diff options
Diffstat (limited to 'kernel')
46 files changed, 1011 insertions, 585 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index e794544f5e63..a871bf80fde1 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -54,6 +54,10 @@ #include <linux/kthread.h> #include <linux/kernel.h> #include <linux/syscalls.h> +#include <linux/spinlock.h> +#include <linux/rcupdate.h> +#include <linux/mutex.h> +#include <linux/gfp.h> #include <linux/audit.h> @@ -90,13 +94,34 @@ static u32 audit_default; /* If auditing cannot proceed, audit_failure selects what happens. */ static u32 audit_failure = AUDIT_FAIL_PRINTK; -/* - * If audit records are to be written to the netlink socket, audit_pid - * contains the pid of the auditd process and audit_nlk_portid contains - * the portid to use to send netlink messages to that process. +/* private audit network namespace index */ +static unsigned int audit_net_id; + +/** + * struct audit_net - audit private network namespace data + * @sk: communication socket */ -int audit_pid; -static __u32 audit_nlk_portid; +struct audit_net { + struct sock *sk; +}; + +/** + * struct auditd_connection - kernel/auditd connection state + * @pid: auditd PID + * @portid: netlink portid + * @net: the associated network namespace + * @lock: spinlock to protect write access + * + * Description: + * This struct is RCU protected; you must either hold the RCU lock for reading + * or the included spinlock for writing. + */ +static struct auditd_connection { + int pid; + u32 portid; + struct net *net; + spinlock_t lock; +} auditd_conn; /* If audit_rate_limit is non-zero, limit the rate of sending audit records * to that number per second. This prevents DoS attacks, but results in @@ -123,10 +148,6 @@ u32 audit_sig_sid = 0; */ static atomic_t audit_lost = ATOMIC_INIT(0); -/* The netlink socket. */ -static struct sock *audit_sock; -static unsigned int audit_net_id; - /* Hash for inode-based rules */ struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; @@ -192,6 +213,43 @@ struct audit_reply { struct sk_buff *skb; }; +/** + * auditd_test_task - Check to see if a given task is an audit daemon + * @task: the task to check + * + * Description: + * Return 1 if the task is a registered audit daemon, 0 otherwise. + */ +int auditd_test_task(const struct task_struct *task) +{ + int rc; + + rcu_read_lock(); + rc = (auditd_conn.pid && task->tgid == auditd_conn.pid ? 1 : 0); + rcu_read_unlock(); + + return rc; +} + +/** + * audit_get_sk - Return the audit socket for the given network namespace + * @net: the destination network namespace + * + * Description: + * Returns the sock pointer if valid, NULL otherwise. The caller must ensure + * that a reference is held for the network namespace while the sock is in use. + */ +static struct sock *audit_get_sk(const struct net *net) +{ + struct audit_net *aunet; + + if (!net) + return NULL; + + aunet = net_generic(net, audit_net_id); + return aunet->sk; +} + static void audit_set_portid(struct audit_buffer *ab, __u32 portid) { if (ab) { @@ -210,9 +268,7 @@ void audit_panic(const char *message) pr_err("%s\n", message); break; case AUDIT_FAIL_PANIC: - /* test audit_pid since printk is always losey, why bother? */ - if (audit_pid) - panic("audit: %s\n", message); + panic("audit: %s\n", message); break; } } @@ -370,21 +426,60 @@ static int audit_set_failure(u32 state) return audit_do_config_change("audit_failure", &audit_failure, state); } -/* - * For one reason or another this nlh isn't getting delivered to the userspace - * audit daemon, just send it to printk. +/** + * auditd_set - Set/Reset the auditd connection state + * @pid: auditd PID + * @portid: auditd netlink portid + * @net: auditd network namespace pointer + * + * Description: + * This function will obtain and drop network namespace references as + * necessary. + */ +static void auditd_set(int pid, u32 portid, struct net *net) +{ + unsigned long flags; + + spin_lock_irqsave(&auditd_conn.lock, flags); + auditd_conn.pid = pid; + auditd_conn.portid = portid; + if (auditd_conn.net) + put_net(auditd_conn.net); + if (net) + auditd_conn.net = get_net(net); + else + auditd_conn.net = NULL; + spin_unlock_irqrestore(&auditd_conn.lock, flags); +} + +/** + * kauditd_print_skb - Print the audit record to the ring buffer + * @skb: audit record + * + * Whatever the reason, this packet may not make it to the auditd connection + * so write it via printk so the information isn't completely lost. */ static void kauditd_printk_skb(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); char *data = nlmsg_data(nlh); - if (nlh->nlmsg_type != AUDIT_EOE) { - if (printk_ratelimit()) - pr_notice("type=%d %s\n", nlh->nlmsg_type, data); - else - audit_log_lost("printk limit exceeded"); - } + if (nlh->nlmsg_type != AUDIT_EOE && printk_ratelimit()) + pr_notice("type=%d %s\n", nlh->nlmsg_type, data); +} + +/** + * kauditd_rehold_skb - Handle a audit record send failure in the hold queue + * @skb: audit record + * + * Description: + * This should only be used by the kauditd_thread when it fails to flush the + * hold queue. + */ +static void kauditd_rehold_skb(struct sk_buff *skb) +{ + /* put the record back in the queue at the same place */ + skb_queue_head(&audit_hold_queue, skb); } /** @@ -444,48 +539,143 @@ static void kauditd_retry_skb(struct sk_buff *skb) * auditd_reset - Disconnect the auditd connection * * Description: - * Break the auditd/kauditd connection and move all the records in the retry - * queue into the hold queue in case auditd reconnects. The audit_cmd_mutex - * must be held when calling this function. + * Break the auditd/kauditd connection and move all the queued records into the + * hold queue in case auditd reconnects. */ static void auditd_reset(void) { struct sk_buff *skb; - /* break the connection */ - if (audit_sock) { - sock_put(audit_sock); - audit_sock = NULL; - } - audit_pid = 0; - audit_nlk_portid = 0; + /* if it isn't already broken, break the connection */ + rcu_read_lock(); + if (auditd_conn.pid) + auditd_set(0, 0, NULL); + rcu_read_unlock(); - /* flush all of the retry queue to the hold queue */ + /* flush all of the main and retry queues to the hold queue */ while ((skb = skb_dequeue(&audit_retry_queue))) kauditd_hold_skb(skb); + while ((skb = skb_dequeue(&audit_queue))) + kauditd_hold_skb(skb); } /** - * kauditd_send_unicast_skb - Send a record via unicast to auditd + * auditd_send_unicast_skb - Send a record via unicast to auditd * @skb: audit record + * + * Description: + * Send a skb to the audit daemon, returns positive/zero values on success and + * negative values on failure; in all cases the skb will be consumed by this + * function. If the send results in -ECONNREFUSED the connection with auditd + * will be reset. This function may sleep so callers should not hold any locks + * where this would cause a problem. */ -static int kauditd_send_unicast_skb(struct sk_buff *skb) +static int auditd_send_unicast_skb(struct sk_buff *skb) { int rc; + u32 portid; + struct net *net; + struct sock *sk; - /* if we know nothing is connected, don't even try the netlink call */ - if (!audit_pid) - return -ECONNREFUSED; + /* NOTE: we can't call netlink_unicast while in the RCU section so + * take a reference to the network namespace and grab local + * copies of the namespace, the sock, and the portid; the + * namespace and sock aren't going to go away while we hold a + * reference and if the portid does become invalid after the RCU + * section netlink_unicast() should safely return an error */ - /* get an extra skb reference in case we fail to send */ - skb_get(skb); - rc = netlink_unicast(audit_sock, skb, audit_nlk_portid, 0); - if (rc >= 0) { - consume_skb(skb); - rc = 0; + rcu_read_lock(); + if (!auditd_conn.pid) { + rcu_read_unlock(); + rc = -ECONNREFUSED; + goto err; } + net = auditd_conn.net; + get_net(net); + sk = audit_get_sk(net); + portid = auditd_conn.portid; + rcu_read_unlock(); + + rc = netlink_unicast(sk, skb, portid, 0); + put_net(net); + if (rc < 0) + goto err; return rc; + +err: + if (rc == -ECONNREFUSED) + auditd_reset(); + return rc; +} + +/** + * kauditd_send_queue - Helper for kauditd_thread to flush skb queues + * @sk: the sending sock + * @portid: the netlink destination + * @queue: the skb queue to process + * @retry_limit: limit on number of netlink unicast failures + * @skb_hook: per-skb hook for additional processing + * @err_hook: hook called if the skb fails the netlink unicast send + * + * Description: + * Run through the given queue and attempt to send the audit records to auditd, + * returns zero on success, negative values on failure. It is up to the caller + * to ensure that the @sk is valid for the duration of this function. + * + */ +static int kauditd_send_queue(struct sock *sk, u32 portid, + struct sk_buff_head *queue, + unsigned int retry_limit, + void (*skb_hook)(struct sk_buff *skb), + void (*err_hook)(struct sk_buff *skb)) +{ + int rc = 0; + struct sk_buff *skb; + static unsigned int failed = 0; + + /* NOTE: kauditd_thread takes care of all our locking, we just use + * the netlink info passed to us (e.g. sk and portid) */ + + while ((skb = skb_dequeue(queue))) { + /* call the skb_hook for each skb we touch */ + if (skb_hook) + (*skb_hook)(skb); + + /* can we send to anyone via unicast? */ + if (!sk) { + if (err_hook) + (*err_hook)(skb); + continue; + } + + /* grab an extra skb reference in case of error */ + skb_get(skb); + rc = netlink_unicast(sk, skb, portid, 0); + if (rc < 0) { + /* fatal failure for our queue flush attempt? */ + if (++failed >= retry_limit || + rc == -ECONNREFUSED || rc == -EPERM) { + /* yes - error processing for the queue */ + sk = NULL; + if (err_hook) + (*err_hook)(skb); + if (!skb_hook) + goto out; + /* keep processing with the skb_hook */ + continue; + } else + /* no - requeue to preserve ordering */ + skb_queue_head(queue, skb); + } else { + /* it worked - drop the extra reference and continue */ + consume_skb(skb); + failed = 0; + } + } + +out: + return (rc >= 0 ? 0 : rc); } /* @@ -493,16 +683,19 @@ static int kauditd_send_unicast_skb(struct sk_buff *skb) * @skb: audit record * * Description: - * This function doesn't consume an skb as might be expected since it has to - * copy it anyways. + * Write a multicast message to anyone listening in the initial network + * namespace. This function doesn't consume an skb as might be expected since + * it has to copy it anyways. */ static void kauditd_send_multicast_skb(struct sk_buff *skb) { struct sk_buff *copy; - struct audit_net *aunet = net_generic(&init_net, audit_net_id); - struct sock *sock = aunet->nlsk; + struct sock *sock = audit_get_sk(&init_net); struct nlmsghdr *nlh; + /* NOTE: we are not taking an additional reference for init_net since + * we don't have to worry about it going away */ + if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG)) return; @@ -526,149 +719,79 @@ static void kauditd_send_multicast_skb(struct sk_buff *skb) } /** - * kauditd_wake_condition - Return true when it is time to wake kauditd_thread - * - * Description: - * This function is for use by the wait_event_freezable() call in - * kauditd_thread(). + * kauditd_thread - Worker thread to send audit records to userspace + * @dummy: unused */ -static int kauditd_wake_condition(void) -{ - static int pid_last = 0; - int rc; - int pid = audit_pid; - - /* wake on new messages or a change in the connected auditd */ - rc = skb_queue_len(&audit_queue) || (pid && pid != pid_last); - if (rc) - pid_last = pid; - - return rc; -} - static int kauditd_thread(void *dummy) { int rc; - int auditd = 0; - int reschedule = 0; - struct sk_buff *skb; - struct nlmsghdr *nlh; + u32 portid = 0; + struct net *net = NULL; + struct sock *sk = NULL; #define UNICAST_RETRIES 5 -#define AUDITD_BAD(x,y) \ - ((x) == -ECONNREFUSED || (x) == -EPERM || ++(y) >= UNICAST_RETRIES) - - /* NOTE: we do invalidate the auditd connection flag on any sending - * errors, but we only "restore" the connection flag at specific places - * in the loop in order to help ensure proper ordering of audit - * records */ set_freezable(); while (!kthread_should_stop()) { - /* NOTE: possible area for future improvement is to look at - * the hold and retry