diff options
Diffstat (limited to 'kernel')
128 files changed, 8858 insertions, 6475 deletions
diff --git a/kernel/async.c b/kernel/async.c index d2edd6efec56..2cbd3dd5940d 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -114,14 +114,14 @@ static void async_run_entry_fn(struct work_struct *work) ktime_t uninitialized_var(calltime), delta, rettime; /* 1) run (and print duration) */ - if (initcall_debug && system_state == SYSTEM_BOOTING) { + if (initcall_debug && system_state < SYSTEM_RUNNING) { pr_debug("calling %lli_%pF @ %i\n", (long long)entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); } entry->func(entry->data, entry->cookie); - if (initcall_debug && system_state == SYSTEM_BOOTING) { + if (initcall_debug && system_state < SYSTEM_RUNNING) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n", @@ -284,14 +284,14 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain { ktime_t uninitialized_var(starttime), delta, endtime; - if (initcall_debug && system_state == SYSTEM_BOOTING) { + if (initcall_debug && system_state < SYSTEM_RUNNING) { pr_debug("async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); } wait_event(async_done, lowest_in_progress(domain) >= cookie); - if (initcall_debug && system_state == SYSTEM_BOOTING) { + if (initcall_debug && system_state < SYSTEM_RUNNING) { endtime = ktime_get(); delta = ktime_sub(endtime, starttime); diff --git a/kernel/audit.c b/kernel/audit.c index 4b7d49868ce1..833267bbd80b 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -575,12 +575,16 @@ static void kauditd_retry_skb(struct sk_buff *skb) /** * auditd_reset - Disconnect the auditd connection + * @ac: auditd connection state * * Description: * Break the auditd/kauditd connection and move all the queued records into the - * hold queue in case auditd reconnects. + * hold queue in case auditd reconnects. It is important to note that the @ac + * pointer should never be dereferenced inside this function as it may be NULL + * or invalid, you can only compare the memory address! If @ac is NULL then + * the connection will always be reset. */ -static void auditd_reset(void) +static void auditd_reset(const struct auditd_connection *ac) { unsigned long flags; struct sk_buff *skb; @@ -590,17 +594,21 @@ static void auditd_reset(void) spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); + if (ac && ac != ac_old) { + /* someone already registered a new auditd connection */ + spin_unlock_irqrestore(&auditd_conn_lock, flags); + return; + } rcu_assign_pointer(auditd_conn, NULL); spin_unlock_irqrestore(&auditd_conn_lock, flags); if (ac_old) call_rcu(&ac_old->rcu, auditd_conn_free); - /* flush all of the main and retry queues to the hold queue */ + /* flush the retry queue to the hold queue, but don't touch the main + * queue since we need to process that normally for multicast */ while ((skb = skb_dequeue(&audit_retry_queue))) kauditd_hold_skb(skb); - while ((skb = skb_dequeue(&audit_queue))) - kauditd_hold_skb(skb); } /** @@ -649,8 +657,8 @@ static int auditd_send_unicast_skb(struct sk_buff *skb) return rc; err: - if (rc == -ECONNREFUSED) - auditd_reset(); + if (ac && rc == -ECONNREFUSED) + auditd_reset(ac); return rc; } @@ -795,9 +803,9 @@ static int kauditd_thread(void *dummy) rc = kauditd_send_queue(sk, portid, &audit_hold_queue, UNICAST_RETRIES, NULL, kauditd_rehold_skb); - if (rc < 0) { + if (ac && rc < 0) { sk = NULL; - auditd_reset(); + auditd_reset(ac); goto main_queue; } @@ -805,9 +813,9 @@ static int kauditd_thread(void *dummy) rc = kauditd_send_queue(sk, portid, &audit_retry_queue, UNICAST_RETRIES, NULL, kauditd_hold_skb); - if (rc < 0) { + if (ac && rc < 0) { sk = NULL; - auditd_reset(); + auditd_reset(ac); goto main_queue; } @@ -815,12 +823,13 @@ main_queue: /* process the main queue - do the multicast send and attempt * unicast, dump failed record sends to the retry queue; if * sk == NULL due to previous failures we will just do the - * multicast send and move the record to the retry queue */ + * multicast send and move the record to the hold queue */ rc = kauditd_send_queue(sk, portid, &audit_queue, 1, kauditd_send_multicast_skb, - kauditd_retry_skb); - if (sk == NULL || rc < 0) - auditd_reset(); + (sk ? + kauditd_retry_skb : kauditd_hold_skb)); + if (ac && rc < 0) + auditd_reset(ac); sk = NULL; /* drop our netns reference, no auditd sends past this line */ @@ -1230,7 +1239,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) auditd_pid, 1); /* unregister the auditd connection */ - auditd_reset(); + auditd_reset(NULL); } } if (s.mask & AUDIT_STATUS_RATE_LIMIT) { @@ -1999,22 +2008,10 @@ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) { - kernel_cap_t *perm = &name->fcap.permitted; - kernel_cap_t *inh = &name->fcap.inheritable; - int log = 0; - - if (!cap_isclear(*perm)) { - audit_log_cap(ab, "cap_fp", perm); - log = 1; - } - if (!cap_isclear(*inh)) { - audit_log_cap(ab, "cap_fi", inh); - log = 1; - } - - if (log) - audit_log_format(ab, " cap_fe=%d cap_fver=%x", - name->fcap.fE, name->fcap_ver); + audit_log_cap(ab, "cap_fp", &name->fcap.permitted); + audit_log_cap(ab, "cap_fi", &name->fcap.inheritable); + audit_log_format(ab, " cap_fe=%d cap_fver=%x", + name->fcap.fE, name->fcap_ver); } static inline int audit_copy_fcaps(struct audit_names *name, diff --git a/kernel/audit.h b/kernel/audit.h index ddfce2ea4891..b331d9b83f63 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -68,6 +68,7 @@ struct audit_cap_data { unsigned int fE; /* effective bit of file cap */ kernel_cap_t effective; /* effective set of process */ }; + kernel_cap_t ambient; }; /* When fs/namei.c:getname() is called, we store the pointer in name and bump @@ -247,13 +248,13 @@ struct audit_netlink_list { struct sk_buff_head q; }; -int audit_send_list(void *); +int audit_send_list(void *_dest); extern int selinux_audit_rule_update(void); extern struct mutex audit_filter_mutex; -extern int audit_del_rule(struct audit_entry *); -extern void audit_free_rule_rcu(struct rcu_head *); +extern int audit_del_rule(struct audit_entry *entry); +extern void audit_free_rule_rcu(struct rcu_head *head); extern struct list_head audit_filter_list[]; extern struct audit_entry *audit_dupe_rule(struct audit_krule *old); @@ -301,17 +302,17 @@ extern int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark #endif /* CONFIG_AUDIT_WATCH */ #ifdef CONFIG_AUDIT_TREE -extern struct audit_chunk *audit_tree_lookup(const struct inode *); -extern void audit_put_chunk(struct audit_chunk *); -extern bool audit_tree_match(struct audit_chunk *, struct audit_tree *); -extern int audit_make_tree(struct audit_krule *, char *, u32); -extern int audit_add_tree_rule(struct audit_krule *); -extern int audit_remove_tree_rule(struct audit_krule *); +extern struct audit_chunk *audit_tree_lookup(const struct inode *inode); +extern void audit_put_chunk(struct audit_chunk *chunk); +extern bool audit_tree_match(struct audit_chunk *chunk, struct audit_tree *tree); +extern int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op); +extern int audit_add_tree_rule(struct audit_krule *rule); +extern int audit_remove_tree_rule(struct audit_krule *rule); extern void audit_trim_trees(void); extern int audit_tag_tree(char *old, char *new); -extern const char *audit_tree_path(struct audit_tree *); -extern void audit_put_tree(struct audit_tree *); -extern void audit_kill_trees(struct list_head *); +extern const char *audit_tree_path(struct audit_tree *tree); +extern void audit_put_tree(struct audit_tree *tree); +extern void audit_kill_trees(struct list_head *list); #else #define audit_remove_tree_rule(rule) BUG() #define audit_add_tree_rule(rule) -EINVAL @@ -323,7 +324,7 @@ extern void audit_kill_trees(struct list_head *); #define audit_kill_trees(list) BUG() #endif -extern char *audit_unpack_string(void **, size_t *, size_t); +extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len); extern pid_t audit_sig_pid; extern kuid_t audit_sig_uid; @@ -333,7 +334,7 @@ extern int audit_filter(int msgtype, unsigned int listtype); #ifdef CONFIG_AUDITSYSCALL extern int audit_signal_info(int sig, struct task_struct *t); -extern void audit_filter_inodes(struct task_struct *, struct audit_context *); +extern void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx); extern struct list_head *audit_killed_trees(void); #else #define audit_signal_info(s,t) AUDIT_DISABLED diff --git a/kernel/auditsc.c b/kernel/auditsc.c index bb724baa7ac9..3260ba2312a9 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1261,6 +1261,7 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_cap(ab, "cap_pi", &context->capset.cap.inheritable); audit_log_cap(ab, "cap_pp", &context->capset.cap.permitted); audit_log_cap(ab, "cap_pe", &context->capset.cap.effective); + audit_log_cap(ab, "cap_pa", &context->capset.cap.ambient); break; case AUDIT_MMAP: audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd, @@ -1382,9 +1383,11 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts audit_log_cap(ab, "old_pp", &axs->old_pcap.permitted); audit_log_cap(ab, "old_pi", &axs->old_pcap.inheritable); audit_log_cap(ab, "old_pe", &axs->old_pcap.effective); - audit_log_cap(ab, "new_pp", &axs->new_pcap.permitted); - audit_log_cap(ab, "new_pi", &axs->new_pcap.inheritable); - audit_log_cap(ab, "new_pe", &axs->new_pcap.effective); + audit_log_cap(ab, "old_pa", &axs->old_pcap.ambient); + audit_log_cap(ab, "pp", &axs->new_pcap.permitted); + audit_log_cap(ab, "pi", &axs->new_pcap.inheritable); + audit_log_cap(ab, "pe", &axs->new_pcap.effective); + audit_log_cap(ab, "pa", &axs->new_pcap.ambient); break; } } @@ -2342,10 +2345,12 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, ax->old_pcap.permitted = old->cap_permitted; ax->old_pcap.inheritable = old->cap_inheritable; ax->old_pcap.effective = old->cap_effective; + ax->old_pcap.ambient = old->cap_ambient; ax->new_pcap.permitted = new->cap_permitted; ax->new_pcap.inheritable = new->cap_inheritable; ax->new_pcap.effective = new->cap_effective; + ax->new_pcap.ambient = new->cap_ambient; return 0; } @@ -2364,6 +2369,7 @@ void __audit_log_capset(const struct cred *new, const struct cred *old) context->capset.cap.effective = new->cap_effective; context->capset.cap.inheritable = new->cap_effective; context->capset.cap.permitted = new->cap_permitted; + context->capset.cap.ambient = new->cap_ambient; context->type = AUDIT_CAPSET; } diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 172dc8ee0e3b..d771a3872500 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -335,6 +335,26 @@ static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) } /* only called from syscall */ +int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value) +{ + void **elem, *ptr; + int ret = 0; + + if (!map->ops->map_fd_sys_lookup_elem) + return -ENOTSUPP; + + rcu_read_lock(); + elem = array_map_lookup_elem(map, key); + if (elem && (ptr = READ_ONCE(*elem))) + *value = map->ops->map_fd_sys_lookup_elem(ptr); + else + ret = -ENOENT; + rcu_read_unlock(); + + return ret; +} + +/* only called from syscall */ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags) { @@ -400,6 +420,11 @@ static void prog_fd_array_put_ptr(void *ptr) bpf_prog_put(ptr); } +static u32 prog_fd_array_sys_lookup_elem(void *ptr) +{ + return ((struct bpf_prog *)ptr)->aux->id; +} + /* decrement refcnt of all bpf_progs that are stored in this map */ void bpf_fd_array_map_clear(struct bpf_map *map) { @@ -418,6 +443,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = prog_fd_array_get_ptr, .map_fd_put_ptr = prog_fd_array_put_ptr, + .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, }; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, @@ -452,38 +478,24 @@ static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee) static void *perf_event_fd_array_get_ptr(struct bpf_map *map, struct file *map_file, int fd) { - const struct perf_event_attr *attr; struct bpf_event_entry *ee; struct perf_event *event; struct file *perf_file; + u64 value; perf_file = perf_event_get(fd); if (IS_ERR(perf_file)) return perf_file; + ee = ERR_PTR(-EOPNOTSUPP); event = perf_file->private_data; - ee = ERR_PTR(-EINVAL); - - attr = perf_event_attrs(event); - if (IS_ERR(attr) || attr->inherit) + if (perf_event_read_local(event, &value) == -EOPNOTSUPP) goto err_out; - switch (attr->type) { - case PERF_TYPE_SOFTWARE: - if (attr->config != PERF_COUNT_SW_BPF_OUTPUT) - goto err_out; - /* fall-through */ - case PERF_TYPE_RAW: - case PERF_TYPE_HARDWARE: - ee = bpf_event_entry_gen(perf_file, map_file); - if (ee) - return ee; - ee = ERR_PTR(-ENOMEM); - /* fall-through */ - default: - break; - } - + ee = bpf_event_entry_gen(perf_file, map_file); + if (ee) + return ee; + ee = ERR_PTR(-ENOMEM); err_out: fput(perf_file); return ee; @@ -599,4 +611,5 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = bpf_map_fd_get_ptr, .map_fd_put_ptr = bpf_map_fd_put_ptr, + .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, }; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ea6033cba947..546113430049 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -236,3 +236,40 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); + +/** + * __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock + * @sk: socket to get cgroup from + * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains + * sk with connection information (IP addresses, etc.) May not contain + * cgroup info if it is a req sock. + * @type: The type of program to be exectuted + * + * socket passed is expected to be of type INET or INET6. + * + * The program type passed in via @type must be suitable for sock_ops + * filtering. No further check is performed to assert that. + * + * This function will return %-EPERM if any if an attached program was found + * and if it returned != 1 during execution. In all other cases, 0 is returned. + */ +int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, + struct bpf_sock_ops_kern *sock_ops, + enum bpf_attach_type type) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_prog *prog; + int ret = 0; + + + rcu_read_lock(); + + prog = rcu_dereference(cgrp->bpf.effective[type]); + if (prog) + ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM; + + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index dedf367f59bb..ad5f55922a13 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -763,10 +763,10 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); * * Decode and execute eBPF instructions. */ -static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) +static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, + u64 *stack) { - u64 stack[MAX_BPF_STACK / sizeof(u64)]; - u64 regs[MAX_BPF_REG], tmp; + u64 tmp; static const void *jumptable[256] = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ @@ -824,7 +824,7 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, /* Call instruction */ [BPF_JMP | BPF_CALL] = &&JMP_CALL, - [BPF_JMP | BPF_CALL | BPF_X] = &&JMP_TAIL_CALL, + [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, /* Jumps */ [BPF_JMP | BPF_JA] = &&JMP_JA, [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X, @@ -874,9 +874,6 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) #define CONT ({ insn++; goto select_insn; }) #define CONT_JMP ({ insn++; goto select_insn; }) - FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; - ARG1 = (u64) (unsigned long) ctx; - select_insn: goto *jumptable[insn->code]; @@ -1219,7 +1216,39 @@ load_byte: WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); return 0; } -STACK_FRAME_NON_STANDARD(__bpf_prog_run); /* jump table */ +STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */ + +#define PROG_NAME(stack_size) __bpf_prog_run##stack_size +#define DEFINE_BPF_PROG_RUN(stack_size) \ +static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \ +{ \ + u64 stack[stack_size / sizeof(u64)]; \ + u64 regs[MAX_BPF_REG]; \ +\ + FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ + ARG1 = (u64) (unsigned long) ctx; \ + return ___bpf_prog_run(regs, insn, stack); \ +} + +#define EVAL1(FN, X) FN(X) +#define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y) +#define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y) +#define EVAL4(FN, X, Y...) FN(X) EVAL3(FN, Y) +#define EVAL5(FN, X, Y...) FN(X) EVAL4(FN, Y) +#define EVAL6(FN, X, Y...) FN(X) EVAL5(FN, Y) + +EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192); +EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384); +EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512); + +#define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size), + +static unsigned int (*interpreters[])(const void *ctx, + const struct bpf_insn *insn) = { +EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) +EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) +EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) +}; bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) @@ -1268,7 +1297,9 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { - fp->bpf_func = (void *) __bpf_prog_run; + u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); + + fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 004334ea13ba..4fb463172aa8 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1244,6 +1244,26 @@ static void fd_htab_map_free(struct bpf_map *map) } /* only called from syscall */ +int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value) +{ + void **ptr; + int ret = 0; + + if (!map->ops->map_fd_sys_lookup_elem) + return -ENOTSUPP; + + rcu_read_lock(); + ptr = htab_map_lookup_elem(map, key); + if (ptr) + *value = map->ops->map_fd_sys_lookup_elem(READ_ONCE(*ptr)); + else + ret = -ENOENT; + rcu_read_unlock(); + + return ret; +} + +/* only called from syscall */ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags) { @@ -1305,4 +1325,5 @@ const struct bpf_map_ops htab_of_maps_map_ops = { .map_delete_elem = htab_map_delete_elem, .map_fd_get_ptr = bpf_map_fd_get_ptr, .map_fd_put_ptr = bpf_map_fd_put_ptr, + .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, }; diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 59bcdf821ae4..1da574612bea 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -95,3 +95,8 @@ void bpf_map_fd_put_ptr(void *ptr) */ bpf_map_put(ptr); } + +u32 bpf_map_fd_sys_lookup_elem(void *ptr) +{ + return ((struct bpf_map *)ptr)->id; +} diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h index 177fadb689dc..6183db9ec08c 100644 --- a/kernel/bpf/map_in_map.h +++ b/kernel/bpf/map_in_map.h @@ -19,5 +19,6 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file, int ufd); void bpf_map_fd_put_ptr(void *ptr); +u32 bpf_map_fd_sys_lookup_elem(void *ptr); #endif diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 265a0d854e33..045646da97cc 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -22,8 +22,20 @@ #include <linux/filter.h> #include <linux/version.h> #include <linux/kernel.h> +#include <linux/idr.h> + +#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ + (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ + (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ + (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) +#define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) +#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map)) DEFINE_PER_CPU(int, bpf_prog_active); +static DEFINE_IDR(prog_idr); +static DEFINE_SPINLOCK(prog_idr_lock); +static DEFINE_IDR(map_idr); +static DEFINE_SPINLOCK(map_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly; @@ -114,6 +126,37 @@ static void bpf_map_uncharge_memlock(struct bpf_map *map) free_uid(user); } +static int bpf_map_alloc_id(struct bpf_map *map) +{ + int id; + + spin_lock_bh(&map_idr_lock); + id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); + if (id > 0) + map->id = id; + spin_unlock_bh(&map_idr_lock); + + if (WARN_ON_ONCE(!id)) + return -ENOSPC; + + return id > 0 ? 