From ed2b82c03dc187018307c7c6bf9299705f3db383 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Fri, 29 Jun 2018 14:48:20 +0200 Subject: bpf: hash map: decrement counter on error Decrement the number of elements in the map in case the allocation of a new node fails. Fixes: 6c9059817432 ("bpf: pre-allocate hash map elements") Signed-off-by: Mauricio Vasquez B Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/hashtab.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3ca2198a6d22..513d9dfcf4ee 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, * old element will be freed immediately. * Otherwise return an error */ - atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); + l_new = ERR_PTR(-E2BIG); + goto dec_count; } l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); - if (!l_new) - return ERR_PTR(-ENOMEM); + if (!l_new) { + l_new = ERR_PTR(-ENOMEM); + goto dec_count; + } } memcpy(l_new->key, key, key_size); @@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, GFP_ATOMIC | __GFP_NOWARN); if (!pptr) { kfree(l_new); - return ERR_PTR(-ENOMEM); + l_new = ERR_PTR(-ENOMEM); + goto dec_count; } } @@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new->hash = hash; return l_new; +dec_count: + atomic_dec(&htab->count); + return l_new; } static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, -- cgit v1.2.3 From 547b3aa451ae2739585547db9fbdee11a43ff999 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:05:56 -0700 Subject: bpf: sockmap, error path can not release psock in multi-map case The current code, in the error path of sock_hash_ctx_update_elem, checks if the sock has a psock in the user data and if so decrements the reference count of the psock. However, if the error happens early in the error path we may have never incremented the psock reference count and if the psock exists because the sock is in another map then we may inadvertently decrement the reference count. Fix this by making the error path only call smap_release_sock if the error happens after the increment. Reported-by: syzbot+d464d2c20c717ef5a6a8@syzkaller.appspotmail.com Fixes: 81110384441a ("bpf: sockmap, add hash map support") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index cf7b6a6dbd1f..3847a7ce7dae 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1896,7 +1896,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); if (!e) { err = -ENOMEM; - goto out_progs; + goto out_free; } } @@ -2342,7 +2342,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, if (err) goto err; - /* bpf_map_update_elem() can be called in_irq() */ + /* psock is valid here because otherwise above *ctx_update_elem would + * have thrown an error. It is safe to skip error check. + */ + psock = smap_psock_sk(sock); raw_spin_lock_bh(&b->lock); l_old = lookup_elem_raw(head, hash, key, key_size); if (l_old && map_flags == BPF_NOEXIST) { @@ -2360,12 +2363,6 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, goto bucket_err; } - psock = smap_psock_sk(sock); - if (unlikely(!psock)) { - err = -EINVAL; - goto bucket_err; - } - rcu_assign_pointer(e->hash_link, l_new); rcu_assign_pointer(e->htab, container_of(map, struct bpf_htab, map)); @@ -2388,12 +2385,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, raw_spin_unlock_bh(&b->lock); return 0; bucket_err: + smap_release_sock(psock, sock); raw_spin_unlock_bh(&b->lock); err: kfree(e); - psock = smap_psock_sk(sock); - if (psock) - smap_release_sock(psock, sock); return err; } -- cgit v1.2.3 From 1d1ef005dbc6de673c62cbd2562290ada3090463 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:06:01 -0700 Subject: bpf: sockmap, hash table is RCU so readers do not need locks This removes locking from readers of RCU hash table. Its not necessary. Fixes: 81110384441a ("bpf: sockmap, add hash map support") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 3847a7ce7dae..00fb2e328d1b 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -2467,10 +2467,8 @@ struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - raw_spin_lock_bh(&b->lock); l = lookup_elem_raw(head, hash, key, key_size); sk = l ? l->sk : NULL; - raw_spin_unlock_bh(&b->lock); return sk; } -- cgit v1.2.3 From 99ba2b5aba24e022683a7db63204f9e306fe7ab9 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:50:04 -0700 Subject: bpf: sockhash, disallow bpf_tcp_close and update in parallel After latest lock updates there is no longer anything preventing a close and recvmsg call running in parallel. Additionally, we can race update with close if we close a socket and simultaneously update if via the BPF userspace API (note the cgroup ops are already run with sock_lock held). To resolve this take sock_lock in close and update paths. Reported-by: syzbot+b680e42077a0d7c9a0c4@syzkaller.appspotmail.com Fixes: e9db4ef6bf4c ("bpf: sockhash fix omitted bucket lock in sock_close") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 15 +++++++++++++++ kernel/bpf/syscall.c | 4 +++- 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 00fb2e328d1b..9c67e96fe336 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -312,10 +312,12 @@ static void bpf_tcp_close(struct sock *sk, long timeout) struct smap_psock *psock; struct sock *osk; + lock_sock(sk); rcu_read_lock(); psock = smap_psock_sk(sk); if (unlikely(!psock)) { rcu_read_unlock(); + release_sock(sk); return sk->sk_prot->close(sk, timeout); } @@ -371,6 +373,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout) e = psock_map_pop(sk, psock); } rcu_read_unlock(); + release_sock(sk); close_fun(sk, timeout); } @@ -2069,7 +2072,13 @@ static int sock_map_update_elem(struct bpf_map *map, return -EOPNOTSUPP; } + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); err = sock_map_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); fput(socket->file); return err; } @@ -2410,7 +2419,13 @@ static int sock_hash_update_elem(struct bpf_map *map, return -EINVAL; } + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); err = sock_hash_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); fput(socket->file); return err; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d10ecd78105f..a31a1ba0f8ea 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_update_elem(map, key, value, attr->flags); goto out; - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP) { err = map->ops->map_update_elem(map, key, value, attr->flags); goto out; } -- cgit v1.2.3 From 7ebc14d507b4b55105da8d1a1eda323381529cc7 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:50:10 -0700 Subject: bpf: sockmap, consume_skb in close path Currently, when a sock is closed and the bpf_tcp_close() callback is used we remove memory but do not free the skb. Call consume_skb() if the skb is attached to the buffer. Reported-by: syzbot+d464d2c20c717ef5a6a8@syzkaller.appspotmail.com Fixes: 1aa12bdf1bfb ("bpf: sockmap, add sock close() hook to remove socks") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 9c67e96fe336..dfc8a8a07c1f 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -571,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) while (sg[i].length) { free += sg[i].length; sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); + if (!md->skb) + put_page(sg_page(&sg[i])); sg[i].length = 0; sg[i].page_link = 0; sg[i].offset = 0; @@ -580,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) if (i == MAX_SKB_FRAGS) i = 0; } + if (md->skb) + consume_skb(md->skb); return free; } -- cgit v1.2.3 From 0ea488ff8d23c93da383fcf424825c298b13b1fb Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:50:15 -0700 Subject: bpf: sockmap, convert bpf_compute_data_pointers to bpf_*_sk_skb In commit 'bpf: bpf_compute_data uses incorrect cb structure' (8108a7751512) we added the routine bpf_compute_data_end_sk_skb() to compute the correct data_end values, but this has since been lost. In kernel v4.14 this was correct and the above patch was applied in it entirety. Then when v4.14 was merged into v4.15-rc1 net-next tree we lost the piece that renamed bpf_compute_data_pointers to the new function bpf_compute_data_end_sk_skb. This was done here, e1ea2f9856b7 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net") When it conflicted with the following rename patch, 6aaae2b6c433 ("bpf: rename bpf_compute_data_end into bpf_compute_data_pointers") Finally, after a refactor I thought even the function bpf_compute_data_end_sk_skb() was no longer needed and it was erroneously removed. However, we never reverted the sk_skb_convert_ctx_access() usage of tcp_skb_cb which had been committed and survived the merge conflict. Here we fix this by adding back the helper and *_data_end_sk_skb() usage. Using the bpf_skc_data_end mapping is not correct because it expects a qdisc_skb_cb object but at the sock layer this is not the case. Even though it happens to work here because we don't overwrite any data in-use at the socket layer and the cb structure is cleared later this has potential to create some subtle issues. But, even more concretely the filter.c access check uses tcp_skb_cb. And by some act of chance though, struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; /* 0 28 */ /* XXX 4 bytes hole, try to pack */ void * data_meta; /* 32 8 */ void * data_end; /* 40 8 */ /* size: 48, cachelines: 1, members: 3 */ /* sum members: 44, holes: 1, sum holes: 4 */ /* last cacheline: 48 bytes */ }; and then tcp_skb_cb, struct tcp_skb_cb { [...] struct { __u32 flags; /* 24 4 */ struct sock * sk_redir; /* 32 8 */ void * data_end; /* 40 8 */ } bpf; /* 24 */ }; So when we use offset_of() to track down the byte offset we get 40 in either case and everything continues to work. Fix this mess and use correct structures its unclear how long this might actually work for until someone moves the structs around. Reported-by: Martin KaFai Lau Fixes: e1ea2f9856b7 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net") Fixes: 6aaae2b6c433 ("bpf: rename bpf_compute_data_end into bpf_compute_data_pointers") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- include/net/tcp.h | 4 +++ kernel/bpf/sockmap.c | 4 +-- net/core/filter.c | 98 ++++++++++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 97 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/include/net/tcp.h b/include/net/tcp.h index 800582b5dd54..af3ec72d5d41 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -828,6 +828,10 @@ struct tcp_skb_cb { #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) +static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); +} #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index dfc8a8a07c1f..98fb7938beea 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1236,7 +1236,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) */ TCP_SKB_CB(skb)->bpf.sk_redir = NULL; skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); preempt_enable(); @@ -1491,7 +1491,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); diff --git a/net/core/filter.c b/net/core/filter.c index 3095f1ba7015..470268024a40 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1762,6 +1762,37 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = { .arg2_type = ARG_ANYTHING, }; +static inline int sk_skb_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + int err = __bpf_try_make_writable(skb, write_len); + + bpf_compute_data_end_sk_skb(skb); + return err; +} + +BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) +{ + /* Idea is the following: should the needed direct read/write + * test fail during runtime, we can pull in more data and redo + * again, since implicitly, we invalidate previous checks here. + * + * Or, since we know how much we need to make read/writeable, + * this can be done once at the program beginning for direct + * access case. By this we overcome limitations of only current + * headroom being accessible. + */ + return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); +} + +static const struct bpf_func_proto sk_skb_pull_data_proto = { + .func = sk_skb_pull_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { @@ -2864,8 +2895,8 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) return __skb_trim_rcsum(skb, new_len); } -BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, - u64, flags) +static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, + u64 flags) { u32 max_len = __bpf_skb_max_len(skb); u32 min_len = __bpf_skb_min_len(skb); @@ -2901,6 +2932,13 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, + u64, flags) +{ + int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; @@ -2915,8 +2953,26 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, +BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) +{ + int ret = __bpf_skb_change_tail(skb, new_len, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_tail_proto = { + .func = sk_skb_change_tail, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, + u64 flags) { u32 max_len = __bpf_skb_max_len(skb); u32 new_len = skb->len + head_room; @@ -2942,8 +2998,16 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, skb_reset_mac_header(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + bpf_compute_data_pointers(skb); - return 0; + return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { @@ -2955,6 +3019,23 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_head_proto = { + .func = sk_skb_change_head, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -4618,9 +4699,12 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_skb_store_bytes || func == bpf_skb_change_proto || func == bpf_skb_change_head || + func == sk_skb_change_head || func == bpf_skb_change_tail || + func == sk_skb_change_tail || func == bpf_skb_adjust_room || func == bpf_skb_pull_data || + func == sk_skb_pull_data || func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || @@ -4872,11 +4956,11 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: - return &bpf_skb_pull_data_proto; + return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: - return &bpf_skb_change_tail_proto; + return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: - return &bpf_skb_change_head_proto; + return &sk_skb_change_head_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: -- cgit v1.2.3 From d8d7218ad842e18fc6976b87c08ed749e8d56313 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 6 Jul 2018 11:49:00 +0900 Subject: xdp: XDP_REDIRECT should check IFF_UP and MTU Otherwise we end up with attempting to send packets from down devices or to send oversized packets, which may cause unexpected driver/device behaviour. Generic XDP has already done this check, so reuse the