queues, since only this thread - * has access to these queues we might be able to do - * our own queuing and skip some/all of the locking */ - - /* NOTE: it might be a fun experiment to split the hold and - * retry queue handling to another thread, but the - * synchronization issues and other overhead might kill - * any performance gains */ + /* NOTE: see the lock comments in auditd_send_unicast_skb() */ + rcu_read_lock(); + if (!auditd_conn.pid) { + rcu_read_unlock(); + goto main_queue; + } + net = auditd_conn.net; + get_net(net); + sk = audit_get_sk(net); + portid = auditd_conn.portid; + rcu_read_unlock(); /* attempt to flush the hold queue */ - while (auditd && (skb = skb_dequeue(&audit_hold_queue))) { - rc = kauditd_send_unicast_skb(skb); - if (rc) { - /* requeue to the same spot */ - skb_queue_head(&audit_hold_queue, skb); - - auditd = 0; - if (AUDITD_BAD(rc, reschedule)) { - mutex_lock(&audit_cmd_mutex); - auditd_reset(); - mutex_unlock(&audit_cmd_mutex); - reschedule = 0; - } - } else - /* we were able to send successfully */ - reschedule = 0; + rc = kauditd_send_queue(sk, portid, + &audit_hold_queue, UNICAST_RETRIES, + NULL, kauditd_rehold_skb); + if (rc < 0) { + sk = NULL; + auditd_reset(); + goto main_queue; } /* attempt to flush the retry queue */ - while (auditd && (skb = skb_dequeue(&audit_retry_queue))) { - rc = kauditd_send_unicast_skb(skb); - if (rc) { - auditd = 0; - if (AUDITD_BAD(rc, reschedule)) { - kauditd_hold_skb(skb); - mutex_lock(&audit_cmd_mutex); - auditd_reset(); - mutex_unlock(&audit_cmd_mutex); - reschedule = 0; - } else - /* temporary problem (we hope), queue - * to the same spot and retry */ - skb_queue_head(&audit_retry_queue, skb); - } else - /* we were able to send successfully */ - reschedule = 0; + rc = kauditd_send_queue(sk, portid, + &audit_retry_queue, UNICAST_RETRIES, + NULL, kauditd_hold_skb); + if (rc < 0) { + sk = NULL; + auditd_reset(); + goto main_queue; } - /* standard queue processing, try to be as quick as possible */ -quick_loop: - skb = skb_dequeue(&audit_queue); - if (skb) { - /* setup the netlink header, see the comments in - * kauditd_send_multicast_skb() for length quirks */ - nlh = nlmsg_hdr(skb); - nlh->nlmsg_len = skb->len - NLMSG_HDRLEN; - - /* attempt to send to any multicast listeners */ - kauditd_send_multicast_skb(skb); - - /* attempt to send to auditd, queue on failure */ - if (auditd) { - rc = kauditd_send_unicast_skb(skb); - if (rc) { - auditd = 0; - if (AUDITD_BAD(rc, reschedule)) { - mutex_lock(&audit_cmd_mutex); - auditd_reset(); - mutex_unlock(&audit_cmd_mutex); - reschedule = 0; - } +main_queue: + /* process the main queue - do the multicast send and attempt + * unicast, dump failed record sends to the retry queue; if + * sk == NULL due to previous failures we will just do the + * multicast send and move the record to the retry queue */ + rc = kauditd_send_queue(sk, portid, &audit_queue, 1, + kauditd_send_multicast_skb, + kauditd_retry_skb); + if (sk == NULL || rc < 0) + auditd_reset(); + sk = NULL; - /* move to the retry queue */ - kauditd_retry_skb(skb); - } else - /* everything is working so go fast! */ - goto quick_loop; - } else if (reschedule) - /* we are currently having problems, move to - * the retry queue */ - kauditd_retry_skb(skb); - else - /* dump the message via printk and hold it */ - kauditd_hold_skb(skb); - } else { - /* we have flushed the backlog so wake everyone */ - wake_up(&audit_backlog_wait); + /* drop our netns reference, no auditd sends past this line */ + if (net) { + put_net(net); + net = NULL; + } - /* if everything is okay with auditd (if present), go - * to sleep until there is something new in the queue - * or we have a change in the connected auditd; - * otherwise simply reschedule to give things a chance - * to recover */ - if (reschedule) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - } else - wait_event_freezable(kauditd_wait, - kauditd_wake_condition()); + /* we have processed all the queues so wake everyone */ + wake_up(&audit_backlog_wait); - /* update the auditd connection status */ - auditd = (audit_pid ? 1 : 0); - } + /* NOTE: we want to wake up if there is anything on the queue, + * regardless of if an auditd is connected, as we need to + * do the multicast send and rotate records from the + * main queue to the retry/hold queues */ + wait_event_freezable(kauditd_wait, + (skb_queue_len(&audit_queue) ? 1 : 0)); } return 0; @@ -678,17 +801,16 @@ int audit_send_list(void *_dest) { struct audit_netlink_list *dest = _dest; struct sk_buff *skb; - struct net *net = dest->net; - struct audit_net *aunet = net_generic(net, audit_net_id); + struct sock *sk = audit_get_sk(dest->net); /* wait for parent to finish and send an ACK */ mutex_lock(&audit_cmd_mutex); mutex_unlock(&audit_cmd_mutex); while ((skb = __skb_dequeue(&dest->q)) != NULL) - netlink_unicast(aunet->nlsk, skb, dest->portid, 0); + netlink_unicast(sk, skb, dest->portid, 0); - put_net(net); + put_net(dest->net); kfree(dest); return 0; @@ -722,16 +844,15 @@ out_kfree_skb: static int audit_send_reply_thread(void *arg) { struct audit_reply *reply = (struct audit_reply *)arg; - struct net *net = reply->net; - struct audit_net *aunet = net_generic(net, audit_net_id); + struct sock *sk = audit_get_sk(reply->net); mutex_lock(&audit_cmd_mutex); mutex_unlock(&audit_cmd_mutex); /* Ignore failure. It'll only happen if the sender goes away, because our timeout is set to infinite. */ - netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0); - put_net(net); + netlink_unicast(sk, reply->skb, reply->portid, 0); + put_net(reply->net); kfree(reply); return 0; } @@ -949,12 +1070,12 @@ static int audit_set_feature(struct sk_buff *skb) static int audit_replace(pid_t pid) { - struct sk_buff *skb = audit_make_reply(0, 0, AUDIT_REPLACE, 0, 0, - &pid, sizeof(pid)); + struct sk_buff *skb; + skb = audit_make_reply(0, 0, AUDIT_REPLACE, 0, 0, &pid, sizeof(pid)); if (!skb) return -ENOMEM; - return netlink_unicast(audit_sock, skb, audit_nlk_portid, 0); + return auditd_send_unicast_skb(skb); } static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) @@ -981,7 +1102,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memset(&s, 0, sizeof(s)); s.enabled = audit_enabled; s.failure = audit_failure; - s.pid = audit_pid; + rcu_read_lock(); + s.pid = auditd_conn.pid; + rcu_read_unlock(); s.rate_limit = audit_rate_limit; s.backlog_limit = audit_backlog_limit; s.lost = atomic_read(&audit_lost); @@ -1014,30 +1137,44 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) * from the initial pid namespace, but something * to keep in mind if this changes */ int new_pid = s.pid; + pid_t auditd_pid; pid_t requesting_pid = task_tgid_vnr(current); - if ((!new_pid) && (requesting_pid != audit_pid)) { - audit_log_config_change("audit_pid", new_pid, audit_pid, 0); + /* test the auditd connection */ + audit_replace(requesting_pid); + + rcu_read_lock(); + auditd_pid = auditd_conn.pid; + /* only the current auditd can unregister itself */ + if ((!new_pid) && (requesting_pid != auditd_pid)) { + rcu_read_unlock(); + audit_log_config_change("audit_pid", new_pid, + auditd_pid, 0); return -EACCES; } - if (audit_pid && new_pid && - audit_replace(requesting_pid) != -ECONNREFUSED) { - audit_log_config_change("audit_pid", new_pid, audit_pid, 0); + /* replacing a healthy auditd is not allowed */ + if (auditd_pid && new_pid) { + rcu_read_unlock(); + audit_log_config_change("audit_pid", new_pid, + auditd_pid, 0); return -EEXIST; } + rcu_read_unlock(); + if (audit_enabled != AUDIT_OFF) - audit_log_config_change("audit_pid", new_pid, audit_pid, 1); + audit_log_config_change("audit_pid", new_pid, + auditd_pid, 1); + if (new_pid) { - if (audit_sock) - sock_put(audit_sock); - audit_pid = new_pid; - audit_nlk_portid = NETLINK_CB(skb).portid; - sock_hold(skb->sk); - audit_sock = skb->sk; - } else { + /* register a new auditd connection */ + auditd_set(new_pid, + NETLINK_CB(skb).portid, + sock_net(NETLINK_CB(skb).sk)); + /* try to process any backlog */ + wake_up_interruptible(&kauditd_wait); + } else + /* unregister the auditd connection */ auditd_reset(); - } - wake_up_interruptible(&kauditd_wait); } if (s.mask & AUDIT_STATUS_RATE_LIMIT) { err = audit_set_rate_limit(s.rate_limit); @@ -1090,7 +1227,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (err) break; } - mutex_unlock(&audit_cmd_mutex); audit_log_common_recv_msg(&ab, msg_type); if (msg_type != AUDIT_USER_TTY) audit_log_format(ab, " msg='%.*s'", @@ -1108,7 +1244,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } audit_set_portid(ab, NETLINK_CB(skb).portid); audit_log_end(ab); - mutex_lock(&audit_cmd_mutex); } break; case AUDIT_ADD_RULE: @@ -1298,26 +1433,26 @@ static int __net_init audit_net_init(struct net *net) struct audit_net *aunet = net_generic(net, audit_net_id); - aunet->nlsk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg); - if (aunet->nlsk == NULL) { + aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg); + if (aunet->sk == NULL) { audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } - aunet->nlsk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + return 0; } static void __net_exit audit_net_exit(struct net *net) { struct audit_net *aunet = net_generic(net, audit_net_id); - struct sock *sock = aunet->nlsk; - mutex_lock(&audit_cmd_mutex); - if (sock == audit_sock) + + rcu_read_lock(); + if (net == auditd_conn.net) auditd_reset(); - mutex_unlock(&audit_cmd_mutex); + rcu_read_unlock(); - netlink_kernel_release(sock); - aunet->nlsk = NULL; + netlink_kernel_release(aunet->sk); } static struct pernet_operations audit_net_ops __net_initdata = { @@ -1335,20 +1470,24 @@ static int __init audit_init(void) if (audit_initialized == AUDIT_DISABLED) return 0; - pr_info("initializing netlink subsys (%s)\n", - audit_default ? "enabled" : "disabled"); - register_pernet_subsys(&audit_net_ops); + memset(&auditd_conn, 0, sizeof(auditd_conn)); + spin_lock_init(&auditd_conn.lock); skb_queue_head_init(&audit_queue); skb_queue_head_init(&audit_retry_queue); skb_queue_head_init(&audit_hold_queue); - audit_initialized = AUDIT_INITIALIZED; - audit_enabled = audit_default; - audit_ever_enabled |= !!audit_default; for (i = 0; i < AUDIT_INODE_BUCKETS; i++) INIT_LIST_HEAD(&audit_inode_hash[i]); + pr_info("initializing netlink subsys (%s)\n", + audit_default ? "enabled" : "disabled"); + register_pernet_subsys(&audit_net_ops); + + audit_initialized = AUDIT_INITIALIZED; + audit_enabled = audit_default; + audit_ever_enabled |= !!audit_default; + kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd"); if (IS_ERR(kauditd_task)) { int err = PTR_ERR(kauditd_task); @@ -1519,20 +1658,16 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, if (unlikely(!audit_filter(type, AUDIT_FILTER_TYPE))) return NULL; - /* don't ever fail/sleep on these two conditions: + /* NOTE: don't ever fail/sleep on these two conditions: * 1. auditd generated record - since we need auditd to drain the * queue; also, when we are checking for auditd, compare PIDs using * task_tgid_vnr() since auditd_pid is set in audit_receive_msg() * using a PID anchored in the caller's namespace - * 2. audit command message - record types 1000 through 1099 inclusive - * are command messages/records used to manage the kernel subsystem - * and the audit userspace, blocking on these messages could cause - * problems under load so don't do it (note: not all of these - * command types are valid as record types, but it is quicker to - * just check two ints than a series of ints in a if/switch stmt) */ - if (!((audit_pid && audit_pid == task_tgid_vnr(current)) || - (type >= 1000 && type <= 1099))) { - long sleep_time = audit_backlog_wait_time; + * 2. generator holding the audit_cmd_mutex - we don't want to block + * while holding the mutex */ + if (!