From b845c898b2f1ea458d5453f0fa1da6e2dfce3bb4 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 21 Aug 2018 15:55:00 +0200 Subject: bpf, sockmap: fix sock_hash_alloc and reject zero-sized keys Currently, it is possible to create a sock hash map with key size of 0 and have the kernel return a fd back to user space. This is invalid for hash maps (and kernel also hasn't been tested for zero key size support in general at this point). Thus, reject such configuration. Fixes: 81110384441a ("bpf: sockmap, add hash map support") Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Song Liu --- kernel/bpf/sockmap.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 98e621a29e8e..60ceb0e1fa56 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -2140,7 +2140,9 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) return ERR_PTR(-EPERM); /* check sanity of attributes */ - if (attr->max_entries == 0 || attr->value_size != 4 || + if (attr->max_entries == 0 || + attr->key_size == 0 || + attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); -- cgit v1.2.3 From eb29429d81e31b191f3b2bd19cf820279cec6463 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 22 Aug 2018 18:09:17 +0200 Subject: bpf, sockmap: fix sock hash count in alloc_sock_hash_elem When we try to allocate a new sock hash entry and the allocation fails, then sock hash map fails to reduce the map element counter, meaning we keep accounting this element although it was never used. Fix it by dropping the element counter on error. Fixes: 81110384441a ("bpf: sockmap, add hash map support") Signed-off-by: Daniel Borkmann Acked-by: John Fastabend --- kernel/bpf/sockmap.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 60ceb0e1fa56..40c6ef9fc828 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -2269,8 +2269,10 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, } l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); - if (!l_new) + if (!l_new) { + atomic_dec(&htab->count); return ERR_PTR(-ENOMEM); + } memcpy(l_new->key, key, key_size); l_new->sk = sk; -- cgit v1.2.3 From 9b2e0388bec8ec5427403e23faff3b58dd1c3200 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 22 Aug 2018 08:37:37 -0700 Subject: bpf: sockmap: write_space events need to be passed to TCP handler When sockmap code is using the stream parser it also handles the write space events in order to handle the case where (a) verdict redirects skb to another socket and (b) the sockmap then sends the skb but due to memory constraints (or other EAGAIN errors) needs to do a retry. But the initial code missed a third case where the skb_send_sock_locked() triggers an sk_wait_event(). A typically case would be when sndbuf size is exceeded. If this happens because we do not pass the write_space event to the lower layers we never wake up the event and it will wait for sndtimeo. Which as noted in ktls fix may be rather large and look like a hang to the user. To reproduce the best test is to reduce the sndbuf size and send 1B data chunks to stress the memory handling. To fix this pass the event from the upper layer to the lower layer. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- kernel/bpf/sockmap.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 40c6ef9fc828..cf5195c7c331 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1427,12 +1427,15 @@ out: static void smap_write_space(struct sock *sk) { struct smap_psock *psock; + void (*write_space)(struct sock *sk); rcu_read_lock(); psock = smap_psock_sk(sk); if (likely(psock && test_bit(SMAP_TX_RUNNING, &psock->state))) schedule_work(&psock->tx_work); + write_space = psock->save_write_space; rcu_read_unlock(); + write_space(sk); } static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) -- cgit v1.2.3 From c0203475765f827e7b2eaf0a87222d0766e2cc4b Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 22 Aug 2018 23:49:37 +0200 Subject: bpf: use per htab salt for bucket hash All BPF hash and LRU maps currently have a known and global seed we feed into jhash() which is 0. This is suboptimal, thus fix it by generating a random seed upon hashtab setup time which we can later on feed into jhash() on lookup, update and deletions. Fixes: 0f8e4bd8a1fc8 ("bpf: add hashtable type of eBPF maps") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Song Liu Reviewed-by: Eduardo Valentin --- kernel/bpf/hashtab.