; + } + + new_iface = iface_alloc(net_dev); + IF_DEBUG("qtaguid: iface_stat: create6(%s): done " + "entry=%p ip=%pI6c\n", ifname, new_iface, &ifa->addr); + +done_unlock_put: + spin_unlock_bh(&iface_stat_list_lock); +done_put: + in_dev_put(in_dev); +} + +static struct sock_tag *get_sock_stat_nl(const struct sock *sk) +{ + MT_DEBUG("qtaguid: get_sock_stat_nl(sk=%p)\n", sk); + return sock_tag_tree_search(&sock_tag_tree, sk); +} + +static struct sock_tag *get_sock_stat(const struct sock *sk) +{ + struct sock_tag *sock_tag_entry; + MT_DEBUG("qtaguid: get_sock_stat(sk=%p)\n", sk); + if (!sk) + return NULL; + spin_lock_bh(&sock_tag_list_lock); + sock_tag_entry = get_sock_stat_nl(sk); + spin_unlock_bh(&sock_tag_list_lock); + return sock_tag_entry; +} + +static int ipx_proto(const struct sk_buff *skb, + struct xt_action_param *par) +{ + int thoff = 0, tproto; + + switch (par->family) { + case NFPROTO_IPV6: + tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); + if (tproto < 0) + MT_DEBUG("%s(): transport header not found in ipv6" + " skb=%p\n", __func__, skb); + break; + case NFPROTO_IPV4: + tproto = ip_hdr(skb)->protocol; + break; + default: + tproto = IPPROTO_RAW; + } + return tproto; +} + +static void +data_counters_update(struct data_counters *dc, int set, + enum ifs_tx_rx direction, int proto, int bytes) +{ + switch (proto) { + case IPPROTO_TCP: + dc_add_byte_packets(dc, set, direction, IFS_TCP, bytes, 1); + break; + case IPPROTO_UDP: + dc_add_byte_packets(dc, set, direction, IFS_UDP, bytes, 1); + break; + case IPPROTO_IP: + default: + dc_add_byte_packets(dc, set, direction, IFS_PROTO_OTHER, bytes, + 1); + break; + } +} + +/* + * Update stats for the specified interface. Do nothing if the entry + * does not exist (when a device was never configured with an IP address). + * Called when an device is being unregistered. + */ +static void iface_stat_update(struct net_device *net_dev, bool stash_only) +{ + struct rtnl_link_stats64 dev_stats, *stats; + struct iface_stat *entry; + + stats = dev_get_stats(net_dev, &dev_stats); + spin_lock_bh(&iface_stat_list_lock); + entry = get_iface_entry(net_dev->name); + if (entry == NULL) { + IF_DEBUG("qtaguid: iface_stat: update(%s): not tracked\n", + net_dev->name); + spin_unlock_bh(&iface_stat_list_lock); + return; + } + + IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__, + net_dev->name, entry); + if (!entry->active) { + IF_DEBUG("qtaguid: %s(%s): already disabled\n", __func__, + net_dev->name); + spin_unlock_bh(&iface_stat_list_lock); + return; + } + + if (stash_only) { + entry->last_known[IFS_TX].bytes = stats->tx_bytes; + entry->last_known[IFS_TX].packets = stats->tx_packets; + entry->last_known[IFS_RX].bytes = stats->rx_bytes; + entry->last_known[IFS_RX].packets = stats->rx_packets; + entry->last_known_valid = true; + IF_DEBUG("qtaguid: %s(%s): " + "dev stats stashed rx/tx=%llu/%llu\n", __func__, + net_dev->name, stats->rx_bytes, stats->tx_bytes); + spin_unlock_bh(&iface_stat_list_lock); + return; + } + entry->totals_via_dev[IFS_TX].bytes += stats->tx_bytes; + entry->totals_via_dev[IFS_TX].packets += stats->tx_packets; + entry->totals_via_dev[IFS_RX].bytes += stats->rx_bytes; + entry->totals_via_dev[IFS_RX].packets += stats->rx_packets; + /* We don't need the last_known[] anymore */ + entry->last_known_valid = false; + _iface_stat_set_active(entry, net_dev, false); + IF_DEBUG("qtaguid: %s(%s): " + "disable tracking. rx/tx=%llu/%llu\n", __func__, + net_dev->name, stats->rx_bytes, stats->tx_bytes); + spin_unlock_bh(&iface_stat_list_lock); +} + +/* + * Update stats for the specified interface from the skb. + * Do nothing if the entry + * does not exist (when a device was never configured with an IP address). + * Called on each sk. + */ +static void iface_stat_update_from_skb(const struct sk_buff *skb, + struct xt_action_param *par) +{ + struct iface_stat *entry; + const struct net_device *el_dev; + enum ifs_tx_rx direction = par->in ? IFS_RX : IFS_TX; + int bytes = skb->len; + int proto; + + if (!skb->dev) { + MT_DEBUG("qtaguid[%d]: no skb->dev\n", par->hooknum); + el_dev = par->in ? : par->out; + } else { + const struct net_device *other_dev; + el_dev = skb->dev; + other_dev = par->in ? : par->out; + if (el_dev != other_dev) { + MT_DEBUG("qtaguid[%d]: skb->dev=%p %s vs " + "par->(in/out)=%p %s\n", + par->hooknum, el_dev, el_dev->name, other_dev, + other_dev->name); + } + } + + if (unlikely(!el_dev)) { + pr_err_ratelimited("qtaguid[%d]: %s(): no par->in/out?!!\n", + par->hooknum, __func__); + BUG(); + } else if (unlikely(!el_dev->name)) { + pr_err_ratelimited("qtaguid[%d]: %s(): no dev->name?!!\n", + par->hooknum, __func__); + BUG(); + } else { + proto = ipx_proto(skb, par); + MT_DEBUG("qtaguid[%d]: dev name=%s type=%d fam=%d proto=%d\n", + par->hooknum, el_dev->name, el_dev->type, + par->family, proto); + } + + spin_lock_bh(&iface_stat_list_lock); + entry = get_iface_entry(el_dev->name); + if (entry == NULL) { + IF_DEBUG("qtaguid: iface_stat: %s(%s): not tracked\n", + __func__, el_dev->name); + spin_unlock_bh(&iface_stat_list_lock); + return; + } + + IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__, + el_dev->name, entry); + + data_counters_update(&entry->totals_via_skb, 0, direction, proto, + bytes); + spin_unlock_bh(&iface_stat_list_lock); +} + +static void tag_stat_update(struct tag_stat *tag_entry, + enum ifs_tx_rx direction, int proto, int bytes) +{ + int active_set; + active_set = get_active_counter_set(tag_entry->tn.tag); + MT_DEBUG("qtaguid: tag_stat_update(tag=0x%llx (uid=%u) set=%d " + "dir=%d proto=%d bytes=%d)\n", + tag_entry->tn.tag, get_uid_from_tag(tag_entry->tn.tag), + active_set, direction, proto, bytes); + data_counters_update(&tag_entry->counters, active_set, direction, + proto, bytes); + if (tag_entry->parent_counters) + data_counters_update(tag_entry->parent_counters, active_set, + direction, proto, bytes); +} + +/* + * Create a new entry for tracking the specified {acct_tag,uid_tag} within + * the interface. + * iface_entry->tag_stat_list_lock should be held. + */ +static struct tag_stat *create_if_tag_stat(struct iface_stat *iface_entry, + tag_t tag) +{ + struct tag_stat *new_tag_stat_entry = NULL; + IF_DEBUG("qtaguid: iface_stat: %s(): ife=%p tag=0x%llx" + " (uid=%u)\n", __func__, + iface_entry, tag, get_uid_from_tag(tag)); + new_tag_stat_entry = kzalloc(sizeof(*new_tag_stat_entry), GFP_ATOMIC); + if (!new_tag_stat_entry) { + pr_err("qtaguid: iface_stat: tag stat alloc failed\n"); + goto done; + } + new_tag_stat_entry->tn.tag = tag; + tag_stat_tree_insert(new_tag_stat_entry, &iface_entry->tag_stat_tree); +done: + return new_tag_stat_entry; +} + +static void if_tag_stat_update(const char *ifname, uid_t uid, + const struct sock *sk, enum ifs_tx_rx direction, + int proto, int bytes) +{ + struct tag_stat *tag_stat_entry; + tag_t tag, acct_tag; + tag_t uid_tag; + struct data_counters *uid_tag_counters; + struct sock_tag *sock_tag_entry; + struct iface_stat *iface_entry; + struct tag_stat *new_tag_stat = NULL; + MT_DEBUG("qtaguid: if_tag_stat_update(ifname=%s " + "uid=%u sk=%p dir=%d proto=%d bytes=%d)\n", + ifname, uid, sk, direction, proto, bytes); + + + iface_entry = get_iface_entry(ifname); + if (!iface_entry) { + pr_err_ratelimited("qtaguid: iface_stat: stat_update() " + "%s not found\n", ifname); + return; + } + /* It is ok to process data when an iface_entry is inactive */ + + MT_DEBUG("qtaguid: iface_stat: stat_update() dev=%s entry=%p\n", + ifname, iface_entry); + + /* + * Look for a tagged sock. + * It will have an acct_uid. + */ + sock_tag_entry = get_sock_stat(sk); + if (sock_tag_entry) { + tag = sock_tag_entry->tag; + acct_tag = get_atag_from_tag(tag); + uid_tag = get_utag_from_tag(tag); + } else { + acct_tag = make_atag_from_value(0); + tag = combine_atag_with_uid(acct_tag, uid); + uid_tag = make_tag_from_uid(uid); + } + MT_DEBUG("qtaguid: iface_stat: stat_update(): " + " looking for tag=0x%llx (uid=%u) in ife=%p\n", + tag, get_uid_from_tag(tag), iface_entry); + /* Loop over tag list under this interface for {acct_tag,uid_tag} */ + spin_lock_bh(&iface_entry->tag_stat_list_lock); + + tag_stat_entry = tag_stat_tree_search(&iface_entry->tag_stat_tree, + tag); + if (tag_stat_entry) { + /* + * Updating the {acct_tag, uid_tag} entry handles both stats: + * {0, uid_tag} will also get updated. + */ + tag_stat_update(tag_stat_entry, direction, proto, bytes); + spin_unlock_bh(&iface_entry->tag_stat_list_lock); + return; + } + + /* Loop over tag list under this interface for {0,uid_tag} */ + tag_stat_entry = tag_stat_tree_search(&iface_entry->tag_stat_tree, + uid_tag); + if (!tag_stat_entry) { + /* Here: the base uid_tag did not exist */ + /* + * No parent counters. So + * - No {0, uid_tag} stats and no {acc_tag, uid_tag} stats. + */ + new_tag_stat = create_if_tag_stat(iface_entry, uid_tag); + if (!new_tag_stat) + goto unlock; + uid_tag_counters = &new_tag_stat->counters; + } else { + uid_tag_counters = &tag_stat_entry->counters; + } + + if (acct_tag) { + /* Create the child {acct_tag, uid_tag} and hook up parent. */ + new_tag_stat = create_if_tag_stat(iface_entry, tag); + if (!new_tag_stat) + goto unlock; + new_tag_stat->parent_counters = uid_tag_counters; + } else { + /* + * For new_tag_stat to be still NULL here would require: + * {0, uid_tag} exists + * and {acct_tag, uid_tag} doesn't exist + * AND acct_tag == 0. + * Impossible. This reassures us that new_tag_stat + * below will always be assigned. + */ + BUG_ON(!new_tag_stat); + } + tag_stat_update(new_tag_stat, direction, proto, bytes); +unlock: + spin_unlock_bh(&iface_entry->tag_stat_list_lock); +} + +static int iface_netdev_event_handler(struct notifier_block *nb, + unsigned long event, void *ptr) { + struct net_device *dev = ptr; + + if (unlikely(module_passive)) + return NOTIFY_DONE; + + IF_DEBUG("qtaguid: iface_stat: netdev_event(): " + "ev=0x%lx/%s netdev=%p->name=%s\n", + event, netdev_evt_str(event), dev, dev ? dev->name : ""); + + switch (event) { + case NETDEV_UP: + iface_stat_create(dev, NULL); + atomic64_inc(&qtu_events.iface_events); + break; + case NETDEV_DOWN: + case NETDEV_UNREGISTER: + iface_stat_update(dev, event == NETDEV_DOWN); + atomic64_inc(&qtu_events.iface_events); + break; + } + return NOTIFY_DONE; +} + +static int iface_inet6addr_event_handler(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct inet6_ifaddr *ifa = ptr; + struct net_device *dev; + + if (unlikely(module_passive)) + return NOTIFY_DONE; + + IF_DEBUG("qtaguid: iface_stat: inet6addr_event(): " + "ev=0x%lx/%s ifa=%p\n", + event, netdev_evt_str(event), ifa); + + switch (event) { + case NETDEV_UP: + BUG_ON(!ifa || !ifa->idev); + dev = (struct net_device *)ifa->idev->dev; + iface_stat_create_ipv6(dev, ifa); + atomic64_inc(&qtu_events.iface_events); + break; + case NETDEV_DOWN: + case NETDEV_UNREGISTER: + BUG_ON(!ifa || !ifa->idev); + dev = (struct net_device *)ifa->idev->dev; + iface_stat_update(dev, event == NETDEV_DOWN); + atomic64_inc(&qtu_events.iface_events); + break; + } + return NOTIFY_DONE; +} + +static int iface_inetaddr_event_handler(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct in_ifaddr *ifa = ptr; + struct net_device *dev; + + if (unlikely(module_passive)) + return NOTIFY_DONE; + + IF_DEBUG("qtaguid: iface_stat: inetaddr_event(): " + "ev=0x%lx/%s ifa=%p\n", + event, netdev_evt_str(event), ifa); + + switch (event) { + case NETDEV_UP: + BUG_ON(!ifa || !ifa->ifa_dev); + dev = ifa->ifa_dev->dev; + iface_stat_create(dev, ifa); + atomic64_inc(&qtu_events.iface_events); + break; + case NETDEV_DOWN: + case NETDEV_UNREGISTER: + BUG_ON(!ifa || !ifa->ifa_dev); + dev = ifa->ifa_dev->dev; + iface_stat_update(dev, event == NETDEV_DOWN); + atomic64_inc(&qtu_events.iface_events); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block iface_netdev_notifier_blk = { + .notifier_call = iface_netdev_event_handler, +}; + +static struct notifier_block iface_inetaddr_notifier_blk = { + .notifier_call = iface_inetaddr_event_handler, +}; + +static struct notifier_block iface_inet6addr_notifier_blk = { + .notifier_call = iface_inet6addr_event_handler, +}; + +static const struct seq_operations iface_stat_fmt_proc_seq_ops = { + .start = iface_stat_fmt_proc_start, + .next = iface_stat_fmt_proc_next, + .stop = iface_stat_fmt_proc_stop, + .show = iface_stat_fmt_proc_show, +}; + +static int proc_iface_stat_fmt_open(struct inode *inode, struct file *file) +{ + struct proc_iface_stat_fmt_info *s; + + s = __seq_open_private(file, &iface_stat_fmt_proc_seq_ops, + sizeof(struct proc_iface_stat_fmt_info)); + if (!s) + return -ENOMEM; + + s->fmt = (long)PDE_DATA(inode); + return 0; +} + +static const struct file_operations proc_iface_stat_fmt_fops = { + .open = proc_iface_stat_fmt_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +static int __init iface_stat_init(struct proc_dir_entry *parent_procdir) +{ + int err; + + iface_stat_procdir = proc_mkdir(iface_stat_procdirname, parent_procdir); + if (!iface_stat_procdir) { + pr_err("qtaguid: iface_stat: init failed to create proc entry\n"); + err = -1; + goto err; + } + + iface_stat_all_procfile = proc_create_data(iface_stat_all_procfilename, + proc_iface_perms, + parent_procdir, + &proc_iface_stat_fmt_fops, + (void *)1 /* fmt1 */); + if (!iface_stat_all_procfile) { + pr_err("qtaguid: iface_stat: init " + " failed to create stat_old proc entry\n"); + err = -1; + goto err_zap_entry; + } + + iface_stat_fmt_procfile = proc_create_data(iface_stat_fmt_procfilename, + proc_iface_perms, + parent_procdir, + &proc_iface_stat_fmt_fops, + (void *)2 /* fmt2 */); + if (!iface_stat_fmt_procfile) { + pr_err("qtaguid: iface_stat: init " + " failed to create stat_all proc entry\n"); + err = -1; + goto err_zap_all_stats_entry; + } + + + err = register_netdevice_notifier(&iface_netdev_notifier_blk); + if (err) { + pr_err("qtaguid: iface_stat: init " + "failed to register dev event handler\n"); + goto err_zap_all_stats_entries; + } + err = register_inetaddr_notifier(&iface_inetaddr_notifier_blk); + if (err) { + pr_err("qtaguid: iface_stat: init " + "failed to register ipv4 dev event handler\n"); + goto err_unreg_nd; + } + + err = register_inet6addr_notifier(&iface_inet6addr_notifier_blk); + if (err) { + pr_err("qtaguid: iface_stat: init " + "failed to register ipv6 dev event handler\n"); + goto err_unreg_ip4_addr; + } + return 0; + +err_unreg_ip4_addr: + unregister_inetaddr_notifier(&iface_inetaddr_notifier_blk); +err_unreg_nd: + unregister_netdevice_notifier(&iface_netdev_notifier_blk); +err_zap_all_stats_entries: + remove_proc_entry(iface_stat_fmt_procfilename, parent_procdir); +err_zap_all_stats_entry: + remove_proc_entry(iface_stat_all_procfilename, parent_procdir); +err_zap_entry: + remove_proc_entry(iface_stat_procdirname, parent_procdir); +err: + return err; +} + +static struct sock *qtaguid_find_sk(const struct sk_buff *skb, + struct xt_action_param *par) +{ + struct sock *sk; + unsigned int hook_mask = (1 << par->hooknum); + + MT_DEBUG("qtaguid: find_sk(skb=%p) hooknum=%d family=%d\n", skb, + par->hooknum, par->family); + + /* + * Let's not abuse the the xt_socket_get*_sk(), or else it will + * return garbage SKs. + */ + if (!(hook_mask & XT_SOCKET_SUPPORTED_HOOKS)) + return NULL; + + switch (par->family) { + case NFPROTO_IPV6: + sk = xt_socket_get6_sk(skb, par); + break; + case NFPROTO_IPV4: + sk = xt_socket_get4_sk(skb, par); + break; + default: + return NULL; + } + + if (sk) { + MT_DEBUG("qtaguid: %p->sk_proto=%u " + "->sk_state=%d\n", sk, sk->sk_protocol, sk->sk_state); + /* + * When in TCP_TIME_WAIT the sk is not a "struct sock" but + * "struct inet_timewait_sock" which is missing fields. + */ + if (sk->sk_state == TCP_TIME_WAIT) { + xt_socket_put_sk(sk); + sk = NULL; + } + } + return sk; +} + +static void account_for_uid(const struct sk_buff *skb, + const struct sock *alternate_sk, uid_t uid, + struct xt_action_param *par) +{ + const struct net_device *el_dev; + + if (!skb->dev) { + MT_DEBUG("qtaguid[%d]: no skb->dev\n", par->hooknum); + el_dev = par->in ? : par->out; + } else { + const struct net_device *other_dev; + el_dev = skb->dev; + other_dev = par->in ? : par->out; + if (el_dev != other_dev) { + MT_DEBUG("qtaguid[%d]: skb->dev=%p %s vs " + "par->(in/out)=%p %s\n", + par->hooknum, el_dev, el_dev->name, other_dev, + other_dev->name); + } + } + + if (unlikely(!el_dev)) { + pr_info("qtaguid[%d]: no par->in/out?!!\n", par->hooknum); + } else if (unlikely(!el_dev->name)) { + pr_info("qtaguid[%d]: no dev->name?!!\n", par->hooknum); + } else { + int proto = ipx_proto(skb, par); + MT_DEBUG("qtaguid[%d]: dev name=%s type=%d fam=%d proto=%d\n", + par->hooknum, el_dev->name, el_dev->type, + par->family, proto); + + if_tag_stat_update(el_dev->name, uid, + skb->sk ? skb->sk : alternate_sk, + par->in ? IFS_RX : IFS_TX, + proto, skb->len); + } +} + +static bool qtaguid_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_qtaguid_match_info *info = par->matchinfo; + const struct file *filp; + bool got_sock = false; + struct sock *sk; + uid_t sock_uid; + bool res; + + if (unlikely(module_passive)) + return (info->match ^ info->invert) == 0; + + MT_DEBUG("qtaguid[%d]: entered skb=%p par->in=%p/out=%p fam=%d\n", + par->hooknum, skb, par->in, par->out, par->family); + + atomic64_inc(&qtu_events.match_calls); + if (skb == NULL) { + res = (info->match ^ info->invert) == 0; + goto ret_res; + } + + switch (par->hooknum) { + case NF_INET_PRE_ROUTING: + case NF_INET_POST_ROUTING: + atomic64_inc(&qtu_events.match_calls_prepost); + iface_stat_update_from_skb(skb, par); + /* + * We are done in pre/post. The skb will get processed + * further alter. + */ + res = (info->match ^ info->invert); + goto ret_res; + break; + /* default: Fall through and do UID releated work */ + } + + sk = skb->sk; + /* + * When in TCP_TIME_WAIT the sk is not a "struct sock" but + * "struct inet_timewait_sock" which is missing fields. + * So we ignore it. + */ + if (sk && sk->sk_state == TCP_TIME_WAIT) + sk = NULL; + if (sk == NULL) { + /* + * A missing sk->sk_socket happens when packets are in-flight + * and the matching socket is already closed and gone. + */ + sk = qtaguid_find_sk(skb, par); + /* + * If we got the socket from the find_sk(), we will need to put + * it back, as nf_tproxy_get_sock_v4() got it. + */ + got_sock = sk; + if (sk) + atomic64_inc(&qtu_events.match_found_sk_in_ct); + else + atomic64_inc(&qtu_events.match_found_no_sk_in_ct); + } else { + atomic64_inc(&qtu_events.match_found_sk); + } + MT_DEBUG("qtaguid[%d]: sk=%p got_sock=%d fam=%d proto=%d\n", + par->hooknum, sk, got_sock, par->family, ipx_proto(skb, par)); + if (sk != NULL) { + MT_DEBUG("qtaguid[%d]: sk=%p->sk_socket=%p->file=%p\n", + par->hooknum, sk, sk->sk_socket, + sk->sk_socket ? sk->sk_socket->file : (void *)-1LL); + filp = sk->sk_socket ? sk->sk_socket->file : NULL; + MT_DEBUG("qtaguid[%d]: filp...uid=%u\n", + par->hooknum, filp ? filp->f_cred->fsuid : -1); + } + + if (sk == NULL || sk->sk_socket == NULL) { + /* + * Here, the qtaguid_find_sk() using connection tracking + * couldn't find the owner, so for now we just count them + * against the system. + */ + /* + * TODO: unhack how to force just accounting. + * For now we only do iface stats when the uid-owner is not + * requested. + */ + if (!(info->match & XT_QTAGUID_UID)) + account_for_uid(skb, sk, 0, par); + MT_DEBUG("qtaguid[%d]: leaving (sk?sk->sk_socket)=%p\n", + par->hooknum, + sk ? sk->sk_socket : NULL); + res = (info->match ^ info->invert) == 0; + atomic64_inc(&qtu_events.match_no_sk); + goto put_sock_ret_res; + } else if (info->match & info->invert & XT_QTAGUID_SOCKET) { + res = false; + goto put_sock_ret_res; + } + filp = sk->sk_socket->file; + if (filp == NULL) { + MT_DEBUG("qtaguid[%d]: leaving filp=NULL\n", par->hooknum); + account_for_uid(skb, sk, 0, par); + res = ((info->match ^ info->invert) & + (XT_QTAGUID_UID | XT_QTAGUID_GID)) == 0; + atomic64_inc(&qtu_events.match_no_sk_file); + goto put_sock_ret_res; + } + sock_uid = filp->f_cred->fsuid; + /* + * TODO: unhack how to force just accounting. + * For now we only do iface stats when the uid-owner is not requested + */ + if (!(info->match & XT_QTAGUID_UID)) + account_for_uid(skb, sk, sock_uid, par); + + /* + * The following two tests fail the match when: + * id not in range AND no inverted condition requested + * or id in range AND inverted condition requested + * Thus (!a && b) || (a && !b) == a ^ b + */ + if (info->match & XT_QTAGUID_UID) + if ((filp->f_cred->fsuid >= info->uid_min && + filp->f_cred->fsuid <= info->uid_max) ^ + !(info->invert & XT_QTAGUID_UID)) { + MT_DEBUG("qtaguid[%d]: leaving uid not matching\n", + par->hooknum); + res = false; + goto put_sock_ret_res; + } + if (info->match & XT_QTAGUID_GID) + if ((filp->f_cred->fsgid >= info->gid_min && + filp->f_cred->fsgid <= info->gid_max) ^ + !(info->invert & XT_QTAGUID_GID)) { + MT_DEBUG("qtaguid[%d]: leaving gid not matching\n", + par->hooknum); + res = false; + goto put_sock_ret_res; + } + + MT_DEBUG("qtaguid[%d]: leaving matched\n", par->hooknum); + res = true; + +put_sock_ret_res: + if (got_sock) + xt_socket_put_sk(sk); +ret_res: + MT_DEBUG("qtaguid[%d]: left %d\n", par->hooknum, res); + return res; +} + +#ifdef DDEBUG +/* This function is not in xt_qtaguid_print.c because of locks visibility */ +static void prdebug_full_state(int indent_level, const char *fmt, ...) +{ + va_list args; + char *fmt_buff; + char *buff; + + if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK)) + return; + + fmt_buff = kasprintf(GFP_ATOMIC, + "qtaguid: %s(): %s {\n", __func__, fmt); + BUG_ON(!fmt_buff); + va_start(args, fmt); + buff = kvasprintf(GFP_ATOMIC, + fmt_buff, args); + BUG_ON(!buff); + pr_debug("%s", buff); + kfree(fmt_buff); + kfree(buff); + va_end(args); + + spin_lock_bh(&sock_tag_list_lock); + prdebug_sock_tag_tree(indent_level, &sock_tag_tree); + spin_unlock_bh(&sock_tag_list_lock); + + spin_lock_bh(&sock_tag_list_lock); + spin_lock_bh(&uid_tag_data_tree_lock); + prdebug_uid_tag_data_tree(indent_level, &uid_tag_data_tree); + prdebug_proc_qtu_data_tree(indent_level, &proc_qtu_data_tree); + spin_unlock_bh(&uid_tag_data_tree_lock); + spin_unlock_bh(&sock_tag_list_lock); + + spin_lock_bh(&iface_stat_list_lock); + prdebug_iface_stat_list(indent_level, &iface_stat_list); + spin_unlock_bh(&iface_stat_list_lock); + + pr_debug("qtaguid: %s(): }\n", __func__); +} +#else +static void prdebug_full_state(int indent_level, const char *fmt, ...) {} +#endif + +struct proc_ctrl_print_info { + struct sock *sk; /* socket found by reading to sk_pos */ + loff_t sk_pos; +}; + +static void *qtaguid_ctrl_proc_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct proc_ctrl_print_info *pcpi = m->private; + struct sock_tag *sock_tag_entry = v; + struct rb_node *node; + + (*pos)++; + + if (!v || v == SEQ_START_TOKEN) + return NULL; + + node = rb_next(&sock_tag_entry->sock_node); + if (!node) { + pcpi->sk = NULL; + sock_tag_entry = SEQ_START_TOKEN; + } else { + sock_tag_entry = rb_entry(node, struct sock_tag, sock_node); + pcpi->sk = sock_tag_entry->sk; + } + pcpi->sk_pos = *pos; + return sock_tag_entry; +} + +static void *qtaguid_ctrl_proc_start(struct seq_file *m, loff_t *pos) +{ + struct proc_ctrl_print_info *pcpi = m->private; + struct sock_tag *sock_tag_entry; + struct rb_node *node; + + spin_lock_bh(&sock_tag_list_lock); + + if (unlikely(module_passive)) + return NULL; + + if (*pos == 0) { + pcpi->sk_pos = 0; + node = rb_first(&sock_tag_tree); + if (!node) { + pcpi->sk = NULL; + return SEQ_START_TOKEN; + } + sock_tag_entry = rb_entry(node, struct sock_tag, sock_node); + pcpi->sk = sock_tag_entry->sk; + } else { + sock_tag_entry = (pcpi->sk ? get_sock_stat_nl(pcpi->sk) : + NULL) ?: SEQ_START_TOKEN; + if (*pos != pcpi->sk_pos) { + /* seq_read skipped a next call */ + *pos = pcpi->sk_pos; + return qtaguid_ctrl_proc_next(m, sock_tag_entry, pos); + } + } + return sock_tag_entry; +} + +static void qtaguid_ctrl_proc_stop(struct seq_file *m, void *v) +{ + spin_unlock_bh(&sock_tag_list_lock); +} + +/* + * Procfs reader to get all active socket tags using style "1)" as described in + * fs/proc/generic.c + */ +static int