0 : id; +} + +static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) +{ + if (do_idr_lock) + spin_lock_bh(&map_idr_lock); + else + __acquire(&map_idr_lock); + + idr_remove(&map_idr, map->id); + + if (do_idr_lock) + spin_unlock_bh(&map_idr_lock); + else + __release(&map_idr_lock); +} + /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { @@ -135,14 +178,21 @@ static void bpf_map_put_uref(struct bpf_map *map) /* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */ -void bpf_map_put(struct bpf_map *map) +static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) { if (atomic_dec_and_test(&map->refcnt)) { + /* bpf_map_free_id() must be called first */ + bpf_map_free_id(map, do_idr_lock); INIT_WORK(&map->work, bpf_map_free_deferred); schedule_work(&map->work); } } +void bpf_map_put(struct bpf_map *map) +{ + __bpf_map_put(map, true); +} + void bpf_map_put_with_uref(struct bpf_map *map) { bpf_map_put_uref(map); @@ -166,10 +216,12 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) const struct bpf_map *map = filp->private_data; const struct bpf_array *array; u32 owner_prog_type = 0; + u32 owner_jited = 0; if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { array = container_of(map, struct bpf_array, map); owner_prog_type = array->owner_prog_type; + owner_jited = array->owner_jited; } seq_printf(m, @@ -186,9 +238,12 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->map_flags, map->pages * 1ULL << PAGE_SHIFT); - if (owner_prog_type) + if (owner_prog_type) { seq_printf(m, "owner_prog_type:\t%u\n", owner_prog_type); + seq_printf(m, "owner_jited:\t%u\n", + owner_jited); + } } #endif @@ -236,11 +291,22 @@ static int map_create(union bpf_attr *attr) if (err) goto free_map_nouncharge; - err = bpf_map_new_fd(map); - if (err < 0) - /* failed to allocate fd */ + err = bpf_map_alloc_id(map); + if (err) goto free_map; + err = bpf_map_new_fd(map); + if (err < 0) { + /* failed to allocate fd. + * bpf_map_put() is needed because the above + * bpf_map_alloc_id() has published the map + * to the userspace and the userspace may + * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. + */ + bpf_map_put(map); + return err; + } + trace_bpf_map_create(map, err); return err; @@ -295,6 +361,28 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd) return map; } +/* map_idr_lock should have been held */ +static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, + bool uref) +{ + int refold; + + refold = __atomic_add_unless(&map->refcnt, 1, 0); + + if (refold >= BPF_MAX_REFCNT) { + __bpf_map_put(map, false); + return ERR_PTR(-EBUSY); + } + + if (!refold) + return ERR_PTR(-ENOENT); + + if (uref) + atomic_inc(&map->usercnt); + + return map; +} + int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; @@ -322,19 +410,18 @@ static int map_lookup_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - err = -ENOMEM; - key = kmalloc(map->key_size, GFP_USER); - if (!key) + key = memdup_user(ukey, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); goto err_put; - - err = -EFAULT; - if (copy_from_user(key, ukey, map->key_size) != 0) - goto free_key; + } if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) value_size = round_up(map->value_size, 8) * num_possible_cpus(); + else if (IS_FD_MAP(map)) + value_size = sizeof(u32); else value_size = map->value_size; @@ -350,9 +437,10 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_array_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS || - map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { - err = -ENOTSUPP; + } else if (IS_FD_ARRAY(map)) { + err = bpf_fd_array_map_lookup_elem(map, key, value); + } else if (IS_FD_HASH(map)) { + err = bpf_fd_htab_map_lookup_elem(map, key, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); @@ -402,14 +490,11 @@ static int map_update_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - err = -ENOMEM; - key = kmalloc(map->key_size, GFP_USER); - if (!key) + key = memdup_user(ukey, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); goto err_put; - - err = -EFAULT; - if (copy_from_user(key, ukey, map->key_size) != 0) - goto free_key; + } if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || @@ -488,14 +573,11 @@ static int map_delete_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - err = -ENOMEM; - key = kmalloc(map->key_size, GFP_USER); - if (!key) + key = memdup_user(ukey, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); goto err_put; - - err = -EFAULT; - if (copy_from_user(key, ukey, map->key_size) != 0) - goto free_key; + } preempt_disable(); __this_cpu_inc(bpf_prog_active); @@ -507,7 +589,6 @@ static int map_delete_elem(union bpf_attr *attr) if (!err) trace_bpf_map_delete_elem(map, ufd, key); -free_key: kfree(key); err_put: fdput(f); @@ -536,14 +617,11 @@ static int map_get_next_key(union bpf_attr *attr) return PTR_ERR(map); if (ukey) { - err = -ENOMEM; - key = kmalloc(map->key_size, GFP_USER); - if (!key) + key = memdup_user(ukey, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); goto err_put; - - err = -EFAULT; - if (copy_from_user(key, ukey, map->key_size) != 0) - goto free_key; + } } else { key = NULL; } @@ -650,6 +728,42 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) free_uid(user); } +static int bpf_prog_alloc_id(struct bpf_prog *prog) +{ + int id; + + spin_lock_bh(&prog_idr_lock); + id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC); + if (id > 0) + prog->aux->id = id; + spin_unlock_bh(&prog_idr_lock); + + /* id is in [1, INT_MAX) */ + if (WARN_ON_ONCE(!id)) + return -ENOSPC; + + return id > 0 ? 0 : id; +} + +static void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) +{ + /* cBPF to eBPF migrations are currently not in the idr store. */ + if (!prog->aux->id) + return; + + if (do_idr_lock) + spin_lock_bh(&prog_idr_lock); + else + __acquire(&prog_idr_lock); + + idr_remove(&prog_idr, prog->aux->id); + + if (do_idr_lock) + spin_unlock_bh(&prog_idr_lock); + else + __release(&prog_idr_lock); +} + static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); @@ -659,14 +773,21 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) bpf_prog_free(aux->prog); } -void bpf_prog_put(struct bpf_prog *prog) +static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic_dec_and_test(&prog->aux->refcnt)) { trace_bpf_prog_put_rcu(prog); + /* bpf_prog_free_id() must be called first */ + bpf_prog_free_id(prog, do_idr_lock); bpf_prog_kallsyms_del(prog); call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } } + +void bpf_prog_put(struct bpf_prog *prog) +{ + __bpf_prog_put(prog, true); +} EXPORT_SYMBOL_GPL(bpf_prog_put); static int bpf_prog_release(struct inode *inode, struct file *filp) @@ -748,6 +869,24 @@ struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc); +/* prog_idr_lock should have been held */ +static struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) +{ + int refold; + + refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0); + + if (refold >= BPF_MAX_REFCNT) { + __bpf_prog_put(prog, false); + return ERR_PTR(-EBUSY); + } + + if (!refold) + return ERR_PTR(-ENOENT); + + return prog; +} + static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) { struct fd f = fdget(ufd); @@ -815,7 +954,9 @@ static int bpf_prog_load(union bpf_attr *attr) attr->kern_version != LINUX_VERSION_CODE) return -EINVAL; - if (type != BPF_PROG_TYPE_SOCKET_FILTER && !capable(CAP_SYS_ADMIN)) + if (type != BPF_PROG_TYPE_SOCKET_FILTER && + type != BPF_PROG_TYPE_CGROUP_SKB && + !capable(CAP_SYS_ADMIN)) return -EPERM; /* plain bpf_prog allocation */ @@ -855,11 +996,22 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_used_maps; - err = bpf_prog_new_fd(prog); - if (err < 0) - /* failed to allocate fd */ + err = bpf_prog_alloc_id(prog); + if (err) goto free_used_maps; + err = bpf_prog_new_fd(prog); + if (err < 0) { + /* failed to allocate fd. + * bpf_prog_put() is needed because the above + * bpf_prog_alloc_id() has published the prog + * to the userspace and the userspace may + * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID. + */ + bpf_prog_put(prog); + return err; + } + bpf_prog_kallsyms_add(prog); trace_bpf_prog_load(prog, err); return err; @@ -919,6 +1071,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_INET_SOCK_CREATE: ptype = BPF_PROG_TYPE_CGROUP_SOCK; break; + case BPF_CGROUP_SOCK_OPS: + ptype = BPF_PROG_TYPE_SOCK_OPS; + break; default: return -EINVAL; } @@ -959,6 +1114,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_SOCK_OPS: cgrp = cgroup_get_from_fd(attr->target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); @@ -973,6 +1129,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) return ret; } + #endif /* CONFIG_CGROUP_BPF */ #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration @@ -997,6 +1154,237 @@ static int bpf_prog_test_run(const union bpf_attr *attr, return ret; } +#define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id + +static int bpf_obj_get_next_id(const union bpf_attr *attr, + union bpf_attr __user *uattr, + struct idr *idr, + spinlock_t *lock) +{ + u32 next_id = attr->start_id; + int err = 0; + + if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + next_id++; + spin_lock_bh(lock); + if (!idr_get_next(idr, &next_id)) + err = -ENOENT; + spin_unlock_bh(lock); + + if (!err) + err = put_user(next_id, &uattr->next_id); + + return err; +} + +#define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id + +static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + u32 id = attr->prog_id; + int fd; + + if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + spin_lock_bh(&prog_idr_lock); + prog = idr_find(&prog_idr, id); + if (prog) + prog = bpf_prog_inc_not_zero(prog); + else + prog = ERR_PTR(-ENOENT); + spin_unlock_bh(&prog_idr_lock); + + if (IS_ERR(prog)) + return PTR_ERR(prog); + + fd = bpf_prog_new_fd(prog); + if (fd < 0) + bpf_prog_put(prog); + + return fd; +} + +#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id + +static int bpf_map_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_map *map; + u32 id = attr->map_id; + int fd; + + if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + spin_lock_bh(&map_idr_lock); + map = idr_find(&map_idr, id); + if (map) + map = bpf_map_inc_not_zero(map, true); + else + map = ERR_PTR(-ENOENT); + spin_unlock_bh(&map_idr_lock); + + if (IS_ERR(map)) + return PTR_ERR(map); + + fd = bpf_map_new_fd(map); + if (fd < 0) + bpf_map_put(map); + + return fd; +} + +static int check_uarg_tail_zero(void __user *uaddr, + size_t expected_size, + size_t actual_size) +{ + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + int err; + + if (actual_size <= expected_size) + return 0; + + addr = uaddr + expected_size; + end = uaddr + actual_size; + + for (; addr < end; addr++) { + err = get_user(val, addr); + if (err) + return err; + if (val) + return -E2BIG; + } + + return 0; +} + +static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); + struct bpf_prog_info info = {}; + u32 info_len = attr->info.info_len; + char __user *uinsns; + u32 ulen; + int err; + + err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + if (err) + return err; + info_len = min_t(u32, sizeof(info), info_len); + + if (copy_from_user(&info, uinfo, info_len)) + return err; + + info.type = prog->type; + info.id = prog->aux->id; + + memcpy(info.tag, prog->tag, sizeof(prog->tag)); + + if (!capable(CAP_SYS_ADMIN)) { + info.jited_prog_len = 0; + info.xlated_prog_len = 0; + goto done; + } + + ulen = info.jited_prog_len; + info.jited_prog_len = prog->jited_len; + if (info.jited_prog_len && ulen) { + uinsns = u64_to_user_ptr(info.jited_prog_insns); + ulen = min_t(u32, info.jited_prog_len, ulen); + if (copy_to_user(uinsns, prog->bpf_func, ulen)) + return -EFAULT; + } + + ulen = info.xlated_prog_len; + info.xlated_prog_len = bpf_prog_size(prog->len); + if (info.xlated_prog_len && ulen) { + uinsns = u64_to_user_ptr(info.xlated_prog_insns); + ulen = min_t(u32, info.xlated_prog_len, ulen); + if (copy_to_user(uinsns, prog->insnsi, ulen)) + return -EFAULT; + } + +done: + if (copy_to_user(uinfo, &info, info_len) || + put_user(info_len, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} + +static int bpf_map_get_info_by_fd(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); + struct bpf_map_info info = {}; + u32 info_len = attr->info.info_len; + int err; + + err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + if (err) + return err; + info_len = min_t(u32, sizeof(info), info_len); + + info.type = map->map_type; + info.id = map->id; + info.key_size = map->key_size; + info.value_size = map->value_size; + info.max_entries = map->max_entries; + info.map_flags = map->map_flags; + + if (copy_to_user(uinfo, &info, info_len) || + put_user(info_len, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} + +#define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info + +static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + int ufd = attr->info.bpf_fd; + struct fd f; + int err; + + if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD)) + return -EINVAL; + + f = fdget(ufd); + if (!f.file) + return -EBADFD; + + if (f.file->f_op == &bpf_prog_fops) + err = bpf_prog_get_info_by_fd(f.file->private_data, attr, + uattr); + else if (f.file->f_op == &bpf_map_fops) + err = bpf_map_get_info_by_fd(f.file->private_data, attr, + uattr); + else + err = -EINVAL; + + fdput(f); + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -1016,23 +1404,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz * user-space does not rely on any kernel feature * extensions we dont know about yet. */ - if (size > sizeof(attr)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uattr + sizeof(attr); - end = (void __user *)uattr + size; - - for (; addr < end; addr++) { - err = get_user(val, addr); - if (err) - return err; - if (val) - return -E2BIG; - } - size = sizeof(attr); - } + err = check_uarg_tail_zero(uattr, sizeof(attr), size); + if (err) + return err; + size = min_t(u32, size, sizeof(attr)); /* copy attributes from user space, may be less than sizeof(bpf_attr) */ if (copy_from_user(&attr, uattr, size) != 0) @@ -1074,6 +1449,23 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr); break; + case BPF_PROG_GET_NEXT_ID: + err = bpf_obj_get_next_id(&attr, uattr, + &prog_idr, &prog_idr_lock); + break; + case BPF_MAP_GET_NEXT_ID: + err = bpf_obj_get_next_id(&attr, uattr, + &map_idr, &map_idr_lock); + break; + case BPF_PROG_GET_FD_BY_ID: + err = bpf_prog_get_fd_by_id(&attr); + break; + case BPF_MAP_GET_FD_BY_ID: + err = bpf_map_get_fd_by_id(&attr); + break; + case BPF_OBJ_GET_INFO_BY_FD: + err = bpf_obj_get_info_by_fd(&attr, uattr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 339c8a1371de..6a86723c5b64 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -546,20 +546,6 @@ static int check_reg_arg(struct bpf_reg_state *regs, u32 regno, return 0; } -static int bpf_size_to_bytes(int bpf_size) -{ - if (bpf_size == BPF_W) - return 4; - else if (bpf_size == BPF_H) - return 2; - else if (bpf_size == BPF_B) - return 1; - else if (bpf_size == BPF_DW) - return 8; - else - return -EINVAL; -} - static bool is_spillable_regtype(enum bpf_reg_type type) { switch (type) { @@ -758,15 +744,29 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, } /* check access to 'struct bpf_context' fields */ -static int check_ctx_access(struct bpf_verifier_env *env, int off, int size, +static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type) { + struct bpf_insn_access_aux info = { + .reg_type = *reg_type, + }; + /* for analyzer ctx accesses are already validated and converted */ if (env->analyzer_ops) return 0; if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) { + env->prog->aux->ops->is_valid_access(off, size, t, &info)) { + /* A non zero info.ctx_field_size indicates that this field is a + * candidate for later verifier transformation to load the whole + * field and then apply a mask when accessed with a narrower + * access than actual ctx access size. A zero info.ctx_field_size + * will only allow for whole field access and rejects any other + * type of narrower access. + */ + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + *reg_type = info.reg_type; + /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; @@ -868,7 +868,7 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ -static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, +static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int bpf_size, enum bpf_access_type t, int value_regno) { @@ -911,7 +911,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, verbose("R%d leaks addr into ctx\n", value_regno); return -EACCES; } - err = check_ctx_access(env, off, size, t, ®_type); + err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { mark_reg_unknown_value_and_range(state->regs, value_regno); @@ -926,6 +926,10 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, verbose("invalid stack off=%d size=%d\n", off, size); return -EACCES; } + + if (env->prog->aux->stack_depth < -off) + env->prog->aux->stack_depth = -off; + if (t == BPF_WRITE) { if (!env->allow_ptr_leaks && state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL && @@ -968,7 +972,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, return err; } -static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn) +static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { struct bpf_reg_state *regs = env->cur_state.regs; int err; @@ -989,14 +993,19 @@ static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + if (is_pointer_value(env, insn->src_reg)) { + verbose("R%d leaks addr into mem\n", insn->src_reg); + return -EACCES; + } + /* check whether atomic_add can read the memory */ - err = check_mem_access(env, insn->dst_reg, insn->off, + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); if (err) return err; /* check whether atomic_add can write into the same memory */ - return check_mem_access(env, insn->dst_reg, insn->off, + return check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1); } @@ -1032,6 +1041,9 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, return -EACCES; } + if (env->prog->aux->stack_depth < -off) + env->prog->aux->stack_depth = -off; + if (meta && meta->raw_mode) { meta->access_size = access_size; meta->regno = regno; @@ -1339,8 +1351,8 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_PACKET_END) continue; - reg->type = UNKNOWN_VALUE; - reg->imm = 0; + __mark_reg_unknown_value(state->spilled_regs, + i / BPF_REG_SIZE); } } @@ -1409,7 +1421,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) * is inferred from register state. */ for (i = 0; i < meta.access_size; i++) { - err = check_mem_access(env, meta.regno, i, BPF_B, BPF_WRITE, -1); + err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1); if (err) return err; } @@ -1645,6 +1657,65 @@ static int evaluate_reg_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } +static int evaluate_reg_imm_alu_unknown(struct bpf_verifier_env *env, + struct bpf_insn *insn) +{ + struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *dst_reg = ®s[insn->dst_reg]; + struct bpf_reg_state *src_reg = ®s[insn->src_reg]; + u8 opcode = BPF_OP(insn->code); + s64 imm_log2 = __ilog2_u64((long long)dst_reg->imm); + + /* BPF_X code with src_reg->type UNKNOWN_VALUE here. */ + if (src_reg->imm > 0 && dst_reg->imm) { + switch (opcode) { + case BPF_ADD: + /* dreg += sreg + * where both have zero upper bits. Adding them + * can only result making one more bit non-zero + * in the larger value. + * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47) + * 0xffff (imm=48) + 0xffff = 0x1fffe (imm=47) + */ + dst_reg->imm = min(src_reg->imm, 63 - imm_log2); + dst_reg->imm--; + break; + case BPF_AND: + /* dreg &= sreg + * AND can not extend zero bits only shrink + * Ex. 0x00..00ffffff + * & 0x0f..ffffffff + * ---------------- + * 0x00..00ffffff + */ + dst_reg->imm = max(src_reg->imm, 63 - imm_log2); + break; + case BPF_OR: + /* dreg |= sreg + * OR can only extend zero bits + * Ex. 0x00..00ffffff + * | 0x0f..ffffffff + * ---------------- + * 0x0f..00ffffff + */ + dst_reg->imm = min(src_reg->imm, 63 - imm_log2); + break; + case BPF_SUB: + case BPF_MUL: + case BPF_RSH: + case BPF_LSH: + /* These may be flushed out later */ + default: + mark_reg_unknown_value(regs, insn->dst_reg); + } + } else { + mark_reg_unknown_value(regs, insn->dst_reg); + } + + dst_reg->type = UNKNOWN_VALUE; + return 0; +} + static int evaluate_reg_imm_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) { @@ -1654,6 +1725,9 @@ static int evaluate_reg_imm_alu(struct bpf_verifier_env *env, u8 opcode = BPF_OP(insn->code); u64 dst_imm = dst_reg->imm; + if (BPF_SRC(insn->code) == BPF_X && src_reg->type == UNKNOWN_VALUE) + return evaluate_reg_imm_alu_unknown(env, insn); + /* dst_reg->type == CONST_IMM here. Simulate execution of insns * containing ALU ops. Don't care about overflow or negative * values, just add/sub/... them; registers are in u64. @@ -1945,6 +2019,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) */ regs[insn->dst_reg].type = CONST_IMM; regs[insn->dst_reg].imm = insn->imm; + regs[insn->dst_reg].id = 0; regs[insn->dst_reg].max_value = insn->imm; regs[insn->dst_reg].min_value = insn->imm; regs[insn->dst_reg].min_align = calc_align(insn->imm); @@ -2402,6 +2477,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) regs[insn->dst_reg].type = CONST_IMM; regs[insn->dst_reg].imm = imm; + regs[insn->dst_reg].id = 0; return 0; } @@ -2821,6 +2897,8 @@ static bool states_equal(struct bpf_verifier_env *env, return false; if (i % BPF_REG_SIZE) continue; + if (old->stack_slot_type[i] != STACK_SPILL) + continue; if (memcmp(&old->spilled_regs[i / BPF_REG_SIZE], &cur->spilled_regs[i / BPF_REG_SIZE], sizeof(old->spilled_regs[0]))) @@ -2982,18 +3060,12 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (src_reg + off) is readable, * the state of dst_reg will be updated by this func */ - err = check_mem_access(env, insn->src_reg, insn->off, + err = check_mem_access(env, insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, insn->dst_reg); if (err) return err; - if (BPF_SIZE(insn->code) != BPF_W && - BPF_SIZE(insn->code) != BPF_DW) { - insn_idx++; - continue; - } - prev_src_type = &env->insn_aux_data[insn_idx].ptr_type; if (*prev_src_type == NOT_INIT) { @@ -3021,7 +3093,7 @@ static int do_check(struct bpf_verifier_env *env) enum bpf_reg_type *prev_dst_type, dst_reg_type; if (BPF_MODE(insn->code) == BPF_XADD) { - err = check_xadd(env, insn); + err = check_xadd(env, insn_idx, insn); if (err) return err; insn_idx++; @@ -3040,7 +3112,7 @@ static int do_check(struct bpf_verifier_env *env) dst_reg_type = regs[insn->dst_reg].type; /* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, insn->dst_reg, insn->off, + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, insn->src_reg); if (err) @@ -3069,7 +3141,7 @@ static int do_check(struct bpf_verifier_env *env) return err; /* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, insn->dst_reg, insn->off, + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1); if (err) @@ -3167,7 +3239,8 @@ process_bpf_exit: insn_idx++; } - verbose("processed %d insns\n", insn_processed); + verbose("processed %d insns, stack depth %d\n", + insn_processed, env->prog->aux->stack_depth); return 0; } @@ -3367,11 +3440,13 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of static int convert_ctx_accesses(struct bpf_verifier_env *env) { const struct bpf_verifier_ops *ops = env->prog->aux->ops; + int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; struct bpf_prog *new_prog; enum bpf_access_type type; - int i, cnt, delta = 0; + bool is_narrower_load; + u32 target_size; if (ops->gen_prologue) { cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, @@ -3411,12 +3486,52 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) continue; - cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog); - if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; + size = BPF_LDST_BYTES(insn); + + /* If the read access is a narrower load of the field, + * convert to a 4/8-byte load, to minimum program type specific + * convert_ctx_access changes. If conversion is successful, + * we will apply proper mask to the result. + */ + is_narrower_load = size < ctx_field_size; + if (is_narrower_load) { + u32 off = insn->off; + u8 size_code; + + if (type == BPF_WRITE) { + verbose("bpf verifier narrow ctx access misconfigured\n"); + return -EINVAL; + } + + size_code = BPF_H; + if (ctx_field_size == 4) + size_code = BPF_W; + else if (ctx_field_size == 8) + size_code = BPF_DW; + + insn->off = off & ~(ctx_field_size - 1); + insn->code = BPF_LDX | BPF_MEM | size_code; + } + + target_size = 0; + cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog, + &target_size); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || + (ctx_field_size && !target_size)) { verbose("bpf verifier is misconfigured\n"); return -EINVAL; } + if (is_narrower_load && size < target_size) { + if (ctx_field_size <= 4) + insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, + (1 << size * 8) - 1); + else + insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, + (1 << size * 8) - 1); + } + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; @@ -3462,6 +3577,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) * the program array. */ prog->cb_access = 1; + env->prog->aux->stack_depth = MAX_BPF_STACK; /* mark bpf_tail_call as different opcode to avoid * conditional branch in the interpeter for every normal @@ -3469,7 +3585,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) * that doesn't support bpf_tail_call yet */ insn->imm = 0; - insn->code |= BPF_X; + insn->code = BPF_JMP | BPF_TAIL_CALL; continue; } diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile index 387348a40c64..ce693ccb8c58 100644 --- a/kernel/cgroup/Makefile +++ b/kernel/cgroup/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_CGROUP_FREEZER) += freezer.o obj-$(CONFIG_CGROUP_PIDS) += pids.o obj-$(CONFIG_CGROUP_RDMA) += rdma.o obj-$(CONFIG_CPUSETS) += cpuset.o +obj-$(CONFIG_CGROUP_DEBUG) += debug.o diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 00f4d6bf048f..793565c05742 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -192,6 +192,8 @@ int cgroup_rmdir(struct kernfs_node *kn); int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root); +int cgroup_task_count(const struct cgroup *cgrp); + /* * namespace.c */ diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 85d75152402d..7bf4b1533f34 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -334,19 +334,15 @@ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question - * - * Return the number of tasks in the cgroup. The returned number can be - * higher than the actual number of tasks due to css_set references from - * namespace roots and temporary usages. */ -static int cgroup_task_count(const struct cgroup *cgrp) +int cgroup_task_count(const struct cgroup *cgrp) { int count = 0; struct cgrp_cset_link *link; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) - count += refcount_read(&link->cset->refcount); + count += link->cset->nr_tasks; spin_unlock_irq(&css_set_lock); return count; } @@ -1263,150 +1259,3 @@ static int __init cgroup_no_v1(char *str) return 1; } __setup("cgroup_no_v1=", cgroup_no_v1); - - -#ifdef CONFIG_CGROUP_DEBUG -static struct cgroup_subsys_state * -debug_css_alloc(struct cgroup_subsys_state *parent_css) -{ - struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL); - - if (!css) - return ERR_PTR(-ENOMEM); - - return css; -} - -static void debug_css_free(struct cgroup_subsys_state *css) -{ - kfree(css); -} - -static u64 debug_taskcount_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - return cgroup_task_count(css->cgroup); -} - -static u64 current_css_set_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - return (u64)(unsigned long)current->cgroups; -} - -static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - u64 count; - - rcu_read_lock(); - count = refcount_read(&task_css_set(current)->refcount); - rcu_read_unlock(); - return count; -} - -static int current_css_set_cg_links_read(struct seq_file *seq, void *v) -{ - struct cgrp_cset_link *link; - struct css_set *cset; - char *name_buf; - - name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); - if (!name_buf) - return -ENOMEM; - - spin_lock_irq(&css_set_lock); - rcu_read_lock(); - cset = rcu_dereference(current->cgroups); - list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { - struct cgroup *c = link->cgrp; - - cgroup_name(c, name_buf, NAME_MAX + 1); - seq_printf(seq, "Root %d group %s\n", - c->root->hierarchy_id, name_buf); - } - rcu_read_unlock(); - spin_unlock_irq(&css_set_lock); - kfree(name_buf); - return 0; -} - -#define MAX_TASKS_SHOWN_PER_CSS 25 -static int cgroup_css_links_read(struct seq_file *seq, void *v) -{ - struct cgroup_subsys_state *css = seq_css(seq); - struct cgrp_cset_link *link; - - spin_lock_irq(&css_set_lock); - list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { - struct css_set *cset = link->cset; - struct task_struct *task; - int count = 0; - - seq_printf(seq, "css_set %pK\n", cset); - - list_for_each_entry(task, &cset->tasks, cg_list) { - if (count++ > MAX_TASKS_SHOWN_PER_CSS) - goto overflow; - seq_printf(seq, " task %d\n", task_pid_vnr(task)); - } - - list_for_each_entry(task, &cset->mg_tasks, cg_list) { - if (count++ > MAX_TASKS_SHOWN_PER_CSS) - goto overflow; - seq_printf(seq, " task %d\n", task_pid_vnr(task)); - } - continue; - overflow: - seq_puts(seq, " ...\n"); - } - spin_unlock_irq(&css_set_lock); - return 0; -} - -static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft) -{ - return (!cgroup_is_populated(css->cgroup) && - !css_has_online_children(&css->cgroup->self)); -} - -static struct cftype debug_files[] = { - { - .name = "taskcount", - .read_u64 = debug_taskcount_read, - }, - - { - .name = "current_css_set", - .read_u64 = current_css_set_read, - }, - - { - .name = "current_css_set_refcount", - .read_u64 = current_css_set_refcount_read, - }, - - { - .name = "current_css_set_cg_links", - .seq_show = current_css_set_cg_links_read, - }, - - { - .name = "cgroup_css_links", - .seq_show = cgroup_css_links_read, - }, - - { - .name = "releasable", - .read_u64 = releasable_read, - }, - - { } /* terminate */ -}; - -struct cgroup_subsys debug_cgrp_subsys = { - .css_alloc = debug_css_alloc, - .css_free = debug_css_free, - .legacy_cftypes = debug_files, -}; -#endif /* CONFIG_CGROUP_DEBUG */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8d4e85eae42c..620794a20a33 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -573,6 +573,11 @@ static int css_set_count = 1; /* 1 for init_css_set */ /** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set + * + * css_set_populated() should be the same as !!cset->nr_tasks at steady + * state. However, css_set_populated() can be called while a task is being + * added to or removed from the linked list before the nr_tasks is + * properly updated. Hence, we can't just look at ->nr_tasks here. */ static bool css_set_populated(struct css_set *cset) { @@ -1542,10 +1547,56 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, return len; } +static int parse_cgroup_root_flags(char *data, unsigned int *root_flags) +{ + char *token; + + *root_flags = 0; + + if (!data) + return 0; + + while ((token = strsep(&data, ",")) != NULL) { + if (!strcmp(token, "nsdelegate")) { + *root_flags |= CGRP_ROOT_NS_DELEGATE; + continue; + } + + pr_err("cgroup2: unknown option \"%s\"\n", token); + return -EINVAL; + } + + return 0; +} + +static void apply_cgroup_root_flags(unsigned int root_flags) +{ + if (current->nsproxy->cgroup_ns == &init_cgroup_ns) { + if (root_flags & CGRP_ROOT_NS_DELEGATE) + cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE; + else + cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE; + } +} + +static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) +{ + if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) + seq_puts(seq, ",nsdelegate"); + return 0; +} + static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) { - pr_err("remount is not allowed\n"); - return -EINVAL; + unsigned int root_flags; + int ret; + + ret = parse_cgroup_root_flags(data, &root_flags); + if (ret) + return ret; + + apply_cgroup_root_flags(root_flags); + return 0; } /* @@ -1598,6 +1649,7 @@ static void cgroup_enable_task_cg_lists(void) css_set_update_populated(cset, true); list_add_tail(&p->cg_list, &cset->tasks); get_css_set(cset); + cset->nr_tasks++; } spin_unlock(&p->sighand->siglock); } while_each_thread(g, p); @@ -1784,6 +1836,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, { struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct dentry *dentry; + int ret; get_cgroup_ns(ns); @@ -1801,16 +1854,21 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, cgroup_enable_task_cg_lists(); if (fs_type == &cgroup2_fs_type) { - if (data) { - pr_err("cgroup2: unknown option \"%s\"\n", (char *)data); + unsigned int root_flags; + + ret = parse_cgroup_root_flags(data, &root_flags); + if (ret) { put_cgroup_ns(ns); - return ERR_PTR(-EINVAL); + return ERR_PTR(ret); } + cgrp_dfl_visible = true; cgroup_get_live(&cgrp_dfl_root.cgrp); dentry = cgroup_do_mount(&cgroup2_fs_type, flags, &cgrp_dfl_root, CGROUP2_SUPER_MAGIC, ns); + if (!IS_ERR(dentry)) + apply_cgroup_root_flags(root_flags); } else { dentry = cgroup1_mount(&cgroup_fs_type, flags, data, CGROUP_SUPER_MAGIC, ns); @@ -2064,8 +2122,10 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) struct css_set *to_cset = cset->mg_dst_cset; get_css_set(to_cset); + to_cset->nr_tasks++; css_set_move_task(task, from_cset, to_cset, true); put_css_set_locked(from_cset); + from_cset->nr_tasks--; } } spin_unlock_irq(&css_set_lock); @@ -2355,27 +2415,14 @@ static int cgroup_procs_write_permission(struct task_struct *task, struct cgroup *dst_cgrp, struct kernfs_open_file *of) { - int ret = 0; - - if (cgroup_on_dfl(dst_cgrp)) { - struct super_block *sb = of->file->f_path.dentry->d_sb; - struct cgroup *cgrp; - struct inode *inode; - - spin_lock_irq(&css_set_lock); - cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); - spin_unlock_irq(&css_set_lock); - - while (!cgroup_is_descendant(dst_cgrp, cgrp)) - cgrp = cgroup_parent(cgrp); + struct super_block *sb = of->file->f_path.dentry->d_sb; + struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; + struct cgroup *root_cgrp = ns->root_cset->dfl_cgrp; + struct cgroup *src_cgrp, *com_cgrp; + struct inode *inode; + int ret; - ret = -ENOMEM; - inode = kernfs_get_inode(sb, cgrp->procs_file.kn); - if (inode) { - ret = inode_permission(inode, MAY_WRITE); - iput(inode); - } - } else { + if (!cgroup_on_dfl(dst_cgrp)) { const struct cred *cred = current_cred(); const struct cred *tcred = get_task_cred(task); @@ -2383,14 +2430,47 @@ static int cgroup_procs_write_permission(struct task_struct *task, * even if we're attaching all tasks in the thread group, * we only need to check permissions on one of them. */ - if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && - !uid_eq(cred->euid, tcred->uid) && - !uid_eq(cred->euid, tcred->suid)) + if (uid_eq(cred->euid, GLOBAL_ROOT_UID) || + uid_eq(cred->euid, tcred->uid) || + uid_eq(cred->euid, tcred->suid)) + ret = 0; + else ret = -EACCES; + put_cred(tcred); + return ret; } - return ret; + /* find the source cgroup */ + spin_lock_irq(&css_set_lock); + src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); + spin_unlock_irq(&css_set_lock); + + /* and the common ancestor */ + com_cgrp = src_cgrp; + while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) + com_cgrp = cgroup_parent(com_cgrp); + + /* %current should be authorized to migrate to the common ancestor */ + inode = kernfs_get_inode(sb, com_cgrp->procs_file.kn); + if (!inode) + return -ENOMEM; + + ret = inode_permission(inode, MAY_WRITE); + iput(inode); + if (ret) + return ret; + + /* + * If namespaces are delegation boundaries, %current must be able + * to see both source and destination cgroups from its namespace. + */ + if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && + (!cgroup_is_descendant(src_cgrp, root_cgrp) || + !cgroup_is_descendant(dst_cgrp, root_cgrp))) + return -ENOENT; + + return 0; } /* @@ -2954,11 +3034,23 @@ static void cgroup_file_release(struct kernfs_open_file *of) static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { + struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of->kn->priv; struct cgroup_subsys_state *css; int ret; + /* + * If namespaces are delegation boundaries, disallow writes to + * files in an non-init namespace root from inside the namespace + * except for the files explicitly marked delegatable - + * cgroup.procs and cgroup.subtree_control. + */ + if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && + !(cft->flags & CFTYPE_NS_DELEGATABLE) && + ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp) + return -EPERM; + if (cft->write) return cft->write(of, buf, nbytes, off); @@ -3792,6 +3884,7 @@ static int cgroup_procs_show(struct seq_file *s, void *v) static struct cftype cgroup_base_files[] = { { .name = "cgroup.procs", + .flags = CFTYPE_NS_DELEGATABLE, .file_offset = offsetof(struct cgroup, procs_file), .release = cgroup_procs_release, .seq_start = cgroup_procs_start, @@ -3805,6 +3898,7 @@ static struct cftype cgroup_base_files[] = { }, { .name = "cgroup.subtree_control", + .flags = CFTYPE_NS_DELEGATABLE, .seq_show = cgroup_subtree_control_show, .write = cgroup_subtree_control_write, }, @@ -4393,6 +4487,7 @@ int cgroup_rmdir(struct kernfs_node *kn) } static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { + .show_options = cgroup_show_options, .remount_fs = cgroup_remount, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, @@ -4789,6 +4884,7 @@ void cgroup_post_fork(struct task_struct *child) cset = task_css_set(current); if (list_empty(&child->cg_list)) { get_css_set(cset); + cset->nr_tasks++; css_set_move_task(child, NULL, cset, false); } spin_unlock_irq(&css_set_lock); @@ -4838,6 +4934,7 @@ void cgroup_exit(struct task_struct *tsk) if (!list_empty(&tsk->cg_list)) { spin_lock_irq(&css_set_lock); css_set_move_task(tsk, cset, NULL, false); + cset->nr_tasks--; spin_unlock_irq(&css_set_lock); } else { get_css_set(cset); diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c new file mode 100644 index 000000000000..dac46af22782 --- /dev/null +++ b/kernel/cgroup/debug.c @@ -0,0 +1,357 @@ +/* + * Debug controller + * + * WARNING: This controller is for cgroup core debugging only. + * Its interfaces are unstable and subject to changes at any time. + */ +#include <linux/ctype.h> +#include <linux/mm.h> +#include <linux/slab.h> + +#include "cgroup-internal.h" + +static struct cgroup_subsys_state * +debug_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL); + + if (!css) + return ERR_PTR(-ENOMEM); + + return css; +} + +static void debug_css_free(struct cgroup_subsys_state *css) +{ + kfree(css); +} + +/* + * debug_taskcount_read - return the number of tasks in a cgroup. + * @cgrp: the cgroup in question + */ +static u64 debug_taskcount_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return cgroup_task_count(css->cgroup); +} + +static int current_css_set_read(struct seq_file *seq, void *v) +{ + struct kernfs_open_file *of = seq->private; + struct css_set *cset; + struct cgroup_subsys *ss; + struct cgroup_subsys_state *css; + int i, refcnt; + + if (!cgroup_kn_lock_live(of->kn, false)) + return -ENODEV; + + spin_lock_irq(&css_set_lock); + rcu_read_lock(); + cset = rcu_dereference(current->cgroups); + refcnt = refcount_read(&cset->refcount); + seq_printf(seq, "css_set %pK %d", cset, refcnt); + if (refcnt > cset->nr_tasks) + seq_printf(seq, " +%d", refcnt - cset->nr_tasks); + seq_puts(seq, "\n"); + + /* + * Print the css'es stored in the current css_set. + */ + for_each_subsys(ss, i) { + css = cset->subsys[ss->id]; + if (!css) + continue; + seq_printf(seq, "%2d: %-4s\t- %lx[%d]\n", ss->id, ss->name, + (unsigned long)css, css->id); + } + rcu_read_unlock(); + spin_unlock_irq(&css_set_lock); + cgroup_kn_unlock(of->kn); + return 0; +} + +static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + u64 count; + + rcu_read_lock(); + count = refcount_read(&task_css_set(current)->refcount); + rcu_read_unlock(); + return count; +} + +static int current_css_set_cg_links_read(struct seq_file *seq, void *v) +{ + struct cgrp_cset_link *link; + struct css_set *cset; + char *name_buf; + + name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!name_buf) + return -ENOMEM; + + spin_lock_irq(&css_set_lock); + rcu_read_lock(); + cset = rcu_dereference(current->cgroups); + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { + struct cgroup *c = link->cgrp; + + cgroup_name(c, name_buf, NAME_MAX + 1); + seq_printf(seq, "Root %d group %s\n", + c->root->hierarchy_id, name_buf); + } + rcu_read_unlock(); + spin_unlock_irq(&css_set_lock); + kfree(name_buf); + return 0; +} + +#define MAX_TASKS_SHOWN_PER_CSS 25 +static int cgroup_css_links_read(struct seq_file *seq, void *v) +{ + struct cgroup_subsys_state *css = seq_css(seq); + struct cgrp_cset_link *link; + int dead_cnt = 0, extra_refs = 0; + + spin_lock_irq(&css_set_lock); + list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { + struct css_set *cset = link->cset; + struct task_struct *task; + int count = 0; + int refcnt = refcount_read(&cset->refcount); + + seq_printf(seq, " %d", refcnt); + if (refcnt - cset->nr_tasks > 0) { + int extra = refcnt - cset->nr_tasks; + + seq_printf(seq, " +%d", extra); + /* + * Take out the one additional reference in + * init_css_set. + */ + if (cset == &init_css_set) + extra--; + extra_refs += extra; + } + seq_puts(seq, "\n"); + + list_for_each_entry(task, &cset->tasks, cg_list) { + if (count++ <= MAX_TASKS_SHOWN_PER_CSS) + seq_printf(seq, " task %d\n", + task_pid_vnr(task)); + } + + list_for_each_entry(task, &cset->mg_tasks, cg_list) { + if (count++ <= MAX_TASKS_SHOWN_PER_CSS) + seq_printf(seq, " task %d\n", + task_pid_vnr(task)); + } + /* show # of overflowed tasks */ + if (count > MAX_TASKS_SHOWN_PER_CSS) + seq_printf(seq, " ... (%d)\n", + count - MAX_TASKS_SHOWN_PER_CSS); + + if (cset->dead) { + seq_puts(seq, " [dead]\n"); + dead_cnt++; + } + + WARN_ON(count != cset->nr_tasks); + } + spin_unlock_irq(&css_set_lock); + + if (!dead_cnt && !extra_refs) + return 0; + + seq_puts(seq, "\n"); + if (extra_refs) + seq_printf(seq, "extra references = %d\n", extra_refs); + if (dead_cnt) + seq_printf(seq, "dead css_sets = %d\n", dead_cnt); + + return 0; +} + +static int cgroup_subsys_states_read(struct seq_file *seq, void *v) +{ + struct kernfs_open_file *of = seq->private; + struct cgroup *cgrp; + struct cgroup_subsys *ss; + struct cgroup_subsys_state *css; + char pbuf[16]; + int i; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + + for_each_subsys(ss, i) { + css = rcu_dereference_check(cgrp->subsys[ss->id], true); + if (!css) + continue; + + pbuf[0] = '\0'; + + /* Show the parent CSS if applicable*/ + if (css->parent) + snprintf(pbuf, sizeof(pbuf) - 1, " P=%d", + css->parent->id); + seq_printf(seq, "%2d: %-4s\t- %lx[%d] %d%s\n", ss->id, ss->name, + (unsigned long)css, css->id, + atomic_read(&css->online_cnt), pbuf); + } + + cgroup_kn_unlock(of->kn); + return 0; +} + +static void cgroup_masks_read_one(struct seq_file *seq, const char *name, + u16 mask) +{ + struct cgroup_subsys *ss; + int ssid; + bool first = true; + + seq_printf(seq, "%-17s: ", name); + for_each_subsys(ss, ssid) { + if (!