(auditd_test_task(current) || + (current == __mutex_owner(&audit_cmd_mutex)))) { + long stime = audit_backlog_wait_time; while (audit_backlog_limit && (skb_queue_len(&audit_queue) > audit_backlog_limit)) { @@ -1541,14 +1676,13 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, /* sleep if we are allowed and we haven't exhausted our * backlog wait limit */ - if ((gfp_mask & __GFP_DIRECT_RECLAIM) && - (sleep_time > 0)) { + if (gfpflags_allow_blocking(gfp_mask) && (stime > 0)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&audit_backlog_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); - sleep_time = schedule_timeout(sleep_time); + stime = schedule_timeout(stime); remove_wait_queue(&audit_backlog_wait, &wait); } else { if (audit_rate_check() && printk_ratelimit()) @@ -2127,15 +2261,27 @@ out: */ void audit_log_end(struct audit_buffer *ab) { + struct sk_buff *skb; + struct nlmsghdr *nlh; + if (!ab) return; - if (!audit_rate_check()) { - audit_log_lost("rate limit exceeded"); - } else { - skb_queue_tail(&audit_queue, ab->skb); - wake_up_interruptible(&kauditd_wait); + + if (audit_rate_check()) { + skb = ab->skb; ab->skb = NULL; - } + + /* setup the netlink header, see the comments in + * kauditd_send_multicast_skb() for length quirks */ + nlh = nlmsg_hdr(skb); + nlh->nlmsg_len = skb->len - NLMSG_HDRLEN; + + /* queue the netlink packet and poke the kauditd thread */ + skb_queue_tail(&audit_queue, skb); + wake_up_interruptible(&kauditd_wait); + } else + audit_log_lost("rate limit exceeded"); + audit_buffer_free(ab); } diff --git a/kernel/audit.h b/kernel/audit.h index ca579880303a..0d87f8ab8778 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -218,7 +218,7 @@ extern void audit_log_name(struct audit_context *context, struct audit_names *n, const struct path *path, int record_num, int *call_panic); -extern int audit_pid; +extern int auditd_test_task(const struct task_struct *task); #define AUDIT_INODE_BUCKETS 32 extern struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; @@ -250,10 +250,6 @@ struct audit_netlink_list { int audit_send_list(void *); -struct audit_net { - struct sock *nlsk; -}; - extern int selinux_audit_rule_update(void); extern struct mutex audit_filter_mutex; @@ -337,14 +333,7 @@ extern u32 audit_sig_sid; extern int audit_filter(int msgtype, unsigned int listtype); #ifdef CONFIG_AUDITSYSCALL -extern int __audit_signal_info(int sig, struct task_struct *t); -static inline int audit_signal_info(int sig, struct task_struct *t) -{ - if (unlikely((audit_pid && t->tgid == audit_pid) || - (audit_signals && !audit_dummy_context()))) - return __audit_signal_info(sig, t); - return 0; -} +extern int audit_signal_info(int sig, struct task_struct *t); extern void audit_filter_inodes(struct task_struct *, struct audit_context *); extern struct list_head *audit_killed_trees(void); #else diff --git a/kernel/auditsc.c b/kernel/auditsc.c index d6a8de5f8fa3..1c2333155893 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -762,7 +762,7 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk, struct audit_entry *e; enum audit_state state; - if (audit_pid && tsk->tgid == audit_pid) + if (auditd_test_task(tsk)) return AUDIT_DISABLED; rcu_read_lock(); @@ -816,7 +816,7 @@ void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx) { struct audit_names *n; - if (audit_pid && tsk->tgid == audit_pid) + if (auditd_test_task(tsk)) return; rcu_read_lock(); @@ -2249,26 +2249,27 @@ void __audit_ptrace(struct task_struct *t) * If the audit subsystem is being terminated, record the task (pid) * and uid that is doing that. */ -int __audit_signal_info(int sig, struct task_struct *t) +int audit_signal_info(int sig, struct task_struct *t) { struct audit_aux_data_pids *axp; struct task_struct *tsk = current; struct audit_context *ctx = tsk->audit_context; kuid_t uid = current_uid(), t_uid = task_uid(t); - if (audit_pid && t->tgid == audit_pid) { - if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) { - audit_sig_pid = task_tgid_nr(tsk); - if (uid_valid(tsk->loginuid)) - audit_sig_uid = tsk->loginuid; - else - audit_sig_uid = uid; - security_task_getsecid(tsk, &audit_sig_sid); - } - if (!audit_signals || audit_dummy_context()) - return 0; + if (auditd_test_task(t) && + (sig == SIGTERM || sig == SIGHUP || + sig == SIGUSR1 || sig == SIGUSR2)) { + audit_sig_pid = task_tgid_nr(tsk); + if (uid_valid(tsk->loginuid)) + audit_sig_uid = tsk->loginuid; + else + audit_sig_uid = uid; + security_task_getsecid(tsk, &audit_sig_sid); } + if (!audit_signals || audit_dummy_context()) + return 0; + /* optimize the common case by putting first signal recipient directly * in audit_context */ if (!ctx->target_pid) { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index f45827e205d3..b4f1cb0c5ac7 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1162,12 +1162,12 @@ out: LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ off = IMM; load_word: - /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are - * only appearing in the programs where ctx == - * skb. All programs keep 'ctx' in regs[BPF_REG_CTX] - * == BPF_R6, bpf_convert_filter() saves it in BPF_R6, - * internal BPF verifier will check that BPF_R6 == - * ctx. + /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only + * appearing in the programs where ctx == skb + * (see may_access_skb() in the verifier). All programs + * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6, + * bpf_convert_filter() saves it in BPF_R6, internal BPF + * verifier will check that BPF_R6 == ctx. * * BPF_ABS and BPF_IND are wrappers of function calls, * so they scratch BPF_R1-BPF_R5 registers, preserve diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3ea87fb19a94..361a69dfe543 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -13,11 +13,12 @@ #include <linux/bpf.h> #include <linux/jhash.h> #include <linux/filter.h> +#include <linux/rculist_nulls.h> #include "percpu_freelist.h" #include "bpf_lru_list.h" struct bucket { - struct hlist_head head; + struct hlist_nulls_head head; raw_spinlock_t lock; }; @@ -29,28 +30,26 @@ struct bpf_htab { struct pcpu_freelist freelist; struct bpf_lru lru; }; - void __percpu *extra_elems; + struct htab_elem *__percpu *extra_elems; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ }; -enum extra_elem_state { - HTAB_NOT_AN_EXTRA_ELEM = 0, - HTAB_EXTRA_ELEM_FREE, - HTAB_EXTRA_ELEM_USED -}; - /* each htab element is struct htab_elem + key + value */ struct htab_elem { union { - struct hlist_node hash_node; - struct bpf_htab *htab; - struct pcpu_freelist_node fnode; + struct hlist_nulls_node hash_node; + struct { + void *padding; + union { + struct bpf_htab *htab; + struct pcpu_freelist_node fnode; + }; + }; }; union { struct rcu_head rcu; - enum extra_elem_state state; struct bpf_lru_node lru_node; }; u32 hash; @@ -71,6 +70,11 @@ static bool htab_is_percpu(const struct bpf_htab *htab) htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; } +static bool htab_is_prealloc(const struct bpf_htab *htab) +{ + return !(htab->map.map_flags & BPF_F_NO_PREALLOC); +} + static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, void __percpu *pptr) { @@ -122,17 +126,20 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, static int prealloc_init(struct bpf_htab *htab) { + u32 num_entries = htab->map.max_entries; int err = -ENOMEM, i; - htab->elems = bpf_map_area_alloc(htab->elem_size * - htab->map.max_entries); + if (!htab_is_percpu(htab) && !htab_is_lru(htab)) + num_entries += num_possible_cpus(); + + htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries); if (!htab->elems) return -ENOMEM; if (!htab_is_percpu(htab)) goto skip_percpu_elems; - for (i = 0; i < htab->map.max_entries; i++) { + for (i = 0; i < num_entries; i++) { u32 size = round_up(htab->map.value_size, 8); void __percpu *pptr; @@ -160,10 +167,11 @@ skip_percpu_elems: if (htab_is_lru(htab)) bpf_lru_populate(&htab->lru, htab->elems, offsetof(struct htab_elem, lru_node), - htab->elem_size, htab->map.max_entries); + htab->elem_size, num_entries); else - pcpu_freelist_populate(&htab->freelist, htab->elems, - htab->elem_size, htab->map.max_entries); + pcpu_freelist_populate(&htab->freelist, + htab->elems + offsetof(struct htab_elem, fnode), + htab->elem_size, num_entries); return 0; @@ -184,16 +192,22 @@ static void prealloc_destroy(struct bpf_htab *htab) static int alloc_extra_elems(struct bpf_htab *htab) { - void __percpu *pptr; + struct htab_elem *__percpu *pptr, *l_new; + struct pcpu_freelist_node *l; int cpu; - pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN); + pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8, + GFP_USER | __GFP_NOWARN); if (!pptr) return -ENOMEM; for_each_possible_cpu(cpu) { - ((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state = - HTAB_EXTRA_ELEM_FREE; + l = pcpu_freelist_pop(&htab->freelist); + /* pop will succeed, since prealloc_init() + * preallocated extra num_possible_cpus elements + */ + l_new = container_of(l, struct htab_elem, fnode); + *per_cpu_ptr(pptr, cpu) = l_new; } htab->extra_elems = pptr; return 0; @@ -217,6 +231,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) int err, i; u64 cost; + BUILD_BUG_ON(offsetof(struct htab_elem, htab) != + offsetof(struct htab_elem, hash_node.pprev)); + BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) != + offsetof(struct htab_elem, hash_node.pprev)); + if (lru && !capable(CAP_SYS_ADMIN)) /* LRU implementation is much complicated than other * maps. Hence, limit to CAP_SYS_ADMIN for now. @@ -326,29 +345,29 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) goto free_htab; for (i = 0; i < htab->n_buckets; i++) { - INIT_HLIST_HEAD(&htab->buckets[i].head); + INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); raw_spin_lock_init(&htab->buckets[i].lock); } - if (!percpu && !lru) { - /* lru itself can remove the least used element, so - * there is no need for an extra elem during map_update. - */ - err = alloc_extra_elems(htab); - if (err) - goto free_buckets; - } - if (prealloc) { err = prealloc_init(htab); if (err) - goto free_extra_elems; + goto free_buckets; + + if (!percpu && !lru) { + /* lru itself can remove the least used element, so + * there is no need for an extra elem during map_update. + */ + err = alloc_extra_elems(htab); + if (err) + goto free_prealloc; + } } return &htab->map; -free_extra_elems: - free_percpu(htab->extra_elems); +free_prealloc: + prealloc_destroy(htab); free_buckets: bpf_map_area_free(htab->buckets); free_htab: @@ -366,20 +385,44 @@ static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) return &htab->buckets[hash & (htab->n_buckets - 1)]; } -static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash) { return &__select_bucket(htab, hash)->head; } -static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash, +/* this lookup function can only be called with bucket lock taken */ +static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash, void *key, u32 key_size) { + struct hlist_nulls_node *n; + struct htab_elem *l; + + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) + if (l->hash == hash && !memcmp(&l->key, key, key_size)) + return l; + + return NULL; +} + +/* can be called without bucket lock. it will repeat the loop in + * the unlikely event when elements moved from one bucket into another + * while link list is being walked + */ +static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head, + u32 hash, void *key, + u32 key_size, u32 n_buckets) +{ + struct hlist_nulls_node *n; struct htab_elem *l; - hlist_for_each_entry_rcu(l, head, hash_node) +again: + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l->hash == hash && !memcmp(&l->key, key, key_size)) return l; + if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1)))) + goto again; + return NULL; } @@ -387,7 +430,7 @@ static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash, static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct htab_elem *l; u32 hash, key_size; @@ -400,7 +443,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) head = select_bucket(htab, hash); - l = lookup_elem_raw(head, hash, key, key_size); + l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets); return l; } @@ -433,8 +476,9 @@ static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) { struct bpf_htab *htab = (struct bpf_htab *)arg; - struct htab_elem *l, *tgt_l; - struct hlist_head *head; + struct htab_elem *l = NULL, *tgt_l; + struct hlist_nulls_head *head; + struct hlist_nulls_node *n; unsigned long flags; struct bucket *b; @@ -444,9 +488,9 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) raw_spin_lock_irqsave(&b->lock, flags); - hlist_for_each_entry_rcu(l, head, hash_node) + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_del_rcu(&l->hash_node); break; } @@ -459,7 +503,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct htab_elem *l, *next_l; u32 hash, key_size; int i; @@ -473,7 +517,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) head = select_bucket(htab, hash); /* lookup the key */ - l = lookup_elem_raw(head, hash, key, key_size); + l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets); if (!l) { i = 0; @@ -481,7 +525,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) } /* key was found, get next key in the same bucket */ - next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)), + next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)), struct htab_elem, hash_node); if (next_l) { @@ -500,7 +544,7 @@ find_first_elem: head = select_bucket(htab, i); /* pick first element in the bucket */ - next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)), struct htab_elem, hash_node); if (next_l) { /* if it's not empty, just return it */ @@ -538,12 +582,7 @@ static void htab_elem_free_rcu(struct rcu_head *head) static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { - if (l->state == HTAB_EXTRA_ELEM_USED) { - l->state = HTAB_EXTRA_ELEM_FREE; - return; - } - - if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) { + if (htab_is_prealloc(htab)) { pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); @@ -573,43 +612,43 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, bool percpu, bool onallcpus, - bool old_elem_exists) + struct htab_elem *old_elem) { u32 size = htab->map.value_size; - bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC); - struct htab_elem *l_new; + bool prealloc = htab_is_prealloc(htab); + struct htab_elem *l_new, **pl_new; void __percpu *pptr; - int err = 0; if (prealloc) { - l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist); - if (!l_new) - err = -E2BIG; - } else { - if (atomic_inc_return(&htab->count) > htab->map.max_entries) { - atomic_dec(&htab->count); - err = -E2BIG; + if (old_elem) { + /* if we're updating the existing element, + * use per-cpu extra elems to avoid freelist_pop/push + */ + pl_new = this_cpu_ptr(htab->extra_elems); + l_new = *pl_new; + *pl_new = old_elem; } else { - l_new = kmalloc(htab->elem_size, - GFP_ATOMIC | __GFP_NOWARN); - if (!l_new) - return ERR_PTR(-ENOMEM); - } - } + struct pcpu_freelist_node *l; - if (err) { - if (!old_elem_exists) - return ERR_PTR(err); - - /* if we're updating the existing element and the hash table - * is full, use per-cpu extra elems - */ - l_new = this_cpu_ptr(htab->extra_elems); - if (l_new->state != HTAB_EXTRA_ELEM_FREE) - return ERR_PTR(-E2BIG); - l_new->state = HTAB_EXTRA_ELEM_USED; + l = pcpu_freelist_pop(&htab->freelist); + if (!l) + return ERR_PTR(-E2BIG); + l_new = container_of(l, struct htab_elem, fnode); + } } else { - l_new->state = HTAB_NOT_AN_EXTRA_ELEM; + if (atomic_inc_return(&htab->count) > htab->map.max_entries) + if (!old_elem) { + /* when map is full and update() is replacing + * old element, it's ok to allocate, since + * old element will be freed immediately. + * Otherwise return an error + */ + atomic_dec(&htab->count); + return ERR_PTR(-E2BIG); + } + l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (!l_new) + return ERR_PTR(-ENOMEM); } memcpy(l_new->key, key, key_size); @@ -661,7 +700,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -690,7 +729,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, goto err; l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false, - !!l_old); + l_old); if (IS_ERR(l_new)) { /* all pre-allocated elements are in use or memory exhausted */ ret = PTR_ERR(l_new); @@ -700,10 +739,11 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, /* add new element to the head of the list, so that * concurrent search will find it before old elem */ - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { - hlist_del_rcu(&l_old->hash_node); - free_htab_elem(htab, l_old); + hlist_nulls_del_rcu(&l_old->hash_node); + if (!htab_is_prealloc(htab)) + free_htab_elem(htab, l_old); } ret = 0; err: @@ -716,7 +756,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new, *l_old = NULL; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -757,10 +797,10 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, /* add new element to the head of the list, so that * concurrent search will find it before old elem */ - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { bpf_lru_node_set_ref(&l_new->lru_node); - hlist_del_rcu(&l_old->hash_node); + hlist_nulls_del_rcu(&l_old->hash_node); } ret = 0; @@ -781,7 +821,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -815,12 +855,12 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, value, onallcpus); } else { l_new = alloc_htab_elem(htab, key, value, key_size, - hash, true, onallcpus, false); + hash, true, onallcpus, NULL); if (IS_ERR(l_new)) { ret = PTR_ERR(l_new); goto err; } - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); } ret = 0; err: @@ -834,7 +874,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; - struct hlist_head *head; + struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; @@ -882,7 +922,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, } else { pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size), value, onallcpus); - hlist_add_head_rcu(&l_new->hash_node, head); + hlist_nulls_add_head_rcu(&l_new->hash_node, head); l_new = NULL; } ret = 0; @@ -910,7 +950,7 @@ static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, static int htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct bucket *b; struct htab_elem *l; unsigned long flags; @@ -930,7 +970,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) l = lookup_elem_raw(head, hash, key, key_size); if (l) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_del_rcu(&l->hash_node); free_htab_elem(htab, l); ret = 0; } @@ -942,7 +982,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; + struct hlist_nulls_head *head; struct bucket *b; struct htab_elem *l; unsigned long flags; @@ -962,7 +1002,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) l = lookup_elem_raw(head, hash, key, key_size); if (l) { - hlist_del_rcu(&l->hash_node); + hlist_nulls_del_rcu(&l->hash_node); ret = 0; } @@ -977,14 +1017,13 @@ static void delete_all_elements(struct bpf_htab *htab) int i; for (i = 0; i < htab->n_buckets; i++) { - struct hlist_head *head = select_bucket(htab, i); - struct hlist_node *n; + struct hlist_nulls_head *head = select_bucket(htab, i); + struct hlist_nulls_node *n; struct htab_elem *l; - hlist_for_each_entry_safe(l, n, head, hash_node) { - hlist_del_rcu(&l->hash_node); - if (l->state != HTAB_EXTRA_ELEM_USED) - htab_elem_free(htab, l); + hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { + hlist_nulls_del_rcu(&l->hash_node); + htab_elem_free(htab, l); } } } @@ -1004,7 +1043,7 @@ static void htab_map_free(struct bpf_map *map) * not have executed. Wait for them. */ rcu_barrier(); - if (htab->map.map_flags & BPF_F_NO_PREALLOC) + if (!htab_is_prealloc(htab)) delete_all_elements(htab); else prealloc_destroy(htab); diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 8bfe0afaee10..b37bd9ab7f57 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -500,9 +500,15 @@ unlock: raw_spin_unlock(&trie->lock); } +static int trie_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -ENOTSUPP; +} + static const struct bpf_map_ops trie_ops = { .map_alloc = trie_alloc, .map_free = trie_free, + .map_get_next_key = trie_get_next_key, .map_lookup_elem = trie_lookup_elem, .map_update_elem = trie_update_elem, .map_delete_elem = trie_delete_elem, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7af0dcc5d755..821f9e807de5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -617,6 +617,14 @@ static void fixup_bpf_calls(struct bpf_prog *prog) if (insn->imm == BPF_FUNC_xdp_adjust_head) prog->xdp_adjust_head = 1; if (insn->imm == BPF_FUNC_tail_call) { + /* If we tail call into other programs, we + * cannot make any assumptions since they + * can be replaced dynamically during runtime + * in the program array. + */ + prog->cb_access = 1; + prog->xdp_adjust_head = 1; + /* mark bpf_tail_call as different opcode * to avoid conditional branch in * interpeter for every normal call diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 796b68d00119..a834068a400e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -765,38 +765,56 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) } } -static int check_ptr_alignment(struct bpf_verifier_env *env, - struct bpf_reg_state *reg, int off, int size) +static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, + int off, int size) { - if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_MAP_VALUE_ADJ) { - if (off % size != 0) { - verbose("misaligned access off %d size %d\n", - off, size); - return -EACCES; - } else { - return 0; - } - } - - if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) - /* misaligned access to packet is ok on x86,arm,arm64 */ - return 0; - if (reg->id && size != 1) { - verbose("Unknown packet alignment. Only byte-sized access allowed\n"); + verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n"); return -EACCES; } /* skb->data is NET_IP_ALIGN-ed */ - if (reg->type == PTR_TO_PACKET && - (NET_IP_ALIGN + reg->off + off) % size != 0) { + if ((NET_IP_ALIGN + reg->off + off) % size != 0) { verbose("misaligned packet access off %d+%d+%d size %d\n", NET_IP_ALIGN, reg->off, off, size); return -EACCES; } + return 0; } +static int check_val_ptr_alignment(const struct bpf_reg_state *reg, + int size) +{ + if (size != 1) { + verbose("Unknown alignment. Only byte-sized access allowed in value access.\n"); + return -EACCES; + } + + return 0; +} + +static int check_ptr_alignment(const struct bpf_reg_state *reg, + int off, int size) +{ + switch (reg->type) { + case PTR_TO_PACKET: + return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 : + check_pkt_ptr_alignment(reg, off, size); + case PTR_TO_MAP_VALUE_ADJ: + return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 : + check_val_ptr_alignment(reg, size); + default: + if (off % size != 0) { + verbose("misaligned access off %d size %d\n", + off, size); + return -EACCES; + } + + return 0; + } +} + /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -818,7 +836,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, if (size < 0) return size; - err = check_ptr_alignment(env, reg, off, size); + err = check_ptr_alignment(reg, off, size); if (err) return err; @@ -1925,6 +1943,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * register as unknown. */ if (env->allow_ptr_leaks && + BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD && (dst_reg->type == PTR_TO_MAP_VALUE || dst_reg->type == PTR_TO_MAP_VALUE_ADJ)) dst_reg->type = PTR_TO_MAP_VALUE_ADJ; @@ -1973,14 +1992,15 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, for (i = 0; i < MAX_BPF_REG; i++) if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) - regs[i].range = dst_reg->off; + /* keep the maximum range already checked */ + regs[i].range = max(regs[i].range, dst_reg->off); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) - reg->range = dst_reg->off; + reg->range = max(reg->range, dst_reg->off); } } diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 56eba9caa632..1dc22f6b49f5 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1329,7 +1329,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) struct task_struct *task; int count = 0; - seq_printf(seq, "css_set %p\n", cset); + seq_printf(seq, "css_set %pK\n", cset); list_for_each_entry(task, &cset->tasks, cg_list) { if (count++ > MAX_TASKS_SHOWN_PER_CSS) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 0125589c7428..687f5e0194ef 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2425,11 +2425,12 @@ ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, tsk = tsk->group_leader; /* - * Workqueue threads may acquire PF_NO_SETAFFINITY and become - * trapped in a cpuset, or RT worker may be born in a cgroup - * with no rt_runtime allocated. Just say no. + * kthreads may acquire PF_NO_SETAFFINITY during initialization. + * If userland migrates such a kthread to a non-root cgroup, it can + * become trapped in a