logic in native XDP. Fixes: 814abfabef3c ("xdp: add bpf_redirect helper function") Signed-off-by: Toshiaki Makita Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 6 +++--- kernel/bpf/devmap.c | 7 ++++++- net/core/filter.c | 9 +++++++-- 3 files changed, 16 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/linux/filter.h b/include/linux/filter.h index 300baad62c88..c73dd7396886 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -765,8 +765,8 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); -static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, - struct net_device *fwd) +static inline int xdp_ok_fwd_dev(const struct net_device *fwd, + unsigned int pktlen) { unsigned int len; @@ -774,7 +774,7 @@ static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; - if (skb->len > len) + if (pktlen > len) return -EMSGSIZE; return 0; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 642c97f6d1b8..d361fc1e3bf3 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -334,10 +334,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, { struct net_device *dev = dst->dev; struct xdp_frame *xdpf; + int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + xdpf = convert_to_xdp_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; @@ -350,7 +355,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, { int err; - err = __xdp_generic_ok_fwd_dev(skb, dst->dev); + err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; skb->dev = dst->dev; diff --git a/net/core/filter.c b/net/core/filter.c index 470268024a40..5fa66a33927f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3128,12 +3128,16 @@ static int __bpf_tx_xdp(struct net_device *dev, u32 index) { struct xdp_frame *xdpf; - int sent; + int err, sent; if (!dev->netdev_ops->ndo_xdp_xmit) { return -EOPNOTSUPP; } + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + xdpf = convert_to_xdp_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; @@ -3367,7 +3371,8 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, goto err; } - if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + err = xdp_ok_fwd_dev(fwd, skb->len); + if (unlikely(err)) goto err; skb->dev = fwd; -- cgit v1.2.3 From b65f370d0671c4980ffe866c41e327b88893245c Mon Sep 17 00:00:00 2001 From: Okash Khawaja Date: Tue, 10 Jul 2018 14:33:07 -0700 Subject: bpf: btf: Fix bitfield extraction for big endian When extracting bitfield from a number, btf_int_bits_seq_show() builds a mask and accesses least significant byte of the number in a way specific to little-endian. This patch fixes that by checking endianness of the machine and then shifting left and right the unneeded bits. Thanks to Martin Lau for the help in navigating potential pitfalls when dealing with endianess and for the final solution. Fixes: b00b8daec828 ("bpf: btf: Add pretty print capability for data with BTF type info") Signed-off-by: Okash Khawaja Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- kernel/bpf/btf.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2d49d18b793a..e016ac3afa24 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -991,16 +991,13 @@ static void btf_int_bits_seq_show(const struct btf *btf, void *data, u8 bits_offset, struct seq_file *m) { + u16 left_shift_bits, right_shift_bits; u32 int_data = btf_type_int(t); u16 nr_bits = BTF_INT_BITS(int_data); u16 total_bits_offset; u16 nr_copy_bytes; u16 nr_copy_bits; - u8 nr_upper_bits; - union { - u64 u64_num; - u8 u8_nums[8]; - } print_num; + u64 print_num; total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); @@ -1008,21 +1005,20 @@ static void btf_int_bits_seq_show(const struct btf *btf, nr_copy_bits = nr_bits + bits_offset; nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); - print_num.u64_num = 0; - memcpy(&print_num.u64_num, data, nr_copy_bytes); + print_num = 0; + memcpy(&print_num, data, nr_copy_bytes); - /* Ditch the higher order bits */ - nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits); - if (nr_upper_bits) { - /* We need to mask out some bits of the upper byte. */ - u8 mask = (1 << nr_upper_bits) - 1; +#ifdef __BIG_ENDIAN_BITFIELD + left_shift_bits = bits_offset; +#else + left_shift_bits = BITS_PER_U64 - nr_copy_bits; +#endif + right_shift_bits = BITS_PER_U64 - nr_bits; - print_num.u8_nums[nr_copy_bytes - 1] &= mask; - } - - print_num.u64_num >>= bits_offset; + print_num <<= left_shift_bits; + print_num >>= right_shift_bits; - seq_printf(m, "0x%llx", print_num.u64_num); + seq_printf(m, "0x%llx", print_num); } static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, -- cgit v1.2.3 From c7a897843224a92209f306c984975b704969b89d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 12 Jul 2018 21:44:28 +0200 Subject: bpf: don't leave partial mangled prog in jit_subprogs error path syzkaller managed to trigger the following bug through fault injection: [...] [ 141.043668] verifier bug. No program starts at insn 3 [ 141.044648] WARNING: CPU: 3 PID: 4072 at kernel/bpf/verifier.c:1613 get_callee_stack_depth kernel/bpf/verifier.c:1612 [inline] [ 141.044648] WARNING: CPU: 3 PID: 4072 at kernel/bpf/verifier.c:1613 fixup_call_args kernel/bpf/verifier.c:5587 [inline] [ 141.044648] WARNING: CPU: 3 PID: 4072 at kernel/bpf/verifier.c:1613 bpf_check+0x525e/0x5e60 kernel/bpf/verifier.c:5952 [ 141.047355] CPU: 3 PID: 4072 Comm: a.out Not tainted 4.18.0-rc4+ #51 [ 141.048446] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),BIOS 1.10.2-1 04/01/2014 [ 141.049877] Call Trace: [ 141.050324] __dump_stack lib/dump_stack.c:77 [inline] [ 141.050324] dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113 [ 141.050950] ? dump_stack_print_info.cold.2+0x52/0x52 lib/dump_stack.c:60 [ 141.051837] panic+0x238/0x4e7 kernel/panic.c:184 [ 141.052386] ? add_taint.cold.5+0x16/0x16 kernel/panic.c:385 [ 141.053101] ? __warn.cold.8+0x148/0x1ba kernel/panic.c:537 [ 141.053814] ? __warn.cold.8+0x117/0x1ba kernel/panic.c:530 [ 141.054506] ? get_callee_stack_depth kernel/bpf/verifier.c:1612 [inline] [ 141.054506] ? fixup_call_args kernel/bpf/verifier.c:5587 [inline] [ 141.054506] ? bpf_check+0x525e/0x5e60 kernel/bpf/verifier.c:5952 [ 141.055163] __warn.cold.8+0x163/0x1ba kernel/panic.c:538 [ 141.055820] ? get_callee_stack_depth kernel/bpf/verifier.c:1612 [inline] [ 141.055820] ? fixup_call_args kernel/bpf/verifier.c:5587 [inline] [ 141.055820] ? bpf_check+0x525e/0x5e60 kernel/bpf/verifier.c:5952 [...] What happens in jit_subprogs() is that kcalloc() for the subprog func buffer is failing with NULL where we then bail out. Latter is a plain return -ENOMEM, and this is definitely not okay since earlier in the loop we are walking all subprogs and temporarily rewrite insn->off to remember the subprog id as well as insn->imm to temporarily point the call to __bpf_call_base + 1 for the initial JIT pass. Thus, bailing out in such state and handing this over to the interpreter is troublesome since later/subsequent e.g. find_subprog() lookups are based on wrong insn->imm. Therefore, once we hit this point, we need to jump to out_free path where we undo all changes from earlier loop, so that interpreter can work on unmodified insn->{off,imm}. Another point is that should find_subprog() fail in jit_subprogs() due to a verifier bug, then we also should not simply defer the program to the