qtaguid_ctrl_proc_show(struct seq_file *m, void *v) +{ + struct sock_tag *sock_tag_entry = v; + uid_t uid; + long f_count; + + CT_DEBUG("qtaguid: proc ctrl pid=%u tgid=%u uid=%u\n", + current->pid, current->tgid, current_fsuid()); + + if (sock_tag_entry != SEQ_START_TOKEN) { + uid = get_uid_from_tag(sock_tag_entry->tag); + CT_DEBUG("qtaguid: proc_read(): sk=%p tag=0x%llx (uid=%u) " + "pid=%u\n", + sock_tag_entry->sk, + sock_tag_entry->tag, + uid, + sock_tag_entry->pid + ); + f_count = atomic_long_read( + &sock_tag_entry->socket->file->f_count); + seq_printf(m, "sock=%p tag=0x%llx (uid=%u) pid=%u " + "f_count=%lu\n", + sock_tag_entry->sk, + sock_tag_entry->tag, uid, + sock_tag_entry->pid, f_count); + } else { + seq_printf(m, "events: sockets_tagged=%llu " + "sockets_untagged=%llu " + "counter_set_changes=%llu " + "delete_cmds=%llu " + "iface_events=%llu " + "match_calls=%llu " + "match_calls_prepost=%llu " + "match_found_sk=%llu " + "match_found_sk_in_ct=%llu " + "match_found_no_sk_in_ct=%llu " + "match_no_sk=%llu " + "match_no_sk_file=%llu\n", + atomic64_read(&qtu_events.sockets_tagged), + atomic64_read(&qtu_events.sockets_untagged), + atomic64_read(&qtu_events.counter_set_changes), + atomic64_read(&qtu_events.delete_cmds), + atomic64_read(&qtu_events.iface_events), + atomic64_read(&qtu_events.match_calls), + atomic64_read(&qtu_events.match_calls_prepost), + atomic64_read(&qtu_events.match_found_sk), + atomic64_read(&qtu_events.match_found_sk_in_ct), + atomic64_read(&qtu_events.match_found_no_sk_in_ct), + atomic64_read(&qtu_events.match_no_sk), + atomic64_read(&qtu_events.match_no_sk_file)); + + /* Count the following as part of the last item_index */ + prdebug_full_state(0, "proc ctrl"); + } + + return 0; +} + +/* + * Delete socket tags, and stat tags associated with a given + * accouting tag and uid. + */ +static int ctrl_cmd_delete(const char *input) +{ + char cmd; + uid_t uid; + uid_t entry_uid; + tag_t acct_tag; + tag_t tag; + int res, argc; + struct iface_stat *iface_entry; + struct rb_node *node; + struct sock_tag *st_entry; + struct rb_root st_to_free_tree = RB_ROOT; + struct tag_stat *ts_entry; + struct tag_counter_set *tcs_entry; + struct tag_ref *tr_entry; + struct uid_tag_data *utd_entry; + + argc = sscanf(input, "%c %llu %u", &cmd, &acct_tag, &uid); + CT_DEBUG("qtaguid: ctrl_delete(%s): argc=%d cmd=%c " + "user_tag=0x%llx uid=%u\n", input, argc, cmd, + acct_tag, uid); + if (argc < 2) { + res = -EINVAL; + goto err; + } + if (!valid_atag(acct_tag)) { + pr_info("qtaguid: ctrl_delete(%s): invalid tag\n", input); + res = -EINVAL; + goto err; + } + if (argc < 3) { + uid = current_fsuid(); + } else if (!can_impersonate_uid(uid)) { + pr_info("qtaguid: ctrl_delete(%s): " + "insufficient priv from pid=%u tgid=%u uid=%u\n", + input, current->pid, current->tgid, current_fsuid()); + res = -EPERM; + goto err; + } + + tag = combine_atag_with_uid(acct_tag, uid); + CT_DEBUG("qtaguid: ctrl_delete(%s): " + "looking for tag=0x%llx (uid=%u)\n", + input, tag, uid); + + /* Delete socket tags */ + spin_lock_bh(&sock_tag_list_lock); + node = rb_first(&sock_tag_tree); + while (node) { + st_entry = rb_entry(node, struct sock_tag, sock_node); + entry_uid = get_uid_from_tag(st_entry->tag); + node = rb_next(node); + if (entry_uid != uid) + continue; + + CT_DEBUG("qtaguid: ctrl_delete(%s): st tag=0x%llx (uid=%u)\n", + input, st_entry->tag, entry_uid); + + if (!acct_tag || st_entry->tag == tag) { + rb_erase(&st_entry->sock_node, &sock_tag_tree); + /* Can't sockfd_put() within spinlock, do it later. */ + sock_tag_tree_insert(st_entry, &st_to_free_tree); + tr_entry = lookup_tag_ref(st_entry->tag, NULL); + BUG_ON(tr_entry->num_sock_tags <= 0); + tr_entry->num_sock_tags--; + /* + * TODO: remove if, and start failing. + * This is a hack to work around the fact that in some + * places we have "if (IS_ERR_OR_NULL(pqd_entry))" + * and are trying to work around apps + * that didn't open the /dev/xt_qtaguid. + */ + if (st_entry->list.next && st_entry->list.prev) + list_del(&st_entry->list); + } + } + spin_unlock_bh(&sock_tag_list_lock); + + sock_tag_tree_erase(&st_to_free_tree); + + /* Delete tag counter-sets */ + spin_lock_bh(&tag_counter_set_list_lock); + /* Counter sets are only on the uid tag, not full tag */ + tcs_entry = tag_counter_set_tree_search(&tag_counter_set_tree, tag); + if (tcs_entry) { + CT_DEBUG("qtaguid: ctrl_delete(%s): " + "erase tcs: tag=0x%llx (uid=%u) set=%d\n", + input, + tcs_entry->tn.tag, + get_uid_from_tag(tcs_entry->tn.tag), + tcs_entry->active_set); + rb_erase(&tcs_entry->tn.node, &tag_counter_set_tree); + kfree(tcs_entry); + } + spin_unlock_bh(&tag_counter_set_list_lock); + + /* + * If acct_tag is 0, then all entries belonging to uid are + * erased. + */ + spin_lock_bh(&iface_stat_list_lock); + list_for_each_entry(iface_entry, &iface_stat_list, list) { + spin_lock_bh(&iface_entry->tag_stat_list_lock); + node = rb_first(&iface_entry->tag_stat_tree); + while (node) { + ts_entry = rb_entry(node, struct tag_stat, tn.node); + entry_uid = get_uid_from_tag(ts_entry->tn.tag); + node = rb_next(node); + + CT_DEBUG("qtaguid: ctrl_delete(%s): " + "ts tag=0x%llx (uid=%u)\n", + input, ts_entry->tn.tag, entry_uid); + + if (entry_uid != uid) + continue; + if (!acct_tag || ts_entry->tn.tag == tag) { + CT_DEBUG("qtaguid: ctrl_delete(%s): " + "erase ts: %s 0x%llx %u\n", + input, iface_entry->ifname, + get_atag_from_tag(ts_entry->tn.tag), + entry_uid); + rb_erase(&ts_entry->tn.node, + &iface_entry->tag_stat_tree); + kfree(ts_entry); + } + } + spin_unlock_bh(&iface_entry->tag_stat_list_lock); + } + spin_unlock_bh(&iface_stat_list_lock); + + /* Cleanup the uid_tag_data */ + spin_lock_bh(&uid_tag_data_tree_lock); + node = rb_first(&uid_tag_data_tree); + while (node) { + utd_entry = rb_entry(node, struct uid_tag_data, node); + entry_uid = utd_entry->uid; + node = rb_next(node); + + CT_DEBUG("qtaguid: ctrl_delete(%s): " + "utd uid=%u\n", + input, entry_uid); + + if (entry_uid != uid) + continue; + /* + * Go over the tag_refs, and those that don't have + * sock_tags using them are freed. + */ + put_tag_ref_tree(tag, utd_entry); + put_utd_entry(utd_entry); + } + spin_unlock_bh(&uid_tag_data_tree_lock); + + atomic64_inc(&qtu_events.delete_cmds); + res = 0; + +err: + return res; +} + +static int ctrl_cmd_counter_set(const char *input) +{ + char cmd; + uid_t uid = 0; + tag_t tag; + int res, argc; + struct tag_counter_set *tcs; + int counter_set; + + argc = sscanf(input, "%c %d %u", &cmd, &counter_set, &uid); + CT_DEBUG("qtaguid: ctrl_counterset(%s): argc=%d cmd=%c " + "set=%d uid=%u\n", input, argc, cmd, + counter_set, uid); + if (argc != 3) { + res = -EINVAL; + goto err; + } + if (counter_set < 0 || counter_set >= IFS_MAX_COUNTER_SETS) { + pr_info("qtaguid: ctrl_counterset(%s): invalid counter_set range\n", + input); + res = -EINVAL; + goto err; + } + if (!can_manipulate_uids()) { + pr_info("qtaguid: ctrl_counterset(%s): " + "insufficient priv from pid=%u tgid=%u uid=%u\n", + input, current->pid, current->tgid, current_fsuid()); + res = -EPERM; + goto err; + } + + tag = make_tag_from_uid(uid); + spin_lock_bh(&tag_counter_set_list_lock); + tcs = tag_counter_set_tree_search(&tag_counter_set_tree, tag); + if (!tcs) { + tcs = kzalloc(sizeof(*tcs), GFP_ATOMIC); + if (!tcs) { + spin_unlock_bh(&tag_counter_set_list_lock); + pr_err("qtaguid: ctrl_counterset(%s): " + "failed to alloc counter set\n", + input); + res = -ENOMEM; + goto err; + } + tcs->tn.tag = tag; + tag_counter_set_tree_insert(tcs, &tag_counter_set_tree); + CT_DEBUG("qtaguid: ctrl_counterset(%s): added tcs tag=0x%llx " + "(uid=%u) set=%d\n", + input, tag, get_uid_from_tag(tag), counter_set); + } + tcs->active_set = counter_set; + spin_unlock_bh(&tag_counter_set_list_lock); + atomic64_inc(&qtu_events.counter_set_changes); + res = 0; + +err: + return res; +} + +static int ctrl_cmd_tag(const char *input) +{ + char cmd; + int sock_fd = 0; + uid_t uid = 0; + tag_t acct_tag = make_atag_from_value(0); + tag_t full_tag; + struct socket *el_socket; + int res, argc; + struct sock_tag *sock_tag_entry; + struct tag_ref *tag_ref_entry; + struct uid_tag_data *uid_tag_data_entry; + struct proc_qtu_data *pqd_entry; + + /* Unassigned args will get defaulted later. */ + argc = sscanf(input, "%c %d %llu %u", &cmd, &sock_fd, &acct_tag, &uid); + CT_DEBUG("qtaguid: ctrl_tag(%s): argc=%d cmd=%c sock_fd=%d " + "acct_tag=0x%llx uid=%u\n", input, argc, cmd, sock_fd, + acct_tag, uid); + if (argc < 2) { + res = -EINVAL; + goto err; + } + el_socket = sockfd_lookup(sock_fd, &res); /* This locks the file */ + if (!el_socket) { + pr_info("qtaguid: ctrl_tag(%s): failed to lookup" + " sock_fd=%d err=%d pid=%u tgid=%u uid=%u\n", + input, sock_fd, res, current->pid, current->tgid, + current_fsuid()); + goto err; + } + CT_DEBUG("qtaguid: ctrl_tag(%s): socket->...->f_count=%ld ->sk=%p\n", + input, atomic_long_read(&el_socket->file->f_count), + el_socket->sk); + if (argc < 3) { + acct_tag = make_atag_from_value(0); + } else if (!valid_atag(acct_tag)) { + pr_info("qtaguid: ctrl_tag(%s): invalid tag\n", input); + res = -EINVAL; + goto err_put; + } + CT_DEBUG("qtaguid: ctrl_tag(%s): " + "pid=%u tgid=%u uid=%u euid=%u fsuid=%u " + "ctrl.gid=%u in_group()=%d in_egroup()=%d\n", + input, current->pid, current->tgid, current_uid(), + current_euid(), current_fsuid(), + xt_qtaguid_ctrl_file->gid, + in_group_p(xt_qtaguid_ctrl_file->gid), + in_egroup_p(xt_qtaguid_ctrl_file->gid)); + if (argc < 4) { + uid = current_fsuid(); + } else if (!can_impersonate_uid(uid)) { + pr_info("qtaguid: ctrl_tag(%s): " + "insufficient priv from pid=%u tgid=%u uid=%u\n", + input, current->pid, current->tgid, current_fsuid()); + res = -EPERM; + goto err_put; + } + full_tag = combine_atag_with_uid(acct_tag, uid); + + spin_lock_bh(&sock_tag_list_lock); + sock_tag_entry = get_sock_stat_nl(el_socket->sk); + tag_ref_entry = get_tag_ref(full_tag, &uid_tag_data_entry); + if (IS_ERR(tag_ref_entry)) { + res = PTR_ERR(tag_ref_entry); + spin_unlock_bh(&sock_tag_list_lock); + goto err_put; + } + tag_ref_entry->num_sock_tags++; + if (sock_tag_entry) { + struct tag_ref *prev_tag_ref_entry; + + CT_DEBUG("qtaguid: ctrl_tag(%s): retag for sk=%p " + "st@%p ...->f_count=%ld\n", + input, el_socket->sk, sock_tag_entry, + atomic_long_read(&el_socket->file->f_count)); + /* + * This is a re-tagging, so release the sock_fd that was + * locked at the time of the 1st tagging. + * There is still the ref from this call's sockfd_lookup() so + * it can be done within the spinlock. + */ + sockfd_put(sock_tag_entry->socket); + prev_tag_ref_entry = lookup_tag_ref(sock_tag_entry->tag, + &uid_tag_data_entry); + BUG_ON(IS_ERR_OR_NULL(prev_tag_ref_entry)); + BUG_ON(prev_tag_ref_entry->num_sock_tags <= 0); + prev_tag_ref_entry->num_sock_tags--; + sock_tag_entry->tag = full_tag; + } else { + CT_DEBUG("qtaguid: ctrl_tag(%s): newtag for sk=%p\n", + input, el_socket->sk); + sock_tag_entry = kzalloc(sizeof(*sock_tag_entry), + GFP_ATOMIC); + if (!sock_tag_entry) { + pr_err("qtaguid: ctrl_tag(%s): " + "socket tag alloc failed\n", + input); + spin_unlock_bh(&sock_tag_list_lock); + res = -ENOMEM; + goto err_tag_unref_put; + } + sock_tag_entry->sk = el_socket->sk; + sock_tag_entry->socket = el_socket; + sock_tag_entry->pid = current->tgid; + sock_tag_entry->tag = combine_atag_with_uid(acct_tag, + uid); + spin_lock_bh(&uid_tag_data_tree_lock); + pqd_entry = proc_qtu_data_tree_search( + &proc_qtu_data_tree, current->tgid); + /* + * TODO: remove if, and start failing. + * At first, we want to catch user-space code that is not + * opening the /dev/xt_qtaguid. + */ + if (IS_ERR_OR_NULL(pqd_entry)) + pr_warn_once( + "qtaguid: %s(): " + "User space forgot to open /dev/xt_qtaguid? " + "pid=%u tgid=%u uid=%u\n", __func__, + current->pid, current->tgid, + current_fsuid()); + else + list_add(&sock_tag_entry->list, + &pqd_entry->sock_tag_list); + spin_unlock_bh(&uid_tag_data_tree_lock); + + sock_tag_tree_insert(sock_tag_entry, &sock_tag_tree); + atomic64_inc(&qtu_events.sockets_tagged); + } + spin_unlock_bh(&sock_tag_list_lock); + /* We keep the ref to the socket (file) until it is untagged */ + CT_DEBUG("qtaguid: ctrl_tag(%s): done st@%p ...