cpuset, or RT kthread may be born in a + * cgroup with no rt_runtime allocated. Just say no. */ - if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) { + if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; goto out_unlock_rcu; } @@ -2669,7 +2670,7 @@ static bool css_visible(struct cgroup_subsys_state *css) * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for - * cleaning up with cgroup_apply_control_disble(). + * cleaning up with cgroup_apply_control_disable(). */ static int cgroup_apply_control_enable(struct cgroup *cgrp) { diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index e756dae49300..2237201d66d5 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -229,7 +229,7 @@ static int pids_can_fork(struct task_struct *task) /* Only log the first time events_limit is incremented. */ if (atomic64_inc_return(&pids->events_limit) == 1) { pr_info("cgroup: fork rejected by pids controller in "); - pr_cont_cgroup_path(task_cgroup(current, pids_cgrp_id)); + pr_cont_cgroup_path(css->cgroup); pr_cont("\n"); } cgroup_file_notify(&pids->events_file); diff --git a/kernel/cpu.c b/kernel/cpu.c index f7c063239fa5..37b223e4fc05 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1335,26 +1335,21 @@ static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, struct cpuhp_step *sp; int ret = 0; - mutex_lock(&cpuhp_state_mutex); - if (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN) { ret = cpuhp_reserve_state(state); if (ret < 0) - goto out; + return ret; state = ret; } sp = cpuhp_get_step(state); - if (name && sp->name) { - ret = -EBUSY; - goto out; - } + if (name && sp->name) + return -EBUSY; + sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); -out: - mutex_unlock(&cpuhp_state_mutex); return ret; } @@ -1428,6 +1423,7 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, return -EINVAL; get_online_cpus(); + mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; @@ -1447,16 +1443,14 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); - goto err; + goto unlock; } } add_node: ret = 0; - mutex_lock(&cpuhp_state_mutex); hlist_add_head(node, &sp->list); +unlock: mutex_unlock(&cpuhp_state_mutex); - -err: put_online_cpus(); return ret; } @@ -1491,6 +1485,7 @@ int __cpuhp_setup_state(enum cpuhp_state state, return -EINVAL; get_online_cpus(); + mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); @@ -1524,6 +1519,7 @@ int __cpuhp_setup_state(enum cpuhp_state state, } } out: + mutex_unlock(&cpuhp_state_mutex); put_online_cpus(); /* * If the requested state is CPUHP_AP_ONLINE_DYN, return the @@ -1547,6 +1543,8 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state, return -EINVAL; get_online_cpus(); + mutex_lock(&cpuhp_state_mutex); + if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* @@ -1563,7 +1561,6 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state, } remove: - mutex_lock(&cpuhp_state_mutex); hlist_del(node); mutex_unlock(&cpuhp_state_mutex); put_online_cpus(); @@ -1571,6 +1568,7 @@ remove: return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); + /** * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state * @state: The state to remove @@ -1589,6 +1587,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) get_online_cpus(); + mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", @@ -1613,6 +1612,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); + mutex_unlock(&cpuhp_state_mutex); put_online_cpus(); } EXPORT_SYMBOL(__cpuhp_remove_state); diff --git a/kernel/events/core.c b/kernel/events/core.c index 6f41548f2e32..ff01cba86f43 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -998,7 +998,7 @@ list_update_cgroup_event(struct perf_event *event, */ #define PERF_CPU_HRTIMER (1000 / HZ) /* - * function must be called with interrupts disbled + * function must be called with interrupts disabled */ static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr) { @@ -4256,7 +4256,7 @@ int perf_event_release_kernel(struct perf_event *event) raw_spin_lock_irq(&ctx->lock); /* - * Mark this even as STATE_DEAD, there is no external reference to it + * Mark this event as STATE_DEAD, there is no external reference to it * anymore. * * Anybody acquiring event->child_mutex after the below loop _must_ @@ -10417,21 +10417,22 @@ void perf_event_free_task(struct task_struct *task) continue; mutex_lock(&ctx->mutex); -again: - list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, - group_entry) - perf_free_event(event, ctx); + raw_spin_lock_irq(&ctx->lock); + /* + * Destroy the task <-> ctx relation and mark the context dead. + * + * This is important because even though the task hasn't been + * exposed yet the context has been (through child_list). + */ + RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], NULL); + WRITE_ONCE(ctx->task, TASK_TOMBSTONE); + put_task_struct(task); /* cannot be last */ + raw_spin_unlock_irq(&ctx->lock); - list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, - group_entry) + list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) perf_free_event(event, ctx); - if (!list_empty(&ctx->pinned_groups) || - !list_empty(&ctx->flexible_groups)) - goto again; - mutex_unlock(&ctx->mutex); - put_ctx(ctx); } } @@ -10469,7 +10470,12 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event) } /* - * inherit a event from parent task to child task: + * Inherit a event from parent task to child task. + * + * Returns: + * - valid pointer on success + * - NULL for orphaned events + * - IS_ERR() on error */ static struct perf_event * inherit_event(struct perf_event *parent_event, @@ -10563,6 +10569,16 @@ inherit_event(struct perf_event *parent_event, return child_event; } +/* + * Inherits an event group. + * + * This will quietly suppress orphaned events; !inherit_event() is not an error. + * This matches with perf_event_release_kernel() removing all child events. + * + * Returns: + * - 0 on success + * - <0 on error + */ static int inherit_group(struct perf_event *parent_event, struct task_struct *parent, struct perf_event_context *parent_ctx, @@ -10577,6 +10593,11 @@ static int inherit_group(struct perf_event *parent_event, child, NULL, child_ctx); if (IS_ERR(leader)) return PTR_ERR(leader); + /* + * @leader can be NULL here because of is_orphaned_event(). In this + * case inherit_event() will create individual events, similar to what + * perf_group_detach() would do anyway. + */ list_for_each_entry(sub, &parent_event->sibling_list, group_entry) { child_ctr = inherit_event(sub, parent, parent_ctx, child, leader, child_ctx); @@ -10586,6 +10607,17 @@ static int inherit_group(struct perf_event *parent_event, return 0; } +/* + * Creates the child task context and tries to inherit the event-group. + * + * Clears @inherited_all on !attr.inherited or error. Note that we'll leave + * inherited_all set when we 'fail' to inherit an orphaned event; this is + * consistent with perf_event_release_kernel() removing all child events. + * + * Returns: + * - 0 on success + * - <0 on error + */ static int inherit_task_group(struct perf_event *event, struct task_struct *parent, struct perf_event_context *parent_ctx, @@ -10608,7 +10640,6 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent, * First allocate and initialize a context for the * child. */ - child_ctx = alloc_perf_context(parent_ctx->pmu, child); if (!child_ctx) return -ENOMEM; @@ -10670,7 +10701,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) ret = inherit_task_group(event, parent, parent_ctx, child, ctxn, &inherited_all); if (ret) - break; + goto out_unlock; } /* @@ -10686,7 +10717,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) ret = inherit_task_group(event, parent, parent_ctx, child, ctxn, &inherited_all); if (ret) - break; + goto out_unlock; } raw_spin_lock_irqsave(&parent_ctx->lock, flags); @@ -10714,6 +10745,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) } raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); +out_unlock: mutex_unlock(&parent_ctx->mutex); perf_unpin_context(parent_ctx); diff --git a/kernel/exit.c b/kernel/exit.c index e126ebf2400c..516acdb0e0ec 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -554,7 +554,6 @@ static void exit_mm(void) enter_lazy_tlb(mm, current); task_unlock(current); mm_update_next_owner(mm); - userfaultfd_exit(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) exit_oom_victim(); diff --git a/kernel/futex.c b/kernel/futex.c index 229a744b1781..45858ec73941 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2815,7 +2815,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, { struct hrtimer_sleeper timeout, *to = NULL; struct rt_mutex_waiter rt_waiter; - struct rt_mutex *pi_mutex = NULL; struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; @@ -2899,6 +2898,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); + if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) + rt_mutex_unlock(&q.pi_state->pi_mutex); /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. @@ -2907,6 +2908,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, spin_unlock(q.lock_ptr); } } else { + struct rt_mutex *pi_mutex; + /* * We have been woken up by futex_unlock_pi(), a timeout, or a * signal. futex_unlock_pi() will not destroy the lock_ptr nor @@ -2930,18 +2933,19 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (res) ret = (res < 0) ? res : 0; + /* + * If fixup_pi_state_owner() faulted and was unable to handle + * the fault, unlock the rt_mutex and return the fault to + * userspace. + */ + if (ret && rt_mutex_owner(pi_mutex) == current) + rt_mutex_unlock(pi_mutex); + /* Unqueue and drop the lock. */ unqueue_me_pi(&q); } - /* - * If fixup_pi_state_owner() faulted and was unable to handle the - * fault, unlock the rt_mutex and return the fault to userspace. - */ - if (ret == -EFAULT) { - if (pi_mutex && rt_mutex_owner(pi_mutex) == current) - rt_mutex_unlock(pi_mutex); - } else if (ret == -EINTR) { + if (ret == -EINTR) { /* * We've already been requeued, but cannot restart by calling * futex_lock_pi() directly. We could restart this syscall, but diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index 4544b115f5eb..e2d356dd7581 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -59,7 +59,7 @@ static int get_nodes_in_cpumask(const struct cpumask *mask, nodemask_t *nodemsk) struct cpumask * irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) { - int n, nodes, vecs_per_node, cpus_per_vec, extra_vecs, curvec; + int n, nodes, cpus_per_vec, extra_vecs, curvec; int affv = nvecs - affd->pre_vectors - affd->post_vectors; int last_affv = affv + affd->pre_vectors; nodemask_t nodemsk = NODE_MASK_NONE; @@ -94,19 +94,21 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) goto done; } - /* Spread the vectors per node */ - vecs_per_node = affv / nodes; - /* Account for rounding errors */ - extra_vecs = affv - (nodes * vecs_per_node); - for_each_node_mask(n, nodemsk) { - int ncpus, v, vecs_to_assign = vecs_per_node; + int ncpus, v, vecs_to_assign, vecs_per_node; + + /* Spread the vectors per node */ + vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes; /* Get the cpus on this node which are in the mask */ cpumask_and(nmsk, cpu_online_mask, cpumask_of_node(n)); /* Calculate the number of cpus per vector */ ncpus = cpumask_weight(nmsk); + vecs_to_assign = min(vecs_per_node, ncpus); + + /* Account for rounding errors */ + extra_vecs = ncpus - vecs_to_assign * (ncpus / vecs_to_assign); for (v = 0; curvec < last_affv && v < vecs_to_assign; curvec++, v++) { @@ -115,14 +117,14 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) /* Account for extra vectors to compensate rounding errors */ if (extra_vecs) { cpus_per_vec++; - if (!