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 04b8eda94e7d..03cc59ee9c95 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include "percpu_freelist.h" #include "bpf_lru_list.h" @@ -41,6 +42,7 @@ struct bpf_htab { 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 */ + u32 hashrnd; }; /* each htab element is struct htab_elem + key + value */ @@ -371,6 +373,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (!htab->buckets) goto free_htab; + htab->hashrnd = get_random_int(); for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); raw_spin_lock_init(&htab->buckets[i].lock); @@ -402,9 +405,9 @@ free_htab: return ERR_PTR(err); } -static inline u32 htab_map_hash(const void *key, u32 key_len) +static inline u32 htab_map_hash(const void *key, u32 key_len, u32 hashrnd) { - return jhash(key, key_len, 0); + return jhash(key, key_len, hashrnd); } static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) @@ -470,7 +473,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); head = select_bucket(htab, hash); @@ -597,7 +600,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) if (!key) goto find_first_elem; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); head = select_bucket(htab, hash); @@ -824,7 +827,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -880,7 +883,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -945,7 +948,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -998,7 +1001,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -1071,7 +1074,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -1103,7 +1106,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; -- cgit v1.2.3 From e06fa9c16ce4b740996189fa5610eabcee734e6c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 24 Aug 2018 22:08:50 +0200 Subject: bpf, sockmap: fix potential use after free in bpf_tcp_close bpf_tcp_close() we pop the psock linkage to a map via psock_map_pop(). A parallel update on the sock hash map can happen between psock_map_pop() and lookup_elem_raw() where we override the element under link->hash / link->key. In bpf_tcp_close()'s lookup_elem_raw() we subsequently only test whether an element is present, but we do not test whether the element is infact the element we were looking for. We lock the sock in bpf_tcp_close() during that time, so do we hold the lock in sock_hash_update_elem(). However, the latter locks the sock which is newly updated, not the one we're purging from the hash table. This means that while one CPU is doing the lookup from bpf_tcp_close(), another CPU is doing the map update in parallel, dropped our sock from the hlist and released the psock. Subsequently the first CPU will find the new sock and attempts to drop and release the old sock yet another time. Fix is that we need to check the elements for a match after lookup, similar as we do in the sock map. Note that the hash tab elems are freed via RCU, so access to their link->hash / link->key is fine since we're under RCU read side there. Fixes: e9db4ef6bf4c ("bpf: sockhash fix omitted bucket lock in sock_close") Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index cf5195c7c331..01879e4d599a 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -369,7 +369,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout) /* If another thread deleted this object skip deletion. * The refcnt on psock may or may not be zero. */ - if (l) { + if (l && l == link) { hlist_del_rcu(&link->hash_node); smap_release_sock(psock, link->sk); free_htab_elem(htab, link); -- cgit v1.2.3 From 15c480efab01197c965ce0562a43ffedd852b8f9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 24 Aug 2018 22:08:51 +0200 Subject: bpf, sockmap: fix psock refcount leak in bpf_tcp_recvmsg In bpf_tcp_recvmsg() we first took a reference on the psock, however once we find that there are skbs in the normal socket's receive queue we return with processing them through tcp_recvmsg(). Problem is that we leak the taken reference on the psock in that path. Given we don't really do anything with the psock at this point, move the skb_queue_empty() test before we fetch the psock to fix this case. Fixes: 8934ce2fd081 ("bpf: sockmap redirect ingress support") Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 01879e4d599a..26d8a3053407 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -912,6 +912,8 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); + if (!skb_queue_empty(&sk->sk_receive_queue)) + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); rcu_read_lock(); psock = smap_psock_sk(sk); @@ -922,9 +924,6 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, goto out; rcu_read_unlock(); - if (!skb_queue_empty(&sk->sk_receive_queue)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - lock_sock(sk); bytes_ready: while (copied != len) { -- cgit v1.2.3 From 501ca81760c204ec59b73e4a00bee5971fc0f1b1 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 24 Aug 2018 17:37:00 -0700 Subject: bpf: sockmap, decrement copied count correctly in redirect error case Currently, when a redirect occurs in sockmap and an error occurs in the redirect call we unwind the scatterlist once in the error path