->f_count=%ld\n", + input, sock_tag_entry, + atomic_long_read(&el_socket->file->f_count)); + return 0; + +err_tag_unref_put: + BUG_ON(tag_ref_entry->num_sock_tags <= 0); + tag_ref_entry->num_sock_tags--; + free_tag_ref_from_utd_entry(tag_ref_entry, uid_tag_data_entry); +err_put: + CT_DEBUG("qtaguid: ctrl_tag(%s): done. ...->f_count=%ld\n", + input, atomic_long_read(&el_socket->file->f_count) - 1); + /* Release the sock_fd that was grabbed by sockfd_lookup(). */ + sockfd_put(el_socket); + return res; + +err: + CT_DEBUG("qtaguid: ctrl_tag(%s): done.\n", input); + return res; +} + +static int ctrl_cmd_untag(const char *input) +{ + char cmd; + int sock_fd = 0; + struct socket *el_socket; + int res, argc; + struct sock_tag *sock_tag_entry; + struct tag_ref *tag_ref_entry; + struct uid_tag_data *utd_entry; + struct proc_qtu_data *pqd_entry; + + argc = sscanf(input, "%c %d", &cmd, &sock_fd); + CT_DEBUG("qtaguid: ctrl_untag(%s): argc=%d cmd=%c sock_fd=%d\n", + input, argc, cmd, sock_fd); + if (argc < 2) { + res = -EINVAL; + goto err; + } + el_socket = sockfd_lookup(sock_fd, &res); /* This locks the file */ + if (!el_socket) { + pr_info("qtaguid: ctrl_untag(%s): failed to lookup" + " sock_fd=%d err=%d pid=%u tgid=%u uid=%u\n", + input, sock_fd, res, current->pid, current->tgid, + current_fsuid()); + goto err; + } + CT_DEBUG("qtaguid: ctrl_untag(%s): socket->...->f_count=%ld ->sk=%p\n", + input, atomic_long_read(&el_socket->file->f_count), + el_socket->sk); + spin_lock_bh(&sock_tag_list_lock); + sock_tag_entry = get_sock_stat_nl(el_socket->sk); + if (!sock_tag_entry) { + spin_unlock_bh(&sock_tag_list_lock); + res = -EINVAL; + goto err_put; + } + /* + * The socket already belongs to the current process + * so it can do whatever it wants to it. + */ + rb_erase(&sock_tag_entry->sock_node, &sock_tag_tree); + + tag_ref_entry = lookup_tag_ref(sock_tag_entry->tag, &utd_entry); + BUG_ON(!tag_ref_entry); + BUG_ON(tag_ref_entry->num_sock_tags <= 0); + spin_lock_bh(&uid_tag_data_tree_lock); + pqd_entry = proc_qtu_data_tree_search( + &proc_qtu_data_tree, current->tgid); + /* + * TODO: remove if, and start failing. + * At first, we want to catch user-space code that is not + * opening the /dev/xt_qtaguid. + */ + if (IS_ERR_OR_NULL(pqd_entry)) + pr_warn_once("qtaguid: %s(): " + "User space forgot to open /dev/xt_qtaguid? " + "pid=%u tgid=%u uid=%u\n", __func__, + current->pid, current->tgid, current_fsuid()); + else + list_del(&sock_tag_entry->list); + spin_unlock_bh(&uid_tag_data_tree_lock); + /* + * We don't free tag_ref from the utd_entry here, + * only during a cmd_delete(). + */ + tag_ref_entry->num_sock_tags--; + spin_unlock_bh(&sock_tag_list_lock); + /* + * Release the sock_fd that was grabbed at tag time, + * and once more for the sockfd_lookup() here. + */ + sockfd_put(sock_tag_entry->socket); + CT_DEBUG("qtaguid: ctrl_untag(%s): done. st@%p ...->f_count=%ld\n", + input, sock_tag_entry, + atomic_long_read(&el_socket->file->f_count) - 1); + sockfd_put(el_socket); + + kfree(sock_tag_entry); + atomic64_inc(&qtu_events.sockets_untagged); + + return 0; + +err_put: + CT_DEBUG("qtaguid: ctrl_untag(%s): done. socket->...->f_count=%ld\n", + input, atomic_long_read(&el_socket->file->f_count) - 1); + /* Release the sock_fd that was grabbed by sockfd_lookup(). */ + sockfd_put(el_socket); + return res; + +err: + CT_DEBUG("qtaguid: ctrl_untag(%s): done.\n", input); + return res; +} + +static int qtaguid_ctrl_parse(const char *input, int count) +{ + char cmd; + int res; + + CT_DEBUG("qtaguid: ctrl(%s): pid=%u tgid=%u uid=%u\n", + input, current->pid, current->tgid, current_fsuid()); + + cmd = input[0]; + /* Collect params for commands */ + switch (cmd) { + case 'd': + res = ctrl_cmd_delete(input); + break; + + case 's': + res = ctrl_cmd_counter_set(input); + break; + + case 't': + res = ctrl_cmd_tag(input); + break; + + case 'u': + res = ctrl_cmd_untag(input); + break; + + default: + res = -EINVAL; + goto err; + } + if (!res) + res = count; +err: + CT_DEBUG("qtaguid: ctrl(%s): res=%d\n", input, res); + return res; +} + +#define MAX_QTAGUID_CTRL_INPUT_LEN 255 +static ssize_t qtaguid_ctrl_proc_write(struct file *file, const char __user *buffer, + size_t count, loff_t *offp) +{ + char input_buf[MAX_QTAGUID_CTRL_INPUT_LEN]; + + if (unlikely(module_passive)) + return count; + + if (count >= MAX_QTAGUID_CTRL_INPUT_LEN) + return -EINVAL; + + if (copy_from_user(input_buf, buffer, count)) + return -EFAULT; + + input_buf[count] = '\0'; + return qtaguid_ctrl_parse(input_buf, count); +} + +struct proc_print_info { + struct iface_stat *iface_entry; + int item_index; + tag_t tag; /* tag found by reading to tag_pos */ + off_t tag_pos; + int tag_item_index; +}; + +static void pp_stats_header(struct seq_file *m) +{ + seq_puts(m, + "idx iface acct_tag_hex uid_tag_int cnt_set " + "rx_bytes rx_packets " + "tx_bytes tx_packets " + "rx_tcp_bytes rx_tcp_packets " + "rx_udp_bytes rx_udp_packets " + "rx_other_bytes rx_other_packets " + "tx_tcp_bytes tx_tcp_packets " + "tx_udp_bytes tx_udp_packets " + "tx_other_bytes tx_other_packets\n"); +} + +static int pp_stats_line(struct seq_file *m, struct tag_stat *ts_entry, + int cnt_set) +{ + int ret; + struct data_counters *cnts; + tag_t tag = ts_entry->tn.tag; + uid_t stat_uid = get_uid_from_tag(tag); + struct proc_print_info *ppi = m->private; + /* Detailed tags are not available to everybody */ + if (get_atag_from_tag(tag) && !can_read_other_uid_stats(stat_uid)) { + CT_DEBUG("qtaguid: stats line: " + "%s 0x%llx %u: insufficient priv " + "from pid=%u tgid=%u uid=%u stats.gid=%u\n", + ppi->iface_entry->ifname, + get_atag_from_tag(tag), stat_uid, + current->pid, current->tgid, current_fsuid(), + xt_qtaguid_stats_file->gid); + return 0; + } + ppi->item_index++; + cnts = &ts_entry->counters; + ret = seq_printf(m, "%d %s 0x%llx %u %u " + "%llu %llu " + "%llu %llu " + "%llu %llu " + "%llu %llu " + "%llu %llu " + "%llu %llu " + "%llu %llu " + "%llu %llu\n", + ppi->item_index, + ppi->iface_entry->ifname, + get_atag_from_tag(tag), + stat_uid, + cnt_set, + dc_sum_bytes(cnts, cnt_set, IFS_RX), + dc_sum_packets(cnts, cnt_set, IFS_RX), + dc_sum_bytes(cnts, cnt_set, IFS_TX), + dc_sum_packets(cnts, cnt_set, IFS_TX), + cnts->bpc[cnt_set][IFS_RX][IFS_TCP].bytes, + cnts->bpc[cnt_set][IFS_RX][IFS_TCP].packets, + cnts->bpc[cnt_set][IFS_RX][IFS_UDP].bytes, + cnts->bpc[cnt_set][IFS_RX][IFS_UDP].packets, + cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].bytes, + cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].packets, + cnts->bpc[cnt_set][IFS_TX][IFS_TCP].bytes, + cnts->bpc[cnt_set][IFS_TX][IFS_TCP].packets, + cnts->bpc[cnt_set][IFS_TX][IFS_UDP].bytes, + cnts->bpc[cnt_set][IFS_TX][IFS_UDP].packets, + cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].bytes, + cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].packets); + return ret ?: 1; +} + +static bool pp_sets(struct seq_file *m, struct tag_stat *ts_entry) +{ + int ret; + int counter_set; + for (counter_set = 0; counter_set < IFS_MAX_COUNTER_SETS; + counter_set++) { + ret = pp_stats_line(m, ts_entry, counter_set); + if (ret < 0) + return false; + } + return true; +} + +static int qtaguid_stats_proc_iface_stat_ptr_valid(struct iface_stat *ptr) +{ + struct iface_stat *iface_entry; + + if (!ptr) + return false; + + list_for_each_entry(iface_entry, &iface_stat_list, list) + if (iface_entry == ptr) + return true; + return false; +} + +static void qtaguid_stats_proc_next_iface_entry(struct proc_print_info *ppi) +{ + spin_unlock_bh(&ppi->iface_entry->tag_stat_list_lock); + list_for_each_entry_continue(ppi->iface_entry, &iface_stat_list, list) { + spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock); + return; + } + ppi->iface_entry = NULL; +} + +static void *qtaguid_stats_proc_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct proc_print_info *ppi = m->private; + struct tag_stat *ts_entry; + struct rb_node *node; + + if (!v) { + pr_err("qtaguid: %s(): unexpected v: NULL\n", __func__); + return NULL; + } + + (*pos)++; + + if (!ppi->iface_entry || unlikely(module_passive)) + return NULL; + + if (v == SEQ_START_TOKEN) + node = rb_first(&ppi->iface_entry->tag_stat_tree); + else + node = rb_next(&((struct tag_stat *)v)->tn.node); + + while (!node) { + qtaguid_stats_proc_next_iface_entry(ppi); + if (!ppi->iface_entry) + return NULL; + node = rb_first(&ppi->iface_entry->tag_stat_tree); + } + + ts_entry = rb_entry(node, struct tag_stat, tn.node); + ppi->tag = ts_entry->tn.tag; + ppi->tag_pos = *pos; + ppi->tag_item_index = ppi->item_index; + return ts_entry; +} + +static void *qtaguid_stats_proc_start(struct seq_file *m, loff_t *pos) +{ + struct proc_print_info *ppi = m->private; + struct tag_stat *ts_entry = NULL; + + spin_lock_bh(&iface_stat_list_lock); + + if (*pos == 0) { + ppi->item_index = 1; + ppi->tag_pos = 0; + if (list_empty(&iface_stat_list)) { + ppi->iface_entry = NULL; + } else { + ppi->iface_entry = list_first_entry(&iface_stat_list, + struct iface_stat, + list); + spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock); + } + return SEQ_START_TOKEN; + } + if (!qtaguid_stats_proc_iface_stat_ptr_valid(ppi->iface_entry)) { + if (ppi->iface_entry) { + pr_err("qtaguid: %s(): iface_entry %p not found\n", + __func__, ppi->iface_entry); + ppi->iface_entry = NULL; + } + return NULL; + } + + spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock); + + if (!ppi->tag_pos) { + /* seq_read skipped first next call */ + ts_entry = SEQ_START_TOKEN; + } else { + ts_entry = tag_stat_tree_search( + &ppi->iface_entry->tag_stat_tree, ppi->tag); + if (!ts_entry) { + pr_info("qtaguid: %s(): tag_stat.tag 0x%llx not found. Abort.\n", + __func__, ppi->tag); + return NULL; + } + } + + if (*pos == ppi->tag_pos) { /* normal resume */ + ppi->item_index = ppi->tag_item_index; + } else { + /* seq_read skipped a next call */ + *pos = ppi->tag_pos; + ts_entry = qtaguid_stats_proc_next(m, ts_entry, pos); + } + + return ts_entry; +} + +static void qtaguid_stats_proc_stop(struct seq_file *m, void *v) +{ + struct proc_print_info *ppi = m->private; + if (ppi->iface_entry) + spin_unlock_bh(&ppi->iface_entry->tag_stat_list_lock); + spin_unlock_bh(&iface_stat_list_lock); +} + +/* + * Procfs reader to get all tag stats using style "1)" as described in + * fs/proc/generic.c + * Groups all protocols tx/rx bytes. + */ +static int qtaguid_stats_proc_show(struct seq_file *m, void *v) +{ + struct tag_stat *ts_entry = v; + + if (v == SEQ_START_TOKEN) + pp_stats_header(m); + else + pp_sets(m, ts_entry); + + return 0; +} + +/*------------------------------------------*/ +static int qtudev_open(struct inode *inode, struct file *file) +{ + struct uid_tag_data *utd_entry; + struct proc_qtu_data *pqd_entry; + struct proc_qtu_data *new_pqd_entry; + int res; + bool utd_entry_found; + + if (unlikely(qtu_proc_handling_passive)) + return 0; + + DR_DEBUG("qtaguid: qtudev_open(): pid=%u tgid=%u uid=%u\n", + current->pid, current->tgid, current_fsuid()); + + spin_lock_bh(&uid_tag_data_tree_lock); + + /* Look for existing uid data, or alloc one. */ + utd_entry = get_uid_data(current_fsuid(), &utd_entry_found); + if (IS_ERR_OR_NULL(utd_entry)) { + res = PTR_ERR(utd_entry); + goto err_unlock; + } + + /* Look for existing PID based proc_data */ + pqd_entry = proc_qtu_data_tree_search(&proc_qtu_data_tree, + current->tgid); + if (pqd_entry) { + pr_err("qtaguid: qtudev_open(): %u/%u %u " + "%s already opened\n", + current->pid, current->tgid, current_fsuid(), + QTU_DEV_NAME); + res = -EBUSY; + goto err_unlock_free_utd; + } + + new_pqd_entry = kzalloc(sizeof(*new_pqd_entry), GFP_ATOMIC); + if (!new_pqd_entry) { + pr_err("qtaguid: qtudev_open(): %u/%u %u: " + "proc data alloc failed\n", + current->pid, current->tgid, current_fsuid()); + res = -ENOMEM; + goto err_unlock_free_utd; + } + new_pqd_entry->pid = current->tgid; + INIT_LIST_HEAD(&new_pqd_entry->sock_tag_list); + new_pqd_entry->parent_tag_data = utd_entry; + utd_entry->num_pqd++; + + proc_qtu_data_tree_insert(new_pqd_entry, + &proc_qtu_data_tree); + + spin_unlock_bh(&uid_tag_data_tree_lock); + DR_DEBUG("qtaguid: tracking data for uid=%u in pqd=%p\n", + current_fsuid(), new_pqd_entry); + file->private_data = new_pqd_entry; + return 0; + +err_unlock_free_utd: + if (!utd_entry_found) { + rb_erase(&utd_entry->node, &uid_tag_data_tree); + kfree(utd_entry); + } +err_unlock: + spin_unlock_bh(&uid_tag_data_tree_lock); + return res; +} + +static int qtudev_release(struct inode *inode, struct file *file) +{ + struct proc_qtu_data *pqd_entry = file->private_data; + struct uid_tag_data *utd_entry = pqd_entry->parent_tag_data; + struct sock_tag *st_entry; + struct rb_root st_to_free_tree = RB_ROOT; + struct list_head *entry, *next; + struct tag_ref *tr; + + if (unlikely(qtu_proc_handling_passive)) + return 0; + + /* + * Do not trust the current->pid, it might just be a kworker cleaning + * up after a dead proc. + */ + DR_DEBUG("qtaguid: qtudev_release(): " + "pid=%u tgid=%u uid=%u " + "pqd_entry=%p->pid=%u utd_entry=%p->active_tags=%d\n", + current->pid, current->tgid, pqd_entry->parent_tag_data->uid, + pqd_entry, pqd_entry->pid, utd_entry, + utd_entry->num_active_tags); + + spin_lock_bh(&sock_tag_list_lock); + spin_lock_bh(&uid_tag_data_tree_lock); + + list_for_each_safe(entry, next, &pqd_entry->sock_tag_list) { + st_entry = list_entry(entry, struct sock_tag, list); + DR_DEBUG("qtaguid: %s(): " + "erase sock_tag=%p->sk=%p pid=%u tgid=%u uid=%u\n", + __func__, + st_entry, st_entry->sk, + current->pid, current->tgid, + pqd_entry->parent_tag_data->uid); + + utd_entry = uid_tag_data_tree_search( + &uid_tag_data_tree, + get_uid_from_tag(st_entry->tag)); + BUG_ON(IS_ERR_OR_NULL(utd_entry)); + DR_DEBUG("qtaguid: %s(): " + "looking for tag=0x%llx in utd_entry=%p\n", __func__, + st_entry->tag, utd_entry); + tr = tag_ref_tree_search(&utd_entry->tag_ref_tree, + st_entry->tag); + BUG_ON(!tr); + BUG_ON(tr->num_sock_tags <= 0); + tr->num_sock_tags--; + free_tag_ref_from_utd_entry(tr, utd_entry); + + rb_erase(&st_entry->sock_node, &sock_tag_tree); + list_del(&st_entry->list); + /* Can't sockfd_put() within spinlock, do it later. */ + sock_tag_tree_insert(st_entry, &st_to_free_tree); + + /* + * Try to free the utd_entry if no other proc_qtu_data is + * using it (num_pqd is 0) and it doesn't have active tags + * (num_active_tags is 0). + */ + put_utd_entry(utd_entry); + } + + rb_erase(&pqd_entry->node, &proc_qtu_data_tree); + BUG_ON(pqd_entry->parent_tag_data->num_pqd < 1); + pqd_entry->parent_tag_data->num_pqd--; + put_utd_entry(pqd_entry->parent_tag_data); + kfree(pqd_entry); + file->private_data = NULL; + + spin_unlock_bh(&uid_tag_data_tree_lock); + spin_unlock_bh(&sock_tag_list_lock); + + + sock_tag_tree_erase(&st_to_free_tree); + + prdebug_full_state(0, "%s(): pid=%u tgid=%u", __func__, + current->pid, current->tgid); + return 0; +} + +/*------------------------------------------*/ +static const struct file_operations qtudev_fops = { + .owner = THIS_MODULE, + .open = qtudev_open, + .release = qtudev_release, +}; + +static struct miscdevice qtu_device = { + .minor = MISC_DYNAMIC_MINOR, + .name = QTU_DEV_NAME, + .fops = &qtudev_fops, + /* How sad it doesn't allow for defaults: .mode = S_IRUGO | S_IWUSR */ +}; + +static const struct seq_operations proc_qtaguid_ctrl_seqops = { + .start = qtaguid_ctrl_proc_start, + .next = qtaguid_ctrl_proc_next, + .stop = qtaguid_ctrl_proc_stop, + .show = qtaguid_ctrl_proc_show, +}; + +static int proc_qtaguid_ctrl_open(struct inode *inode, struct file *file) +{ + return seq_open_private(file, &proc_qtaguid_ctrl_seqops, + sizeof(struct proc_ctrl_print_info)); +} + +static const struct file_operations proc_qtaguid_ctrl_fops = { + .open = proc_qtaguid_ctrl_open, + .read = seq_read, + .write = qtaguid_ctrl_proc_write, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +static const struct seq_operations proc_qtaguid_stats_seqops = { + .start = qtaguid_stats_proc_start, + .next = qtaguid_stats_proc_next, + .stop = qtaguid_stats_proc_stop, + .show = qtaguid_stats_proc_show, +}; + +static int proc_qtaguid_stats_open(struct inode *inode, struct file *file) +{ + return seq_open_private(file, &proc_qtaguid_stats_seqops, + sizeof(struct proc_print_info)); +} + +static const struct file_operations proc_qtaguid_stats_fops = { + .open = proc_qtaguid_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +/*------------------------------------------*/ +static int __init qtaguid_proc_register(struct proc_dir_entry **res_procdir) +{ + int ret; + *res_procdir = proc_mkdir(module_procdirname, init_net.proc_net); + if (!*res_procdir) { + pr_err("qtaguid: failed to create proc/.../xt_qtaguid\n"); + ret = -ENOMEM; + goto no_dir; + } + + xt_qtaguid_ctrl_file = proc_create_data("ctrl", proc_ctrl_perms, + *res_procdir, + &proc_qtaguid_ctrl_fops, + NULL); + if (!xt_qtaguid_ctrl_file) { + pr_err("qtaguid: failed to create xt_qtaguid/ctrl " + " file\n"); + ret = -ENOMEM; + goto no_ctrl_entry; + } + + xt_qtaguid_stats_file = proc_create_data("stats", proc_stats_perms, + *res_procdir, + &proc_qtaguid_stats_fops, + NULL); + if (!xt_qtaguid_stats_file) { + pr_err("qtaguid: failed to create xt_qtaguid/stats " + "file\n"); + ret = -ENOMEM; + goto no_stats_entry; + } + /* + * TODO: add support counter hacking + * xt_qtaguid_stats_file->write_proc = qtaguid_stats_proc_write; + */ + return 0; + +no_stats_entry: + remove_proc_entry("ctrl", *res_procdir); +no_ctrl_entry: + remove_proc_entry("xt_qtaguid", NULL); +no_dir: + return ret; +} + +static struct xt_match qtaguid_mt_reg __read_mostly = { + /* + * This module masquerades as the "owner" module so that iptables + * tools can deal with it. + */ + .name = "owner", + .revision = 1, + .family = NFPROTO_UNSPEC, + .match = qtaguid_mt, + .matchsize = sizeof(struct xt_qtaguid_match_info), + .me = THIS_MODULE, +}; + +static int __init qtaguid_mt_init(void) +{ + if (qtaguid_proc_register(&xt_qtaguid_procdir) + || iface_stat_init(xt_qtaguid_procdir) + || xt_register_match(&qtaguid_mt_reg) + || misc_register(&qtu_device)) + return -1; + return 0; +} + +/* + * TODO: allow unloading of the module. + * For now stats are permanent. + * Kconfig forces'y/n' and never an 'm'. + */ + +module_init(qtaguid_mt_init); +MODULE_AUTHOR("jpa <jpa@google.com>"); +MODULE_DESCRIPTION("Xtables: socket owner+tag matching and associated stats"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_owner"); +MODULE_ALIAS("ip6t_owner"); +MODULE_ALIAS("ipt_qtaguid"); +MODULE_ALIAS("ip6t_qtaguid"); diff --git a/net/netfilter/xt_qtaguid_internal.h b/net/netfilter/xt_qtaguid_internal.h new file mode 100644 index 00000000000..6dc14a9c688 --- /dev/null +++ b/net/netfilter/xt_qtaguid_internal.h @@ -0,0 +1,352 @@ +/* + * Kernel iptables module to track stats for packets based on user tags. + * + * (C) 2011 Google, Inc + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __XT_QTAGUID_INTERNAL_H__ +#define __XT_QTAGUID_INTERNAL_H__ + +#include <linux/types.h> +#include <linux/rbtree.h> +#include <linux/spinlock_types.h> +#include <linux/workqueue.h> + +/* Iface handling */ +#define IDEBUG_MASK (1<<0) +/* Iptable Matching. Per packet. */ +#define MDEBUG_MASK (1<<1) +/* Red-black tree handling. Per packet. */ +#define RDEBUG_MASK (1<<2) +/* procfs ctrl/stats handling */ +#define CDEBUG_MASK (1<<3) +/* dev and resource tracking */ +#define DDEBUG_MASK (1<<4) + +/* E.g (IDEBUG_MASK | CDEBUG_MASK | DDEBUG_MASK) */ +#define DEFAULT_DEBUG_MASK 0 + +/* + * (Un)Define these *DEBUG to compile out/in the pr_debug calls. + * All undef: text size ~ 0x3030; all def: ~ 0x4404. + */ +#define IDEBUG +#define MDEBUG +#define RDEBUG +#define CDEBUG +#define DDEBUG + +#define MSK_DEBUG(mask, ...) do { \ + if (unlikely(qtaguid_debug_mask & (mask))) \ + pr_debug(__VA_ARGS__); \ + } while (0) +#ifdef IDEBUG +#define IF_DEBUG(...) MSK_DEBUG(IDEBUG_MASK, __VA_ARGS__) +#else +#define IF_DEBUG(...) no_printk(__VA_ARGS__) +#endif +#ifdef MDEBUG +#define MT_DEBUG(...) MSK_DEBUG(MDEBUG_MASK, __VA_ARGS__) +#else +#define MT_DEBUG(...) no_printk(__VA_ARGS__) +#endif +#ifdef RDEBUG +#define RB_DEBUG(...) MSK_DEBUG(RDEBUG_MASK, __VA_ARGS__) +#else +#define RB_DEBUG(...) no_printk(__VA_ARGS__) +#endif +#ifdef CDEBUG +#define CT_DEBUG(...) MSK_DEBUG(CDEBUG_MASK, __VA_ARGS__) +#else +#define CT_DEBUG(...) no_printk(__VA_ARGS__) +#endif +#ifdef DDEBUG +#define DR_DEBUG(...) MSK_DEBUG(DDEBUG_MASK, __VA_ARGS__) +#else +#define DR_DEBUG(...) no_printk(__VA_ARGS__) +#endif + +extern uint qtaguid_debug_mask; + +/*---------------------------------------------------------------------------*/ +/* + * Tags: + * + * They represent what the data usage counters will be tracked against. + * By default a tag is just based on the UID. + * The UID is used as the base for policing, and can not be ignored. + * So a tag will always at least represent a UID (uid_tag). + * + * A tag can be augmented with an "accounting tag" which is associated + * with a UID. + * User space can set the acct_tag portion of the tag which is then used + * with sockets: all data belonging to that socket will be counted against the + * tag. The policing is then based on the tag's uid_tag portion, + * and stats are collected for the acct_tag portion separately. + * + * There could be + * a: {acct_tag=1, uid_tag=10003} + * b: {acct_tag=2, uid_tag=10003} + * c: {acct_tag=3, uid_tag=10003} + * d: {acct_tag=0, uid_tag=10003} + * a, b, and c represent tags associated with specific sockets. + * d is for the totals for that uid, including all untagged traffic. + * Typically d is used with policing/quota rules. + * + * We want tag_t big enough to distinguish uid_t and acct_tag. + * It might become a struct if needed. + * Nothing should be using it as an int. + */ +typedef uint64_t tag_t; /* Only used via accessors */ + +#define TAG_UID_MASK 0xFFFFFFFFULL +#define TAG_ACCT_MASK (~0xFFFFFFFFULL) + +static inline int tag_compare(tag_t t1, tag_t t2) +{ + return t1 < t2 ? -1 : t1 == t2 ? 0 : 1; +} + +static inline tag_t combine_atag_with_uid(tag_t acct_tag, uid_t uid) +{ + return acct_tag | uid; +} +static inline tag_t make_tag_from_uid(uid_t uid) +{ + return uid; +} +static inline uid_t get_uid_from_tag(tag_t tag) +{ + return tag & TAG_UID_MASK; +} +static inline tag_t get_utag_from_tag(tag_t tag) +{ + return tag & TAG_UID_MASK; +} +static inline tag_t get_atag_from_tag(tag_t tag) +{ + return tag & TAG_ACCT_MASK; +} + +static inline bool valid_atag(tag_t tag) +{ + return !