--extra_vecs) - vecs_per_node++; + --extra_vecs; } irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec); } if (curvec >= last_affv) break; + --nodes; } done: diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index b56a558e406d..b118735fea9d 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -614,13 +614,13 @@ static int kexec_calculate_store_digests(struct kimage *image) ret = crypto_shash_final(desc, digest); if (ret) goto out_free_digest; - ret = kexec_purgatory_get_set_symbol(image, "sha_regions", - sha_regions, sha_region_sz, 0); + ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions", + sha_regions, sha_region_sz, 0); if (ret) goto out_free_digest; - ret = kexec_purgatory_get_set_symbol(image, "sha256_digest", - digest, SHA256_DIGEST_SIZE, 0); + ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest", + digest, SHA256_DIGEST_SIZE, 0); if (ret) goto out_free_digest; } diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 4cef7e4706b0..799a8a452187 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -15,11 +15,7 @@ int kimage_is_destination_range(struct kimage *image, extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE -struct kexec_sha_region { - unsigned long start; - unsigned long len; -}; - +#include <linux/purgatory.h> void kimage_file_post_load_cleanup(struct kimage *image); #else /* CONFIG_KEXEC_FILE */ static inline void kimage_file_post_load_cleanup(struct kimage *image) { } diff --git a/kernel/kthread.c b/kernel/kthread.c index 2f26adea0f84..26db528c1d88 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -20,6 +20,7 @@ #include <linux/freezer.h> #include <linux/ptrace.h> #include <linux/uaccess.h> +#include <linux/cgroup.h> #include <trace/events/sched.h> static DEFINE_SPINLOCK(kthread_create_lock); @@ -225,6 +226,7 @@ static int kthread(void *_create) ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) { + cgroup_kthread_ready(); __kthread_parkme(self); ret = threadfn(data); } @@ -538,6 +540,7 @@ int kthreadd(void *unused) set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; + cgroup_init_kthreadd(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 12e38c213b70..a95e5d1f4a9c 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3262,10 +3262,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (depth) { hlock = curr->held_locks + depth - 1; if (hlock->class_idx == class_idx && nest_lock) { - if (hlock->references) + if (hlock->references) { + /* + * Check: unsigned int references:12, overflow. + */ + if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1)) + return 0; + hlock->references++; - else + } else { hlock->references = 2; + } return 1; } diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index c2b88490d857..c08fbd2f5ba9 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -46,13 +46,13 @@ enum { (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) /* - * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text, + * CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text, * .data and .bss to fit in required 32MB limit for the kernel. With - * PROVE_LOCKING we could go over this limit and cause system boot-up problems. + * CONFIG_LOCKDEP we could go over this limit and cause system boot-up problems. * So, reduce the static allocations for lockdeps related structures so that * everything fits in current required size limit. */ -#ifdef CONFIG_PROVE_LOCKING_SMALL +#ifdef CONFIG_LOCKDEP_SMALL /* * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies * we track. diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 7bc24d477805..c65f7989f850 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -213,10 +213,9 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state) */ if (sem->count == 0) break; - if (signal_pending_state(state, current)) { - ret = -EINTR; - goto out; - } + if (signal_pending_state(state, current)) + goto out_nolock; + set_current_state(state); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); schedule(); @@ -224,12 +223,19 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state) } /* got the lock */ sem->count = -1; -out: list_del(&waiter.list); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); return ret; + +out_nolock: + list_del(&waiter.list); + if (!list_empty(&sem->wait_list)) + __rwsem_do_wake(sem, 1); + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return -EINTR; } void __sched __down_write(struct rw_semaphore *sem) diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index da6c9a34f62f..6b7abb334ca6 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -50,7 +50,7 @@ static void test_mutex_work(struct work_struct *work) if (mtx->flags & TEST_MTX_TRY) { while (!ww_mutex_trylock(&mtx->mutex)) - cpu_relax(); + cond_resched(); } else { ww_mutex_lock(&mtx->mutex, NULL); } @@ -88,7 +88,7 @@ static int __test_mutex(unsigned int flags) ret = -EINVAL; break; } - cpu_relax(); + cond_resched(); } while (time_before(jiffies, timeout)); } else { ret = wait_for_completion_timeout(&mtx.done, TIMEOUT); @@ -627,7 +627,7 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; - ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL); + ret = stress(4095, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL); if (ret) return ret; diff --git a/kernel/memremap.c b/kernel/memremap.c index 06123234f118..07e85e5229da 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -247,11 +247,9 @@ static void devm_memremap_pages_release(struct device *dev, void *data) align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(resource_size(res), SECTION_SIZE); - lock_device_hotplug(); mem_hotplug_begin(); arch_remove_memory(align_start, align_size); mem_hotplug_done(); - unlock_device_hotplug(); untrack_pfn(NULL, PHYS_PFN(align_start), align_size); pgmap_radix_release(res); @@ -364,11 +362,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (error) goto err_pfn_remap; - lock_device_hotplug(); mem_hotplug_begin(); error = arch_add_memory(nid, align_start, align_size, true); mem_hotplug_done(); - unlock_device_hotplug(); if (error) goto err_add_memory; diff --git a/kernel/padata.c b/kernel/padata.c index 05316c9f32da..3202aa17492c 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -186,19 +186,20 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd) reorder = &next_queue->reorder; + spin_lock(&reorder->lock); if (!list_empty(&reorder->list)) { padata = list_entry(reorder->list.next, struct padata_priv, list); - spin_lock(&reorder->lock); list_del_init(&padata->list); atomic_dec(&pd->reorder_objects); - spin_unlock(&reorder->lock); pd->processed++; + spin_unlock(&reorder->lock); goto out; } + spin_unlock(&reorder->lock); if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) { padata = ERR_PTR(-ENODATA); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 0af928712174..266ddcc1d8bb 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -184,11 +184,17 @@ static void ptrace_unfreeze_traced(struct task_struct *task) WARN_ON(!task->ptrace || task->parent != current); + /* + * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely. + * Recheck state under the lock to close this race. + */ spin_lock_irq(&task->sighand->siglock); - if (__fatal_signal_pending(task)) - wake_up_state(task, __TASK_TRACED); - else - task->state = TASK_TRACED; + if (task->state == __TASK_TRACED) { + if (__fatal_signal_pending(task)) + wake_up_state(task, __TASK_TRACED); + else + task->state = TASK_TRACED; + } spin_unlock_irq(&task->sighand->siglock); } diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index a08795e21628..00a45c45beca 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -96,10 +96,10 @@ static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable); static int __sched_clock_stable_early = 1; /* - * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset + * We want: ktime_get_ns() + __gtod_offset == sched_clock() + __sched_clock_offset */ -static __read_mostly u64 raw_offset; -static __read_mostly u64 gtod_offset; +__read_mostly u64 __sched_clock_offset; +static __read_mostly u64 __gtod_offset; struct sched_clock_data { u64 tick_raw; @@ -131,17 +131,24 @@ static void __set_sched_clock_stable(void) /* * Attempt to make the (initial) unstable->stable transition continuous. */ - raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw); + __sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw); printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n", - scd->tick_gtod, gtod_offset, - scd->tick_raw, raw_offset); + scd->tick_gtod, __gtod_offset, + scd->tick_raw, __sched_clock_offset); static_branch_enable(&__sched_clock_stable); tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); } -static void __clear_sched_clock_stable(struct work_struct *work) +static void __sched_clock_work(struct work_struct *work) +{ + static_branch_disable(&__sched_clock_stable); +} + +static DECLARE_WORK(sched_clock_work, __sched_clock_work); + +static void __clear_sched_clock_stable(void) { struct sched_clock_data *scd = this_scd(); @@ -154,17 +161,17 @@ static void __clear_sched_clock_stable(struct work_struct *work) * * Still do what we can. */ - gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod); + __gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod); printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n", - scd->tick_gtod, gtod_offset, - scd->tick_raw, raw_offset); + scd->tick_gtod, __gtod_offset, + scd->tick_raw, __sched_clock_offset); - static_branch_disable(&__sched_clock_stable); tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); -} -static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable); + if (sched_clock_stable()) + schedule_work(&sched_clock_work); +} void clear_sched_clock_stable(void) { @@ -173,7 +180,7 @@ void clear_sched_clock_stable(void) smp_mb(); /* matches sched_clock_init_late() */ if (sched_clock_running == 2) - schedule_work(&sched_clock_work); + __clear_sched_clock_stable(); } void sched_clock_init_late(void) @@ -214,7 +221,7 @@ static inline u64 wrap_max(u64 x, u64 y) */ static u64 sched_clock_local(struct sched_clock_data *scd) { - u64 now, clock, old_clock, min_clock, max_clock; + u64 now, clock, old_clock, min_clock, max_clock, gtod; s64 delta; again: @@ -231,9 +238,10 @@ again: * scd->tick_gtod + TICK_NSEC); */ - clock = scd->tick_gtod + gtod_offset + delta; - min_clock = wrap_max(scd->tick_gtod, old_clock); - max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC); + gtod = scd->tick_gtod + __gtod_offset; + clock = gtod + delta; + min_clock = wrap_max(gtod, old_clock); + max_clock = wrap_max(old_clock, gtod + TICK_NSEC); clock = wrap_max(clock, min_clock); clock = wrap_min(clock, max_clock); @@ -317,7 +325,7 @@ u64 sched_clock_cpu(int cpu) u64 clock; if (sched_clock_stable()) - return sched_clock() + raw_offset; + return sched_clock() + __sched_clock_offset; if (unlikely(!sched_clock_running)) return 0ull; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 956383844116..3b31fc05a0f1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3287,10 +3287,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) struct task_struct *p; /* - * Optimization: we know that if all tasks are in - * the fair class we can call that function directly: + * Optimization: we know that if all tasks are in the fair class we can + * call that function directly, but only if the @prev task wasn't of a + * higher scheduling class, because otherwise those loose the + * opportunity to pull in more work from other CPUs. */ - if (likely(rq->nr_running == rq->cfs.h_nr_running)) { + if (likely((prev->sched_class == &idle_sched_class || + prev->sched_class == &fair_sched_class) && + rq->nr_running == rq->cfs.h_nr_running)) { + p = fair_sched_class.pick_next_task(rq, prev, rf); if (unlikely(p == RETRY_TASK)) goto again; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 8f8de3d4d6b7..54c577578da6 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -36,6 +36,7 @@ struct sugov_policy { u64 last_freq_update_time; s64 freq_update_delay_ns; unsigned int next_freq; + unsigned int cached_raw_freq; /* The next fields are only needed if fast switch cannot be used. */ struct irq_work irq_work; @@ -52,7 +53,6 @@ struct sugov_cpu { struct update_util_data update_util; struct sugov_policy *sg_policy; - unsigned int cached_raw_freq; unsigned long iowait_boost; unsigned long iowait_boost_max; u64 last_update; @@ -116,7 +116,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, /** * get_next_freq - Compute a new frequency for a given cpufreq policy. - * @sg_cpu: schedutil cpu object to compute the new frequency for. + * @sg_policy: schedutil policy object to compute the new frequency for. * @util: Current CPU utilization. * @max: CPU capacity. * @@ -136,19 +136,18 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, * next_freq (as calculated above) is returned, subject to policy