of bpf_tcp_sendmsg_do_redirect() and then again in sendmsg(). Then in the error path of sendmsg we decrement the copied count by the send size. However, its possible we partially sent data before the error was generated. This can happen if do_tcp_sendpages() partially sends the scatterlist before encountering a memory pressure error. If this happens we need to decrement the copied value (the value tracking how many bytes were actually sent to TCP stack) by the number of remaining bytes _not_ the entire send size. Otherwise we risk confusing userspace. Also we don't need two calls to free the scatterlist one is good enough. So remove the one in bpf_tcp_sendmsg_do_redirect() and then properly reduce copied by the number of remaining bytes which may in fact be the entire send size if no bytes were sent. To do this use bool to indicate if free_start_sg() should do mem accounting or not. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- kernel/bpf/sockmap.c | 45 ++++++++++++++++++++++----------------------- 1 file changed, 22 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 26d8a3053407..ce63e5801746 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -236,7 +236,7 @@ static int bpf_tcp_init(struct sock *sk) } static void smap_release_sock(struct smap_psock *psock, struct sock *sock); -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md); +static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge); static void bpf_tcp_release(struct sock *sk) { @@ -248,7 +248,7 @@ static void bpf_tcp_release(struct sock *sk) goto out; if (psock->cork) { - free_start_sg(psock->sock, psock->cork); + free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); psock->cork = NULL; } @@ -330,14 +330,14 @@ static void bpf_tcp_close(struct sock *sk, long timeout) close_fun = psock->save_close; if (psock->cork) { - free_start_sg(psock->sock, psock->cork); + free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); psock->cork = NULL; } list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { list_del(&md->list); - free_start_sg(psock->sock, md); + free_start_sg(psock->sock, md, true); kfree(md); } @@ -570,14 +570,16 @@ static void free_bytes_sg(struct sock *sk, int bytes, md->sg_start = i; } -static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) +static int free_sg(struct sock *sk, int start, + struct sk_msg_buff *md, bool charge) { struct scatterlist *sg = md->sg_data; int i = start, free = 0; while (sg[i].length) { free += sg[i].length; - sk_mem_uncharge(sk, sg[i].length); + if (charge) + sk_mem_uncharge(sk, sg[i].length); if (!md->skb) put_page(sg_page(&sg[i])); sg[i].length = 0; @@ -594,9 +596,9 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) return free; } -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md) +static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge) { - int free = free_sg(sk, md->sg_start, md); + int free = free_sg(sk, md->sg_start, md, charge); md->sg_start = md->sg_end; return free; @@ -604,7 +606,7 @@ static int free_start_sg(struct sock *sk, struct sk_msg_buff *md) static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md) { - return free_sg(sk, md->sg_curr, md); + return free_sg(sk, md->sg_curr, md, true); } static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md) @@ -718,7 +720,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes, list_add_tail(&r->list, &psock->ingress); sk->sk_data_ready(sk); } else { - free_start_sg(sk, r); + free_start_sg(sk, r, true); kfree(r); } @@ -752,14 +754,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send, release_sock(sk); } smap_release_sock(psock, sk); - if (unlikely(err)) - goto out; - return 0; + return err; out_rcu: rcu_read_unlock(); -out: - free_bytes_sg(NULL, send, md, false); - return err; + return 0; } static inline void bpf_md_init(struct smap_psock *psock) @@ -822,7 +820,7 @@ more_data: case __SK_PASS: err = bpf_tcp_push(sk, send, m, flags, true); if (unlikely(err)) { - *copied -= free_start_sg(sk, m); + *copied -= free_start_sg(sk, m, true); break; } @@ -845,16 +843,17 @@ more_data: lock_sock(sk); if (unlikely(err < 0)) { - free_start_sg(sk, m); + int free = free_start_sg(sk, m, false); + psock->sg_size = 0; if (!cork) - *copied -= send; + *copied -= free; } else { psock->sg_size -= send; } if (cork) { - free_start_sg(sk, m); + free_start_sg(sk, m, true); psock->sg_size = 0; kfree(m); m = NULL; @@ -1121,7 +1120,7 @@ wait_for_memory: err = sk_stream_wait_memory(sk, &timeo); if (err) { if (m && m != psock->cork) - free_start_sg(sk, m); + free_start_sg(sk, m, true); goto out_err; } } @@ -1580,13 +1579,13 @@ static void smap_gc_work(struct work_struct *w) bpf_prog_put(psock->bpf_tx_msg); if (psock->cork) { - free_start_sg(psock->sock, psock->cork); + free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); } list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { list_del(&md->list); - free_start_sg(psock->sock, md); + free_start_sg(psock->sock, md, true); kfree(md); } -- cgit v1.2.3 From cb9d7fd51d9fbb329d182423bd7b92d0f8cb0e01 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Tue, 21 Aug 2018 17:25:07 +0200 Subject: watchdog: Mark watchdog touch functions as notrace Some architectures need to use stop_machine() to patch functions for ftrace, and the assumption is that the stopped CPUs do not make function calls to traceable functions when they are in the stopped state. Commit ce4f06dcbb5d ("stop_machine: Touch_nmi_watchdog() after MULTI_STOP_PREPARE") added calls to the watchdog touch functions from the stopped CPUs and those functions lack notrace annotations. This leads to crashes when enabling/disabling ftrace on ARM kernels built with the Thumb-2 instruction set. Fix it by adding the necessary notrace annotations. Fixes: ce4f06dcbb5d ("stop_machine: Touch_nmi_watchdog() after MULTI_STOP_PREPARE") Signed-off-by: Vincent Whitchurch Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: oleg@redhat.com Cc: tj@kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180821152507.18313-1-vincent.whitchurch@axis.com --- kernel/watchdog.c | 4 ++-- kernel/watchdog_hld.c | 2 +- kernel/workqueue.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5470dce212c0..977918d5d350 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -261,7 +261,7 @@ static void __touch_watchdog(void) * entering idle state. This should only be used for scheduler events. * Use touch_softlockup_watchdog() for everything else. */ -void touch_softlockup_watchdog_sched(void) +notrace void touch_softlockup_watchdog_sched(void) { /* * Preemption can be enabled. It doesn't matter which CPU's timestamp @@ -270,7 +270,7 @@ void touch_softlockup_watchdog_sched(void) raw_cpu_write(watchdog_touch_ts, 0); } -void touch_softlockup_watchdog(void) +notrace void touch_softlockup_watchdog(void) { touch_softlockup_watchdog_sched(); wq_watchdog_touch(raw_smp_processor_id()); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 1f7020d65d0a..71381168dede 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -29,7 +29,7 @@ static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; static atomic_t watchdog_cpus = ATOMIC_INIT(0); -void arch_touch_nmi_watchdog(void) +notrace void arch_touch_nmi_watchdog(void) { /* * Using __raw here because some code paths have diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 60e80198c3df..0280deac392e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5574,7 +5574,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) mod_timer(&wq_watchdog_timer, jiffies + thresh); } -void wq_watchdog_touch(int cpu) +notrace void wq_watchdog_touch(int cpu) { if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; -- cgit v1.2.3 From 13ba17bee18e321b073b49a88dcab10881f757da Mon Sep 17 00:00:00 2001 From: Mukesh Ojha Date: Fri, 24 Aug 2018 18:03:53 +0530 Subject: notifier: Remove notifier header file wherever not used The conversion of the hotplug notifiers to a state machine left the notifier.h includes around in some places. Remove them. Signed-off-by: Mukesh Ojha Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/1535114033-4605-1-git-send-email-mojha@codeaurora.org --- fs/buffer.c | 1 - kernel/printk/printk.c | 1 - lib/percpu_counter.c | 1 - mm/page-writeback.c | 1 - mm/page_alloc.c | 1 - mm/slub.c | 1 - net/core/dev.c | 1 - 7 files changed, 7 deletions(-) (limited to 'kernel') diff --git a/fs/buffer.c b/fs/buffer.c index 4cc679d5bf58..6f1ae3ac9789 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -39,7 +39,6 @@ #include #include #include -#include #include #include #include diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 924e37fb1620..fd6f8ed28e01 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -38,7 +38,6 @@ #include #include #include -#include #include #include #include diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index c72577e472f2..a66595ba5543 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -4,7 +4,6 @@ */ #include -#include #include #include #include diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6551d3b0dc30..84ae9bf5858a 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e75865d58ba7..05e983f42316 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -32,7 +32,6 @@ #include #include #include -#include #include #include #include diff --git a/mm/slub.c b/mm/slub.c index ce2b9e5cea77..8da34a8af53d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -19,7 +19,6 @@ #include #include "slab.h" #include -#include #include #include #include diff --git a/net/core/dev.c