(tag & TAG_UID_MASK); +} +static inline tag_t make_atag_from_value(uint32_t value) +{ + return (uint64_t)value << 32; +} +/*---------------------------------------------------------------------------*/ + +/* + * Maximum number of socket tags that a UID is allowed to have active. + * Multiple processes belonging to the same UID contribute towards this limit. + * Special UIDs that can impersonate a UID also contribute (e.g. download + * manager, ...) + */ +#define DEFAULT_MAX_SOCK_TAGS 1024 + +/* + * For now we only track 2 sets of counters. + * The default set is 0. + * Userspace can activate another set for a given uid being tracked. + */ +#define IFS_MAX_COUNTER_SETS 2 + +enum ifs_tx_rx { + IFS_TX, + IFS_RX, + IFS_MAX_DIRECTIONS +}; + +/* For now, TCP, UDP, the rest */ +enum ifs_proto { + IFS_TCP, + IFS_UDP, + IFS_PROTO_OTHER, + IFS_MAX_PROTOS +}; + +struct byte_packet_counters { + uint64_t bytes; + uint64_t packets; +}; + +struct data_counters { + struct byte_packet_counters bpc[IFS_MAX_COUNTER_SETS][IFS_MAX_DIRECTIONS][IFS_MAX_PROTOS]; +}; + +static inline uint64_t dc_sum_bytes(struct data_counters *counters, + int set, + enum ifs_tx_rx direction) +{ + return counters->bpc[set][direction][IFS_TCP].bytes + + counters->bpc[set][direction][IFS_UDP].bytes + + counters->bpc[set][direction][IFS_PROTO_OTHER].bytes; +} + +static inline uint64_t dc_sum_packets(struct data_counters *counters, + int set, + enum ifs_tx_rx direction) +{ + return counters->bpc[set][direction][IFS_TCP].packets + + counters->bpc[set][direction][IFS_UDP].packets + + counters->bpc[set][direction][IFS_PROTO_OTHER].packets; +} + + +/* Generic X based nodes used as a base for rb_tree ops */ +struct tag_node { + struct rb_node node; + tag_t tag; +}; + +struct tag_stat { + struct tag_node tn; + struct data_counters counters; + /* + * If this tag is acct_tag based, we need to count against the + * matching parent uid_tag. + */ + struct data_counters *parent_counters; +}; + +struct iface_stat { + struct list_head list; /* in iface_stat_list */ + char *ifname; + bool active; + /* net_dev is only valid for active iface_stat */ + struct net_device *net_dev; + + struct byte_packet_counters totals_via_dev[IFS_MAX_DIRECTIONS]; + struct data_counters totals_via_skb; + /* + * We keep the last_known, because some devices reset their counters + * just before NETDEV_UP, while some will reset just before + * NETDEV_REGISTER (which is more normal). + * So now, if the device didn't do a NETDEV_UNREGISTER and we see + * its current dev stats smaller that what was previously known, we + * assume an UNREGISTER and just use the last_known. + */ + struct byte_packet_counters last_known[IFS_MAX_DIRECTIONS]; + /* last_known is usable when last_known_valid is true */ + bool last_known_valid; + + struct proc_dir_entry *proc_ptr; + + struct rb_root tag_stat_tree; + spinlock_t tag_stat_list_lock; +}; + +/* This is needed to create proc_dir_entries from atomic context. */ +struct iface_stat_work { + struct work_struct iface_work; + struct iface_stat *iface_entry; +}; + +/* + * Track tag that this socket is transferring data for, and not necessarily + * the uid that owns the socket. + * This is the tag against which tag_stat.counters will be billed. + * These structs need to be looked up by sock and pid. + */ +struct sock_tag { + struct rb_node sock_node; + struct sock *sk; /* Only used as a number, never dereferenced */ + /* The socket is needed for sockfd_put() */ + struct socket *socket; + /* Used to associate with a given pid */ + struct list_head list; /* in proc_qtu_data.sock_tag_list */ + pid_t pid; + + tag_t tag; +}; + +struct qtaguid_event_counts { + /* Various successful events */ + atomic64_t sockets_tagged; + atomic64_t sockets_untagged; + atomic64_t counter_set_changes; + atomic64_t delete_cmds; + atomic64_t iface_events; /* Number of NETDEV_* events handled */ + + atomic64_t match_calls; /* Number of times iptables called mt */ + /* Number of times iptables called mt from pre or post routing hooks */ + atomic64_t match_calls_prepost; + /* + * match_found_sk_*: numbers related to the netfilter matching + * function finding a sock for the sk_buff. + * Total skbs processed is sum(match_found*). + */ + atomic64_t match_found_sk; /* An sk was already in the sk_buff. */ + /* The connection tracker had or didn't have the sk. */ + atomic64_t match_found_sk_in_ct; + atomic64_t match_found_no_sk_in_ct; + /* + * No sk could be found. No apparent owner. Could happen with + * unsolicited traffic. + */ + atomic64_t match_no_sk; + /* + * The file ptr in the sk_socket wasn't there. + * This might happen for traffic while the socket is being closed. + */ + atomic64_t match_no_sk_file; +}; + +/* Track the set active_set for the given tag. */ +struct tag_counter_set { + struct tag_node tn; + int active_set; +}; + +/*----------------------------------------------*/ +/* + * The qtu uid data is used to track resources that are created directly or + * indirectly by processes (uid tracked). + * It is shared by the processes with the same uid. + * Some of the resource will be counted to prevent further rogue allocations, + * some will need freeing once the owner process (uid) exits. + */ +struct uid_tag_data { + struct rb_node node; + uid_t uid; + + /* + * For the uid, how many accounting tags have been set. + */ + int num_active_tags; + /* Track the number of proc_qtu_data that reference it */ + int num_pqd; + struct rb_root tag_ref_tree; + /* No tag_node_tree_lock; use uid_tag_data_tree_lock */ +}; + +struct tag_ref { + struct tag_node tn; + + /* + * This tracks the number of active sockets that have a tag on them + * which matches this tag_ref.tn.tag. + * A tag ref can live on after the sockets are untagged. + * A tag ref can only be removed during a tag delete command. + */ + int num_sock_tags; +}; + +struct proc_qtu_data { + struct rb_node node; + pid_t pid; + + struct uid_tag_data *parent_tag_data; + + /* Tracks the sock_tags that need freeing upon this proc's death */ + struct list_head sock_tag_list; + /* No spinlock_t sock_tag_list_lock; use the global one. */ +}; + +/*----------------------------------------------*/ +#endif /* ifndef __XT_QTAGUID_INTERNAL_H__ */ diff --git a/net/netfilter/xt_qtaguid_print.c b/net/netfilter/xt_qtaguid_print.c new file mode 100644 index 00000000000..f6a00a3520e --- /dev/null +++ b/net/netfilter/xt_qtaguid_print.c @@ -0,0 +1,566 @@ +/* + * Pretty printing Support for iptables xt_qtaguid module. + * + * (C) 2011 Google, Inc + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * Most of the functions in this file just waste time if DEBUG is not defined. + * The matching xt_qtaguid_print.h will static inline empty funcs if the needed + * debug flags ore not defined. + * Those funcs that fail to allocate memory will panic as there is no need to + * hobble allong just pretending to do the requested work. + */ + +#define DEBUG + +#include <linux/fs.h> +#include <linux/gfp.h> +#include <linux/net.h> +#include <linux/rbtree.h> +#include <linux/slab.h> +#include <linux/spinlock_types.h> + + +#include "xt_qtaguid_internal.h" +#include "xt_qtaguid_print.h" + +#ifdef DDEBUG + +static void _bug_on_err_or_null(void *ptr) +{ + if (IS_ERR_OR_NULL(ptr)) { + pr_err("qtaguid: kmalloc failed\n"); + BUG(); + } +} + +char *pp_tag_t(tag_t *tag) +{ + char *res; + + if (!tag) + res = kasprintf(GFP_ATOMIC, "tag_t@null{}"); + else + res = kasprintf(GFP_ATOMIC, + "tag_t@%p{tag=0x%llx, uid=%u}", + tag, *tag, get_uid_from_tag(*tag)); + _bug_on_err_or_null(res); + return res; +} + +char *pp_data_counters(struct data_counters *dc, bool showValues) +{ + char *res; + + if (!dc) + res = kasprintf(GFP_ATOMIC, "data_counters@null{}"); + else if (showValues) + res = kasprintf( + GFP_ATOMIC, "data_counters@%p{" + "set0{" + "rx{" + "tcp{b=%llu, p=%llu}, " + "udp{b=%llu, p=%llu}," + "other{b=%llu, p=%llu}}, " + "tx{" + "tcp{b=%llu, p=%llu}, " + "udp{b=%llu, p=%llu}," + "other{b=%llu, p=%llu}}}, " + "set1{" + "rx{" + "tcp{b=%llu, p=%llu}, " + "udp{b=%llu, p=%llu}," + "other{b=%llu, p=%llu}}, " + "tx{" + "tcp{b=%llu, p=%llu}, " + "udp{b=%llu, p=%llu}," + "other{b=%llu, p=%llu}}}}", + dc, + dc->bpc[0][IFS_RX][IFS_TCP].bytes, + dc->bpc[0][IFS_RX][IFS_TCP].packets, + dc->bpc[0][IFS_RX][IFS_UDP].bytes, + dc->bpc[0][IFS_RX][IFS_UDP].packets, + dc->bpc[0][IFS_RX][IFS_PROTO_OTHER].bytes, + dc->bpc[0][IFS_RX][IFS_PROTO_OTHER].packets, + dc->bpc[0][IFS_TX][IFS_TCP].bytes, + dc->bpc[0][IFS_TX][IFS_TCP].packets, + dc->bpc[0][IFS_TX][IFS_UDP].bytes, + dc->bpc[0][IFS_TX][IFS_UDP].packets, + dc->bpc[0][IFS_TX][IFS_PROTO_OTHER].bytes, + dc->bpc[0][IFS_TX][IFS_PROTO_OTHER].packets, + dc->bpc[1][IFS_RX][IFS_TCP].bytes, + dc->bpc[1][IFS_RX][IFS_TCP].packets, + dc->bpc[1][IFS_RX][IFS_UDP].bytes, + dc->bpc[1][IFS_RX][IFS_UDP].packets, + dc->bpc[1][IFS_RX][IFS_PROTO_OTHER].bytes, + dc->bpc[1][IFS_RX][IFS_PROTO_OTHER].packets, + dc->bpc[1][IFS_TX][IFS_TCP].bytes, + dc->bpc[1][IFS_TX][IFS_TCP].packets, + dc->bpc[1][IFS_TX][IFS_UDP].bytes, + dc->bpc[1][IFS_TX][IFS_UDP].packets, + dc->bpc[1][IFS_TX][IFS_PROTO_OTHER].bytes, + dc->bpc[1][IFS_TX][IFS_PROTO_OTHER].packets); + else + res = kasprintf(GFP_ATOMIC, "data_counters@%p{...}", dc); + _bug_on_err_or_null(res); + return res; +} + +char *pp_tag_node(struct tag_node *tn) +{ + char *tag_str; + char *res; + + if (!tn) { + res = kasprintf(GFP_ATOMIC, "tag_node@null{}"); + _bug_on_err_or_null(res); + return res; + } + tag_str = pp_tag_t(&tn->tag); + res = kasprintf(GFP_ATOMIC, + "tag_node@%p{tag=%s}", + tn, tag_str); + _bug_on_err_or_null(res); + kfree(tag_str); + return res; +} + +char *pp_tag_ref(struct tag_ref *tr) +{ + char *tn_str; + char *res; + + if (!tr) { + res = kasprintf(GFP_ATOMIC, "tag_ref@null{}"); + _bug_on_err_or_null(res); + return res; + } + tn_str = pp_tag_node(&tr->tn); + res = kasprintf(GFP_ATOMIC, + "tag_ref@%p{%s, num_sock_tags=%d}", + tr, tn_str, tr->num_sock_tags); + _bug_on_err_or_null(res); + kfree(tn_str); + return res; +} + +char *pp_tag_stat(struct tag_stat *ts) +{ + char *tn_str; + char *counters_str; + char *parent_counters_str; + char *res; + + if (!ts) { + res = kasprintf(GFP_ATOMIC, "tag_stat@null{}"); + _bug_on_err_or_null(res); + return res; + } + tn_str = pp_tag_node(&ts->tn); + counters_str = pp_data_counters(&ts->counters, true); + parent_counters_str = pp_data_counters(ts->parent_counters, false); + res = kasprintf(GFP_ATOMIC, + "tag_stat@%p{%s, counters=%s, parent_counters=%s}", + ts, tn_str, counters_str, parent_counters_str); + _bug_on_err_or_null(res); + kfree(tn_str); + kfree(counters_str); + kfree(parent_counters_str); + return res; +} + +char *pp_iface_stat(struct iface_stat *is) +{ + char *res; + if (!is) { + res = kasprintf(GFP_ATOMIC, "iface_stat@null{}"); + } else { + struct data_counters *cnts = &is->totals_via_skb; + res = kasprintf(GFP_ATOMIC, "iface_stat@%p{" + "list=list_head{...}, " + "ifname=%s, " + "total_dev={rx={bytes=%llu, " + "packets=%llu}, " + "tx={bytes=%llu, " + "packets=%llu}}, " + "total_skb={rx={bytes=%llu, " + "packets=%llu}, " + "tx={bytes=%llu, " + "packets=%llu}}, " + "last_known_valid=%d, " + "last_known={rx={bytes=%llu, " + "packets=%llu}, " + "tx={bytes=%llu, " + "packets=%llu}}, " + "active=%d, " + "net_dev=%p, " + "proc_ptr=%p, " + "tag_stat_tree=rb_root{...}}", + is, + is->ifname, + is->totals_via_dev[IFS_RX].bytes, + is->totals_via_dev[IFS_RX].packets, + is->totals_via_dev[IFS_TX].bytes, + is->totals_via_dev[IFS_TX].packets, + dc_sum_bytes(cnts, 0, IFS_RX), + dc_sum_packets(cnts, 0, IFS_RX), + dc_sum_bytes(cnts, 0, IFS_TX), + dc_sum_packets(cnts, 0, IFS_TX), + is->last_known_valid, + is->last_known[IFS_RX].bytes, + is->last_known[IFS_RX].packets, + is->last_known[IFS_TX].bytes, + is->last_known[IFS_TX].packets, + is->active, + is->net_dev, + is->proc_ptr); + } + _bug_on_err_or_null(res); + return res; +} + +char *pp_sock_tag(struct sock_tag *st) +{ + char *tag_str; + char *res; + + if (!st) { + res = kasprintf(GFP_ATOMIC, "sock_tag@null{}"); + _bug_on_err_or_null(res); + return res; + } + tag_str = pp_tag_t(&st->tag); + res = kasprintf(GFP_ATOMIC, "sock_tag@%p{" + "sock_node=rb_node{...}, " + "sk=%p socket=%p (f_count=%lu), list=list_head{...}, " + "pid=%u, tag=%s}", + st, st->sk, st->socket, atomic_long_read( + &st->socket->file->f_count), + st->pid, tag_str); + _bug_on_err_or_null(res); + kfree(tag_str); + return res; +} + +char *pp_uid_tag_data(struct uid_tag_data *utd) +{ + char *res; + + if (!utd) + res = kasprintf(GFP_ATOMIC, "uid_tag_data@null{}"); + else + res = kasprintf(GFP_ATOMIC, "uid_tag_data@%p{" + "uid=%u, num_active_acct_tags=%d, " + "num_pqd=%d, " + "tag_node_tree=rb_root{...}, " + "proc_qtu_data_tree=rb_root{...}}", + utd, utd->uid, + utd->num_active_tags, utd->num_pqd); + _bug_on_err_or_null(res); + return res; +} + +char *pp_proc_qtu_data(struct proc_qtu_data *pqd) +{ + char *parent_tag_data_str; + char *res; + + if (!pqd) { + res = kasprintf(GFP_ATOMIC, "proc_qtu_data@null{}"); + _bug_on_err_or_null(res); + return res; + } + parent_tag_data_str = pp_uid_tag_data(pqd->parent_tag_data); + res = kasprintf(GFP_ATOMIC, "proc_qtu_data@%p{" + "node=rb_node{...}, pid=%u, " + "parent_tag_data=%s, " + "sock_tag_list=list_head{...