interpreter since also here we did partial modifications. Instead we should just bail out entirely and return an error to the user who is trying to load the program. Fixes: 1c2a088a6626 ("bpf: x64: add JIT support for multi-function programs") Reported-by: syzbot+7d427828b2ea6e592804@syzkaller.appspotmail.com Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e2bf834f13a..63aaac52a265 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; + /* Upon error here we cannot fall back to interpreter but + * need a hard reject of the program. Thus -EFAULT is + * propagated in any case. + */ subprog = find_subprog(env, i + insn->imm + 1); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", @@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) - return -ENOMEM; + goto out_undo_insn; for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; @@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); - err = -EFAULT; + err = -ENOTSUPP; goto out_free; } cond_resched(); @@ -5552,6 +5556,7 @@ out_free: if (func[i]) bpf_jit_free(func[i]); kfree(func); +out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { @@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env) err = jit_subprogs(env); if (err == 0) return 0; + if (err == -EFAULT) + return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON for (i = 0; i < prog->len; i++, insn++) { -- cgit v1.2.3 From 9fb8d5dc4b649dd190e1af4ead670753e71bf907 Mon Sep 17 00:00:00 2001 From: "Isaac J. Manjarres" Date: Tue, 3 Jul 2018 15:02:14 -0700 Subject: stop_machine: Disable preemption when waking two stopper threads When cpu_stop_queue_two_works() begins to wake the stopper threads, it does so without preemption disabled, which leads to the following race condition: The source CPU calls cpu_stop_queue_two_works(), with cpu1 as the source CPU, and cpu2 as the destination CPU. When adding the stopper threads to the wake queue used in this function, the source CPU stopper thread is added first, and the destination CPU stopper thread is added last. When wake_up_q() is invoked to wake the stopper threads, the threads are woken up in the order that they are queued in, so the source CPU's stopper thread is woken up first, and it preempts the thread running on the source CPU. The stopper thread will then execute on the source CPU, disable preemption, and begin executing multi_cpu_stop(), and wait for an ack from the destination CPU's stopper thread, with preemption still disabled. Since the worker thread that woke up the stopper thread on the source CPU is affine to the source CPU, and preemption is disabled on the source CPU, that thread will never run to dequeue the destination CPU's stopper thread from the wake queue, and thus, the destination CPU's stopper thread will never run, causing the source CPU's stopper thread to wait forever, and stall. Disable preemption when waking the stopper threads in cpu_stop_queue_two_works(). Fixes: 0b26351b910f ("stop_machine, sched: Fix migrate_swap() vs. active_balance() deadlock") Co-Developed-by: Prasad Sodagudi Signed-off-by: Prasad Sodagudi Co-Developed-by: Pavankumar Kondeti Signed-off-by: Pavankumar Kondeti Signed-off-by: Isaac J. Manjarres Signed-off-by: Thomas Gleixner Cc: peterz@infradead.org Cc: matt@codeblueprint.co.uk Cc: bigeasy@linutronix.de Cc: gregkh@linuxfoundation.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1530655334-4601-1-git-send-email-isaacm@codeaurora.org --- kernel/stop_machine.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index f89014a2c238..1ff523dae6e2 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -270,7 +270,11 @@ unlock: goto retry; } - wake_up_q(&wakeq); + if (!err) { + preempt_disable(); + wake_up_q(&wakeq); + preempt_enable(); + } return err; } -- cgit v1.2.3 From e117cb52bdb4d376b711bee34af6434c9e314b3b Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Wed, 11 Jul 2018 09:29:48 +0200 Subject: sched/deadline: Fix switched_from_dl() warning Mark noticed that syzkaller is able to reliably trigger the following warning: dl_rq->running_bw > dl_rq->this_bw WARNING: CPU: 1 PID: 153 at kernel/sched/deadline.c:124 switched_from_dl+0x454/0x608 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 153 Comm: syz-executor253 Not tainted 4.18.0-rc3+ #29 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x458 show_stack+0x20/0x30 dump_stack+0x180/0x250 panic+0x2dc/0x4ec __warn_printk+0x0/0x150 report_bug+0x228/0x2d8 bug_handler+0xa0/0x1a0 brk_handler+0x2f0/0x568 do_debug_exception+0x1bc/0x5d0 el1_dbg+0x18/0x78 switched_from_dl+0x454/0x608 __sched_setscheduler+0x8cc/0x2018 sys_sched_setattr+0x340/0x758 el0_svc_naked+0x30/0x34 syzkaller reproducer runs a bunch of threads that constantly switch between DEADLINE and NORMAL classes while interacting through futexes. The splat above is caused by the fact that if a DEADLINE task is setattr back to NORMAL while in non_contending state (blocked on a futex - inactive timer armed), its contribution to running_bw is not removed before sub_rq_bw() gets called (!task_on_rq_queued() branch) and the latter sees running_bw > this_bw. Fix it by removing a task contribution from running_bw if the task is not queued and in non_contending state while switched to a different class. Reported-by: Mark Rutland Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Daniel Bristot de Oliveira Reviewed-by: Luca Abeni Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: claudio@evidence.eu.com Cc: rostedt@goodmis.org Link: http://lkml.kernel.org/r/20180711072948.27061-1-juri.lelli@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fbfc3f1d368a..10c7b51c0d1f 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2290,8 +2290,17 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && p->dl.dl_runtime) task_non_contending(p); - if (!task_on_rq_queued(p)) + if (!task_on_rq_queued(p)) { + /* + * Inactive timer is armed. However, p is leaving DEADLINE and + * might migrate away from this rq while continuing to run on + * some other class. We need to remove its contribution from + * this rq running_bw now, or sub_rq_bw (below) will complain. + */ + if (p->dl.dl_non_contending) + sub_running_bw(&p->dl, &rq->dl); sub_rq_bw(&p->dl, &rq->dl); + } /* * We cannot use inactive_task_timer() to invoke sub_running_bw() -- cgit v1.2.3 From 3c53776e29f81719efcf8f7a6e30cdf753bee94d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 8 Jan 2018 11:51:04 -0800 Subject: Mark HI and TASKLET softirq synchronous Way back in 4.9, we committed 4cd13c21b207 ("softirq: Let ksoftirqd do its job"), and ever since we've had small nagging issues with it. For example, we've had: 1ff688209e2e ("watchdog: core: make sure the watchdog_worker is not deferred") 8d5755b3f77b ("watchdog: softdog: fire watchdog even if softirqs do not get to run") 217f69743681 ("net: busy-poll: allow preemption in sk_busy_loop()") all of which worked around some of the effects of that commit. The DVB people have also complained that the commit causes excessive USB URB latencies, which seems to be due to the USB code using tasklets to schedule USB traffic. This seems to be an issue mainly when already living on the edge, but waiting for ksoftirqd to handle it really does seem to cause excessive latencies. Now Hanna Hawa reports that this issue isn't