min/max and * cpufreq driver limitations. */ -static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util, - unsigned long max) +static unsigned int get_next_freq(struct sugov_policy *sg_policy, + unsigned long util, unsigned long max) { - struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; unsigned int freq = arch_scale_freq_invariant() ? policy->cpuinfo.max_freq : policy->cur; freq = (freq + (freq >> 2)) * util / max; - if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX) + if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX) return sg_policy->next_freq; - sg_cpu->cached_raw_freq = freq; + sg_policy->cached_raw_freq = freq; return cpufreq_driver_resolve_freq(policy, freq); } @@ -213,7 +212,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, } else { sugov_get_util(&util, &max); sugov_iowait_boost(sg_cpu, &util, &max); - next_f = get_next_freq(sg_cpu, util, max); + next_f = get_next_freq(sg_policy, util, max); } sugov_update_commit(sg_policy, time, next_f); } @@ -267,7 +266,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, sugov_iowait_boost(j_sg_cpu, &util, &max); } - return get_next_freq(sg_cpu, util, max); + return get_next_freq(sg_policy, util, max); } static void sugov_update_shared(struct update_util_data *hook, u64 time, @@ -580,25 +579,19 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->next_freq = UINT_MAX; sg_policy->work_in_progress = false; sg_policy->need_freq_update = false; + sg_policy->cached_raw_freq = 0; for_each_cpu(cpu, policy->cpus) { struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); + memset(sg_cpu, 0, sizeof(*sg_cpu)); sg_cpu->sg_policy = sg_policy; - if (policy_is_shared(policy)) { - sg_cpu->util = 0; - sg_cpu->max = 0; - sg_cpu->flags = SCHED_CPUFREQ_RT; - sg_cpu->last_update = 0; - sg_cpu->cached_raw_freq = 0; - sg_cpu->iowait_boost = 0; - sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; - cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, - sugov_update_shared); - } else { - cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, - sugov_update_single); - } + sg_cpu->flags = SCHED_CPUFREQ_RT; + sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; + cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, + policy_is_shared(policy) ? + sugov_update_shared : + sugov_update_single); } return 0; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 99b2c33a9fbc..a2ce59015642 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -445,13 +445,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * * This function returns true if: * - * runtime / (deadline - t) > dl_runtime / dl_period , + * runtime / (deadline - t) > dl_runtime / dl_deadline , * * IOW we can't recycle current parameters. * - * Notice that the bandwidth check is done against the period. For + * Notice that the bandwidth check is done against the deadline. For * task with deadline equal to period this is the same of using - * dl_deadline instead of dl_period in the equation above. + * dl_period instead of dl_deadline in the equation above. */ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, struct sched_dl_entity *pi_se, u64 t) @@ -476,7 +476,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, * of anything below microseconds resolution is actually fiction * (but still we want to give the user that illusion >;). */ - left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) * (pi_se->dl_runtime >> DL_SCALE); @@ -505,10 +505,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, } } +static inline u64 dl_next_period(struct sched_dl_entity *dl_se) +{ + return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period; +} + /* * If the entity depleted all its runtime, and if we want it to sleep * while waiting for some new execution time to become available, we - * set the bandwidth enforcement timer to the replenishment instant + * set the bandwidth replenishment timer to the replenishment instant * and try to activate it. * * Notice that it is important for the caller to know if the timer @@ -530,7 +535,7 @@ static int start_dl_timer(struct task_struct *p) * that it is actually coming from rq->clock and not from * hrtimer's time base reading. */ - act = ns_to_ktime(dl_se->deadline); + act = ns_to_ktime(dl_next_period(dl_se)); now = hrtimer_cb_get_time(timer); delta = ktime_to_ns(now) - rq_clock(rq); act = ktime_add_ns(act, delta); @@ -638,6 +643,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) lockdep_unpin_lock(&rq->lock, rf.cookie); rq = dl_task_offline_migration(rq, p); rf.cookie = lockdep_pin_lock(&rq->lock); + update_rq_clock(rq); /* * Now that the task has been migrated to the new RQ and we @@ -689,6 +695,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) timer->function = dl_task_timer; } +/* + * During the activation, CBS checks if it can reuse the current task's + * runtime and period. If the deadline of the task is in the past, CBS + * cannot use the runtime, and so it replenishes the task. This rule + * works fine for implicit deadline tasks (deadline == period), and the + * CBS was designed for implicit deadline tasks. However, a task with + * constrained deadline (deadine < period) might be awakened after the + * deadline, but before the next period. In this case, replenishing the + * task would allow it to run for runtime / deadline. As in this case + * deadline < period, CBS enables a task to run for more than the + * runtime / period. In a very loaded system, this can cause a domino + * effect, making other tasks miss their deadlines. + * + * To avoid this problem, in the activation of a constrained deadline + * task after the deadline but before the next period, throttle the + * task and set the replenishing timer to the begin of the next period, + * unless it is boosted. + */ +static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) +{ + struct task_struct *p = dl_task_of(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se)); + + if (dl_time_before(dl_se->deadline, rq_clock(rq)) && + dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { + if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) + return; + dl_se->dl_throttled = 1; + } +} + static int dl_runtime_exceeded(struct sched_dl_entity *dl_se) { @@ -922,6 +959,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) __dequeue_dl_entity(dl_se); } +static inline bool dl_is_constrained(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_deadline < dl_se->dl_period; +} + static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { struct task_struct *pi_task = rt_mutex_get_top_task(p); @@ -948,6 +990,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) } /* + * Check if a constrained deadline task was activated + * after the deadline but before the next period. + * If that is the case, the task will be throttled and + * the replenishment timer will be set to the next period. + */ + if (!p->dl.dl_throttled && dl_is_constrained(&p->dl)) + dl_check_constrained_dl(&p->dl); + + /* * If p is throttled, we do nothing. In fact, if it exhausted * its budget it needs a replenishment and, since it now is on * its rq, the bandwidth timer callback (which clearly has not diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3e88b35ac157..dea138964b91 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5799,7 +5799,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t * Due to large variance we need a large fuzz factor; hackbench in * particularly is sensitive here. */ - if ((avg_idle / 512) < avg_cost) + if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost) return -1; time = local_clock(); diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 69631fa46c2f..1b3c8189b286 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -51,6 +51,11 @@ SCHED_FEAT(NONTASK_CAPACITY, true) */ SCHED_FEAT(TTWU_QUEUE, true) +/* + * When doing wakeups, attempt to limit superfluous scans of the LLC domain. + */ +SCHED_FEAT(SIS_AVG_CPU, false) + #ifdef HAVE_RT_PUSH_IPI /* * In order to avoid a thundering herd attack of CPUs that are diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 7296b7308eca..f15fb2bdbc0d 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -169,7 +169,7 @@ static inline int calc_load_write_idx(void) * If the folding window started, make sure we start writing in the * next idle-delta. */ - if (!time_before(jiffies, calc_load_update)) + if (!time_before(jiffies, READ_ONCE(calc_load_update))) idx++; return idx & 1; @@ -202,8 +202,9 @@ void calc_load_exit_idle(void) struct rq *this_rq = this_rq(); /* - * If we're still before the sample window, we're done. + * If we're still before the pending sample window, we're done. */ + this_rq->calc_load_update = READ_ONCE(calc_load_update); if (time_before(jiffies, this_rq->calc_load_update)) return; @@ -212,7 +213,6 @@ void calc_load_exit_idle(void) * accounted through the nohz accounting, so skip the entire deal and * sync up for the next window. */ - this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update + 10)) this_rq->calc_load_update += LOAD_FREQ; } @@ -308,13 +308,15 @@ calc_load_n(unsigned long load, unsigned long exp, */ static void calc_global_nohz(void) { + unsigned long sample_window; long delta, active, n; - if (!time_before(jiffies, calc_load_update + 10)) { + sample_window = READ_ONCE(calc_load_update); + if (!time_before(jiffies, sample_window + 10)) { /* * Catch-up, fold however many we are behind still */ - delta = jiffies - calc_load_update - 10; + delta = jiffies - sample_window - 10; n = 1 + (delta / LOAD_FREQ); active = atomic_long_read(&calc_load_tasks); @@ -324,7 +326,7 @@ static void calc_global_nohz(void) avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); - calc_load_update += n * LOAD_FREQ; + WRITE_ONCE(calc_load_update, sample_window + n * LOAD_FREQ); } /* @@ -352,9 +354,11 @@ static inline void calc_global_nohz(void) { } */ void calc_global_load(unsigned long ticks) { + unsigned long sample_window; long active, delta; - if (time_before(jiffies, calc_load_update + 10)) + sample_window = READ_ONCE(calc_load_update); + if (time_before(jiffies, sample_window + 10)) return; /* @@ -371,7 +375,7 @@ void calc_global_load(unsigned long ticks) avenrun[1] = calc_load(avenrun[1], EXP_5, active); avenrun[2] = calc_load(avenrun[2], EXP_15, active); - calc_load_update += LOAD_FREQ; + WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ); /* * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk. diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 4d2ea6f25568..b8c84c6dee64 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -242,6 +242,45 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) } EXPORT_SYMBOL(prepare_to_wait_event); +/* + * Note! These two wait functions are entered with the + * wait-queue lock held (and interrupts off in the _irq + * case), so there is no race with testing the wakeup + * condition in the caller before they add the wait + * entry to the wake queue. + */ +int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait) +{ + if (likely(list_empty(&wait->task_list))) + __add_wait_queue_tail(wq, wait); + + set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) + return -ERESTARTSYS; + + spin_unlock(&wq->lock); + schedule(); + spin_lock(&wq->lock); + return 0; +} +EXPORT_SYMBOL(do_wait_intr); + +int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait) +{ + if (likely(list_empty(&wait->task_list))) + __add_wait_queue_tail(wq, wait); + + set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) + return -ERESTARTSYS; + + spin_unlock_irq(&wq->lock); + schedule(); + spin_lock_irq(&wq->lock); + return 0; +} +EXPORT_SYMBOL(do_wait_intr_irq); + /** * finish_wait - clean up after waiting in a queue * @q: waitqueue waited on diff --git a/kernel/sysctl.c b/kernel/sysctl.c index acf0a5a06da7..8c8714fcb53c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2133,9 +2133,12 @@ static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, if (write) { if (*negp) return -EINVAL; + if (*lvalp > UINT_MAX) + return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; + *negp = false; *lvalp = (unsigned long)val; } return 0; diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 7906b3f0c41a..497719127bf9 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -125,7 +125,7 @@ int register_refined_jiffies(long cycles_per_second) shift_hz += cycles_per_tick/2; do_div(shift_hz, cycles_per_tick); /* Calculate nsec_per_tick using shift_hz */ - nsec_per_tick = (u64)TICK_NSEC << 8; + nsec_per_tick = (u64)NSEC_PER_SEC << 8; nsec_per_tick += (u32)shift_hz/2; do_div(nsec_per_tick, (u32)shift_hz); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d5038005eb5d..d4a06e714645 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -429,7 +429,7 @@ config BLK_DEV_IO_TRACE If unsure, say N. -config KPROBE_EVENT +config KPROBE_EVENTS depends on KPROBES depends on HAVE_REGS_AND_STACK_ACCESS_API bool "Enable kprobes-based dynamic events" @@ -447,7 +447,7 @@ config KPROBE_EVENT This option is also required by perf-probe subcommand of perf tools. If you want to use perf tools, this option is strongly recommended. -config UPROBE_EVENT +config UPROBE_EVENTS bool "Enable uprobes-based dynamic events" depends on ARCH_SUPPORTS_UPROBES depends on MMU @@ -466,7 +466,7 @@ config UPROBE_EVENT config BPF_EVENTS depends on BPF_SYSCALL - depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS + depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS bool default y help diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index e57980845549..90f2701d92a7 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -57,7 +57,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o -obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o +obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM),y) obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o @@ -66,7 +66,7 @@ ifeq ($(CONFIG_TRACING),y) obj-$(CONFIG_KGDB_KDB) += trace_kdb.o endif obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o -obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o +obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 0d1597c9ee30..dd3e91d68dc7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3755,23 +3755,24 @@ static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash) ftrace_probe_registered = 1; } -static void __disable_ftrace_function_probe(void) +static bool __disable_ftrace_function_probe(void) { int i; if (!ftrace_probe_registered) - return; + return false; for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { struct hlist_head *hhd = &ftrace_func_hash[i]; if (hhd->first) - return; + return false; } /* no more funcs left */ ftrace_shutdown(&trace_probe_ops, 0); ftrace_probe_registered = 0; + return true; } @@ -3901,6 +3902,7 @@ static void __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data, int flags) { + struct ftrace_ops_hash old_hash_ops; struct ftrace_func_entry *rec_entry; struct ftrace_func_probe *entry; struct ftrace_func_probe *p; @@ -3912,6 +3914,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, struct hlist_node *tmp; char str[KSYM_SYMBOL_LEN]; int i, ret; + bool disabled; if (glob && (strcmp(glob, "*") == 0 || !strlen(glob))) func_g.search = NULL; @@ -3930,6 +3933,10 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, mutex_lock(&trace_probe_ops.func_hash->regex_lock); + old_hash_ops.filter_hash = old_hash; + /* Probes only have filters */ + old_hash_ops.notrace_hash = NULL; + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); if (!hash) /* Hmm, should report this somehow */ @@ -3967,12 +3974,17 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, } } mutex_lock(&ftrace_lock); - __disable_ftrace_function_probe(); + disabled = __disable_ftrace_function_probe(); /* * Remove after the disable is called. Otherwise, if the last * probe is removed, a null hash means *all enabled*. */ ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash); + + /* still need to update the function call sites */ + if (ftrace_enabled && !disabled) + ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS, + &old_hash_ops); synchronize_sched(); if (!ret) free_ftrace_hash_rcu(old_hash); @@ -4416,16 +4428,24 @@ static int __init set_graph_notrace_function(char *str) } __setup("ftrace_graph_notrace=", set_graph_notrace_function); +static int __init set_graph_max_depth_function(char *str) +{ + if (!str) + return 0; + fgraph_max_depth = simple_strtoul(str, NULL, 0); + return 1; +} +__setup("ftrace_graph_max_depth=", set_graph_max_depth_function); + static void __init set_ftrace_early_graph(char *buf, int enable) { int ret; char *func; struct ftrace_hash *hash; - if (enable) - hash = ftrace_graph_hash; - else - hash = ftrace_graph_notrace_hash; + hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS); + if (WARN_ON(!hash)) + return; while (buf) { func = strsep(&buf, ","); @@ -4435,6 +4455,11 @@ static void __init set_ftrace_early_graph(char *buf, int enable) printk(KERN_DEBUG "ftrace: function %s not " "traceable\n", func); } + + if (enable) + ftrace_graph_hash = hash; + else + ftrace_graph_notrace_hash = hash; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -5488,7 +5513,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, * Normally the mcount trampoline will call the ops->func, but there * are times that it should not. For example, if the ops does not * have its own recursion protection, then it should call the - * ftrace_ops_recurs_func() instead. + * ftrace_ops_assist_func() instead. * * Returns the function that the trampoline should call for @ops. */ @@ -5541,6 +5566,15 @@ static void clear_ftrace_pids(struct trace_array *tr) trace_free_pid_list(pid_list); } +void ftrace_clear_pids(struct trace_array *tr) +{ + mutex_lock(&ftrace_lock); + + clear_ftrace_pids(tr); + + mutex_unlock(&ftrace_lock); +} + static void ftrace_pid_reset(struct trace_array *tr) { mutex_lock(&ftrace_lock); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 96fc3c043ad6..ca47a4fa2986 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3405,11 +3405,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); int ring_buffer_iter_empty(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + struct buffer_page *head_page; + struct buffer_page *commit_page; + unsigned commit; cpu_buffer = iter->cpu_buffer; - return iter->head_page == cpu_buffer->commit_page && - iter->head == rb_commit_index(cpu_buffer); + /* Remember, trace recording is off when iterator is in use */ + reader = cpu_buffer->reader_page; + head_page = cpu_buffer->head_page; + commit_page = cpu_buffer->commit_page; + commit = rb_page_commit(commit_page); + + return ((iter->head_page == commit_page && iter->head == commit) || + (iter->head_page == reader && commit_page == head_page && + head_page->read == commit && + iter->head == rb_page_commit(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); @@ -4826,9 +4838,9 @@ static __init int test_ringbuffer(void) rb_data[cpu].cnt = cpu; rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu], "rbtester/%d", cpu); - if (WARN_ON(!rb_threads[cpu])) { + if (WARN_ON(IS_ERR(rb_threads[cpu]))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_threads[cpu]); goto out_free; } @@ -4838,9 +4850,9 @@ static __init int test_ringbuffer(void) /* Now create the rb hammer! */ rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer"); - if (WARN_ON(!rb_hammer)) { + if (WARN_ON(IS_ERR(rb_hammer))) { pr_cont("FAILED\n"); - ret = -1; + ret = PTR_ERR(rb_hammer); goto out_free; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 707445ceb7ef..0ad75e9698f6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4341,22 +4341,22 @@ static const char readme_msg[] = "\t\t\t traces\n" #endif #endif /* CONFIG_STACK_TRACER */ -#ifdef CONFIG_KPROBE_EVENT +#ifdef CONFIG_KPROBE_EVENTS " kprobe_events\t\t- Add/remove/show the kernel dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif -#ifdef CONFIG_UPROBE_EVENT +#ifdef CONFIG_UPROBE_EVENTS " uprobe_events\t\t- Add/remove/show the userspace dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif -#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT) +#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) "\t accepts: event-definitions (one definition per line)\n" "\t Format: p|r[:[<group>/]<event>] <place> [<args>]\n" "\t -:[<group>/]<event>\n" -#ifdef CONFIG_KPROBE_EVENT +#ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" #endif -#ifdef CONFIG_UPROBE_EVENT +#ifdef CONFIG_UPROBE_EVENTS "\t place: <path>:<offset>\n" #endif "\t args: <name>=fetcharg[:type]\n" @@ -6733,11 +6733,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash, return ret; out_reg: - ret = register_ftrace_function_probe(glob, ops, count); + ret = alloc_snapshot(&global_trace); + if (ret < 0) + goto out; - if (ret >= 0) - alloc_snapshot(&global_trace); + ret = register_ftrace_function_probe(glob, ops, count); + out: return ret < 0 ? ret : 0; } @@ -7402,6 +7404,7 @@ static int instance_rmdir(const char *name) tracing_set_nop(tr); event_trace_del_tracer(tr); + ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); tracefs_remove_recursive(tr->dir); free_trace_buffers(tr); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ae1cce91fead..d19d52d600d6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -896,6 +896,7 @@ int using_ftrace_ops_list_func(void); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d_tracer); +void ftrace_clear_pids(struct trace_array *tr); #else static inline int ftrace_trace_task(struct trace_array *tr) { @@ -914,6 +915,7 @@ ftrace_init_global_array_ops(struct trace_array *tr) { } static inline void ftrace_reset_array_ops(struct trace_array *tr) { } static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { } static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { } +static inline void ftrace_clear_pids(struct trace_array *tr) { } /* ftace_func_t type is not defined, use macro instead of static inline */ #define ftrace_init_array_ops(tr, func) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 0c0ae54d44c6..903273c93e61 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -248,7 +248,7 @@ ASSIGN_FETCH_FUNC(file_offset, ftype), \ #define FETCH_TYPE_STRING 0 #define FETCH_TYPE_STRSIZE 1 -#ifdef CONFIG_KPROBE_EVENT +#ifdef CONFIG_KPROBE_EVENTS struct symbol_cache; unsigned long update_symbol_cache(struct symbol_cache *sc); void free_symbol_cache(struct symbol_cache *sc); @@ -278,7 +278,7 @@ alloc_symbol_cache(const char *sym, long offset) { return NULL; } -#endif /* CONFIG_KPROBE_EVENT */ +#endif /* CONFIG_KPROBE_EVENTS */ struct probe_arg { struct fetch_param fetch; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 1d68b5b7ad41..5fb1f2c87e6b 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -65,7 +65,7 @@ void stack_trace_print(void) } /* - * When arch-specific code overides this function, the following + * When arch-specific code overrides this function, the following * data should be filled up, assuming stack_trace_max_lock is held to * prevent concurrent updates. * stack_trace_index[] diff --git a/kernel/ucount.c b/kernel/ucount.c index 62630a40ab3a..b4eeee03934f 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -144,7 +144,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) new->ns = ns; new->uid = uid; - atomic_set(&new->count, 0); + new->count = 0; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); @@ -155,8 +155,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) ucounts = new; } } - if (!atomic_add_unless(&ucounts->count, 1, INT_MAX)) + if (ucounts->count == INT_MAX) ucounts = NULL; + else + ucounts->count += 1; spin_unlock_irq(&ucounts_lock); return ucounts; } @@ -165,13 +167,15 @@ static void put_ucounts(struct ucounts *ucounts) { unsigned long flags; - if (atomic_dec_and_test(&ucounts->count)) { - spin_lock_irqsave(&ucounts_lock, flags); + spin_lock_irqsave(&ucounts_lock, flags); + ucounts->count -= 1; + if (!ucounts->count) hlist_del_init(&ucounts->node); - spin_unlock_irqrestore(&ucounts_lock, flags); + else + ucounts = NULL; + spin_unlock_irqrestore(&ucounts_lock, flags); - kfree(ucounts); - } + kfree(ucounts); } static inline bool atomic_inc_below(atomic_t *v, int u) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 072cbc9b175d..c0168b7da1ea 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1507,6 +1507,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; + WARN_ON_ONCE(!wq); WARN_ON_ONCE(timer->function != delayed_work_timer_fn || timer->data != (unsigned long)dwork); WARN_ON_ONCE(timer_pending(timer)); |