}}", + pqd, pqd->pid, parent_tag_data_str + ); + _bug_on_err_or_null(res); + kfree(parent_tag_data_str); + return res; +} + +/*------------------------------------------*/ +void prdebug_sock_tag_tree(int indent_level, + struct rb_root *sock_tag_tree) +{ + struct rb_node *node; + struct sock_tag *sock_tag_entry; + char *str; + + if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK)) + return; + + if (RB_EMPTY_ROOT(sock_tag_tree)) { + str = "sock_tag_tree=rb_root{}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + return; + } + + str = "sock_tag_tree=rb_root{"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + indent_level++; + for (node = rb_first(sock_tag_tree); + node; + node = rb_next(node)) { + sock_tag_entry = rb_entry(node, struct sock_tag, sock_node); + str = pp_sock_tag(sock_tag_entry); + pr_debug("%*d: %s,\n", indent_level*2, indent_level, str); + kfree(str); + } + indent_level--; + str = "}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); +} + +void prdebug_sock_tag_list(int indent_level, + struct list_head *sock_tag_list) +{ + struct sock_tag *sock_tag_entry; + char *str; + + if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK)) + return; + + if (list_empty(sock_tag_list)) { + str = "sock_tag_list=list_head{}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + return; + } + + str = "sock_tag_list=list_head{"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + indent_level++; + list_for_each_entry(sock_tag_entry, sock_tag_list, list) { + str = pp_sock_tag(sock_tag_entry); + pr_debug("%*d: %s,\n", indent_level*2, indent_level, str); + kfree(str); + } + indent_level--; + str = "}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); +} + +void prdebug_proc_qtu_data_tree(int indent_level, + struct rb_root *proc_qtu_data_tree) +{ + char *str; + struct rb_node *node; + struct proc_qtu_data *proc_qtu_data_entry; + + if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK)) + return; + + if (RB_EMPTY_ROOT(proc_qtu_data_tree)) { + str = "proc_qtu_data_tree=rb_root{}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + return; + } + + str = "proc_qtu_data_tree=rb_root{"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + indent_level++; + for (node = rb_first(proc_qtu_data_tree); + node; + node = rb_next(node)) { + proc_qtu_data_entry = rb_entry(node, + struct proc_qtu_data, + node); + str = pp_proc_qtu_data(proc_qtu_data_entry); + pr_debug("%*d: %s,\n", indent_level*2, indent_level, + str); + kfree(str); + indent_level++; + prdebug_sock_tag_list(indent_level, + &proc_qtu_data_entry->sock_tag_list); + indent_level--; + + } + indent_level--; + str = "}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); +} + +void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree) +{ + char *str; + struct rb_node *node; + struct tag_ref *tag_ref_entry; + + if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK)) + return; + + if (RB_EMPTY_ROOT(tag_ref_tree)) { + str = "tag_ref_tree{}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + return; + } + + str = "tag_ref_tree{"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + indent_level++; + for (node = rb_first(tag_ref_tree); + node; + node = rb_next(node)) { + tag_ref_entry = rb_entry(node, + struct tag_ref, + tn.node); + str = pp_tag_ref(tag_ref_entry); + pr_debug("%*d: %s,\n", indent_level*2, indent_level, + str); + kfree(str); + } + indent_level--; + str = "}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); +} + +void prdebug_uid_tag_data_tree(int indent_level, + struct rb_root *uid_tag_data_tree) +{ + char *str; + struct rb_node *node; + struct uid_tag_data *uid_tag_data_entry; + + if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK)) + return; + + if (RB_EMPTY_ROOT(uid_tag_data_tree)) { + str = "uid_tag_data_tree=rb_root{}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + return; + } + + str = "uid_tag_data_tree=rb_root{"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + indent_level++; + for (node = rb_first(uid_tag_data_tree); + node; + node = rb_next(node)) { + uid_tag_data_entry = rb_entry(node, struct uid_tag_data, + node); + str = pp_uid_tag_data(uid_tag_data_entry); + pr_debug("%*d: %s,\n", indent_level*2, indent_level, str); + kfree(str); + if (!RB_EMPTY_ROOT(&uid_tag_data_entry->tag_ref_tree)) { + indent_level++; + prdebug_tag_ref_tree(indent_level, + &uid_tag_data_entry->tag_ref_tree); + indent_level--; + } + } + indent_level--; + str = "}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); +} + +void prdebug_tag_stat_tree(int indent_level, + struct rb_root *tag_stat_tree) +{ + char *str; + struct rb_node *node; + struct tag_stat *ts_entry; + + if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK)) + return; + + if (RB_EMPTY_ROOT(tag_stat_tree)) { + str = "tag_stat_tree{}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + return; + } + + str = "tag_stat_tree{"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + indent_level++; + for (node = rb_first(tag_stat_tree); + node; + node = rb_next(node)) { + ts_entry = rb_entry(node, struct tag_stat, tn.node); + str = pp_tag_stat(ts_entry); + pr_debug("%*d: %s\n", indent_level*2, indent_level, + str); + kfree(str); + } + indent_level--; + str = "}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); +} + +void prdebug_iface_stat_list(int indent_level, + struct list_head *iface_stat_list) +{ + char *str; + struct iface_stat *iface_entry; + + if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK)) + return; + + if (list_empty(iface_stat_list)) { + str = "iface_stat_list=list_head{}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + return; + } + + str = "iface_stat_list=list_head{"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + indent_level++; + list_for_each_entry(iface_entry, iface_stat_list, list) { + str = pp_iface_stat(iface_entry); + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); + kfree(str); + + spin_lock_bh(&iface_entry->tag_stat_list_lock); + if (!RB_EMPTY_ROOT(&iface_entry->tag_stat_tree)) { + indent_level++; + prdebug_tag_stat_tree(indent_level, + &iface_entry->tag_stat_tree); + indent_level--; + } + spin_unlock_bh(&iface_entry->tag_stat_list_lock); + } + indent_level--; + str = "}"; + pr_debug("%*d: %s\n", indent_level*2, indent_level, str); +} + +#endif /* ifdef DDEBUG */ +/*------------------------------------------*/ +static const char * const netdev_event_strings[] = { + "netdev_unknown", + "NETDEV_UP", + "NETDEV_DOWN", + "NETDEV_REBOOT", + "NETDEV_CHANGE", + "NETDEV_REGISTER", + "NETDEV_UNREGISTER", + "NETDEV_CHANGEMTU", + "NETDEV_CHANGEADDR", + "NETDEV_GOING_DOWN", + "NETDEV_CHANGENAME", + "NETDEV_FEAT_CHANGE", + "NETDEV_BONDING_FAILOVER", + "NETDEV_PRE_UP", + "NETDEV_PRE_TYPE_CHANGE", + "NETDEV_POST_TYPE_CHANGE", + "NETDEV_POST_INIT", + "NETDEV_UNREGISTER_BATCH", + "NETDEV_RELEASE", + "NETDEV_NOTIFY_PEERS", + "NETDEV_JOIN", +}; + +const char *netdev_evt_str(int netdev_event) +{ + if (netdev_event < 0 + || netdev_event >= ARRAY_SIZE(netdev_event_strings)) + return "bad event num"; + return netdev_event_strings[netdev_event]; +} diff --git a/net/netfilter/xt_qtaguid_print.h b/net/netfilter/xt_qtaguid_print.h new file mode 100644 index 00000000000..b63871a0be5 --- /dev/null +++ b/net/netfilter/xt_qtaguid_print.h @@ -0,0 +1,120 @@ +/* + * Pretty printing Support for iptables xt_qtaguid module. + * + * (C) 2011 Google, Inc + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __XT_QTAGUID_PRINT_H__ +#define __XT_QTAGUID_PRINT_H__ + +#include "xt_qtaguid_internal.h" + +#ifdef DDEBUG + +char *pp_tag_t(tag_t *tag); +char *pp_data_counters(struct data_counters *dc, bool showValues); +char *pp_tag_node(struct tag_node *tn); +char *pp_tag_ref(struct tag_ref *tr); +char *pp_tag_stat(struct tag_stat *ts); +char *pp_iface_stat(struct iface_stat *is); +char *pp_sock_tag(struct sock_tag *st); +char *pp_uid_tag_data(struct uid_tag_data *qtd); +char *pp_proc_qtu_data(struct proc_qtu_data *pqd); + +/*------------------------------------------*/ +void prdebug_sock_tag_list(int indent_level, + struct list_head *sock_tag_list); +void prdebug_sock_tag_tree(int indent_level, + struct rb_root *sock_tag_tree); +void prdebug_proc_qtu_data_tree(int indent_level, + struct rb_root *proc_qtu_data_tree); +void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree); +void prdebug_uid_tag_data_tree(int indent_level, + struct rb_root *uid_tag_data_tree); +void prdebug_tag_stat_tree(int indent_level, + struct rb_root *tag_stat_tree); +void prdebug_iface_stat_list(int indent_level, + struct list_head *iface_stat_list); + +#else + +/*------------------------------------------*/ +static inline char *pp_tag_t(tag_t *tag) +{ + return NULL; +} +static inline char *pp_data_counters(struct data_counters *dc, bool showValues) +{ + return NULL; +} +static inline char *pp_tag_node(struct tag_node *tn) +{ + return NULL; +} +static inline char *pp_tag_ref(struct tag_ref *tr) +{ + return NULL; +} +static inline char *pp_tag_stat(struct tag_stat *ts) +{ + return NULL; +} +static inline char *pp_iface_stat(struct iface_stat *is) +{ + return NULL; +} +static inline char *pp_sock_tag(struct sock_tag *st) +{ + return NULL; +} +static inline char *pp_uid_tag_data(struct uid_tag_data *qtd) +{ + return NULL; +} +static inline char *pp_proc_qtu_data(struct proc_qtu_data *pqd) +{ + return NULL; +} + +/*------------------------------------------*/ +static inline +void prdebug_sock_tag_list(int indent_level, + struct list_head *sock_tag_list) +{ +} +static inline +void prdebug_sock_tag_tree(int indent_level, + struct rb_root *sock_tag_tree) +{ +} +static inline +void prdebug_proc_qtu_data_tree(int indent_level, + struct rb_root *proc_qtu_data_tree) +{ +} +static inline +void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree) +{ +} +static inline +void prdebug_uid_tag_data_tree(int indent_level, + struct rb_root *uid_tag_data_tree) +{ +} +static inline +void prdebug_tag_stat_tree(int indent_level, + struct rb_root *tag_stat_tree) +{ +} +static inline +void prdebug_iface_stat_list(int indent_level, + struct list_head *iface_stat_list) +{ +} +#endif +/*------------------------------------------*/ +const char *netdev_evt_str(int netdev_event); +#endif /* ifndef __XT_QTAGUID_PRINT_H__ */ diff --git a/net/netfilter/xt_quota2.c b/net/netfilter/xt_quota2.c new file mode 100644 index 00000000000..4328562572f --- /dev/null +++ b/net/netfilter/xt_quota2.c @@ -0,0 +1,385 @@ +/* + * xt_quota2 - enhanced xt_quota that can count upwards and in packets + * as a minimal accounting match. + * by Jan Engelhardt <jengelh@medozas.de>, 2008 + * + * Originally based on xt_quota.c: + * netfilter module to enforce network quotas + * Sam Johnston <samj@samj.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License; either + * version 2 of the License, as published by the Free Software Foundation. + */ +#include <linux/list.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> +#include <asm/atomic.h> +#include <net/netlink.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_quota2.h> +#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG +#include <linux/netfilter_ipv4/ipt_ULOG.h> +#endif + +/** + * @lock: lock to protect quota writers from each other + */ +struct xt_quota_counter { + u_int64_t quota; + spinlock_t lock; + struct list_head list; + atomic_t ref; + char name[sizeof(((struct xt_quota_mtinfo2 *)NULL)->name)]; + struct proc_dir_entry *procfs_entry; +}; + +#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG +/* Harald's favorite number +1 :D From ipt_ULOG.C */ +static int qlog_nl_event = 112; +module_param_named(event_num, qlog_nl_event, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(event_num, + "Event number for NETLINK_NFLOG message. 