(mask & (1 << ssid))) + continue; + if (!first) + seq_puts(seq, ", "); + seq_puts(seq, ss->name); + first = false; + } + seq_putc(seq, '\n'); +} + +static int cgroup_masks_read(struct seq_file *seq, void *v) +{ + struct kernfs_open_file *of = seq->private; + struct cgroup *cgrp; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + + cgroup_masks_read_one(seq, "subtree_control", cgrp->subtree_control); + cgroup_masks_read_one(seq, "subtree_ss_mask", cgrp->subtree_ss_mask); + + cgroup_kn_unlock(of->kn); + return 0; +} + +static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return (!cgroup_is_populated(css->cgroup) && + !css_has_online_children(&css->cgroup->self)); +} + +static struct cftype debug_legacy_files[] = { + { + .name = "taskcount", + .read_u64 = debug_taskcount_read, + }, + + { + .name = "current_css_set", + .seq_show = current_css_set_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "current_css_set_refcount", + .read_u64 = current_css_set_refcount_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "current_css_set_cg_links", + .seq_show = current_css_set_cg_links_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "cgroup_css_links", + .seq_show = cgroup_css_links_read, + }, + + { + .name = "cgroup_subsys_states", + .seq_show = cgroup_subsys_states_read, + }, + + { + .name = "cgroup_masks", + .seq_show = cgroup_masks_read, + }, + + { + .name = "releasable", + .read_u64 = releasable_read, + }, + + { } /* terminate */ +}; + +static struct cftype debug_files[] = { + { + .name = "taskcount", + .read_u64 = debug_taskcount_read, + }, + + { + .name = "current_css_set", + .seq_show = current_css_set_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "current_css_set_refcount", + .read_u64 = current_css_set_refcount_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "current_css_set_cg_links", + .seq_show = current_css_set_cg_links_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + + { + .name = "css_links", + .seq_show = cgroup_css_links_read, + }, + + { + .name = "csses", + .seq_show = cgroup_subsys_states_read, + }, + + { + .name = "masks", + .seq_show = cgroup_masks_read, + }, + + { } /* terminate */ +}; + +struct cgroup_subsys debug_cgrp_subsys = { + .css_alloc = debug_css_alloc, + .css_free = debug_css_free, + .legacy_cftypes = debug_legacy_files, +}; + +/* + * On v2, debug is an implicit controller enabled by "cgroup_debug" boot + * parameter. + */ +static int __init enable_cgroup_debug(char *str) +{ + debug_cgrp_subsys.dfl_cftypes = debug_files; + debug_cgrp_subsys.implicit_on_dfl = true; + return 1; +} +__setup("cgroup_debug", enable_cgroup_debug); diff --git a/kernel/compat.c b/kernel/compat.c index 933bcb31ae10..0621c8e1ab72 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -30,100 +30,66 @@ #include <linux/uaccess.h> -static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp) +int compat_get_timex(struct timex *txc, const struct compat_timex __user *utp) { - memset(txc, 0, sizeof(struct timex)); - - if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) || - __get_user(txc->modes, &utp->modes) || - __get_user(txc->offset, &utp->offset) || - __get_user(txc->freq, &utp->freq) || - __get_user(txc->maxerror, &utp->maxerror) || - __get_user(txc->esterror, &utp->esterror) || - __get_user(txc->status, &utp->status) || - __get_user(txc->constant, &utp->constant) || - __get_user(txc->precision, &utp->precision) || - __get_user(txc->tolerance, &utp->tolerance) || - __get_user(txc->time.tv_sec, &utp->time.tv_sec) || - __get_user(txc->time.tv_usec, &utp->time.tv_usec) || - __get_user(txc->tick, &utp->tick) || - __get_user(txc->ppsfreq, &utp->ppsfreq) || - __get_user(txc->jitter, &utp->jitter) || - __get_user(txc->shift, &utp->shift) || - __get_user(txc->stabil, &utp->stabil) || - __get_user(txc->jitcnt, &utp->jitcnt) || - __get_user(txc->calcnt, &utp->calcnt) || - __get_user(txc->errcnt, &utp->errcnt) || - __get_user(txc->stbcnt, &utp->stbcnt)) - return -EFAULT; - - return 0; -} + struct compat_timex tx32; -static int compat_put_timex(struct compat_timex __user *utp, struct timex *txc) -{ - if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) || - __put_user(txc->modes, &utp->modes) || - __put_user(txc->offset, &utp->offset) || - __put_user(txc->freq, &utp->freq) || - __put_user(txc->maxerror, &utp->maxerror) || - __put_user(txc->esterror, &utp->esterror) || - __put_user(txc->status, &utp->status) || - __put_user(txc->constant, &utp->constant) || - __put_user(txc->precision, &utp->precision) || - __put_user(txc->tolerance, &utp->tolerance) || - __put_user(txc->time.tv_sec, &utp->time.tv_sec) || - __put_user(txc->time.tv_usec, &utp->time.tv_usec) || - __put_user(txc->tick, &utp->tick) || - __put_user(txc->ppsfreq, &utp->ppsfreq) || - __put_user(txc->jitter, &utp->jitter) || - __put_user(txc->shift, &utp->shift) || - __put_user(txc->stabil, &utp->stabil) || - __put_user(txc->jitcnt, &utp->jitcnt) || - __put_user(txc->calcnt, &utp->calcnt) || - __put_user(txc->errcnt, &utp->errcnt) || - __put_user(txc->stbcnt, &utp->stbcnt) || - __put_user(txc->tai, &utp->tai)) + if (copy_from_user(&tx32, utp, sizeof(struct compat_timex))) return -EFAULT; - return 0; -} -COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv, - struct timezone __user *, tz) -{ - if (tv) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (compat_put_timeval(&ktv, tv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } + txc->modes = tx32.modes; + txc->offset = tx32.offset; + txc->freq = tx32.freq; + txc->maxerror = tx32.maxerror; + txc->esterror = tx32.esterror; + txc->status = tx32.status; + txc->constant = tx32.constant; + txc->precision = tx32.precision; + txc->tolerance = tx32.tolerance; + txc->time.tv_sec = tx32.time.tv_sec; + txc->time.tv_usec = tx32.time.tv_usec; + txc->tick = tx32.tick; + txc->ppsfreq = tx32.ppsfreq; + txc->jitter = tx32.jitter; + txc->shift = tx32.shift; + txc->stabil = tx32.stabil; + txc->jitcnt = tx32.jitcnt; + txc->calcnt = tx32.calcnt; + txc->errcnt = tx32.errcnt; + txc->stbcnt = tx32.stbcnt; return 0; } -COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv, - struct timezone __user *, tz) -{ - struct timespec64 new_ts; - struct timeval user_tv; - struct timezone new_tz; - - if (tv) { - if (compat_get_timeval(&user_tv, tv)) - return -EFAULT; - new_ts.tv_sec = user_tv.tv_sec; - new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC; - } - if (tz) { - if (copy_from_user(&new_tz, tz, sizeof(*tz))) - return -EFAULT; - } - - return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); +int compat_put_timex(struct compat_timex __user *utp, const struct timex *txc) +{ + struct compat_timex tx32; + + memset(&tx32, 0, sizeof(struct compat_timex)); + tx32.modes = txc->modes; + tx32.offset = txc->offset; + tx32.freq = txc->freq; + tx32.maxerror = txc->maxerror; + tx32.esterror = txc->esterror; + tx32.status = txc->status; + tx32.constant = txc->constant; + tx32.precision = txc->precision; + tx32.tolerance = txc->tolerance; + tx32.time.tv_sec = txc->time.tv_sec; + tx32.time.tv_usec = txc->time.tv_usec; + tx32.tick = txc->tick; + tx32.ppsfreq = txc->ppsfreq; + tx32.jitter = txc->jitter; + tx32.shift = txc->shift; + tx32.stabil = txc->stabil; + tx32.jitcnt = txc->jitcnt; + tx32.calcnt = txc->calcnt; + tx32.errcnt = txc->errcnt; + tx32.stbcnt = txc->stbcnt; + tx32.tai = txc->tai; + if (copy_to_user(utp, &tx32, sizeof(struct compat_timex))) + return -EFAULT; + return 0; } static int __compat_get_timeval(struct timeval *tv, const struct compat_timeval __user *ctv) @@ -154,6 +120,50 @@ static int __compat_put_timespec(const struct timespec *ts, struct compat_timesp __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; } +static int __compat_get_timespec64(struct timespec64 *ts64, + const struct compat_timespec __user *cts) +{ + struct compat_timespec ts; + int ret; + + ret = copy_from_user(&ts, cts, sizeof(ts)); + if (ret) + return -EFAULT; + + ts64->tv_sec = ts.tv_sec; + ts64->tv_nsec = ts.tv_nsec; + + return 0; +} + +static int __compat_put_timespec64(const struct timespec64 *ts64, + struct compat_timespec __user *cts) +{ + struct compat_timespec ts = { + .tv_sec = ts64->tv_sec, + .tv_nsec = ts64->tv_nsec + }; + return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; +} + +int compat_get_timespec64(struct timespec64 *ts, const void __user *uts) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; + else + return __compat_get_timespec64(ts, uts); +} +EXPORT_SYMBOL_GPL(compat_get_timespec64); + +int compat_put_timespec64(const struct timespec64 *ts, void __user *uts) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; + else + return __compat_put_timespec64(ts, uts); +} +EXPORT_SYMBOL_GPL(compat_put_timespec64); + int compat_get_timeval(struct timeval *tv, const void __user *utv) { if (COMPAT_USE_64BIT_TIME) @@ -213,141 +223,28 @@ int compat_convert_timespec(struct timespec __user **kts, return 0; } -static long compat_nanosleep_restart(struct restart_block *restart) +int get_compat_itimerval(struct itimerval *o, const struct compat_itimerval __user *i) { - struct compat_timespec __user *rmtp; - struct timespec rmt; - mm_segment_t oldfs; - long ret; - - restart->nanosleep.rmtp = (struct timespec __user *) &rmt; - oldfs = get_fs(); - set_fs(KERNEL_DS); - ret = hrtimer_nanosleep_restart(restart); - set_fs(oldfs); - - if (ret == -ERESTART_RESTARTBLOCK) { - rmtp = restart->nanosleep.compat_rmtp; + struct compat_itimerval v32; - if (rmtp && compat_put_timespec(&rmt, rmtp)) - return -EFAULT; - } - - return ret; -} - -COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, - struct compat_timespec __user *, rmtp) -{ - struct timespec tu, rmt; - struct timespec64 tu64; - mm_segment_t oldfs; - long ret; - - if (compat_get_timespec(&tu, rqtp)) + if (copy_from_user(&v32, i, sizeof(struct compat_itimerval))) return -EFAULT; - - tu64 = timespec_to_timespec64(tu); - if (!timespec64_valid(&tu64)) - return -EINVAL; - - oldfs = get_fs(); - set_fs(KERNEL_DS); - ret = hrtimer_nanosleep(&tu64, - rmtp ? (struct timespec __user *)&rmt : NULL, - HRTIMER_MODE_REL, CLOCK_MONOTONIC); - set_fs(oldfs); - - /* - * hrtimer_nanosleep() can only return 0 or - * -ERESTART_RESTARTBLOCK here because: - * - * - we call it with HRTIMER_MODE_REL and therefor exclude the - * -ERESTARTNOHAND return path. - * - * - we supply the rmtp argument from the task stack (due to - * the necessary compat conversion. So the update cannot - * fail, which excludes the -EFAULT return path as well. If - * it fails nevertheless we have a bigger problem and wont - * reach this place anymore. - * - * - if the return value is 0, we do not have to update rmtp - * because there is no remaining time. - * - * We check for -ERESTART_RESTARTBLOCK nevertheless if the - * core implementation decides to return random nonsense. - */ - if (ret == -ERESTART_RESTARTBLOCK) { - struct restart_block *restart = ¤t->restart_block; - - restart->fn = compat_nanosleep_restart; - restart->nanosleep.compat_rmtp = rmtp; - - if (rmtp && compat_put_timespec(&rmt, rmtp)) - return -EFAULT; - } - return ret; -} - -static inline long get_compat_itimerval(struct itimerval *o, - struct compat_itimerval __user *i) -{ - return (!access_ok(VERIFY_READ, i, sizeof(*i)) || - (__get_user(o->it_interval.tv_sec, &i->it_interval.tv_sec) | - __get_user(o->it_interval.tv_usec, &i->it_interval.tv_usec) | - __get_user(o->it_value.tv_sec, &i->it_value.tv_sec) | - __get_user(o->it_value.tv_usec, &i->it_value.tv_usec))); -} - -static inline long put_compat_itimerval(struct compat_itimerval __user *o, - struct itimerval *i) -{ - return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || - (__put_user(i->it_interval.tv_sec, &o->it_interval.tv_sec) | - __put_user(i->it_interval.tv_usec, &o->it_interval.tv_usec) | - __put_user(i->it_value.tv_sec, &o->it_value.tv_sec) | - __put_user(i->it_value.tv_usec, &o->it_value.tv_usec))); -} - -asmlinkage long sys_ni_posix_timers(void); - -COMPAT_SYSCALL_DEFINE2(getitimer, int, which, - struct compat_itimerval __user *, it) -{ - struct itimerval kit; - int error; - - if (!IS_ENABLED(CONFIG_POSIX_TIMERS)) - return sys_ni_posix_timers(); - - error = do_getitimer(which, &kit); - if (!error && put_compat_itimerval(it, &kit)) - error = -EFAULT; - return error; + o->it_interval.tv_sec = v32.it_interval.tv_sec; + o->it_interval.tv_usec = v32.it_interval.tv_usec; + o->it_value.tv_sec = v32.it_value.tv_sec; + o->it_value.tv_usec = v32.it_value.tv_usec; + return 0; } -COMPAT_SYSCALL_DEFINE3(setitimer, int, which, - struct compat_itimerval __user *, in, - struct compat_itimerval __user *, out) +int put_compat_itimerval(struct compat_itimerval __user *o, const struct itimerval *i) { - struct itimerval kin, kout; - int error; - - if (!IS_ENABLED(CONFIG_POSIX_TIMERS)) - return sys_ni_posix_timers(); - - if (in) { - if (get_compat_itimerval(&kin, in)) - return -EFAULT; - } else - memset(&kin, 0, sizeof(kin)); + struct compat_itimerval v32; - error = do_setitimer(which, &kin, out ? &kout : NULL); - if (error || !out) - return error; - if (put_compat_itimerval(out, &kout)) - return -EFAULT; - return 0; + v32.it_interval.tv_sec = i->it_interval.tv_sec; + v32.it_interval.tv_usec = i->it_interval.tv_usec; + v32.it_value.tv_sec = i->it_value.tv_sec; + v32.it_value.tv_usec = i->it_value.tv_usec; + return copy_to_user(o, &v32, sizeof(struct compat_itimerval)) ? -EFAULT : 0; } static compat_clock_t clock_t_to_compat_clock_t(clock_t x) @@ -543,72 +440,6 @@ int put_compat_rusage(const struct rusage *r, struct compat_rusage __user *ru) return 0; } -COMPAT_SYSCALL_DEFINE4(wait4, - compat_pid_t, pid, - compat_uint_t __user *, stat_addr, - int, options, - struct compat_rusage __user *, ru) -{ - if (!ru) { - return sys_wait4(pid, stat_addr, options, NULL); - } else { - struct rusage r; - int ret; - unsigned int status; - mm_segment_t old_fs = get_fs(); - - set_fs (KERNEL_DS); - ret = sys_wait4(pid, - (stat_addr ? - (unsigned int __user *) &status : NULL), - options, (struct rusage __user *) &r); - set_fs (old_fs); - - if (ret > 0) { - if (put_compat_rusage(&r, ru)) - return -EFAULT; - if (stat_addr && put_user(status, stat_addr)) - return -EFAULT; - } - return ret; - } -} - -COMPAT_SYSCALL_DEFINE5(waitid, - int, which, compat_pid_t, pid, - struct compat_siginfo __user *, uinfo, int, options, - struct compat_rusage __user *, uru) -{ - siginfo_t info; - struct rusage ru; - long ret; - mm_segment_t old_fs = get_fs(); - - memset(&info, 0, sizeof(info)); - - set_fs(KERNEL_DS); - ret = sys_waitid(which, pid, (siginfo_t __user *)&info, options, - uru ? (struct rusage __user *)&ru : NULL); - set_fs(old_fs); - - if ((ret < 0) || (info.si_signo == 0)) - return ret; - - if (uru) { - /* sys_waitid() overwrites everything in ru */ - if (COMPAT_USE_64BIT_TIME) - ret = copy_to_user(uru, &ru, sizeof(ru)); - else - ret = put_compat_rusage(&ru, uru); - if (ret) - return -EFAULT; - } - - BUG_ON(info.si_code & __SI_MASK); - info.si_code |= __SI_CHLD; - return copy_siginfo_to_user32(uinfo, &info); -} - static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr, unsigned len, struct cpumask *new_mask) { @@ -689,192 +520,26 @@ int put_compat_itimerspec(struct compat_itimerspec __user *dst, return 0; } -COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock, - struct compat_sigevent __user *, timer_event_spec, - timer_t __user *, created_timer_id) -{ - struct sigevent __user *event = NULL; - - if (timer_event_spec) { - struct sigevent kevent; - - event = compat_alloc_user_space(sizeof(*event)); - if (get_compat_sigevent(&kevent, timer_event_spec) || - copy_to_user(event, &kevent, sizeof(*event))) - return -EFAULT; - } - - return sys_timer_create(which_clock, event, created_timer_id); -} - -COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - struct compat_itimerspec __user *, new, - struct compat_itimerspec __user *, old) -{ - long err; - mm_segment_t oldfs; - struct itimerspec newts, oldts; - - if (!new) - return -EINVAL; - if (get_compat_itimerspec(&newts, new)) - return -EFAULT; - oldfs = get_fs(); - set_fs(KERNEL_DS); - err = sys_timer_settime(timer_id, flags, - (struct itimerspec __user *) &newts, - (struct itimerspec __user *) &oldts); - set_fs(oldfs); - if (!err && old && put_compat_itimerspec(old, &oldts)) - return -EFAULT; - return err; -} - -COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct compat_itimerspec __user *, setting) -{ - long err; - mm_segment_t oldfs; - struct itimerspec ts; - - oldfs = get_fs(); - set_fs(KERNEL_DS); - err = sys_timer_gettime(timer_id, - (struct itimerspec __user *) &ts); - set_fs(oldfs); - if (!err && put_compat_itimerspec(setting, &ts)) - return -EFAULT; - return err; -} - -COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, - struct compat_timespec __user *, tp) -{ - long err; - mm_segment_t oldfs; - struct timespec ts; - - if (compat_get_timespec(&ts, tp)) - return -EFAULT; - oldfs = get_fs(); - set_fs(KERNEL_DS); - err = sys_clock_settime(which_clock, - (struct timespec __user *) &ts); - set_fs(oldfs); - return err; -} - -COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, - struct compat_timespec __user *, tp) -{ - long err; - mm_segment_t oldfs; - struct timespec ts; - - oldfs = get_fs(); - set_fs(KERNEL_DS); - err = sys_clock_gettime(which_clock, - (struct timespec __user *) &ts); - set_fs(oldfs); - if (!err && compat_put_timespec(&ts, tp)) - return -EFAULT; - return err; -} - -COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, - struct compat_timex __user *, utp) -{ - struct timex txc; - mm_segment_t oldfs; - int err, ret; - - err = compat_get_timex(&txc, utp); - if (err) - return err; - - oldfs = get_fs(); - set_fs(KERNEL_DS); - ret = sys_clock_adjtime(which_clock, (struct timex __user *) &txc); - set_fs(oldfs); - - err = compat_put_timex(utp, &txc); - if (err) - return err; - - return ret; -} - -COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, - struct compat_timespec __user *, tp) +int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits) { - long err; - mm_segment_t oldfs; - struct timespec ts; - oldfs = get_fs(); - set_fs(KERNEL_DS); - err = sys_clock_getres(which_clock, - (struct timespec __user *) &ts); - set_fs(oldfs); - if (!err && tp && compat_put_timespec(&ts, tp)) + if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || + __compat_get_timespec64(&its->it_value, &uits->it_value)) return -EFAULT; - return err; + return 