just limited to USB URB and DVB, but also causes timeout problems for the Marvell SoC team: "I'm facing kernel panic issue while running raid 5 on sata disks connected to Macchiatobin (Marvell community board with Armada-8040 SoC with 4 ARMv8 cores of CA72) Raid 5 built with Marvell DMA engine and async_tx mechanism (ASYNC_TX_DMA [=y]); the DMA driver (mv_xor_v2) uses a tasklet to clean the done descriptors from the queue" The latency problem causes a panic: mv_xor_v2 f0400000.xor: dma_sync_wait: timeout! Kernel panic - not syncing: async_tx_quiesce: DMA error waiting for transaction We've discussed simply just reverting the original commit entirely, and also much more involved solutions (with per-softirq threads etc). This patch is intentionally stupid and fairly limited, because the issue still remains, and the other solutions either got sidetracked or had other issues. We should probably also consider the timer softirqs to be synchronous and not be delayed to ksoftirqd (since they were the issue with the earlier watchdog problems), but that should be done as a separate patch. This does only the tasklet cases. Reported-and-tested-by: Hanna Hawa Reported-and-tested-by: Josef Griebichler Reported-by: Mauro Carvalho Chehab Cc: Alan Stern Cc: Greg Kroah-Hartman Cc: Eric Dumazet Cc: Ingo Molnar Signed-off-by: Linus Torvalds --- kernel/softirq.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/softirq.c b/kernel/softirq.c index 900dcfee542c..75ffc1d1a2e0 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -79,12 +79,16 @@ static void wakeup_softirqd(void) /* * If ksoftirqd is scheduled, we do not want to process pending softirqs - * right now. Let ksoftirqd handle this at its own rate, to get fairness. + * right now. Let ksoftirqd handle this at its own rate, to get fairness, + * unless we're doing some of the synchronous softirqs. */ -static bool ksoftirqd_running(void) +#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ)) +static bool ksoftirqd_running(unsigned long pending) { struct task_struct *tsk = __this_cpu_read(ksoftirqd); + if (pending & SOFTIRQ_NOW_MASK) + return false; return tsk && (tsk->state == TASK_RUNNING); } @@ -328,7 +332,7 @@ asmlinkage __visible void do_softirq(void) pending = local_softirq_pending(); - if (pending && !ksoftirqd_running()) + if (pending && !ksoftirqd_running(pending)) do_softirq_own_stack(); local_irq_restore(flags); @@ -355,7 +359,7 @@ void irq_enter(void) static inline void invoke_softirq(void) { - if (ksoftirqd_running()) + if (ksoftirqd_running(local_softirq_pending())) return; if (!force_irqthreads) { -- cgit v1.2.3 From 3928d4f5ee37cdc523894f6e549e6aae521d8980 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 21 Jul 2018 13:48:51 -0700 Subject: mm: use helper functions for allocating and freeing vm_area structs The vm_area_struct is one of the most fundamental memory management objects, but the management of it is entirely open-coded evertwhere, ranging from allocation and freeing (using kmem_cache_[z]alloc and kmem_cache_free) to initializing all the fields. We want to unify this in order to end up having some unified initialization of the vmas, and the first step to this is to at least have basic allocation functions. Right now those functions are literally just wrappers around the kmem_cache_*() calls. This is a purely mechanical conversion: # new vma: kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL) -> vm_area_alloc() # copy old vma kmem_cache_alloc(vm_area_cachep, GFP_KERNEL) -> vm_area_dup(old) # free vma kmem_cache_free(vm_area_cachep, vma) -> vm_area_free(vma) to the point where the old vma passed in to the vm_area_dup() function isn't even used yet (because I've left all the old manual initialization alone). Signed-off-by: Linus Torvalds --- arch/ia64/kernel/perfmon.c | 4 ++-- arch/ia64/mm/init.c | 8 ++++---- fs/exec.c | 4 ++-- include/linux/mm.h | 4 +++- kernel/fork.c | 21 ++++++++++++++++++--- mm/mmap.c | 22 +++++++++++----------- mm/nommu.c | 8 ++++---- 7 files changed, 44 insertions(+), 27 deletions(-) (limited to 'kernel') diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 3b38c717008a..e859246badca 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2278,7 +2278,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t DPRINT(("smpl_buf @%p\n", smpl_buf)); /* allocate vma */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(); if (!vma) { DPRINT(("Cannot allocate vma\n")); goto error_kmem; @@ -2346,7 +2346,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t return 0; error: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); error_kmem: pfm_rvfree(smpl_buf, size); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 18278b448530..3f2321bffb72 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -114,7 +114,7 @@ ia64_init_addr_space (void) * the problem. When the process attempts to write to the register backing store * for the first time, it will get a SEGFAULT in this case. */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(); if (vma) { INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = current->mm; @@ -125,7 +125,7 @@ ia64_init_addr_space (void) down_write(¤t->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(¤t->mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return; } up_write(¤t->mm->mmap_sem); @@ -133,7 +133,7 @@ ia64_init_addr_space (void) /* map NaT-page at address zero to speed up speculative dereferencing of NULL: */ if (!(current->personality & MMAP_PAGE_ZERO)) { - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(); if (vma) { INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = current->mm; @@ -144,7 +144,7 @@ ia64_init_addr_space (void) down_write(¤t->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(¤t->mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return; } up_write(¤t->mm->mmap_sem); diff --git a/fs/exec.c b/fs/exec.c index 2d4e0075bd24..9bd83989ea25 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -290,7 +290,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) struct vm_area_struct *vma = NULL; struct mm_struct *mm = bprm->mm; - bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + bprm->vma = vma = vm_area_alloc(); if (!vma) return -ENOMEM; @@ -326,7 +326,7 @@ err: up_write(&mm->mmap_sem); err_free: bprm->vma = NULL; - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return err; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 3982c83fdcbf..de2fd86c6154 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -155,7 +155,9 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, * mmap() functions). */ -extern struct kmem_cache *vm_area_cachep; +struct vm_area_struct *vm_area_alloc(void); +struct vm_area_struct *vm_area_dup(struct vm_area_struct *); +void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; diff --git a/kernel/fork.c b/kernel/fork.c index 9440d61b925c..0e23deb5acfc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -303,11 +303,26 @@ struct kmem_cache *files_cachep; struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ -struct kmem_cache *vm_area_cachep; +static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; +struct vm_area_struct *vm_area_alloc(void) +{ + return kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); +} + +struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) +{ + return kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); +} + +void vm_area_free(struct vm_area_struct *vma) +{ + kmem_cache_free(vm_area_cachep, vma); +} + static void account_kernel_stack(struct task_struct *tsk, int account) { void *stack = task_stack_page(tsk); @@ -455,7 +470,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto fail_nomem; charge = len; } - tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; *tmp = *mpnt; @@ -539,7 +554,7 @@ fail_uprobe_end: fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: - kmem_cache_free(vm_area_cachep, tmp); + vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); diff --git a/mm/mmap.c b/mm/mmap.c index 5801b5f0a634..4286ad2dd1f5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -182,7 +182,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return next; } @@ -911,7 +911,7 @@ again: anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); - kmem_cache_free(vm_area_cachep, next); + vm_area_free(next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter @@ -1729,7 +1729,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(); if (!vma) { error = -ENOMEM; goto unacct_error; @@ -1832,7 +1832,7 @@ allow_write_and_free_vma: if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); @@ -2620,7 +2620,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, return err; } - new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new = vm_area_dup(vma); if (!new) return -ENOMEM; @@ -2669,7 +2669,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, out_free_mpol: mpol_put(vma_policy(new)); out_free_vma: - kmem_cache_free(vm_area_cachep, new); + vm_area_free(new); return err; } @@ -2984,7 +2984,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla /* * create a vma struct for an anonymous mapping */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(); if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; @@ -3202,7 +3202,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { - new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new_vma = vm_area_dup(vma); if (!new_vma) goto out; *new_vma = *vma; @@ -3226,7 +3226,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: - kmem_cache_free(vm_area_cachep, new_vma); + vm_area_free(new_vma); out: return NULL; } @@ -3350,7 +3350,7 @@ static struct vm_area_struct *__install_special_mapping( int ret; struct vm_area_struct *vma; - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); @@ -3376,7 +3376,7 @@ static struct vm_area_struct *__install_special_mapping( return vma; out: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return ERR_PTR(ret); } diff --git a/mm/nommu.c b/mm/nommu.c index 4452d8bd9ae4..006e3fe65017 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -769,7 +769,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); put_nommu_region(vma->vm_region); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); } /* @@ -1204,7 +1204,7 @@ unsigned long do_mmap(struct file *file, if (!region) goto error_getting_region; - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(); if (!vma) goto error_getting_vma; @@ -1368,7 +1368,7 @@ error: kmem_cache_free(vm_region_jar, region); if (vma->vm_file) fput(vma->vm_file); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return ret; sharing_violation: @@ -1469,7 +1469,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (!region) return -ENOMEM; - new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new = vm_area_dup(vma); if (!new) { kmem_cache_free(vm_region_jar, region); return -ENOMEM; -- cgit v1.2.3 From 95faf6992df468f617edb788da8c21c6eed0dfa7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 21 Jul 2018 14:48:45 -0700 Subject: mm: make vm_area_dup() actually copy the old vma data .. and re-initialize th eanon_vma_chain head. This removes some boiler-plate from the users, and also makes it clear why it didn't need use the 'zalloc()' version. Signed-off-by: Linus Torvalds --- kernel/fork.c | 10 +++++++--- mm/mmap.c | 7 ------- mm/nommu.c | 1 - 3 files changed, 7 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 0e23deb5acfc..67253e41bfb0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -315,7 +315,13 @@ struct vm_area_struct *vm_area_alloc(void) struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { - return kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + + if (new) { + *new = *orig; + INIT_LIST_HEAD(&new->anon_vma_chain); + } + return new; } void vm_area_free(struct vm_area_struct *vma) @@ -473,8 +479,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; - *tmp = *mpnt; - INIT_LIST_HEAD(&tmp->anon_vma_chain); retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; diff --git a/mm/mmap.c b/mm/mmap.c index 4286ad2dd1f5..b0ed8ce1b67e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2624,11 +2624,6 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (!new) return -ENOMEM; - /* most fields are the same, copy all, and then fixup */ - *new = *vma; - - INIT_LIST_HEAD(&new->anon_vma_chain); - if (new_below) new->vm_end = addr; else { @@ -3205,13 +3200,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, new_vma = vm_area_dup(vma); if (!new_vma) goto out; - *new_vma = *vma; new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; if (vma_dup_policy(vma, new_vma)) goto out_free_vma; - INIT_LIST_HEAD(&new_vma->anon_vma_chain); if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) diff --git a/mm/nommu.c b/mm/nommu.c index 006e3fe65017..c2560e9cc803 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1476,7 +1476,6 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, } /* most fields are the same, copy all, and then fixup */ - *new = *vma; *region = *vma->vm_region; new->vm_region = region; -- cgit v1.2.3 From 490fc053865c9cc40f1085ef8a5504f5341f79d2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 21 Jul 2018 15:24:03 -0700 Subject: mm: make vm_area_alloc() initialize core fields Like vm_area_dup(), it initializes the anon_vma_chain head, and the basic mm pointer. The rest of the fields end up being different for different users, although the plan is to also initialize the 'vm_ops' field to a dummy entry. Signed-off-by: Linus Torvalds --- arch/ia64/kernel/perfmon.c | 4 +--- arch/ia64/mm/init.c | 8 ++------ fs/exec.c | 4 +--- include/linux/mm.h | 2 +- kernel/fork.c | 10 ++++++++-- mm/mmap.c | 12 +++--------- mm/nommu.c | 3 +-- 7 files changed, 17 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index e859246badca..46bff1661836 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2278,17 +2278,15 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t DPRINT(("smpl_buf @%p\n", smpl_buf)); /* allocate vma */ - vma = vm_area_alloc(); + vma = vm_area_alloc(mm); if (!vma) { DPRINT(("Cannot allocate vma\n")); goto error_kmem; } - INIT_LIST_HEAD(&vma->anon_vma_chain); /* * partially initialize the vma for the sampling buffer */ - vma->vm_mm = mm; vma->vm_file = get_file(filp); vma->vm_flags = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP; vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */ diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 3f2321bffb72..bdb14a369137 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -114,10 +114,8 @@ ia64_init_addr_space (void) * the problem. When the process attempts to write to the register backing store * for the first time, it will get a SEGFAULT in this case. */ - vma = vm_area_alloc(); + vma = vm_area_alloc(current->mm); if (vma) { - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = current->mm; vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT; @@ -133,10 +131,8 @@ ia64_init_addr_space (void) /* map NaT-page at address zero to speed up speculative dereferencing of NULL: */ if (!