0 disables log." + "111 is what ipt_ULOG uses."); +static struct sock *nflognl; +#endif + +static LIST_HEAD(counter_list); +static DEFINE_SPINLOCK(counter_list_lock); + +static struct proc_dir_entry *proc_xt_quota; +static unsigned int quota_list_perms = S_IRUGO | S_IWUSR; +static unsigned int quota_list_uid = 0; +static unsigned int quota_list_gid = 0; +module_param_named(perms, quota_list_perms, uint, S_IRUGO | S_IWUSR); +module_param_named(uid, quota_list_uid, uint, S_IRUGO | S_IWUSR); +module_param_named(gid, quota_list_gid, uint, S_IRUGO | S_IWUSR); + + +#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG +static void quota2_log(unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const char *prefix) +{ + ulog_packet_msg_t *pm; + struct sk_buff *log_skb; + size_t size; + struct nlmsghdr *nlh; + + if (!qlog_nl_event) + return; + + size = NLMSG_SPACE(sizeof(*pm)); + size = max(size, (size_t)NLMSG_GOODSIZE); + log_skb = alloc_skb(size, GFP_ATOMIC); + if (!log_skb) { + pr_err("xt_quota2: cannot alloc skb for logging\n"); + return; + } + + nlh = nlmsg_put(log_skb, /*pid*/0, /*seq*/0, qlog_nl_event, + sizeof(*pm), 0); + if (!nlh) { + pr_err("xt_quota2: nlmsg_put failed\n"); + kfree_skb(log_skb); + return; + } + pm = nlmsg_data(nlh); + if (skb->tstamp.tv64 == 0) + __net_timestamp((struct sk_buff *)skb); + pm->data_len = 0; + pm->hook = hooknum; + if (prefix != NULL) + strlcpy(pm->prefix, prefix, sizeof(pm->prefix)); + else + *(pm->prefix) = '\0'; + if (in) + strlcpy(pm->indev_name, in->name, sizeof(pm->indev_name)); + else + pm->indev_name[0] = '\0'; + + if (out) + strlcpy(pm->outdev_name, out->name, sizeof(pm->outdev_name)); + else + pm->outdev_name[0] = '\0'; + + NETLINK_CB(log_skb).dst_group = 1; + pr_debug("throwing 1 packets to netlink group 1\n"); + netlink_broadcast(nflognl, log_skb, 0, 1, GFP_ATOMIC); +} +#else +static void quota2_log(unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const char *prefix) +{ +} +#endif /* if+else CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG */ + +static ssize_t quota_proc_read(struct file *file, char __user *buf, + size_t size, loff_t *ppos) +{ + struct xt_quota_counter *e = PDE_DATA(file_inode(file)); + char tmp[24]; + size_t tmp_size; + + spin_lock_bh(&e->lock); + tmp_size = scnprintf(tmp, sizeof(tmp), "%llu\n", e->quota); + spin_unlock_bh(&e->lock); + return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size); +} + +static ssize_t quota_proc_write(struct file *file, const char __user *input, + size_t size, loff_t *ppos) +{ + struct xt_quota_counter *e = PDE_DATA(file_inode(file)); + char buf[sizeof("18446744073709551616")]; + + if (size > sizeof(buf)) + size = sizeof(buf); + if (copy_from_user(buf, input, size) != 0) + return -EFAULT; + buf[sizeof(buf)-1] = '\0'; + + spin_lock_bh(&e->lock); + e->quota = simple_strtoull(buf, NULL, 0); + spin_unlock_bh(&e->lock); + return size; +} + +static const struct file_operations q2_counter_fops = { + .read = quota_proc_read, + .write = quota_proc_write, + .llseek = default_llseek, +}; + +static struct xt_quota_counter * +q2_new_counter(const struct xt_quota_mtinfo2 *q, bool anon) +{ + struct xt_quota_counter *e; + unsigned int size; + + /* Do not need all the procfs things for anonymous counters. */ + size = anon ? offsetof(typeof(*e), list) : sizeof(*e); + e = kmalloc(size, GFP_KERNEL); + if (e == NULL) + return NULL; + + e->quota = q->quota; + spin_lock_init(&e->lock); + if (!anon) { + INIT_LIST_HEAD(&e->list); + atomic_set(&e->ref, 1); + strlcpy(e->name, q->name, sizeof(e->name)); + } + return e; +} + +/** + * q2_get_counter - get ref to counter or create new + * @name: name of counter + */ +static struct xt_quota_counter * +q2_get_counter(const struct xt_quota_mtinfo2 *q) +{ + struct proc_dir_entry *p; + struct xt_quota_counter *e = NULL; + struct xt_quota_counter *new_e; + + if (*q->name == '\0') + return q2_new_counter(q, true); + + /* No need to hold a lock while getting a new counter */ + new_e = q2_new_counter(q, false); + if (new_e == NULL) + goto out; + + spin_lock_bh(&counter_list_lock); + list_for_each_entry(e, &counter_list, list) + if (strcmp(e->name, q->name) == 0) { + atomic_inc(&e->ref); + spin_unlock_bh(&counter_list_lock); + kfree(new_e); + pr_debug("xt_quota2: old counter name=%s", e->name); + return e; + } + e = new_e; + pr_debug("xt_quota2: new_counter name=%s", e->name); + list_add_tail(&e->list, &counter_list); + /* The entry having a refcount of 1 is not directly destructible. + * This func has not yet returned the new entry, thus iptables + * has not references for destroying this entry. + * For another rule to try to destroy it, it would 1st need for this + * func* to be re-invoked, acquire a new ref for the same named quota. + * Nobody will access the e->procfs_entry either. + * So release the lock. */ + spin_unlock_bh(&counter_list_lock); + + /* create_proc_entry() is not spin_lock happy */ + p = e->procfs_entry = proc_create_data(e->name, quota_list_perms, + proc_xt_quota, &q2_counter_fops, e); + + if (IS_ERR_OR_NULL(p)) { + spin_lock_bh(&counter_list_lock); + list_del(&e->list); + spin_unlock_bh(&counter_list_lock); + goto out; + } + proc_set_user(p, quota_list_uid, quota_list_gid); + return e; + + out: + kfree(e); + return NULL; +} + +static int quota_mt2_check(const struct xt_mtchk_param *par) +{ + struct xt_quota_mtinfo2 *q = par->matchinfo; + + pr_debug("xt_quota2: check() flags=0x%04x", q->flags); + + if (q->flags & ~XT_QUOTA_MASK) + return -EINVAL; + + q->name[sizeof(q->name)-1] = '\0'; + if (*q->name == '.' || strchr(q->name, '/') != NULL) { + printk(KERN_ERR "xt_quota.3: illegal name\n"); + return -EINVAL; + } + + q->master = q2_get_counter(q); + if (q->master == NULL) { + printk(KERN_ERR "xt_quota.3: memory alloc failure\n"); + return -ENOMEM; + } + + return 0; +} + +static void quota_mt2_destroy(const struct xt_mtdtor_param *par) +{ + struct xt_quota_mtinfo2 *q = par->matchinfo; + struct xt_quota_counter *e = q->master; + + if (*q->name == '\0') { + kfree(e); + return; + } + + spin_lock_bh(&counter_list_lock); + if (!atomic_dec_and_test(&e->ref)) { + spin_unlock_bh(&counter_list_lock); + return; + } + + list_del(&e->list); + remove_proc_entry(e->name, proc_xt_quota); + spin_unlock_bh(&counter_list_lock); + kfree(e); +} + +static bool +quota_mt2(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct xt_quota_mtinfo2 *q = (void *)par->matchinfo; + struct xt_quota_counter *e = q->master; + bool ret = q->flags & XT_QUOTA_INVERT; + + spin_lock_bh(&e->lock); + if (q->flags & XT_QUOTA_GROW) { + /* + * While no_change is pointless in "grow" mode, we will + * implement it here simply to have a consistent behavior. + */ + if (!(q->flags & XT_QUOTA_NO_CHANGE)) { + e->quota += (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len; + } + ret = true; + } else { + if (e->quota >= skb->len) { + if (!(q->flags & XT_QUOTA_NO_CHANGE)) + e->quota -= (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len; + ret = !ret; + } else { + /* We are transitioning, log that fact. */ + if (e->quota) { + quota2_log(par->hooknum, + skb, + par->in, + par->out, + q->name); + } + /* we do not allow even small packets from now on */ + e->quota = 0; + } + } + spin_unlock_bh(&e->lock); + return ret; +} + +static struct xt_match quota_mt2_reg[] __read_mostly = { + { + .name = "quota2", + .revision = 3, + .family = NFPROTO_IPV4, + .checkentry = quota_mt2_check, + .match = quota_mt2, + .destroy = quota_mt2_destroy, + .matchsize = sizeof(struct xt_quota_mtinfo2), + .me = THIS_MODULE, + }, + { + .name = "quota2", + .revision = 3, + .family = NFPROTO_IPV6, + .checkentry = quota_mt2_check, + .match = quota_mt2, + .destroy = quota_mt2_destroy, + .matchsize = sizeof(struct xt_quota_mtinfo2), + .me = THIS_MODULE, + }, +}; + +static int __init quota_mt2_init(void) +{ + int ret; + pr_debug("xt_quota2: init()"); + +#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG + nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, NULL); + if (!nflognl) + return -ENOMEM; +#endif + + proc_xt_quota = proc_mkdir("xt_quota", init_net.proc_net); + if (proc_xt_quota == NULL) + return -EACCES; + + ret = xt_register_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg)); + if (ret < 0) + remove_proc_entry("xt_quota", init_net.proc_net); + pr_debug("xt_quota2: init() %d", ret); + return ret; +} + +static void __exit quota_mt2_exit(void) +{ + xt_unregister_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg)); + remove_proc_entry("xt_quota", init_net.proc_net); +} + +module_init(quota_mt2_init); +module_exit(quota_mt2_exit); +MODULE_DESCRIPTION("Xtables: countdown quota match; up counter"); +MODULE_AUTHOR("Sam Johnston <samj@samj.net>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_quota2"); +MODULE_ALIAS("ip6t_quota2"); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 63b2bdb59e9..030f33cd9ee 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -35,7 +35,7 @@ #include <net/netfilter/nf_conntrack.h> #endif -static void +void xt_socket_put_sk(struct sock *sk) { if (sk->sk_state == TCP_TIME_WAIT) @@ -43,6 +43,7 @@ xt_socket_put_sk(struct sock *sk) else sock_put(sk); } +EXPORT_SYMBOL(xt_socket_put_sk); static int extract_icmp4_fields(const struct sk_buff *skb, @@ -101,9 +102,8 @@ extract_icmp4_fields(const struct sk_buff *skb, return 0; } -static bool -socket_match(const struct sk_buff *skb, struct xt_action_param *par, - const struct xt_socket_mtinfo1 *info) +struct sock* +xt_socket_get4_sk(const struct sk_buff *skb, struct xt_action_param *par) { const struct iphdr *iph = ip_hdr(skb); struct udphdr _hdr, *hp = NULL; @@ -120,7 +120,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (hp == NULL) - return false; + return NULL; protocol = iph->protocol; saddr = iph->saddr; @@ -131,9 +131,9 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, } else if (iph->protocol == IPPROTO_ICMP) { if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr, &sport, &dport)) - return false; + return NULL; } else { - return false; + return NULL; } #ifdef XT_SOCKET_HAVE_CONNTRACK @@ -157,6 +157,23 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); + + pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n", + protocol, &saddr, ntohs(sport), + &daddr, ntohs(dport), + &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); + + return sk; +} +EXPORT_SYMBOL(xt_socket_get4_sk); + +static bool +socket_match(const struct sk_buff *skb, struct xt_action_param *par, + const struct xt_socket_mtinfo1 *info) +{ + struct sock *sk; + + sk = xt_socket_get4_sk(skb, par); if (sk != NULL) { bool wildcard; bool transparent = true; @@ -179,11 +196,6 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, sk = NULL; } - pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n", - protocol, &saddr, ntohs(sport), - &daddr, ntohs(dport), - &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); - return (sk != NULL); } @@ -255,8 +267,8 @@ extract_icmp6_fields(const struct sk_buff *skb, return 0; } -static bool -socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) +struct sock* +xt_socket_get6_sk(const struct sk_buff *skb, struct xt_action_param *par) { struct ipv6hdr *iph = ipv6_hdr(skb); struct udphdr _hdr, *hp = NULL; @@ -264,7 +276,6 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) struct in6_addr *daddr = NULL, *saddr = NULL; __be16 uninitialized_var(dport), uninitialized_var(sport); int thoff = 0, uninitialized_var(tproto); - const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); if (tproto < 0) { @@ -276,7 +287,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); if (hp == NULL) - return false; + return NULL; saddr = &iph->saddr; sport = hp->source; @@ -286,13 +297,30 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) } else if (tproto == IPPROTO_ICMPV6) { if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, &sport, &dport)) - return false; + return NULL; } else { - return false; + return NULL; } sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); + pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu " + "(orig %pI6:%hu) sock %p\n", + tproto, saddr, ntohs(sport), + daddr, ntohs(dport), + &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); + return sk; +} +EXPORT_SYMBOL(xt_socket_get6_sk); + +static bool +socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct sock *sk; + const struct xt_socket_mtinfo1 *info; + + info = (struct xt_socket_mtinfo1 *) par->matchinfo; + sk = xt_socket_get6_sk(skb, par); if (sk != NULL) { bool wildcard; bool transparent = true; @@ -315,12 +343,6 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) sk = NULL; } - pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu " - "(orig %pI6:%hu) sock %p\n", - tproto, saddr, ntohs(sport), - daddr, ntohs(dport), - &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); - return (sk != NULL); } #endif |