b/net/core/dev.c index 325fc5088370..82114e1111e6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -93,7 +93,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 6fb86d97207880c1286cd4cb3a7e6a598afbc727 Mon Sep 17 00:00:00 2001 From: Mukesh Ojha Date: Tue, 28 Aug 2018 12:24:54 +0530 Subject: cpu/hotplug: Remove skip_onerr field from cpuhp_step structure When notifiers were there, `skip_onerr` was used to avoid calling particular step startup/teardown callbacks in the CPU up/down rollback path, which made the hotplug asymmetric. As notifiers are gone now after the full state machine conversion, the `skip_onerr` field is no longer required. Remove it from the structure and its usage. Signed-off-by: Mukesh Ojha Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1535439294-31426-1-git-send-email-mojha@codeaurora.org --- kernel/cpu.c | 26 ++++---------------------- 1 file changed, 4 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/kernel/cpu.c b/kernel/cpu.c index ed44d7d34c2d..aa7fe85ad62e 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -102,8 +102,6 @@ static inline void cpuhp_lock_release(bool bringup) { } * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step - * @skip_onerr: Do not invoke the functions on error rollback - * Will go away once the notifiers are gone * @cant_stop: Bringup/teardown can't be stopped at this step */ struct cpuhp_step { @@ -119,7 +117,6 @@ struct cpuhp_step { struct hlist_node *node); } teardown; struct hlist_head list; - bool skip_onerr; bool cant_stop; bool multi_instance; }; @@ -550,12 +547,8 @@ static int bringup_cpu(unsigned int cpu) static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { - for (st->state--; st->state > st->target; st->state--) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); - } + for (st->state--; st->state > st->target; st->state--) + cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, @@ -644,12 +637,6 @@ static void cpuhp_thread_fun(unsigned int cpu) WARN_ON_ONCE(!cpuhp_is_ap_state(state)); - if (st->rollback) { - struct cpuhp_step *step = cpuhp_get_step(state); - if (step->skip_onerr) - goto next; - } - if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); @@ -673,7 +660,6 @@ static void cpuhp_thread_fun(unsigned int cpu) st->should_run = false; } -next: cpuhp_lock_release(bringup); if (!st->should_run) @@ -916,12 +902,8 @@ void cpuhp_report_idle_dead(void) static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) { - for (st->state++; st->state < st->target; st->state++) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); - } + for (st->state++; st->state < st->target; st->state++) + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, -- cgit v1.2.3 From c1d0af1a1d5dfde880f588eceb4c00710e0f60ff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Aug 2018 08:07:52 +0200 Subject: kernel/dma/direct: take DMA offset into account in dma_direct_supported When a device has a DMA offset the dma capable result will change due to the difference between the physical and DMA address. Take that into account. Signed-off-by: Christoph Hellwig Reviewed-by: Benjamin Herrenschmidt Reviewed-by: Robin Murphy --- kernel/dma/direct.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 1c35b7b945d0..de87b0282e74 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -168,7 +168,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, int dma_direct_supported(struct device *dev, u64 mask) { #ifdef CONFIG_ZONE_DMA - if (mask < DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + if (mask < phys_to_dma(dev, DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))) return 0; #else /* @@ -177,7 +177,7 @@ int dma_direct_supported(struct device *dev, u64 mask) * memory, or by providing a ZONE_DMA32. If neither is the case, the * architecture needs to use an IOMMU instead of the direct mapping. */ - if (mask < DMA_BIT_MASK(32)) + if (mask < phys_to_dma(dev, DMA_BIT_MASK(32))) return 0; #endif /* -- cgit v1.2.3 From 597222f72a94118f593e4f32bf58ae7e049a0df1 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 30 Aug 2018 21:25:02 -0700 Subject: bpf: avoid misuse of psock when TCP_ULP_BPF collides with another ULP Currently we check sk_user_data is non NULL to determine if the sk exists in a map. However, this is not sufficient to ensure the psock or the ULP ops are not in use by another user, such as kcm or TLS. To avoid this when adding a sock to a map also verify it is of the correct ULP type. Additionally, when releasing a psock verify that it is the TCP_ULP_BPF type before releasing the ULP. The error case where we abort an update due to ULP collision can cause this error path. For example, __sock_map_ctx_update_elem() [...] err = tcp_set_ulp_id(sock, TCP_ULP_BPF) <- collides with TLS if (err) <- so err out here goto out_free [...] out_free: smap_release_sock() <- calling tcp_cleanup_ulp releases the TLS ULP incorrectly. Fixes: 2f857d04601a ("bpf: sockmap, remove STRPARSER map_flags and add multi-map support") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- kernel/bpf/sockmap.