(current->personality & MMAP_PAGE_ZERO)) { - vma = vm_area_alloc(); + vma = vm_area_alloc(current->mm); if (vma) { - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = current->mm; vma->vm_end = PAGE_SIZE; vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | diff --git a/fs/exec.c b/fs/exec.c index 9bd83989ea25..72e961a62adb 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -290,7 +290,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) struct vm_area_struct *vma = NULL; struct mm_struct *mm = bprm->mm; - bprm->vma = vma = vm_area_alloc(); + bprm->vma = vma = vm_area_alloc(mm); if (!vma) return -ENOMEM; @@ -298,7 +298,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm) err = -EINTR; goto err_free; } - vma->vm_mm = mm; /* * Place the stack at the largest stack address the architecture @@ -311,7 +310,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm) vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); - INIT_LIST_HEAD(&vma->anon_vma_chain); err = insert_vm_struct(mm, vma); if (err) diff --git a/include/linux/mm.h b/include/linux/mm.h index de2fd86c6154..d3a3842316b8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -155,7 +155,7 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, * mmap() functions). */ -struct vm_area_struct *vm_area_alloc(void); +struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); diff --git a/kernel/fork.c b/kernel/fork.c index 67253e41bfb0..a191c05e757d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -308,9 +308,15 @@ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; -struct vm_area_struct *vm_area_alloc(void) +struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { - return kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + + if (vma) { + vma->vm_mm = mm; + INIT_LIST_HEAD(&vma->anon_vma_chain); + } + return vma; } struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) diff --git a/mm/mmap.c b/mm/mmap.c index b0ed8ce1b67e..ff1944d8d458 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1729,19 +1729,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ - vma = vm_area_alloc(); + vma = vm_area_alloc(mm); if (!vma) { error = -ENOMEM; goto unacct_error; } - vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_chain); if (file) { if (vm_flags & VM_DENYWRITE) { @@ -2979,14 +2977,12 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla /* * create a vma struct for an anonymous mapping */ - vma = vm_area_alloc(); + vma = vm_area_alloc(mm); if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; @@ -3343,12 +3339,10 @@ static struct vm_area_struct *__install_special_mapping( int ret; struct vm_area_struct *vma; - vma = vm_area_alloc(); + vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; diff --git a/mm/nommu.c b/mm/nommu.c index c2560e9cc803..1d22fdbf7d7c 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1204,7 +1204,7 @@ unsigned long do_mmap(struct file *file, if (!region) goto error_getting_region; - vma = vm_area_alloc(); + vma = vm_area_alloc(current->mm); if (!vma) goto error_getting_vma; @@ -1212,7 +1212,6 @@ unsigned long do_mmap(struct file *file, region->vm_flags = vm_flags; region->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_flags = vm_flags; vma->vm_pgoff = pgoff; -- cgit v1.2.3 From 6cd0c583b04b2bd9415e07b51b63ab799949dd66 Mon Sep 17 00:00:00 2001 From: Yi Wang Date: Mon, 23 Jul 2018 12:19:07 +0800 Subject: sched/topology: Check variable group before dereferencing it The 'group' variable in sched_domain_debug_one() is not checked when firstly used in cpumask_test_cpu(cpu, sched_group_span(group)), but it might be NULL (it is checked later in the following while loop) and may cause NULL pointer dereference. We need to check it before using to avoid NULL dereference. Signed-off-by: Yi Wang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Jiang Biao Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: zhong.weidong@zte.com.cn Link: http://lkml.kernel.org/r/1532319547-33335-1-git-send-email-wang.yi59@zte.com.cn Signed-off-by: Ingo Molnar --- kernel/sched/topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 05a831427bc7..56a0fed30c0a 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -47,7 +47,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu); } - if (!cpumask_test_cpu(cpu, sched_group_span(group))) { + if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) { printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu); } -- cgit v1.2.3 From 2610e88946632afb78aa58e61f11368ac4c0af7b Mon Sep 17 00:00:00 2001 From: "Isaac J. Manjarres" Date: Tue, 17 Jul 2018 12:35:29 -0700 Subject: stop_machine: Disable preemption after queueing stopper threads This commit: 9fb8d5dc4b64 ("stop_machine, Disable preemption when waking two stopper threads") does not fully address the race condition that can occur as follows: On one CPU, call it CPU 3, thread 1 invokes cpu_stop_queue_two_works(2, 3,...), and the execution is such that thread 1 queues the works for migration/2 and migration/3, and is preempted after releasing the locks for migration/2 and migration/3, but before waking the threads. Then, On CPU 2, a kworker, call it thread 2, is running, and it invokes cpu_stop_queue_two_works(1, 2,...), such that thread 2 queues the works for migration/1 and migration/2. Meanwhile, on CPU 3, thread 1 resumes execution, and wakes migration/2 and migration/3. This means that when CPU 2 releases the locks for migration/1 and migration/2, but before it wakes those threads, it can be preempted by migration/2. If thread 2 is preempted by migration/2, then migration/2 will execute the first work item successfully, since migration/3 was woken up by CPU 3, but when it goes to execute the second work item, it disables preemption, calls multi_cpu_stop(), and thus, CPU 2 will wait forever for migration/1, which should have been woken up by thread 2. However migration/1 cannot be woken up by thread 2, since it is a kworker, so it is affine to CPU 2, but CPU 2 is running migration/2 with preemption disabled, so thread 2 will never run. Disable preemption after queueing works for stopper threads to ensure that the operation of queueing the works and waking the stopper threads is atomic. Co-Developed-by: Prasad Sodagudi Co-Developed-by: Pavankumar Kondeti Signed-off-by: Isaac J. Manjarres Signed-off-by: Prasad Sodagudi Signed-off-by: Pavankumar Kondeti Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: bigeasy@linutronix.de Cc: gregkh@linuxfoundation.org Cc: matt@codeblueprint.co.uk Fixes: 9fb8d5dc4b64 ("stop_machine, Disable preemption when waking two stopper threads") Link: http://lkml.kernel.org/r/1531856129-9871-1-git-send-email-isaacm@codeaurora.org Signed-off-by: Ingo Molnar --- kernel/stop_machine.