0; } +EXPORT_SYMBOL_GPL(get_compat_itimerspec64); -static long compat_clock_nanosleep_restart(struct restart_block *restart) +int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits) { - long err; - mm_segment_t oldfs; - struct timespec tu; - struct compat_timespec __user *rmtp = restart->nanosleep.compat_rmtp; - - restart->nanosleep.rmtp = (struct timespec __user *) &tu; - oldfs = get_fs(); - set_fs(KERNEL_DS); - err = clock_nanosleep_restart(restart); - set_fs(oldfs); - - if ((err == -ERESTART_RESTARTBLOCK) && rmtp && - compat_put_timespec(&tu, rmtp)) + if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || + __compat_put_timespec64(&its->it_value, &uits->it_value)) return -EFAULT; - - if (err == -ERESTART_RESTARTBLOCK) { - restart->fn = compat_clock_nanosleep_restart; - restart->nanosleep.compat_rmtp = rmtp; - } - return err; -} - -COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, - struct compat_timespec __user *, rqtp, - struct compat_timespec __user *, rmtp) -{ - long err; - mm_segment_t oldfs; - struct timespec in, out; - struct restart_block *restart; - - if (compat_get_timespec(&in, rqtp)) - return -EFAULT; - - oldfs = get_fs(); - set_fs(KERNEL_DS); - err = sys_clock_nanosleep(which_clock, flags, - (struct timespec __user *) &in, - (struct timespec __user *) &out); - set_fs(oldfs); - - if ((err == -ERESTART_RESTARTBLOCK) && rmtp && - compat_put_timespec(&out, rmtp)) - return -EFAULT; - - if (err == -ERESTART_RESTARTBLOCK) { - restart = ¤t->restart_block; - restart->fn = compat_clock_nanosleep_restart; - restart->nanosleep.compat_rmtp = rmtp; - } - return err; + return 0; } +EXPORT_SYMBOL_GPL(put_compat_itimerspec64); /* * We currently only need the following fields from the sigevent @@ -1035,64 +700,6 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, return ret; } -#ifdef __ARCH_WANT_COMPAT_SYS_TIME - -/* compat_time_t is a 32 bit "long" and needs to get converted. */ - -COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) -{ - compat_time_t i; - struct timeval tv; - - do_gettimeofday(&tv); - i = tv.tv_sec; - - if (tloc) { - if (put_user(i,tloc)) - return -EFAULT; - } - force_successful_syscall_return(); - return i; -} - -COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr) -{ - struct timespec tv; - int err; - - if (get_user(tv.tv_sec, tptr)) - return -EFAULT; - - tv.tv_nsec = 0; - - err = security_settime(&tv, NULL); - if (err) - return err; - - do_settimeofday(&tv); - return 0; -} - -#endif /* __ARCH_WANT_COMPAT_SYS_TIME */ - -COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp) -{ - struct timex txc; - int err, ret; - - err = compat_get_timex(&txc, utp); - if (err) - return err; - - ret = do_adjtimex(&txc); - - err = compat_put_timex(utp, &txc); - if (err) - return err; - - return ret; -} - #ifdef CONFIG_NUMA COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages, compat_uptr_t __user *, pages32, diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config index 26a06e09a5bd..d70829033bb7 100644 --- a/kernel/configs/android-base.config +++ b/kernel/configs/android-base.config @@ -1,10 +1,13 @@ # KEEP ALPHABETICALLY SORTED # CONFIG_DEVKMEM is not set # CONFIG_DEVMEM is not set +# CONFIG_FHANDLE is not set # CONFIG_INET_LRO is not set -# CONFIG_MODULES is not set +# CONFIG_NFSD is not set +# CONFIG_NFS_FS is not set # CONFIG_OABI_COMPAT is not set # CONFIG_SYSVIPC is not set +# CONFIG_USELIB is not set CONFIG_ANDROID=y CONFIG_ANDROID_BINDER_IPC=y CONFIG_ANDROID_LOW_MEMORY_KILLER=y @@ -13,6 +16,7 @@ CONFIG_ASHMEM=y CONFIG_AUDIT=y CONFIG_BLK_DEV_INITRD=y CONFIG_CGROUPS=y +CONFIG_CGROUP_BPF=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_DEBUG=y CONFIG_CGROUP_FREEZER=y @@ -23,6 +27,8 @@ CONFIG_EMBEDDED=y CONFIG_FB=y CONFIG_HARDENED_USERCOPY=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y CONFIG_INET6_AH=y CONFIG_INET6_ESP=y CONFIG_INET6_IPCOMP=y @@ -60,6 +66,9 @@ CONFIG_IP_NF_TARGET_MASQUERADE=y CONFIG_IP_NF_TARGET_NETMAP=y CONFIG_IP_NF_TARGET_REDIRECT=y CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y CONFIG_NET=y CONFIG_NETDEVICES=y CONFIG_NETFILTER=y diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config index 28ee064b6744..946fb92418f7 100644 --- a/kernel/configs/android-recommended.config +++ b/kernel/configs/android-recommended.config @@ -6,13 +6,15 @@ # CONFIG_NF_CONNTRACK_SIP is not set # CONFIG_PM_WAKELOCKS_GC is not set # CONFIG_VT is not set +CONFIG_ARM64_SW_TTBR0_PAN=y CONFIG_BACKLIGHT_LCD_SUPPORT=y CONFIG_BLK_DEV_DM=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_CC_STACKPROTECTOR_STRONG=y CONFIG_COMPACTION=y -CONFIG_STRICT_KERNEL_RWX=y +CONFIG_CPU_SW_DOMAIN_PAN=y CONFIG_DM_CRYPT=y CONFIG_DM_UEVENT=y CONFIG_DM_VERITY=y @@ -105,6 +107,7 @@ CONFIG_SCHEDSTATS=y CONFIG_SMARTJOYPLUS_FF=y CONFIG_SND=y CONFIG_SOUND=y +CONFIG_STRICT_KERNEL_RWX=y CONFIG_SUSPEND_TIME=y CONFIG_TABLET_USB_ACECAD=y CONFIG_TABLET_USB_AIPTEK=y diff --git a/kernel/cpu.c b/kernel/cpu.c index cb5103413bd8..b03a32595cfe 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -27,6 +27,7 @@ #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> +#include <linux/percpu-rwsem.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS @@ -65,6 +66,12 @@ struct cpuhp_cpu_state { static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); +#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) +static struct lock_class_key cpuhp_state_key; +static struct lockdep_map cpuhp_state_lock_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key); +#endif + /** * cpuhp_step - Hotplug state machine step * @name: Name of the step @@ -196,121 +203,41 @@ void cpu_maps_update_done(void) mutex_unlock(&cpu_add_remove_lock); } -/* If set, cpu_up and cpu_down will return -EBUSY and do nothing. +/* + * If set, cpu_up and cpu_down will return -EBUSY and do nothing. * Should always be manipulated under cpu_add_remove_lock */ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU -static struct { - struct task_struct *active_writer; - /* wait queue to wake up the active_writer */ - wait_queue_head_t wq; - /* verifies that no writer will get active while readers are active */ - struct mutex lock; - /* - * Also blocks the new readers during - * an ongoing cpu hotplug operation. - */ - atomic_t refcount; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -} cpu_hotplug = { - .active_writer = NULL, - .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), - .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), -#ifdef CONFIG_DEBUG_LOCK_ALLOC - .dep_map = STATIC_LOCKDEP_MAP_INIT("cpu_hotplug.dep_map", &cpu_hotplug.dep_map), -#endif -}; - -/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */ -#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map) -#define cpuhp_lock_acquire_tryread() \ - lock_map_acquire_tryread(&cpu_hotplug.dep_map) -#define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) -#define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) +DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); - -void get_online_cpus(void) +void cpus_read_lock(void) { - might_sleep(); - if (cpu_hotplug.active_writer == current) - return; - cpuhp_lock_acquire_read(); - mutex_lock(&cpu_hotplug.lock); - atomic_inc(&cpu_hotplug.refcount); - mutex_unlock(&cpu_hotplug.lock); + percpu_down_read(&cpu_hotplug_lock); } -EXPORT_SYMBOL_GPL(get_online_cpus); +EXPORT_SYMBOL_GPL(cpus_read_lock); -void put_online_cpus(void) +void cpus_read_unlock(void) { - int refcount; - - if (cpu_hotplug.active_writer == current) - return; - - refcount = atomic_dec_return(&cpu_hotplug.refcount); - if (WARN_ON(refcount < 0)) /* try to fix things up */ - atomic_inc(&cpu_hotplug.refcount); - - if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq)) - wake_up(&cpu_hotplug.wq); - - cpuhp_lock_release(); - + percpu_up_read(&cpu_hotplug_lock); } -EXPORT_SYMBOL_GPL(put_online_cpus); +EXPORT_SYMBOL_GPL(cpus_read_unlock); -/* - * This ensures that the hotplug operation can begin only when the - * refcount goes to zero. - * - * Note that during a cpu-hotplug operation, the new readers, if any, - * will be blocked by the cpu_hotplug.lock - * - * Since cpu_hotplug_begin() is always called after invoking - * cpu_maps_update_begin(), we can be sure that only one writer is active. - * - * Note that theoretically, there is a possibility of a livelock: - * - Refcount goes to zero, last reader wakes up the sleeping - * writer. - * - Last reader unlocks the cpu_hotplug.lock. - * - A new reader arrives at this moment, bumps up the refcount. - * - The writer acquires the cpu_hotplug.lock finds the refcount - * non zero and goes to sleep again. - * - * However, this is very difficult to achieve in practice since - * get_online_cpus() not an api which is called all that often. - * - */ -void cpu_hotplug_begin(void) +void cpus_write_lock(void) { - DEFINE_WAIT(wait); - - cpu_hotplug.active_writer = current; - cpuhp_lock_acquire(); + percpu_down_write(&cpu_hotplug_lock); +} - for (;;) { - mutex_lock(&cpu_hotplug.lock); - prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE); - if (likely(!atomic_read(&cpu_hotplug.refcount))) - break; - mutex_unlock(&cpu_hotplug.lock); - schedule(); - } - finish_wait(&cpu_hotplug.wq, &wait); +void cpus_write_unlock(void) +{ + percpu_up_write(&cpu_hotplug_lock); } -void cpu_hotplug_done(void) +void lockdep_assert_cpus_held(void) { - cpu_hotplug.active_writer = NULL; - mutex_unlock(&cpu_hotplug.lock); - cpuhp_lock_release(); + percpu_rwsem_assert_held(&cpu_hotplug_lock); } /* @@ -344,8 +271,6 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */ -/* Notifier wrappers for transitioning to state machine */ - static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); @@ -484,6 +409,7 @@ static void cpuhp_thread_fun(unsigned int cpu) st->should_run = false; + lock_map_acquire(&cpuhp_state_lock_map); /* Single callback invocation for [un]install ? */ if (st->single) { if (st->cb_state < CPUHP_AP_ONLINE) { @@ -510,6 +436,7 @@ static void cpuhp_thread_fun(unsigned int cpu) else if (st->state > st->target) ret = cpuhp_ap_offline(cpu, st); } + lock_map_release(&cpuhp_state_lock_map); st->result = ret; complete(&st->done); } @@ -524,6 +451,9 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, if (!cpu_online(cpu)) return 0; + lock_map_acquire(&cpuhp_state_lock_map); + lock_map_release(&cpuhp_state_lock_map); + /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. @@ -567,6 +497,8 @@ static int cpuhp_kick_ap_work(unsigned int cpu) enum cpuhp_state state = st->state; trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); + lock_map_acquire(&cpuhp_state_lock_map); + lock_map_release(&cpuhp_state_lock_map); __cpuhp_kick_ap_work(st); wait_for_completion(&st->done); trace_cpuhp_exit(cpu, st->state, state, st->result); @@ -630,30 +562,6 @@ void clear_tasks_mm_cpumask(int cpu) rcu_read_unlock(); } -static inline void check_for_tasks(int dead_cpu) -{ - struct task_struct *g, *p; - - read_lock(&tasklist_lock); - for_each_process_thread(g, p) { - if (!p->on_rq) - continue; - /* - * We do the check with unlocked task_rq(p)->lock. - * Order the reading to do not warn about a task, - * which was running on this cpu in the past, and - * it's just been woken on another cpu. - */ - rmb(); - if (task_cpu(p) != dead_cpu) - continue; - - pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n", - p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags); - } - read_unlock(&tasklist_lock); -} - /* Take this CPU down. */ static int take_cpu_down(void *_param) { @@ -701,7 +609,7 @@ static int takedown_cpu(unsigned int cpu) /* * So now all preempt/rcu users must observe !cpu_active(). */ - err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu)); + err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ irq_unlock_sparse(); @@ -773,7 +681,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, if (!cpu_present(cpu)) return -EINVAL; - cpu_hotplug_begin(); + cpus_write_lock(); cpuhp_tasks_frozen = tasks_frozen; @@ -811,7 +719,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, } out: - cpu_hotplug_done(); + cpus_write_unlock(); return ret; } @@ -893,7 +801,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) struct task_struct *idle; int ret = 0; - cpu_hotplug_begin(); + cpus_write_lock(); if (!cpu_present(cpu)) { ret = -EINVAL; @@ -941,7 +849,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, target); out: - cpu_hotplug_done(); + cpus_write_unlock(); return ret; } @@ -1252,6 +1160,11 @@ static struct cpuhp_step cpuhp_ap_states[] = { .startup.single = smpboot_unpark_threads, .teardown.single = NULL, }, + [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { + .name = "irq/affinity:online", + .startup.single = irq_affinity_online_cpu, + .teardown.single = NULL, + }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online", .startup.single = perf_event_init_cpu, @@ -1413,18 +1326,20 @@ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, } } -int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, - bool invoke) +int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, + struct hlist_node *node, + bool invoke) { struct cpuhp_step *sp; int cpu; int ret; + lockdep_assert_cpus_held(); + sp = cpuhp_get_step(state); if (sp->multi_instance == false) return -EINVAL; - get_online_cpus(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) @@ -1453,13 +1368,23 @@ add_node: hlist_add_head(node, &sp->list); unlock: mutex_unlock(&cpuhp_state_mutex); - put_online_cpus(); + return ret; +} + +int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, + bool invoke) +{ + int ret; + + cpus_read_lock(); + ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke); + cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); /** - * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state + * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state * @state: The state to setup * @invoke: If true, the startup function is invoked for cpus where * cpu state >= @state @@ -1468,25 +1393,27 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); * @multi_instance: State is set up for multiple instances which get * added afterwards. * + * The caller needs to hold cpus read locked while calling this function. * Returns: * On success: * Positive state number if @state is CPUHP_AP_ONLINE_DYN * 0 for all other states * On failure: proper (negative) error code */ -int __cpuhp_setup_state(enum cpuhp_state state, - const char *name, bool invoke, - int (*startup)(unsigned int cpu), - int (*teardown)(unsigned int cpu), - bool multi_instance) +int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, + const char *name, bool invoke, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu), + bool multi_instance) { int cpu, ret = 0; bool dynstate; + lockdep_assert_cpus_held(); + if (cpuhp_cb_check(state) || !name) return -EINVAL; - get_online_cpus(); mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, @@ -1522,7 +1449,6 @@ int __cpuhp_setup_state(enum cpuhp_state state, } out: mutex_unlock(&cpuhp_state_mutex); - put_online_cpus(); /* * If the requested state is CPUHP_AP_ONLINE_DYN, return the * dynamically allocated state in case of success. @@ -1531,6 +1457,22 @@ out: return state; return ret; } +EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked); + +int __cpuhp_setup_state(enum cpuhp_state state, + const char *name, bool invoke, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu), + bool multi_instance) +{ + int ret; + + cpus_read_lock(); + ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup, + teardown, multi_instance); + cpus_read_unlock(); + return ret; +} EXPORT_SYMBOL(__cpuhp_setup_state); int __cpuhp_state_remove_instance(enum cpuhp_state state, @@ -1544,7 +1486,7 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state, if (!sp->multi_instance) return -EINVAL; - get_online_cpus(); + cpus_read_lock(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !cpuhp_get_teardown_cb(state)) @@ -1565,29 +1507,30 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state, remove: hlist_del(node); mutex_unlock(&cpuhp_state_mutex); - put_online_cpus(); + cpus_read_unlock(); return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); /** - * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state + * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state * @state: The state to remove * @invoke: If true, the teardown function is invoked for cpus where * cpu state >= @state * + * The caller needs to hold cpus read locked while calling this function. * The teardown callback is currently not allowed to fail. Think * about module removal! */ -void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) +void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); - get_online_cpus(); + lockdep_assert_cpus_held(); mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { @@ -1615,7 +1558,14 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); mutex_unlock(&cpuhp_state_mutex); - put_online_cpus(); +} +EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked); + +void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) +{ + cpus_read_lock(); + __cpuhp_remove_state_cpuslocked(state, invoke); + cpus_read_unlock(); } EXPORT_SYMBOL(__cpuhp_remove_state); @@ -1684,7 +1634,7 @@ static struct attribute *cpuhp_cpu_attrs[] = { NULL }; -static struct attribute_group cpuhp_cpu_attr_group = { +static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", NULL @@ -1716,7 +1666,7 @@ static struct attribute *cpuhp_cpu_root_attrs[] = { NULL }; -static struct attribute_group cpuhp_cpu_root_attr_group = { +static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", NULL diff --git a/kernel/cred.c b/kernel/cred.c index 2bc66075740f..ecf03657e71c 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -1,4 +1,4 @@ -/* Task credentials management - see Documentation/security/credentials.txt +/* Task credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) diff --git a/kernel/events/core.c b/kernel/events/core.c index 6c4e523dc1e2..1538df9b2b65 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -389,6 +389,7 @@ static atomic_t nr_switch_events __read_mostly; static LIST_HEAD(pmus); static DEFINE_MUTEX(pmus_lock); static struct srcu_struct pmus_srcu; +static cpumask_var_t perf_online_mask; /* * perf event paranoia level: @@ -925,11 +926,6 @@ static inline int is_cgroup_event(struct perf_event *event) return 0; } -static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event) -{ - return 0; -} - static inline void update_cgrp_time_from_event(struct perf_event *event) { } @@ -3636,10 +3632,10 @@ static inline u64 perf_event_count(struct perf_event *event) * will not be local and we cannot read them atomically * - must not have a pmu::count method */ -u64 perf_event_read_local(struct perf_event *event) +int perf_event_read_local(struct perf_event *event, u64 *value) { unsigned long flags; - u64 val; + int ret = 0; /* * Disabling interrupts avoids all counter scheduling (context @@ -3647,25 +3643,37 @@ u64 perf_event_read_local(struct perf_event *event) */ local_irq_save(flags); - /* If this is a per-task event, it must be for current */ - WARN_ON_ONCE((event->attach_state & PERF_ATTACH_TASK) && - event->hw.target != current); - - /* If this is a per-CPU event, it must be for this CPU */ - WARN_ON_ONCE(!(event->attach_state & PERF_ATTACH_TASK) && - event->cpu != smp_processor_id()); - /* * It must not be an event with inherit set, we cannot read * all child counters from atomic context. */ - WARN_ON_ONCE(event->attr.inherit); + if (event->attr.inherit) { + ret = -EOPNOTSUPP; + goto out; + } /* * It must not have a pmu::count method, those are not * NMI safe. */ - WARN_ON_ONCE(event->pmu->count); + if (event->pmu->count) { + ret = -EOPNOTSUPP; + goto out; + } + + /* If this is a per-task event, it must be for current */ + if ((event->attach_state & PERF_ATTACH_TASK) && + event->hw.target != current) { + ret = -EINVAL; + goto out; + } + + /* If this is a per-CPU event, it must be for this CPU */ + if (!