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index ce63e5801746..488ef9663c01 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1462,10 +1462,16 @@ static void smap_destroy_psock(struct rcu_head *rcu) schedule_work(&psock->gc_work); } +static bool psock_is_smap_sk(struct sock *sk) +{ + return inet_csk(sk)->icsk_ulp_ops == &bpf_tcp_ulp_ops; +} + static void smap_release_sock(struct smap_psock *psock, struct sock *sock) { if (refcount_dec_and_test(&psock->refcnt)) { - tcp_cleanup_ulp(sock); + if (psock_is_smap_sk(sock)) + tcp_cleanup_ulp(sock); write_lock_bh(&sock->sk_callback_lock); smap_stop_sock(psock, sock); write_unlock_bh(&sock->sk_callback_lock); @@ -1892,6 +1898,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, * doesn't update user data. */ if (psock) { + if (!psock_is_smap_sk(sock)) { + err = -EBUSY; + goto out_progs; + } if (READ_ONCE(psock->bpf_parse) && parse) { err = -EBUSY; goto out_progs; -- cgit v1.2.3 From 1ed0cc5a01a4d868d9907ce96468c4b4c6709556 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Tue, 4 Sep 2018 15:45:41 -0700 Subject: mm: respect arch_dup_mmap() return value Commit d70f2a14b72a ("include/linux/sched/mm.h: uninline mmdrop_async(), etc") ignored the return value of arch_dup_mmap(). As a result, on x86, a failure to duplicate the LDT (e.g. due to memory allocation error) would leave the duplicated memory mapping in an inconsistent state. Fix by using the return value, as it was before the change. Link: http://lkml.kernel.org/r/20180823051229.211856-1-namit@vmware.com Fixes: d70f2a14b72a4 ("include/linux/sched/mm.h: uninline mmdrop_async(), etc") Signed-off-by: Nadav Amit Acked-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index d896e9ca38b0..f0b58479534f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -550,8 +550,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto out; } /* a new mm has just been created */ - arch_dup_mmap(oldmm, mm); - retval = 0; + retval = arch_dup_mmap(oldmm, mm); out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); -- cgit v1.2.3 From f8b7530aa0a1def79c93101216b5b17cf408a70a Mon Sep 17 00:00:00 2001 From: Neeraj Upadhyay Date: Wed, 5 Sep 2018 11:22:07 +0530 Subject: cpu/hotplug: Adjust misplaced smb() in cpuhp_thread_fun() The smp_mb() in cpuhp_thread_fun() is misplaced. It needs to be after the load of st->should_run to prevent reordering of the later load/stores w.r.t. the load of st->should_run. Fixes: 4dddfb5faa61 ("smp/hotplug: Rewrite AP state machine core") Signed-off-by: Neeraj Upadhyay Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: josh@joshtriplett.org Cc: peterz@infradead.org Cc: jiangshanlai@gmail.com Cc: dzickus@redhat.com Cc: brendan.jackman@arm.com Cc: malat@debian.org Cc: mojha@codeaurora.org Cc: sramana@codeaurora.org Cc: linux-arm-msm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1536126727-11629-1-git-send-email-neeraju@codeaurora.org --- kernel/cpu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cpu.c b/kernel/cpu.c index aa7fe85ad62e..eb4041f78073 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -607,15 +607,15 @@ static void cpuhp_thread_fun(unsigned int cpu) bool bringup = st->bringup; enum cpuhp_state state; + if (WARN_ON_ONCE(!st->should_run)) + return; + /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (WARN_ON_ONCE(!st->should_run)) - return; - cpuhp_lock_acquire(bringup); if (st->single) { -- cgit v1.2.3 From 69fa6eb7d6a64801ea261025cce9723d9442d773 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 6 Sep 2018 15:21:38 +0200 Subject: cpu/hotplug: Prevent state corruption on error rollback When a teardown callback fails, the CPU hotplug code brings the CPU back to the previous state. The previous state becomes the new target state. The rollback happens in undo_cpu_down() which increments the state unconditionally even if the state is already the same as the target. As a consequence the next CPU hotplug operation will start at the wrong state. This is easily to observe when __cpu_disable() fails. Prevent the unconditional undo by checking the state vs. target before incrementing state and fix up the consequently wrong conditional in the unplug code which handles the failure of the final CPU take down on the control CPU side. Fixes: 4dddfb5faa61 ("smp/hotplug: Rewrite AP state machine core") Reported-by: Neeraj Upadhyay Signed-off-by: Thomas Gleixner Tested-by: Geert Uytterhoeven Tested-by: Sudeep Holla Tested-by: Neeraj Upadhyay Cc: josh@joshtriplett.org Cc: peterz@infradead.org Cc: jiangshanlai@gmail.com Cc: dzickus@redhat.com Cc: brendan.jackman@arm.com Cc: malat@debian.org Cc: sramana@codeaurora.org Cc: linux-arm-msm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1809051419580.1416@nanos.tec.linutronix.de ---- --- kernel/cpu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cpu.c b/kernel/cpu.c index eb4041f78073..0097acec1c71 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -916,7 +916,8 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); if (ret) { st->target = prev_state; - undo_cpu_down(cpu, st); + if (st->state < prev_state) + undo_cpu_down(cpu, st); break; } } @@ -969,7 +970,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); - if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { + if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) { cpuhp_reset_state(st, prev_state); __cpuhp_kick_ap(st); } -- cgit v1.2.3 From d1c392c9e2a301f38998a353f467f76414e38725 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 5 Sep 2018 16:29:49 -0400 Subject: printk/tracing: Do not trace printk_nmi_enter() I hit the following splat in my tests: ------------[ cut here ]------------ IRQs not enabled as expected WARNING: CPU: 3 PID: 0 at kernel/time/tick-sched.c:982 tick_nohz_idle_enter+0x44/0x8c Modules linked in: ip6t_REJECT nf_reject_ipv6 ip6table_filter ip6_tables ipv6 CPU: 3 PID: 0 Comm: swapper/3 Not tainted 4.19.0-rc2-test+ #2 Hardware name: MSI MS-7823/CSM-H87M-G43 (MS-7823), BIOS V1.6 02/22/2014 EIP: tick_nohz_idle_enter+0x44/0x8c Code: ec 05 00 00 00 75 26 83 b8 c0 05 00 00 00 75 1d 80 3d d0 36 3e c1 00 75 14 68 94 63 12 c1 c6 05 d0 36 3e c1 01 e8 04 ee f8 ff <0f> 0b 58 fa bb a0 e5 66 c1 e8 25 0f 04 00 64 03 1d 28 31 52 c1 8b EAX: 0000001c EBX: f26e7f8c ECX: 00000006 EDX: 00000007 ESI: f26dd1c0 EDI: 00000000 EBP: f26e7f40 ESP: f26e7f38 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010296 CR0: 80050033 CR2: 0813c6b0 CR3: 2f342000 CR4: 001406f0 Call Trace: do_idle+0x33/0x202 cpu_startup_entry+0x61/0x63 start_secondary+0x18e/0x1ed startup_32_smp+0x164/0x168 irq event stamp: 18773830 hardirqs last enabled at (18773829): [] trace_hardirqs_on_thunk+0xc/0x10 hardirqs last disabled at (18773830): [] trace_hardirqs_off_thunk+0xc/0x10 softirqs last enabled at (18773824): [] __do_softirq+0x25f/0x2bf softirqs last disabled at (18773767): [] call_on_stack+0x45/0x4b ---[ end trace b7c64aa79e17954a ]--- After a bit of debugging, I found what was happening. This would trigger when performing "perf" with a high NMI interrupt rate, while enabling and disabling function tracer. Ftrace uses breakpoints to convert the nops at the start of functions to calls to the function trampolines. The breakpoint traps disable interrupts and this makes calls into lockdep via the trace_hardirqs_off_thunk in the entry.S code. What happens is the following: do_idle { [interrupts enabled] [interrupts disabled] TRACE_IRQS_OFF [lockdep says irqs off] [...] TRACE_IRQS_IRET test if pt_regs say return to interrupts enabled [yes] TRACE_IRQS_ON [lockdep says irqs are on] nmi_enter() { printk_nmi_enter() [traced by ftrace] [ hit ftrace breakpoint ] TRACE_IRQS_OFF [lockdep says irqs off] [...] TRACE_IRQS_IRET [return from breakpoint] test if pt_regs say interrupts enabled [no] [iret back to interrupt] [iret back to code] tick_nohz_idle_enter() { lockdep_assert_irqs_enabled() [lockdep say no!] Although interrupts are indeed enabled, lockdep thinks it is not, and since we now do asserts via lockdep, it gives a false warning. The issue here is that printk_nmi_enter() is called before lockdep_off(), which disables lockdep (for this reason) in NMIs. By simply not allowing ftrace to see printk_nmi_enter() (via notrace annotation) we keep lockdep from getting confused. Cc: stable@vger.kernel.org Fixes: 42a0bb3f71383 ("printk/nmi: generic solution for safe printk in NMI") Acked-by: Sergey Senozhatsky Acked-by: Petr Mladek Signed-off-by: Steven Rostedt (VMware) --- kernel/printk/printk_safe.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index a0a74c533e4b..0913b4d385de 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -306,12 +306,12 @@ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) return printk_safe_log_store(s, fmt, args); } -void printk_nmi_enter(void) +void notrace printk_nmi_enter(void) { this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK); } -void printk_nmi_exit(void) +void notrace printk_nmi_exit(void) { this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK); } -- cgit v1.2.3 From e2c631ba75a7e727e8db0a9d30a06bfd434adb3a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 5 Sep 2018 10:41:58 +0200 Subject: clocksource: Revert "Remove kthread" I turns