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 1ff523dae6e2..e190d1ef3a23 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -260,6 +260,15 @@ retry: err = 0; __cpu_stop_queue_work(stopper1, work1, &wakeq); __cpu_stop_queue_work(stopper2, work2, &wakeq); + /* + * The waking up of stopper threads has to happen + * in the same scheduling context as the queueing. + * Otherwise, there is a possibility of one of the + * above stoppers being woken up by another CPU, + * and preempting us. This will cause us to n ot + * wake up the other stopper forever. + */ + preempt_disable(); unlock: raw_spin_unlock(&stopper2->lock); raw_spin_unlock_irq(&stopper1->lock); @@ -271,7 +280,6 @@ unlock: } if (!err) { - preempt_disable(); wake_up_q(&wakeq); preempt_enable(); } -- cgit v1.2.3 From 840d719604b0925ca23dde95f1767e4528668369 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Fri, 20 Jul 2018 11:16:30 +0200 Subject: sched/deadline: Update rq_clock of later_rq when pushing a task Daniel Casini got this warn while running a DL task here at RetisLab: [ 461.137582] ------------[ cut here ]------------ [ 461.137583] rq->clock_update_flags < RQCF_ACT_SKIP [ 461.137599] WARNING: CPU: 4 PID: 2354 at kernel/sched/sched.h:967 assert_clock_updated.isra.32.part.33+0x17/0x20 [a ton of modules] [ 461.137646] CPU: 4 PID: 2354 Comm: label_image Not tainted 4.18.0-rc4+ #3 [ 461.137647] Hardware name: ASUS All Series/Z87-K, BIOS 0801 09/02/2013 [ 461.137649] RIP: 0010:assert_clock_updated.isra.32.part.33+0x17/0x20 [ 461.137649] Code: ff 48 89 83 08 09 00 00 eb c6 66 0f 1f 84 00 00 00 00 00 55 48 c7 c7 98 7a 6c a5 c6 05 bc 0d 54 01 01 48 89 e5 e8 a9 84 fb ff <0f> 0b 5d c3 0f 1f 44 00 00 0f 1f 44 00 00 83 7e 60 01 74 0a 48 3b [ 461.137673] RSP: 0018:ffffa77e08cafc68 EFLAGS: 00010082 [ 461.137674] RAX: 0000000000000000 RBX: ffff8b3fc1702d80 RCX: 0000000000000006 [ 461.137674] RDX: 0000000000000007 RSI: 0000000000000096 RDI: ffff8b3fded164b0 [ 461.137675] RBP: ffffa77e08cafc68 R08: 0000000000000026 R09: 0000000000000339 [ 461.137676] R10: ffff8b3fd060d410 R11: 0000000000000026 R12: ffffffffa4e14e20 [ 461.137677] R13: ffff8b3fdec22940 R14: ffff8b3fc1702da0 R15: ffff8b3fdec22940 [ 461.137678] FS: 00007efe43ee5700(0000) GS:ffff8b3fded00000(0000) knlGS:0000000000000000 [ 461.137679] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 461.137680] CR2: 00007efe30000010 CR3: 0000000301744003 CR4: 00000000001606e0 [ 461.137680] Call Trace: [ 461.137684] push_dl_task.part.46+0x3bc/0x460 [ 461.137686] task_woken_dl+0x60/0x80 [ 461.137689] ttwu_do_wakeup+0x4f/0x150 [ 461.137690] ttwu_do_activate+0x77/0x80 [ 461.137692] try_to_wake_up+0x1d6/0x4c0 [ 461.137693] wake_up_q+0x32/0x70 [ 461.137696] do_futex+0x7e7/0xb50 [ 461.137698] __x64_sys_futex+0x8b/0x180 [ 461.137701] do_syscall_64+0x5a/0x110 [ 461.137703] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 461.137705] RIP: 0033:0x7efe4918ca26 [ 461.137705] Code: 00 00 00 74 17 49 8b 48 20 44 8b 59 10 41 83 e3 30 41 83 fb 20 74 1e be 85 00 00 00 41 ba 01 00 00 00 41 b9 01 00 00 04 0f 05 <48> 3d 01 f0 ff ff 73 1f 31 c0 c3 be 8c 00 00 00 49 89 c8 4d 31 d2 [ 461.137738] RSP: 002b:00007efe43ee4928 EFLAGS: 00000283 ORIG_RAX: 00000000000000ca [ 461.137739] RAX: ffffffffffffffda RBX: 0000000005094df0 RCX: 00007efe4918ca26 [ 461.137740] RDX: 0000000000000001 RSI: 0000000000000085 RDI: 0000000005094e24 [ 461.137741] RBP: 00007efe43ee49c0 R08: 0000000005094e20 R09: 0000000004000001 [ 461.137741] R10: 0000000000000001 R11: 0000000000000283 R12: 0000000000000000 [ 461.137742] R13: 0000000005094df8 R14: 0000000000000001 R15: 0000000000448a10 [ 461.137743] ---[ end trace 187df4cad2bf7649 ]--- This warning happened in the push_dl_task(), because __add_running_bw()->cpufreq_update_util() is getting the rq_clock of the later_rq before its update, which takes place at activate_task(). The fix then is to update the rq_clock before calling add_running_bw(). To avoid double rq_clock_update() call, we set ENQUEUE_NOCLOCK flag to activate_task(). Reported-by: Daniel Casini Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Acked-by: Juri Lelli Cc: Clark Williams Cc: Linus Torvalds Cc: Luca Abeni Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Tommaso Cucinotta Fixes: e0367b12674b sched/deadline: Move CPU frequency selection triggering points Link: http://lkml.kernel.org/r/ca31d073a4788acf0684a8b255f14fea775ccf20.1532077269.git.bristot@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 10c7b51c0d1f..b5fbdde6afa9 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2090,8 +2090,14 @@ retry: sub_rq_bw(&next_task->dl, &rq->dl); set_task_cpu(next_task, later_rq->cpu); add_rq_bw(&next_task->dl, &later_rq->dl); + + /* + * Update the later_rq clock here, because the clock is used + * by the cpufreq_update_util() inside __add_running_bw(). + */ + update_rq_clock(later_rq); add_running_bw(&next_task->dl, &later_rq->dl); - activate_task(later_rq, next_task, 0); + activate_task(later_rq, next_task, ENQUEUE_NOCLOCK); ret = 1; resched_curr(later_rq); -- cgit v1.2.3 From f3d133ee0a17d5694c6f21873eec9863e11fa423 Mon Sep 17 00:00:00 2001 From: Hailong Liu Date: Wed, 18 Jul 2018 08:46:55 +0800 Subject: sched/rt: Restore rt_runtime after disabling RT_RUNTIME_SHARE NO_RT_RUNTIME_SHARE feature is used to prevent a CPU borrow enough runtime with a spin-rt-task. However, if RT_RUNTIME_SHARE feature is enabled and rt_rq has borrowd enough rt_runtime at the beginning, rt_runtime can't be restored to its initial bandwidth rt_runtime after we disable RT_RUNTIME_SHARE. E.g. on my PC with 4 cores, procedure to reproduce: 1) Make sure RT_RUNTIME_SHARE is enabled cat /sys/kernel/debug/sched_features GENTLE_FAIR_SLEEPERS START_DEBIT NO_NEXT_BUDDY LAST_BUDDY CACHE_HOT_BUDDY WAKEUP_PREEMPTION NO_HRTICK NO_DOUBLE_TICK LB_BIAS NONTASK_CAPACITY TTWU_QUEUE NO_SIS_AVG_CPU SIS_PROP NO_WARN_DOUBLE_CLOCK RT_PUSH_IPI RT_RUNTIME_SHARE NO_LB_MIN ATTACH_AGE_LOAD WA_IDLE WA_WEIGHT WA_BIAS 2) Start a spin-rt-task ./loop_rr & 3) set affinity to the last cpu taskset -p 8 $pid_of_loop_rr 4) Observe that last cpu have borrowed enough runtime. cat /proc/sched_debug | grep rt_runtime .rt_runtime : 950.000000 .rt_runtime : 900.000000 .rt_runtime : 950.000000 .rt_runtime : 1000.000000 5) Disable RT_RUNTIME_SHARE echo NO_RT_RUNTIME_SHARE > /sys/kernel/debug/sched_features 6) Observe that rt_runtime can not been restored cat /proc/sched_debug | grep rt_runtime .rt_runtime : 950.000000 .rt_runtime : 900.000000 .rt_runtime : 950.000000 .rt_runtime : 1000.000000 This patch help to restore rt_runtime after we disable RT_RUNTIME_SHARE. Signed-off-by: Hailong Liu Signed-off-by: Jiang Biao Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: zhong.weidong@zte.com.cn Link: http://lkml.kernel.org/r/1531874815-39357-1-git-send-email-liu.hailong6@zte.com.cn Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 572567078b60..eaaec8364f96 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -836,6 +836,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) * can be time-consuming. Try to avoid it when possible. */ raw_spin_lock(&rt_rq->rt_runtime_lock); + if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF) + rt_rq->rt_runtime = rt_b->rt_runtime; skip = !rt_rq->rt_time && !rt_rq->rt_nr_running; raw_spin_unlock(&rt_rq->rt_runtime_lock); if (skip) -- cgit v1.2.3