(event->attach_state & PERF_ATTACH_TASK) && + event->cpu != smp_processor_id()) { + ret = -EINVAL; + goto out; + } /* * If the event is currently on this CPU, its either a per-task event, @@ -3675,10 +3683,11 @@ u64 perf_event_read_local(struct perf_event *event) if (event->oncpu == smp_processor_id()) event->pmu->read(event); - val = local64_read(&event->count); + *value = local64_read(&event->count); +out: local_irq_restore(flags); - return val; + return ret; } static int perf_event_read(struct perf_event *event, bool group) @@ -3812,14 +3821,6 @@ find_get_context(struct pmu *pmu, struct task_struct *task, if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); - /* - * We could be clever and allow to attach a event to an - * offline CPU and activate it when the CPU comes up, but - * that's for later. - */ - if (!cpu_online(cpu)) - return ERR_PTR(-ENODEV); - cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); ctx = &cpuctx->ctx; get_ctx(ctx); @@ -5729,9 +5730,6 @@ static void perf_output_read_one(struct perf_output_handle *handle, __output_copy(handle, values, n * sizeof(u64)); } -/* - * XXX PERF_FORMAT_GROUP vs inherited events seems difficult. - */ static void perf_output_read_group(struct perf_output_handle *handle, struct perf_event *event, u64 enabled, u64 running) @@ -5776,6 +5774,13 @@ static void perf_output_read_group(struct perf_output_handle *handle, #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\ PERF_FORMAT_TOTAL_TIME_RUNNING) +/* + * XXX PERF_SAMPLE_READ vs inherited events seems difficult. + * + * The problem is that its both hard and excessively expensive to iterate the + * child list, not to mention that its impossible to IPI the children running + * on another CPU, from interrupt/NMI context. + */ static void perf_output_read(struct perf_output_handle *handle, struct perf_event *event) { @@ -7724,7 +7729,8 @@ static int swevent_hlist_get_cpu(int cpu) int err = 0; mutex_lock(&swhash->hlist_mutex); - if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) { + if (!swevent_hlist_deref(swhash) && + cpumask_test_cpu(cpu, perf_online_mask)) { struct swevent_hlist *hlist; hlist = kzalloc(sizeof(*hlist), GFP_KERNEL); @@ -7745,7 +7751,7 @@ static int swevent_hlist_get(void) { int err, cpu, failed_cpu; - get_online_cpus(); + mutex_lock(&pmus_lock); for_each_possible_cpu(cpu) { err = swevent_hlist_get_cpu(cpu); if (err) { @@ -7753,8 +7759,7 @@ static int swevent_hlist_get(void) goto fail; } } - put_online_cpus(); - + mutex_unlock(&pmus_lock); return 0; fail: for_each_possible_cpu(cpu) { @@ -7762,8 +7767,7 @@ fail: break; swevent_hlist_put_cpu(cpu); } - - put_online_cpus(); + mutex_unlock(&pmus_lock); return err; } @@ -8058,12 +8062,8 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) bool is_kprobe, is_tracepoint; struct bpf_prog *prog; - if (event->attr.type == PERF_TYPE_HARDWARE || - event->attr.type == PERF_TYPE_SOFTWARE) - return perf_event_set_bpf_handler(event, prog_fd); - if (event->attr.type != PERF_TYPE_TRACEPOINT) - return -EINVAL; + return perf_event_set_bpf_handler(event, prog_fd); if (event->tp_event->prog) return -EEXIST; @@ -8941,7 +8941,7 @@ perf_event_mux_interval_ms_store(struct device *dev, pmu->hrtimer_interval_ms = timer; /* update all cpuctx for this PMU */ - get_online_cpus(); + cpus_read_lock(); for_each_online_cpu(cpu) { struct perf_cpu_context *cpuctx; cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); @@ -8950,7 +8950,7 @@ perf_event_mux_interval_ms_store(struct device *dev, cpu_function_call(cpu, (remote_function_f)perf_mux_hrtimer_restart, cpuctx); } - put_online_cpus(); + cpus_read_unlock(); mutex_unlock(&mux_interval_mutex); return count; @@ -9080,6 +9080,7 @@ skip_type: lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex); lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock); cpuctx->ctx.pmu = pmu; + cpuctx->online = cpumask_test_cpu(cpu, perf_online_mask); __perf_mux_hrtimer_init(cpuctx, cpu); } @@ -9193,7 +9194,7 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) static struct pmu *perf_init_event(struct perf_event *event) { - struct pmu *pmu = NULL; + struct pmu *pmu; int idx; int ret; @@ -9462,9 +9463,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, local64_set(&hwc->period_left, hwc->sample_period); /* - * we currently do not support PERF_FORMAT_GROUP on inherited events + * We currently do not support PERF_SAMPLE_READ on inherited events. + * See perf_output_read(). */ - if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP)) + if (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ)) goto err_ns; if (!has_branch_stack(event)) @@ -9477,9 +9479,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, } pmu = perf_init_event(event); - if (!pmu) - goto err_ns; - else if (IS_ERR(pmu)) { + if (IS_ERR(pmu)) { err = PTR_ERR(pmu); goto err_ns; } @@ -9492,8 +9492,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->addr_filters_offs = kcalloc(pmu->nr_addr_filters, sizeof(unsigned long), GFP_KERNEL); - if (!event->addr_filters_offs) + if (!event->addr_filters_offs) { + err = -ENOMEM; goto err_per_task; + } /* force hw sync on the address filters */ event->addr_filters_gen = 1; @@ -9903,12 +9905,10 @@ SYSCALL_DEFINE5(perf_event_open, goto err_task; } - get_online_cpus(); - if (task) { err = mutex_lock_interruptible(&task->signal->cred_guard_mutex); if (err) - goto err_cpus; + goto err_task; /* * Reuse ptrace permission checks for now. @@ -10094,6 +10094,23 @@ SYSCALL_DEFINE5(perf_event_open, goto err_locked; } + if (!task) { + /* + * Check if the @cpu we're creating an event for is online. + * + * We use the perf_cpu_context::ctx::mutex to serialize against + * the hotplug notifiers. See perf_event_{init,exit}_cpu(). + */ + struct perf_cpu_context *cpuctx = + container_of(ctx, struct perf_cpu_context, ctx); + + if (!cpuctx->online) { + err = -ENODEV; + goto err_locked; + } + } + + /* * Must be under the same ctx::mutex as perf_install_in_context(), * because we need to serialize with concurrent event creation. @@ -10183,8 +10200,6 @@ SYSCALL_DEFINE5(perf_event_open, put_task_struct(task); } - put_online_cpus(); - mutex_lock(¤t->perf_event_mutex); list_add_tail(&event->owner_entry, ¤t->perf_event_list); mutex_unlock(¤t->perf_event_mutex); @@ -10218,8 +10233,6 @@ err_alloc: err_cred: if (task) mutex_unlock(&task->signal->cred_guard_mutex); -err_cpus: - put_online_cpus(); err_task: if (task) put_task_struct(task); @@ -10274,6 +10287,21 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, goto err_unlock; } + if (!task) { + /* + * Check if the @cpu we're creating an event for is online. + * + * We use the perf_cpu_context::ctx::mutex to serialize against + * the hotplug notifiers. See perf_event_{init,exit}_cpu(). + */ + struct perf_cpu_context *cpuctx = + container_of(ctx, struct perf_cpu_context, ctx); + if (!cpuctx->online) { + err = -ENODEV; + goto err_unlock; + } + } + if (!exclusive_event_installable(event, ctx)) { err = -EBUSY; goto err_unlock; @@ -10941,6 +10969,8 @@ static void __init perf_event_init_all_cpus(void) struct swevent_htable *swhash; int cpu; + zalloc_cpumask_var(&perf_online_mask, GFP_KERNEL); + for_each_possible_cpu(cpu) { swhash = &per_cpu(swevent_htable, cpu); mutex_init(&swhash->hlist_mutex); @@ -10956,7 +10986,7 @@ static void __init perf_event_init_all_cpus(void) } } -int perf_event_init_cpu(unsigned int cpu) +void perf_swevent_init_cpu(unsigned int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); @@ -10969,7 +10999,6 @@ int perf_event_init_cpu(unsigned int cpu) rcu_assign_pointer(swhash->swevent_hlist, hlist); } mutex_unlock(&swhash->hlist_mutex); - return 0; } #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE @@ -10987,19 +11016,22 @@ static void __perf_event_exit_context(void *__info) static void perf_event_exit_cpu_context(int cpu) { + struct perf_cpu_context *cpuctx; struct perf_event_context *ctx; struct pmu *pmu; - int idx; - idx = srcu_read_lock(&pmus_srcu); - list_for_each_entry_rcu(pmu, &pmus, entry) { - ctx = &per_cpu_ptr(pmu->pmu_cpu_context, cpu)->ctx; + mutex_lock(&pmus_lock); + list_for_each_entry(pmu, &pmus, entry) { + cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); + ctx = &cpuctx->ctx; mutex_lock(&ctx->mutex); smp_call_function_single(cpu, __perf_event_exit_context, ctx, 1); + cpuctx->online = 0; mutex_unlock(&ctx->mutex); } - srcu_read_unlock(&pmus_srcu, idx); + cpumask_clear_cpu(cpu, perf_online_mask); + mutex_unlock(&pmus_lock); } #else @@ -11007,6 +11039,29 @@ static void perf_event_exit_cpu_context(int cpu) { } #endif +int perf_event_init_cpu(unsigned int cpu) +{ + struct perf_cpu_context *cpuctx; + struct perf_event_context *ctx; + struct pmu *pmu; + + perf_swevent_init_cpu(cpu); + + mutex_lock(&pmus_lock); + cpumask_set_cpu(cpu, perf_online_mask); + list_for_each_entry(pmu, &pmus, entry) { + cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); + ctx = &cpuctx->ctx; + + mutex_lock(&ctx->mutex); + cpuctx->online = 1; + mutex_unlock(&ctx->mutex); + } + mutex_unlock(&pmus_lock); + + return 0; +} + int perf_event_exit_cpu(unsigned int cpu) { perf_event_exit_cpu_context(cpu); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 2831480c63a2..ee97196bb151 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -580,7 +580,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, int ret = -ENOMEM, max_order = 0; if (!has_aux(event)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) { /* diff --git a/kernel/exit.c b/kernel/exit.c index 516acdb0e0ec..b0cc86a2d00b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -62,6 +62,7 @@ #include <linux/kcov.h> #include <linux/random.h> #include <linux/rcuwait.h> +#include <linux/compat.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -318,19 +319,6 @@ void rcuwait_wake_up(struct rcuwait *w) rcu_read_unlock(); } -struct task_struct *try_get_task_struct(struct task_struct **ptask) -{ - struct task_struct *task; - - rcu_read_lock(); - task = task_rcu_dereference(ptask); - if (task) - get_task_struct(task); - rcu_read_unlock(); - - return task; -} - /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected @@ -995,16 +983,23 @@ SYSCALL_DEFINE1(exit_group, int, error_code) return 0; } +struct waitid_info { + pid_t pid; + uid_t uid; + int status; + int cause; +}; + struct wait_opts { enum pid_type wo_type; int wo_flags; struct pid *wo_pid; - struct siginfo __user *wo_info; - int __user *wo_stat; - struct rusage __user *wo_rusage; + struct waitid_info *wo_info; + int wo_stat; + struct rusage *wo_rusage; - wait_queue_t child_wait; + wait_queue_entry_t child_wait; int notask_error; }; @@ -1049,34 +1044,6 @@ eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p) return 1; } -static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p, - pid_t pid, uid_t uid, int why, int status) -{ - struct siginfo __user *infop; - int retval = wo->wo_rusage - ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; - - put_task_struct(p); - infop = wo->wo_info; - if (infop) { - if (!retval) - retval = put_user(SIGCHLD, &infop->si_signo); - if (!retval) - retval = put_user(0, &infop->si_errno); - if (!retval) - retval = put_user((short)why, &infop->si_code); - if (!retval) - retval = put_user(pid, &infop->si_pid); - if (!retval) - retval = put_user(uid, &infop->si_uid); - if (!retval) - retval = put_user(status, &infop->si_status); - } - if (!retval) - retval = pid; - return retval; -} - /* * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold * read_lock(&tasklist_lock) on entry. If we return zero, we still hold @@ -1085,30 +1052,23 @@ static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p, */ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) { - int state, retval, status; + int state, status; pid_t pid = task_pid_vnr(p); uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p)); - struct siginfo __user *infop; + struct waitid_info *infop; if (!likely(wo->wo_flags & WEXITED)) return 0; if (unlikely(wo->wo_flags & WNOWAIT)) { - int exit_code = p->exit_code; - int why; - + status = p->exit_code; get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); - - if ((exit_code & 0x7f) == 0) { - why = CLD_EXITED; - status = exit_code >> 8; - } else { - why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED; - status = exit_code & 0x7f; - } - return wait_noreap_copyout(wo, p, pid, uid, why, status); + if (wo->wo_rusage) + getrusage(p, RUSAGE_BOTH, wo->wo_rusage); + put_task_struct(p); + goto out_info; } /* * Move the task's state to DEAD/TRACE, only one thread can do this. @@ -1181,38 +1141,11 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) spin_unlock_irq(¤t->sighand->siglock); } - retval = wo->wo_rusage - ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; + if (wo->wo_rusage) + getrusage(p, RUSAGE_BOTH, wo->wo_rusage); status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; - if (!retval && wo->wo_stat) - retval = put_user(status, wo->wo_stat); - - infop = wo->wo_info; - if (!retval && infop) - retval = put_user(SIGCHLD, &infop->si_signo); - if (!retval && infop) - retval = put_user(0, &infop->si_errno); - if (!retval && infop) { - int why; - - if ((status & 0x7f) == 0) { - why = CLD_EXITED; - status >>= 8; - } else { - why = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; - status &= 0x7f; - } - retval = put_user((short)why, &infop->si_code); - if (!retval) - retval = put_user(status, &infop->si_status); - } - if (!retval && infop) - retval = put_user(pid, &infop->si_pid); - if (!retval && infop) - retval = put_user(uid, &infop->si_uid); - if (!retval) - retval = pid; + wo->wo_stat = status; if (state == EXIT_TRACE) { write_lock_irq(&tasklist_lock); @@ -1229,7 +1162,21 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) if (state == EXIT_DEAD) release_task(p); - return retval; +out_info: + infop = wo->wo_info; + if (infop) { + if ((status & 0x7f) == 0) { + infop->cause = CLD_EXITED; + infop->status = status >> 8; + } else { + infop->cause = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; + infop->status = status & 0x7f; + } + infop->pid = pid; + infop->uid = uid; + } + + return pid; } static int *task_stopped_code(struct task_struct *p, bool ptrace) @@ -1265,8 +1212,8 @@ static int *task_stopped_code(struct task_struct *p, bool ptrace) static int wait_task_stopped(struct wait_opts *wo, int ptrace, struct task_struct *p) { - struct siginfo __user *infop; - int retval, exit_code, *p_code, why; + struct waitid_info *infop; + int exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; @@ -1311,34 +1258,21 @@ unlock_sig: why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); sched_annotate_sleep(); + if (wo->wo_rusage) + getrusage(p, RUSAGE_BOTH, wo->wo_rusage); + put_task_struct(p); - if (unlikely(wo->wo_flags & WNOWAIT)) - return wait_noreap_copyout(wo, p, pid, uid, why, exit_code); - - retval = wo->wo_rusage - ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; - if (!retval && wo->wo_stat) - retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat); + if (likely(!(wo->wo_flags & WNOWAIT))) + wo->wo_stat = (exit_code << 8) | 0x7f; infop = wo->wo_info; - if (!retval && infop) - retval = put_user(SIGCHLD, &infop->si_signo); - if (!retval && infop) - retval = put_user(0, &infop->si_errno); - if (!retval && infop) - retval = put_user((short)why, &infop->si_code); - if (!retval && infop) - retval = put_user(exit_code, &infop->si_status); - if (!retval && infop) - retval = put_user(pid, &infop->si_pid); - if (!retval && infop) - retval = put_user(uid, &infop->si_uid); - if (!retval) - retval = pid; - put_task_struct(p); - - BUG_ON(!retval); - return retval; + if (infop) { + infop->cause = why; + infop->status = exit_code; + infop->pid = pid; + infop->uid = uid; + } + return pid; } /* @@ -1349,7 +1283,7 @@ unlock_sig: */ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { - int retval; + struct waitid_info *infop; pid_t pid; uid_t uid; @@ -1374,22 +1308,20 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); + if (wo->wo_rusage) + getrusage(p, RUSAGE_BOTH, wo->wo_rusage); + put_task_struct(p); - if (!wo->wo_info) { - retval = wo->wo_rusage - ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; - put_task_struct(p); - if (!retval && wo->wo_stat) - retval = put_user(0xffff, wo->wo_stat); - if (!retval) - retval = pid; + infop = wo->wo_info; + if (!infop) { + wo->wo_stat = 0xffff; } else { - retval = wait_noreap_copyout(wo, p, pid, uid, - CLD_CONTINUED, SIGCONT); - BUG_ON(retval == 0); + infop->cause = CLD_CONTINUED; + infop->pid = pid; + infop->uid = uid; + infop->status = SIGCONT; } - - return retval; + return pid; } /* @@ -1541,7 +1473,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) return 0; } -static int child_wait_callback(wait_queue_t *wait, unsigned mode, +static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct wait_opts *wo = container_of(wait, struct wait_opts, @@ -1617,8 +1549,8 @@ end: return retval; } -SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, - infop, int, options, struct rusage __user *, ru) +static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, + int options, struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; @@ -1656,38 +1588,46 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, wo.wo_pid = pid; wo.wo_flags = options; wo.wo_info = infop; - wo.wo_stat = NULL; wo.wo_rusage = ru; ret = do_wait(&wo); - if (ret > 0) { + if (ret > 0) ret = 0; - } else if (infop) { - /* - * For a WNOHANG return, clear out all the fields - * we would set so the user can easily tell the - * difference. - */ - if (!ret) - ret = put_user(0, &infop->si_signo); - if (!ret) - ret = put_user(0, &infop->si_errno); - if (!ret) - ret = put_user(0, &infop->si_code); - if (!ret) - ret = put_user(0, &infop->si_pid); - if (!ret) - ret = put_user(0, &infop->si_uid); - if (!ret) - ret = put_user(0, &infop->si_status); - } put_pid(pid); return ret; } -SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, - int, options, struct rusage __user *, ru) +SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, + infop, int, options, struct rusage __user *, ru) +{ + struct rusage r; + struct waitid_info info = {.status = 0}; + long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); + + if (!err) { + if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) + return -EFAULT; + } + if (!infop) + return err; + + user_access_begin(); + unsafe_put_user(err ? 0 : SIGCHLD, &infop->si_signo, Efault); + unsafe_put_user(0, &infop->si_errno, Efault); + unsafe_put_user((short)info.cause, &infop->si_code, Efault); + unsafe_put_user(info.pid, &infop->si_pid, Efault); + unsafe_put_user(info.uid, &infop->si_uid, Efault); + unsafe_put_user(info.status, &infop->si_status, Efault); + user_access_end(); + return err; +Efault: + user_access_end(); + return -EFAULT; +} + +long kernel_wait4(pid_t upid, int __user *stat_addr, int options, + struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; @@ -1715,14 +1655,29 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, wo.wo_pid = pid; wo.wo_flags = options | WEXITED; wo.wo_info = NULL; - wo.wo_stat = stat_addr; + wo.wo_stat = 0; wo.wo_rusage = ru; ret = do_wait(&wo); put_pid(pid); + if (ret > 0 && stat_addr && put_user(wo.wo_stat, stat_addr)) + ret = -EFAULT; return ret; } +SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, + int, options, struct rusage __user *, ru) +{ + struct rusage r; + long err = kernel_wait4(upid, stat_addr, options, ru ? &r : NULL); + + if (err > 0) { + if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) + return -EFAULT; + } + return err; +} + #ifdef __ARCH_WANT_SYS_WAITPID /* @@ -1735,3 +1690,56 @@ SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options) } #endif + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(wait4, + compat_pid_t, pid, + compat_uint_t __user *, stat_addr, + int, options, + struct compat_rusage __user *, ru) +{ + struct rusage r; + long err = kernel_wait4(pid, stat_addr, options, ru ? &r : NULL); + if (err > 0) { + if (ru && put_compat_rusage(&r, ru)) + return -EFAULT; + } + return err; +} + +COMPAT_SYSCALL_DEFINE5(waitid, + int, which, compat_pid_t, pid, + struct compat_siginfo __user *, infop, int, options, + struct compat_rusage __user *, uru) +{ + struct rusage ru; + struct waitid_info info = {.status = 0}; + long err = kernel_waitid(which, pid, &info, options, uru ? &ru : NULL); + + if (!err && uru) { + /* kernel_waitid() overwrites everything in ru */ + if (COMPAT_USE_64BIT_TIME) + err = copy_to_user(uru, &ru, sizeof(ru)); + else + err = put_compat_rusage(&ru, uru); + if (err) + return -EFAULT; + } + + if (!infop) + return err; + + user_access_begin(); + unsafe_put_user(err ? 