out that the silly spawn kthread from worker was actually needed. clocksource_watchdog_kthread() cannot be called directly from clocksource_watchdog_work(), because clocksource_select() calls timekeeping_notify() which uses stop_machine(). One cannot use stop_machine() from a workqueue() due lock inversions wrt CPU hotplug. Revert the patch but add a comment that explain why we jump through such apparently silly hoops. Fixes: 7197e77abcb6 ("clocksource: Remove kthread") Reported-by: Siegfried Metz Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Tested-by: Niklas Cassel Tested-by: Kevin Shanahan Tested-by: viktor_jaegerskuepper@freenet.de Tested-by: Siegfried Metz Cc: rafael.j.wysocki@intel.com Cc: len.brown@intel.com Cc: diego.viola@gmail.com Cc: rui.zhang@intel.com Cc: bjorn.andersson@linaro.org Link: https://lkml.kernel.org/r/20180905084158.GR24124@hirez.programming.kicks-ass.net --- kernel/time/clocksource.c | 40 ++++++++++++++++++++++++++++++---------- 1 file changed, 30 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index f74fb00d8064..0e6e97a01942 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -133,19 +133,40 @@ static void inline clocksource_watchdog_unlock(unsigned long *flags) spin_unlock_irqrestore(&watchdog_lock, *flags); } +static int clocksource_watchdog_kthread(void *data); +static void __clocksource_change_rating(struct clocksource *cs, int rating); + /* * Interval: 0.5sec Threshold: 0.0625s */ #define WATCHDOG_INTERVAL (HZ >> 1) #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) +static void clocksource_watchdog_work(struct work_struct *work) +{ + /* + * We cannot directly run clocksource_watchdog_kthread() here, because + * clocksource_select() calls timekeeping_notify() which uses + * stop_machine(). One cannot use stop_machine() from a workqueue() due + * lock inversions wrt CPU hotplug. + * + * Also, we only ever run this work once or twice during the lifetime + * of the kernel, so there is no point in creating a more permanent + * kthread for this. + * + * If kthread_run fails the next watchdog scan over the + * watchdog_list will find the unstable clock again. + */ + kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); +} + static void __clocksource_unstable(struct clocksource *cs) { cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); cs->flags |= CLOCK_SOURCE_UNSTABLE; /* - * If the clocksource is registered clocksource_watchdog_work() will + * If the clocksource is registered clocksource_watchdog_kthread() will * re-rate and re-select. */ if (list_empty(&cs->list)) { @@ -156,7 +177,7 @@ static void __clocksource_unstable(struct clocksource *cs) if (cs->mark_unstable) cs->mark_unstable(cs); - /* kick clocksource_watchdog_work() */ + /* kick clocksource_watchdog_kthread() */ if (finished_booting) schedule_work(&watchdog_work); } @@ -166,7 +187,7 @@ static void __clocksource_unstable(struct clocksource *cs) * @cs: clocksource to be marked unstable * * This function is called by the x86 TSC code to mark clocksources as unstable; - * it defers demotion and re-selection to a work. + * it defers demotion and re-selection to a kthread. */ void clocksource_mark_unstable(struct clocksource *cs) { @@ -391,9 +412,7 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs) } } -static void __clocksource_change_rating(struct clocksource *cs, int rating); - -static int __clocksource_watchdog_work(void) +static int __clocksource_watchdog_kthread(void) { struct clocksource *cs, *tmp; unsigned long flags; @@ -418,12 +437,13 @@ static int __clocksource_watchdog_work(void) return select; } -static void clocksource_watchdog_work(struct work_struct *work) +static int clocksource_watchdog_kthread(void *data) { mutex_lock(&clocksource_mutex); - if (__clocksource_watchdog_work()) + if (__clocksource_watchdog_kthread()) clocksource_select(); mutex_unlock(&clocksource_mutex); + return 0; } static bool clocksource_is_watchdog(struct clocksource *cs) @@ -442,7 +462,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static void clocksource_select_watchdog(bool fallback) { } static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } static inline void clocksource_resume_watchdog(void) { } -static inline int __clocksource_watchdog_work(void) { return 0; } +static inline int __clocksource_watchdog_kthread(void) { return 0; } static bool clocksource_is_watchdog(struct clocksource *cs) { return false; } void clocksource_mark_unstable(struct clocksource *cs) { } @@ -810,7 +830,7 @@ static int __init clocksource_done_booting(void) /* * Run the watchdog first to eliminate unstable clock sources */ - __clocksource_watchdog_work(); + __clocksource_watchdog_kthread(); clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; -- cgit v1.2.3