0 : SIGCHLD, &infop->si_signo, Efault); + unsafe_put_user(0, &infop->si_errno, Efault); + unsafe_put_user((short)info.cause, &infop->si_code, Efault); + unsafe_put_user(info.pid, &infop->si_pid, Efault); + unsafe_put_user(info.uid, &infop->si_uid, Efault); + unsafe_put_user(info.status, &infop->si_status, Efault); + user_access_end(); + return err; +Efault: + user_access_end(); + return -EFAULT; +} +#endif diff --git a/kernel/extable.c b/kernel/extable.c index 2676d7f8baf6..0fbdd8582f08 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -75,7 +75,7 @@ int core_kernel_text(unsigned long addr) addr < (unsigned long)_etext) return 1; - if (system_state == SYSTEM_BOOTING && + if (system_state < SYSTEM_RUNNING && init_kernel_text(addr)) return 1; return 0; diff --git a/kernel/futex.c b/kernel/futex.c index 357348a6cf6b..c934689043b2 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -225,7 +225,7 @@ struct futex_pi_state { * @requeue_pi_key: the requeue_pi target futex key * @bitset: bitset for the optional bitmasked wakeup * - * We use this hashed waitqueue, instead of a normal wait_queue_t, so + * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so * we can wake only the relevant ones (hashed queues may be shared). * * A futex_q has a woken state, just like tasks have TASK_RUNNING. @@ -488,7 +488,7 @@ static void drop_futex_key_refs(union futex_key *key) * * Return: a negative error code or 0 * - * The key words are stored in *key on success. + * The key words are stored in @key on success. * * For shared mappings, it's (page->index, file_inode(vma->vm_file), * offset_within_page). For private mappings, it's (uaddr, current->mm). @@ -1259,9 +1259,9 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) * @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0) * * Return: - * 0 - ready to wait; - * 1 - acquired the lock; - * <0 - error + * - 0 - ready to wait; + * - 1 - acquired the lock; + * - <0 - error * * The hb->lock and futex_key refs shall be held by the caller. */ @@ -1717,9 +1717,9 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, * hb1 and hb2 must be held by the caller. * * Return: - * 0 - failed to acquire the lock atomically; - * >0 - acquired the lock, return value is vpid of the top_waiter - * <0 - error + * - 0 - failed to acquire the lock atomically; + * - >0 - acquired the lock, return value is vpid of the top_waiter + * - <0 - error */ static int futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, @@ -1785,8 +1785,8 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex, * uaddr2 atomically on behalf of the top waiter. * * Return: - * >=0 - on success, the number of tasks requeued or woken; - * <0 - on error + * - >=0 - on success, the number of tasks requeued or woken; + * - <0 - on error */ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_requeue, @@ -2142,8 +2142,8 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) * be paired with exactly one earlier call to queue_me(). * * Return: - * 1 - if the futex_q was still queued (and we removed unqueued it); - * 0 - if the futex_q was already removed by the waking thread + * - 1 - if the futex_q was still queued (and we removed unqueued it); + * - 0 - if the futex_q was already removed by the waking thread */ static int unqueue_me(struct futex_q *q) { @@ -2333,9 +2333,9 @@ static long futex_wait_restart(struct restart_block *restart); * acquire the lock. Must be called with the hb lock held. * * Return: - * 1 - success, lock taken; - * 0 - success, lock not taken; - * <0 - on error (-EFAULT) + * - 1 - success, lock taken; + * - 0 - success, lock not taken; + * - <0 - on error (-EFAULT) */ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) { @@ -2422,8 +2422,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, * with no q.key reference on failure. * * Return: - * 0 - uaddr contains val and hb has been locked; - * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked + * - 0 - uaddr contains val and hb has been locked; + * - <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked */ static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, struct futex_hash_bucket **hb) @@ -2895,8 +2895,8 @@ pi_faulted: * called with the hb lock held. * * Return: - * 0 = no early wakeup detected; - * <0 = -ETIMEDOUT or -ERESTARTNOINTR + * - 0 = no early wakeup detected; + * - <0 = -ETIMEDOUT or -ERESTARTNOINTR */ static inline int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, @@ -2968,8 +2968,8 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, * If 4 or 7, we cleanup and return with -ETIMEDOUT. * * Return: - * 0 - On success; - * <0 - On error + * - 0 - On success; + * - <0 - On error */ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset, diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 3bbfd6a9c475..27c4e774071c 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -21,6 +21,10 @@ config GENERIC_IRQ_SHOW config GENERIC_IRQ_SHOW_LEVEL bool +# Supports effective affinity mask +config GENERIC_IRQ_EFFECTIVE_AFF_MASK + bool + # Facility to allocate a hardware interrupt. This is legacy support # and should not be used in new code. Use irq domains instead. config GENERIC_IRQ_LEGACY_ALLOC_HWIRQ @@ -81,6 +85,9 @@ config GENERIC_MSI_IRQ_DOMAIN config HANDLE_DOMAIN_IRQ bool +config IRQ_TIMINGS + bool + config IRQ_DOMAIN_DEBUG bool "Expose hardware/virtual IRQ mapping via debugfs" depends on IRQ_DOMAIN && DEBUG_FS @@ -108,4 +115,15 @@ config SPARSE_IRQ If you don't know what to do here, say N. +config GENERIC_IRQ_DEBUGFS + bool "Expose irq internals in debugfs" + depends on DEBUG_FS + default n + ---help--- + + Exposes internal state information through debugfs. Mostly for + developers and debugging of hard to diagnose interrupt problems. + + If you don't know what to do here, say N. + endmenu diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 1d3ee3169202..e4aef7351f2b 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,5 +1,6 @@ obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o +obj-$(CONFIG_IRQ_TIMINGS) += timings.o obj-$(CONFIG_GENERIC_IRQ_CHIP) += generic-chip.o obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o @@ -10,3 +11,4 @@ obj-$(CONFIG_PM_SLEEP) += pm.o obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o obj-$(CONFIG_SMP) += affinity.o +obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index e2d356dd7581..d2747f9c5707 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -1,4 +1,7 @@ - +/* + * Copyright (C) 2016 Thomas Gleixner. + * Copyright (C) 2016-2017 Christoph Hellwig. + */ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/slab.h> @@ -35,13 +38,54 @@ static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk, } } -static int get_nodes_in_cpumask(const struct cpumask *mask, nodemask_t *nodemsk) +static cpumask_var_t *alloc_node_to_present_cpumask(void) +{ + cpumask_var_t *masks; + int node; + + masks = kcalloc(nr_node_ids, sizeof(cpumask_var_t), GFP_KERNEL); + if (!masks) + return NULL; + + for (node = 0; node < nr_node_ids; node++) { + if (!zalloc_cpumask_var(&masks[node], GFP_KERNEL)) + goto out_unwind; + } + + return masks; + +out_unwind: + while (--node >= 0) + free_cpumask_var(masks[node]); + kfree(masks); + return NULL; +} + +static void free_node_to_present_cpumask(cpumask_var_t *masks) +{ + int node; + + for (node = 0; node < nr_node_ids; node++) + free_cpumask_var(masks[node]); + kfree(masks); +} + +static void build_node_to_present_cpumask(cpumask_var_t *masks) +{ + int cpu; + + for_each_present_cpu(cpu) + cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]); +} + +static int get_nodes_in_cpumask(cpumask_var_t *node_to_present_cpumask, + const struct cpumask *mask, nodemask_t *nodemsk) { int n, nodes = 0; /* Calculate the number of nodes in the supplied affinity mask */ - for_each_online_node(n) { - if (cpumask_intersects(mask, cpumask_of_node(n))) { + for_each_node(n) { + if (cpumask_intersects(mask, node_to_present_cpumask[n])) { node_set(n, *nodemsk); nodes++; } @@ -64,7 +108,7 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) int last_affv = affv + affd->pre_vectors; nodemask_t nodemsk = NODE_MASK_NONE; struct cpumask *masks; - cpumask_var_t nmsk; + cpumask_var_t nmsk, *node_to_present_cpumask; if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL)) return NULL; @@ -73,13 +117,19 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) if (!masks) goto out; + node_to_present_cpumask = alloc_node_to_present_cpumask(); + if (!node_to_present_cpumask) + goto out; + /* Fill out vectors at the beginning that don't need affinity */ for (curvec = 0; curvec < affd->pre_vectors; curvec++) cpumask_copy(masks + curvec, irq_default_affinity); /* Stabilize the cpumasks */ get_online_cpus(); - nodes = get_nodes_in_cpumask(cpu_online_mask, &nodemsk); + build_node_to_present_cpumask(node_to_present_cpumask); + nodes = get_nodes_in_cpumask(node_to_present_cpumask, cpu_present_mask, + &nodemsk); /* * If the number of nodes in the mask is greater than or equal the @@ -87,7 +137,8 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) */ if (affv <= nodes) { for_each_node_mask(n, nodemsk) { - cpumask_copy(masks + curvec, cpumask_of_node(n)); + cpumask_copy(masks + curvec, + node_to_present_cpumask[n]); if (++curvec == last_affv) break; } @@ -101,7 +152,7 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes; /* Get the cpus on this node which are in the mask */ - cpumask_and(nmsk, cpu_online_mask, cpumask_of_node(n)); + cpumask_and(nmsk, cpu_present_mask, node_to_present_cpumask[n]); /* Calculate the number of cpus per vector */ ncpus = cpumask_weight(nmsk); @@ -133,6 +184,7 @@ done: /* Fill out vectors at the end that don't need affinity */ for (; curvec < nvecs; curvec++) cpumask_copy(masks + curvec, irq_default_affinity); + free_node_to_present_cpumask(node_to_present_cpumask); out: free_cpumask_var(nmsk); return masks; @@ -147,12 +199,10 @@ int irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd) { int resv = affd->pre_vectors + affd->post_vectors; int vecs = maxvec - resv; - int cpus; + int ret; - /* Stabilize the cpumasks */ get_online_cpus(); - cpus = cpumask_weight(cpu_online_mask); + ret = min_t(int, cpumask_weight(cpu_present_mask), vecs) + resv; put_online_cpus(); - - return min(cpus, vecs) + resv; + return ret; } diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index 0119b9d467ae..d30a0dd5cc02 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -53,7 +53,7 @@ unsigned long probe_irq_on(void) if (desc->irq_data.chip->irq_set_type) desc->irq_data.chip->irq_set_type(&desc->irq_data, IRQ_TYPE_PROBE); - irq_startup(desc, false); + irq_startup(desc, IRQ_NORESEND, IRQ_START_FORCE); } raw_spin_unlock_irq(&desc->lock); } @@ -70,7 +70,7 @@ unsigned long probe_irq_on(void) raw_spin_lock_irq(&desc->lock); if (!desc->action && irq_settings_can_probe(desc)) { desc->istate |= IRQS_AUTODETECT | IRQS_WAITING; - if (irq_startup(desc, false)) + if (irq_startup(desc, IRQ_NORESEND, IRQ_START_FORCE)) desc->istate |= IRQS_PENDING; } raw_spin_unlock_irq(&desc->lock); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index c94da688ee9b..ad43468e89f0 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -7,7 +7,7 @@ * This file contains the core interrupt handling code, for irq-chip * based architectures. * - * Detailed information is available in Documentation/DocBook/genericirq + * Detailed information is available in Documentation/core-api/genericirq.rst */ #include <linux/irq.h> @@ -185,47 +185,162 @@ static void irq_state_set_masked(struct irq_desc *desc) irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); } -int irq_startup(struct irq_desc *desc, bool resend) +static void irq_state_clr_started(struct irq_desc *desc) { - int ret = 0; + irqd_clear(&desc->irq_data, IRQD_IRQ_STARTED); +} - irq_state_clr_disabled(desc); - desc->depth = 0; +static void irq_state_set_started(struct irq_desc *desc) +{ + irqd_set(&desc->irq_data, IRQD_IRQ_STARTED); +} + +enum { + IRQ_STARTUP_NORMAL, + IRQ_STARTUP_MANAGED, + IRQ_STARTUP_ABORT, +}; + +#ifdef CONFIG_SMP +static int +__irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + + if (!irqd_affinity_is_managed(d)) + return IRQ_STARTUP_NORMAL; + + irqd_clr_managed_shutdown(d); - irq_domain_activate_irq(&desc->irq_data); - if (desc->irq_data.chip->irq_startup) { - ret = desc->irq_data.chip->irq_startup(&desc->irq_data); + if (cpumask_any_and(aff, cpu_online_mask) > nr_cpu_ids) { + /* + * Catch code which fiddles with enable_irq() on a managed + * and potentially shutdown IRQ. Chained interrupt + * installment or irq auto probing should not happen on + * managed irqs either. Emit a warning, break the affinity + * and start it up as a normal interrupt. + */ + if (WARN_ON_ONCE(force)) + return IRQ_STARTUP_NORMAL; + /* + * The interrupt was requested, but there is no online CPU + * in it's affinity mask. Put it into managed shutdown + * state and let the cpu hotplug mechanism start it up once + * a CPU in the mask becomes available. + */ + irqd_set_managed_shutdown(d); + return IRQ_STARTUP_ABORT; + } + return IRQ_STARTUP_MANAGED; +} +#else +static int +__irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) +{ + return IRQ_STARTUP_NORMAL; +} +#endif + +static int __irq_startup(struct irq_desc *desc) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + int ret = 0; + + irq_domain_activate_irq(d); + if (d->chip->irq_startup) { + ret = d->chip->irq_startup(d); + irq_state_clr_disabled(desc); irq_state_clr_masked(desc); } else { irq_enable(desc); } + irq_state_set_started(desc); + return ret; +} + +int irq_startup(struct irq_desc *desc, bool resend, bool force) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + struct cpumask *aff = irq_data_get_affinity_mask(d); + int ret = 0; + + desc->depth = 0; + + if (irqd_is_started(d)) { + irq_enable(desc); + } else { + switch (__irq_startup_managed(desc, aff, force)) { + case IRQ_STARTUP_NORMAL: + ret = __irq_startup(desc); + irq_setup_affinity(desc); + break; + case IRQ_STARTUP_MANAGED: + ret = __irq_startup(desc); + irq_set_affinity_locked(d, aff, false); + break; + case IRQ_STARTUP_ABORT: + return 0; + } + } if (resend) check_irq_resend(desc); + return ret; } +static void __irq_disable(struct irq_desc *desc, bool mask); + void irq_shutdown(struct irq_desc *desc) { - irq_state_set_disabled(desc); - desc->depth = 1; - if (desc->irq_data.chip->irq_shutdown) - desc->irq_data.chip->irq_shutdown(&desc->irq_data); - else if (desc->irq_data.chip->irq_disable) - desc->irq_data.chip->irq_disable(&desc->irq_data); - else - desc->irq_data.chip->irq_mask(&desc->irq_data); + if (irqd_is_started(&desc->irq_data)) { + desc->depth = 1; + if (desc->irq_data.chip->irq_shutdown) { + desc->irq_data.chip->irq_shutdown(&desc->irq_data); + irq_state_set_disabled(desc); + irq_state_set_masked(desc); + } else { + __irq_disable(desc, true); + } + irq_state_clr_started(desc); + } + /* + * This must be called even if the interrupt was never started up, + * because the activation can happen before the interrupt is + * available for request/startup. It has it's own state tracking so + * it's safe to call it unconditionally. + */ irq_domain_deactivate_irq(&desc->irq_data); - irq_state_set_masked(desc); } void irq_enable(struct irq_desc *desc) { - irq_state_clr_disabled(desc); - if (desc->irq_data.chip->irq_enable) - desc->irq_data.chip->irq_enable(&desc->irq_data); - else - desc->irq_data.chip->irq_unmask(&desc->irq_data); - irq_state_clr_masked(desc); + if (!irqd_irq_disabled(&desc->irq_data)) { + unmask_irq(desc); + } else { + irq_state_clr_disabled(desc); + if (desc->irq_data.chip->irq_enable) { + desc->irq_data.chip->irq_enable(&desc->irq_data); + irq_state_clr_masked(desc); + } else { + unmask_irq(desc); + } + } +} + +static void __irq_disable(struct irq_desc *desc, bool mask) +{ + if (irqd_irq_disabled(&desc->irq_data)) { + if (mask) + mask_irq(desc); + } else { + irq_state_set_disabled(desc); + if (desc->irq_data.chip->irq_disable) { + desc->irq_data.chip->irq_disable(&desc->irq_data); + irq_state_set_masked(desc); + } else if (mask) { + mask_irq(desc); + } + } } /** @@ -250,13 +365,7 @@ void irq_enable(struct irq_desc *desc) */ void irq_disable(struct irq_desc *desc) { - irq_state_set_disabled(desc); - if (desc->irq_data.chip->irq_disable) { - desc->irq_data.chip->irq_disable(&desc->irq_data); - irq_state_set_masked(desc); - } else if (irq_settings_disable_unlazy(desc)) { - mask_irq(desc); - } + __irq_disable(desc, irq_settings_disable_unlazy(desc)); } void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu) @@ -279,18 +388,21 @@ void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu) static inline void mask_ack_irq(struct irq_desc *desc) { - if (desc->irq_data.chip->irq_mask_ack) + if (desc->irq_data.chip->irq_mask_ack) { desc->irq_data.chip->irq_mask_ack(&desc->irq_data); - else { - desc->irq_data.chip->irq_mask(&desc->irq_data); + irq_state_set_masked(desc); + } else { + mask_irq(desc); if (desc->irq_data.chip->irq_ack) desc->irq_data.chip->irq_ack(&desc->irq_data); } - irq_state_set_masked(desc); } void mask_irq(struct irq_desc *desc) { + if (irqd_irq_masked(&desc->irq_data)) + return; + if (desc->irq_data.chip->irq_mask) { desc->irq_data.chip->irq_mask(&desc->irq_data); irq_state_set_masked(desc); @@ -299,6 +411,9 @@ void mask_irq(struct irq_desc *desc) void unmask_irq(struct irq_desc *desc) { + if (!irqd_irq_masked(&desc->irq_data)) + return; + if (desc->irq_data.chip->irq_unmask) { desc->irq_data.chip->irq_unmask(&desc->irq_data); irq_state_clr_masked(desc); @@ -312,10 +427,7 @@ void unmask_threaded_irq(struct irq_desc *desc) if (chip->flags & IRQCHIP_EOI_THREADED) chip->irq_eoi(&desc->irq_data); - if (chip->irq_unmask) { - chip->irq_unmask(&desc->irq_data); - irq_state_clr_masked(desc); - } + unmask_irq(desc); } /* @@ -851,7 +963,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); desc->action = &chained_action; - irq_startup(desc, true); + irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE); } } @@ -903,6 +1015,13 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) if (!desc) return; + + /* + * Warn when a driver sets the no autoenable flag on an already + * active interrupt. + */ + WARN_ON_ONCE(!desc->depth && (set & _IRQ_NOAUTOEN)); + irq_settings_clr_and_set(desc, clr, set); irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU | diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 011f8c4c63da..aee8f7ec40af 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -14,37 +14,99 @@ #include "internals.h" +/* For !GENERIC_IRQ_EFFECTIVE_AFF_MASK this looks at general affinity mask */ +static inline bool irq_needs_fixup(struct irq_data *d) +{ + const struct cpumask *m = irq_data_get_effective_affinity_mask(d); + + return cpumask_test_cpu(smp_processor_id(), m); +} + static bool migrate_one_irq(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); - const struct cpumask *affinity = d->common->affinity; - struct irq_chip *c; - bool ret = false; + struct irq_chip *chip = irq_data_get_irq_chip(d); + bool maskchip = !irq_can_move_pcntxt(d) && !irqd_irq_masked(d); + const struct cpumask *affinity; + bool brokeaff = false; + int err; /* - * If this is a per-CPU interrupt, or the affinity does not - * include this CPU, then we have nothing to do. + * IRQ chip might be already torn down, but the irq descriptor is + * still in the radix tree. Also if the chip has no affinity setter, + * nothing can be done here. */ - if (irqd_is_per_cpu(d) || - !cpumask_test_cpu(smp_processor_id(), affinity)) + if (!chip || !chip->irq_set_affinity) { + pr_debug("IRQ %u: Unable to migrate away\n", d->irq); return false; + } + + /* + * No move required, if: + * - Interrupt is per cpu + * - Interrupt is not started + * - Affinity mask does not include this CPU. + * + * Note: Do not check desc->action as this might be a chained + * interrupt. + */ + if (irqd_is_per_cpu(d) || !irqd_is_started(d) || !irq_needs_fixup(d)) { + /* + * If an irq move is pending, abort it if the dying CPU is + * the sole target. + */ + irq_fixup_move_pending(desc, false); + return false; + } + + /* + * Complete an eventually pending irq move cleanup. If this + * interrupt was moved in hard irq context, then the vectors need + * to be cleaned up. It can't wait until this interrupt actually + * happens and this CPU was involved. + */ + irq_force_complete_move(desc); + + /* + * If there is a setaffinity pending, then try to reuse the pending + * mask, so the last change of the affinity does not get lost. If + * there is no move pending or the pending mask does not contain + * any online CPU, use the current affinity mask. + */ + if (irq_fixup_move_pending(desc, true)) + affinity = irq_desc_get_pending_mask(desc); + else + affinity = irq_data_get_affinity_mask(d); + + /* Mask the chip for interrupts which cannot move in process context */ + if (maskchip && chip->irq_mask) + chip->irq_mask(d); if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { + /* + * If the interrupt is managed, then shut it down and leave + * the affinity untouched. + */ + if (irqd_affinity_is_managed(d)) { + irqd_set_managed_shutdown(d); + irq_shutdown(desc); + return false; + } affinity = cpu_online_mask; - ret = true; + brokeaff = true; } - c = irq_data_get_irq_chip(d); - if (!c->irq_set_affinity) { - pr_debug("IRQ%u: unable to set affinity\n", d->irq); - } else { - int r = irq_do_set_affinity(d, affinity, false); - if (r) - pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n", - d->irq, r); + err = irq_do_set_affinity(d, affinity, true); + if (err) { + pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n", + d->irq, err); + brokeaff = false; } - return ret; + if (maskchip && chip->irq_unmask) + chip->irq_unmask(d); + + return brokeaff; } /** @@ -59,11 +121,8 @@ static bool migrate_one_irq(struct irq_desc *desc) */ void irq_migrate_all_off_this_cpu(void) { - unsigned int irq; struct irq_desc *desc; - unsigned long flags; - - local_irq_save(flags); + unsigned int irq; for_each_active_irq(irq) { bool affinity_broken; @@ -73,10 +132,53 @@ void irq_migrate_all_off_this_cpu(void) affinity_broken = migrate_one_irq(desc); raw_spin_unlock(&desc->lock); - if (affinity_broken) - pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n", + if (affinity_broken) { + pr_warn_ratelimited("IRQ %u: no longer affine to CPU%u\n", irq, smp_processor_id()); + } + } +} + +static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) +{ + struct irq_data *data = irq_desc_get_irq_data(desc); + const struct cpumask *affinity = irq_data_get_affinity_mask(data); + + if (!irqd_affinity_is_managed(data) || !desc->action || + !irq_data_get_irq_chip(data) || !cpumask_test_cpu(cpu, affinity)) + return; + + if (irqd_is_managed_and_shutdown(data)) { + irq_startup(desc, IRQ_RESEND, IRQ_START_COND); + return; + } + + /* + * If the interrupt can only be directed to a single target + * CPU then it is already assigned to a CPU in the affinity + * mask. No point in trying to move it around. + */ + if (!irqd_is_single_target(data)) + irq_set_affinity_locked(data, affinity, false); +} + +/** + * irq_affinity_online_cpu - Restore affinity for managed interrupts + * @cpu: Upcoming CPU for which interrupts should be restored + */ +int irq_affinity_online_cpu(unsigned int cpu) +{ + struct irq_desc *desc; + unsigned int irq; + + irq_lock_sparse(); + for_each_active_irq(irq) { + desc = irq_to_desc(irq); + raw_spin_lock_irq(&desc->lock); + irq_restore_affinity_of_irq(desc, cpu); + raw_spin_unlock_irq(&desc->lock); } + irq_unlock_sparse(); - local_irq_restore(flags); + return 0; } diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c new file mode 100644 index 000000000000..4d384edc0c64 --- /dev/null +++ b/kernel/irq/debugfs.c @@ -0,0 +1,213 @@ +/* + * Copyright 2017 Thomas Gleixner <tglx@linutronix.de> + * + * This file is licensed under the GPL V2. + */ +#include <linux/irqdomain.h> +#include <linux/irq.h> + +#include "internals.h" + +static struct dentry *irq_dir; + +struct irq_bit_descr { + unsigned int mask; + char *name; +}; +#define BIT_MASK_DESCR(m) { .mask = m, .name = #m } + +static void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, + const struct irq_bit_descr *sd, int size) +{ + int i; + + for (i = 0; i < size; i++, sd++) { + if (state & sd->mask) + seq_printf(m, "%*s%s\n", ind + 12, "", sd->name); + } +} + +#ifdef CONFIG_SMP +static void irq_debug_show_masks(struct seq_file *m, struct irq_desc *desc) +{ + struct irq_data *data = irq_desc_get_irq_data(desc); + struct cpumask *msk; + + msk = irq_data_get_affinity_mask(data); + seq_printf(m, "affinity: %*pbl\n", cpumask_pr_args(msk)); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + msk = irq_data_get_effective_affinity_mask(data); + seq_printf(m, "effectiv: %*pbl\n", cpumask_pr_args(msk)); +#endif +#ifdef CONFIG_GENERIC_PENDING_IRQ + msk = desc->pending_mask; + seq_printf(m, "pending: %*pbl\n", cpumask_pr_args(msk)); +#endif +} +#else +static void irq_debug_show_masks(struct seq_file *m, struct irq_desc *desc) { } +#endif + +static const struct irq_bit_descr irqchip_flags[] = { + BIT_MASK_DESCR(IRQCHIP_SET_TYPE_MASKED), + BIT_MASK_DESCR(IRQCHIP_EOI_IF_HANDLED), + BIT_MASK_DESCR(IRQCHIP_MASK_ON_SUSPEND), + BIT_MASK_DESCR(IRQCHIP_ONOFFLINE_ENABLED), + BIT_MASK_DESCR(IRQCHIP_SKIP_SET_WAKE), + BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE), + BIT_MASK_DESCR(IRQCHIP_EOI_THREADED), +}; + +static void +irq_debug_show_chip(struct seq_file *m, struct irq_data *data, int ind) +{ + struct irq_chip *chip = data->chip; + + if (!chip) { + seq_printf(m, "chip: None\n"); + return; + } + seq_printf(m, "%*schip: %s\n", ind, "", chip->name); + seq_printf(m, "%*sflags: 0x%lx\n", ind + 1, "", chip->flags); + irq_debug_show_bits(m, ind, chip->flags, irqchip_flags, + ARRAY_SIZE(irqchip_flags)); +} + +static void +irq_debug_show_data(struct seq_file *m, struct irq_data *data, int ind) +{ + seq_printf(m, "%*sdomain: %s\n", ind, "", + data->domain ? data->domain->name : ""); + seq_printf(m, "%*shwirq: 0x%lx\n", ind + 1, "", data->hwirq); + irq_debug_show_chip(m, data, ind + 1); +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + if (!data->parent_data) + return; + seq_printf(m, "%*sparent:\n", ind + 1, ""); + irq_debug_show_data(m, data->parent_data, ind + 4); +#endif +} + +static const struct irq_bit_descr irqdata_states[] = { + BIT_MASK_DESCR(IRQ_TYPE_EDGE_RISING), + BIT_MASK_DESCR(IRQ_TYPE_EDGE_FALLING), + BIT_MASK_DESCR(IRQ_TYPE_LEVEL_HIGH), + BIT_MASK_DESCR(IRQ_TYPE_LEVEL_LOW), + BIT_MASK_DESCR(IRQD_LEVEL), + + BIT_MASK_DESCR(IRQD_ACTIVATED), + BIT_MASK_DESCR(IRQD_IRQ_STARTED), + BIT_MASK_DESCR(IRQD_IRQ_DISABLED), + BIT_MASK_DESCR(IRQD_IRQ_MASKED), + BIT_MASK_DESCR(IRQD_IRQ_INPROGRESS), + + BIT_MASK_DESCR(IRQD_PER_CPU), + BIT_MASK_DESCR(IRQD_NO_BALANCING), + + BIT_MASK_DESCR(IRQD_SINGLE_TARGET), + BIT_MASK_DESCR(IRQD_MOVE_PCNTXT), + BIT_MASK_DESCR(IRQD_AFFINITY_SET), + BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING), + BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED), + BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN), + + BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU), + + BIT_MASK_DESCR(IRQD_WAKEUP_STATE), + BIT_MASK_DESCR(IRQD_WAKEUP_ARMED), +}; + +static const struct irq_bit_descr irqdesc_states[] = { + BIT_MASK_DESCR(_IRQ_NOPROBE), + BIT_MASK_DESCR(_IRQ_NOREQUEST), + BIT_MASK_DESCR(_IRQ_NOTHREAD), + BIT_MASK_DESCR(_IRQ_NOAUTOEN), + BIT_MASK_DESCR(_IRQ_NESTED_THREAD), + BIT_MASK_DESCR(_IRQ_PER_CPU_DEVID), + BIT_MASK_DESCR(_IRQ_IS_POLLED), + BIT_MASK_DESCR(_IRQ_DISABLE_UNLAZY), +}; + +static const struct irq_bit_descr irqdesc_istates[] = { + BIT_MASK_DESCR(IRQS_AUTODETECT), + BIT_MASK_DESCR(IRQS_SPURIOUS_DISABLED), + BIT_MASK_DESCR(IRQS_POLL_INPROGRESS), + BIT_MASK_DESCR(IRQS_ONESHOT), + BIT_MASK_DESCR(IRQS_REPLAY), + BIT_MASK_DESCR(IRQS_WAITING), + BIT_MASK_DESCR(IRQS_PENDING), + BIT_MASK_DESCR(IRQS_SUSPENDED), +}; + + +static int irq_debug_show(struct seq_file *m, void *p) +{ + struct irq_desc *desc = m->private; + struct irq_data *data; + + raw_spin_lock_irq(&desc->lock); + data = irq_desc_get_irq_data(desc); + seq_printf(m, "handler: %pf\n", desc->handle_irq); + seq_printf(m, "status: 0x%08x\n", desc->status_use_accessors); + irq_debug_show_bits(m, 0, desc->status_use_accessors, irqdesc_states, + ARRAY_SIZE(irqdesc_states)); + seq_printf(m, "istate: 0x%08x\n", desc->istate); + irq_debug_show_bits(m, 0, desc->istate, irqdesc_istates, + ARRAY_SIZE(irqdesc_istates)); + seq_printf(m, "ddepth: %u\n", desc->depth); + seq_printf(m, "wdepth: %u\n", desc->wake_depth); + seq_printf(m, "dstate: 0x%08x\n", irqd_get(data)); + irq_debug_show_bits(m, 0, irqd_get(data), irqdata_states, + ARRAY_SIZE(irqdata_states)); + seq_printf(m, "node: %d\n", irq_data_get_node(data)); + irq_debug_show_masks(m, desc); + irq_debug_show_data(m, data, 0); + raw_spin_unlock_irq(&desc->lock); + return 0; +} + +static int irq_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_debug_show, inode->i_private); +} + +static const struct file_operations dfs_irq_ops = { + .open = irq_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc) +{ + char name [10]; + + if (!irq_dir || !desc || desc->debugfs_file) + return; + + sprintf(name, "%d", irq); + desc->debugfs_file = debugfs_create_file(name, 0444, irq_dir, desc, + &dfs_irq_ops); +} + +static int __init irq_debugfs_init(void) +{ + struct dentry *root_dir; + int irq; + + root_dir = debugfs_create_dir("irq", NULL); + if (!root_dir) + return -ENOMEM; + + irq_domain_debugfs_init(root_dir); + + irq_dir = debugfs_create_dir("irqs", root_dir); + + irq_lock_sparse(); + for_each_active_irq(irq) + irq_add_debugfs_entry(irq, irq_to_desc(irq)); + irq_unlock_sparse(); + + return 0; +} +__initcall(irq_debugfs_init); diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 1613bfd48365..194c506d9d20 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -4,6 +4,8 @@ #include <linux/gfp.h> #include <linux/irq.h> +#include "internals.h" + /* * Device resource management aware IRQ request/free implementation. */ @@ -198,3 +200,87 @@ int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from, return base; } EXPORT_SYMBOL_GPL(__devm_irq_alloc_descs); + +#ifdef CONFIG_GENERIC_IRQ_CHIP +/** + * devm_irq_alloc_generic_chip - Allocate and initialize a generic chip + * for a managed device + * @dev: Device to allocate the generic chip for + * @name: Name of the irq chip + * @num_ct: Number of irq_chip_type instances associated with this + * @irq_base: Interrupt base nr for this chip + * @reg_base: Register base address (virtual) + * @handler: Default flow handler associated with this chip + * + * Returns an initialized irq_chip_generic structure. The chip defaults + * to the primary (index 0) irq_chip_type and @handler + */ +struct irq_chip_generic * +devm_irq_alloc_generic_chip(struct device *dev, const char *name, int num_ct, + unsigned int irq_base, void __iomem *reg_base, + irq_flow_handler_t handler) +{ + struct irq_chip_generic *gc; + unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); + + gc = devm_kzalloc(dev, sz, GFP_KERNEL); + if (gc) + irq_init_generic_chip(gc, name, num_ct, + irq_base, reg_base, handler); + + return gc; +} +EXPORT_SYMBOL_GPL(devm_irq_alloc_generic_chip); + +struct irq_generic_chip_devres { + struct irq_chip_generic *gc; + u32 msk; + unsigned int clr; + unsigned int set; +}; + +static void devm_irq_remove_generic_chip(struct device *dev, void *res) +{ + struct irq_generic_chip_devres *this = res; + + irq_remove_generic_chip(this->gc, this->msk, this->clr, this->set); +} + +/** + * devm_irq_setup_generic_chip - Setup a range of interrupts with a generic + * chip for a managed device + * + * @dev: Device to setup the generic chip for + * @gc: Generic irq chip holding all data + * @msk: Bitmask holding the irqs to initialize relative to gc->irq_base + * @flags: Flags for initialization + * @clr: IRQ_* bits to clear + * @set: IRQ_* bits to set + * + * Set up max. 32 interrupts starting from gc->irq_base. Note, this + * initializes all interrupts to the primary irq_chip_type and its + * associated handler. + */ +int devm_irq_setup_generic_chip(struct device *dev, struct irq_chip_generic *gc, + u32 msk, enum irq_gc_flags flags, + unsigned int clr, unsigned int set) +{ + struct irq_generic_chip_devres *dr; + + dr = devres_alloc(devm_irq_remove_generic_chip, + sizeof(*dr), GFP_KERNEL); + if (!dr) + return -ENOMEM; + + irq_setup_generic_chip(gc, msk, flags, clr, set); + + dr->gc = gc; + dr->msk = msk; + dr->clr = clr; + dr->set = set; + devres_add(dev, dr); + + return 0; +} +EXPORT_SYMBOL_GPL(devm_irq_setup_generic_chip); +#endif /* CONFIG_GENERIC_IRQ_CHIP */ diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index ee32870079c9..f7086b78ad6e 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -201,10 +201,9 @@ static void irq_writel_be(u32 val, void __iomem *addr) iowrite32be(val, addr); } -static void -irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, - int num_ct, unsigned int irq_base, - void __iomem *reg_base, irq_flow_handler_t handler) +void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, + int num_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler) { raw_spin_lock_init(&gc->lock); gc->num_ct = num_ct; diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index d3f24905852c..79f987b942b8 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -6,7 +6,7 @@ * * This file contains the core interrupt handling code. * - * Detailed information is available in Documentation/DocBook/genericirq + * Detailed information is available in Documentation/core-api/genericirq.rst * */ @@ -138,6 +138,8 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags unsigned int irq = desc->irq_data.irq; struct irqaction *action; + record_irq_time(desc); + for_each_action_of_desc(desc, action) { irqreturn_t res; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index bc226e783bd2..9da14d125df4 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -8,6 +8,7 @@ #include <linux/irqdesc.h> #include <linux/kernel_stat.h> #include <linux/pm_runtime.h> +#include <linux/sched/clock.h> #ifdef CONFIG_SPARSE_IRQ # define IRQ_BITMAP_BITS (NR_IRQS + 8196) @@ -57,6 +58,7 @@ enum { IRQS_WAITING = 0x00000080, IRQS_PENDING = 0x00000200, IRQS_SUSPENDED = 0x00000800, + IRQS_TIMINGS = 0x00001000, }; #include "debug.h" @@ -66,7 +68,14 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned long flags); extern void __disable_irq(struct irq_desc *desc); extern void __enable_irq(struct irq_desc *desc); -extern int irq_startup(struct irq_desc *desc, bool resend); +#define IRQ_RESEND true +#define IRQ_NORESEND false + +#define IRQ_START_FORCE true +#define IRQ_START_COND false + +extern int irq_startup(struct irq_desc *desc, bool resend, bool force); + extern void irq_shutdown(struct irq_desc *desc); extern void irq_enable(struct irq_desc *desc); extern void irq_disable(struct irq_desc *desc); @@ -109,13 +118,19 @@ static inline void unregister_handler_proc(unsigned int irq, extern bool irq_can_set_affinity_usr(unsigned int irq); -extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask); +extern int irq_select_affinity_usr(unsigned int irq); extern void irq_set_thread_affinity(struct irq_desc *desc); extern int irq_do_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force); +#ifdef CONFIG_SMP +extern int irq_setup_affinity(struct irq_desc *desc); +#else +static inline int irq_setup_affinity(struct irq_desc *desc) { return 0; } +#endif + /* Inline functions for support of irq chips on slow busses */ static inline void chip_bus_lock(struct irq_desc *desc) { @@ -169,6 +184,11 @@ irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags) #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) +static inline unsigned int irqd_get(struct irq_data *d) +{ + return __irqd_to_state(d); +} + /* * Manipulation functions for irq_data.state */ @@ -182,6 +202,16 @@ static inline void irqd_clr_move_pending(struct irq_data *d) __irqd_to_state(d) &= ~IRQD_SETAFFINITY_PENDING; } +static inline void irqd_set_managed_shutdown(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_MANAGED_SHUTDOWN; +} + +static inline void irqd_clr_managed_shutdown(struct irq_data *d) +{ + __irqd_to_state(d) &= ~IRQD_MANAGED_SHUTDOWN; +} + static inline void irqd_clear(struct irq_data *d, unsigned int mask) { __irqd_to_state(d) &= ~mask; @@ -226,3 +256,194 @@ irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { } static inline void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { } #endif + +#ifdef CONFIG_IRQ_TIMINGS + +#define IRQ_TIMINGS_SHIFT 5 +#define IRQ_TIMINGS_SIZE (1 << IRQ_TIMINGS_SHIFT) +#define IRQ_TIMINGS_MASK (IRQ_TIMINGS_SIZE - 1) + +/** + * struct irq_timings - irq timings storing structure + * @values: a circular buffer of u64 encoded <timestamp,irq> values + * @count: the number of elements in the array + */ +struct irq_timings { + u64 values[IRQ_TIMINGS_SIZE]; + int count; +}; + +DECLARE_PER_CPU(struct irq_timings, irq_timings); + +extern void irq_timings_free(int irq); +extern int irq_timings_alloc(int irq); + +static inline void irq_remove_timings(struct irq_desc *desc) +{ + desc->istate &= ~IRQS_TIMINGS; + + irq_timings_free(irq_desc_get_irq(desc)); +} + +static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) +{ + int irq = irq_desc_get_irq(desc); + int ret; + + /* + * We don't need the measurement because the idle code already + * knows the next expiry event. + */ + if (act->flags & __IRQF_TIMER) + return; + + /* + * In case the timing allocation fails, we just want to warn, + * not fail, so letting the system boot anyway. + */ + ret = irq_timings_alloc(irq); + if (ret) { + pr_warn("Failed to allocate irq timing stats for irq%d (%d)", + irq, ret); + return; + } + + desc->istate |= IRQS_TIMINGS; +} + +extern void irq_timings_enable(void); +extern void irq_timings_disable(void); + +DECLARE_STATIC_KEY_FALSE(irq_timing_enabled); + +/* + * The interrupt number and the timestamp are encoded into a single + * u64 variable to optimize the size. + * 48 bit time stamp and 16 bit IRQ number is way sufficient. + * Who cares an IRQ after 78 hours of idle time? + */ +static inline u64 irq_timing_encode(u64 timestamp, int irq) +{ + return (timestamp << 16) | irq; +} + +static inline int irq_timing_decode(u64 value, u64 *timestamp) +{ + *timestamp = value >> 16; + return value & U16_MAX; +} + +/* + * The function record_irq_time is only called in one place in the + * interrupts handler. We want this function always inline so the code + * inside is embedded in the function and the static key branching + * code can act at the higher level. Without the explicit + * __always_inline we can end up with a function call and a small + * overhead in the hotpath for nothing. + */ +static __always_inline void record_irq_time(struct irq_desc *desc) +{ + if (!static_branch_likely(&irq_timing_enabled)) + return; + + if (desc->istate & IRQS_TIMINGS) { + struct irq_timings *timings = this_cpu_ptr(&irq_timings); + + timings->values[timings->count & IRQ_TIMINGS_MASK] = + irq_timing_encode(local_clock(), + irq_desc_get_irq(desc)); + + timings->count++; + } +} +#else +static inline void irq_remove_timings(struct irq_desc *desc) {} +static inline void irq_setup_timings(struct irq_desc *desc, + struct irqaction *act) {}; +static inline void record_irq_time(struct irq_desc *desc) {} +#endif /* CONFIG_IRQ_TIMINGS */ + + +#ifdef CONFIG_GENERIC_IRQ_CHIP +void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, + int num_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler); +#else +static inline void +irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, + int num_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler) { } +#endif /* CONFIG_GENERIC_IRQ_CHIP */ + +#ifdef CONFIG_GENERIC_PENDING_IRQ +static inline bool irq_can_move_pcntxt(struct irq_data *data) +{ + return irqd_can_move_in_process_context(data); +} +static inline bool irq_move_pending(struct irq_data *data) +{ + return irqd_is_setaffinity_pending(data); +} +static inline void +irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) +{ + cpumask_copy(desc->pending_mask, mask); +} +static inline void +irq_get_pending(struct cpumask *mask, struct irq_desc *desc) +{ + cpumask_copy(mask, desc->pending_mask); +} +static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) +{ + return desc->pending_mask; +} +bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear); +#else /* CONFIG_GENERIC_PENDING_IRQ */ +static inline bool irq_can_move_pcntxt(struct irq_data *data) +{ + return true; +} +static inline bool irq_move_pending(struct irq_data *data) +{ + return false; +} +static inline void +irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) +{ +} +static inline void +irq_get_pending(struct cpumask *mask, struct irq_desc *desc) +{ +} +static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) +{ + return NULL; +} +static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) +{ + return false; +} +#endif /* !CONFIG_GENERIC_PENDING_IRQ */ + +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +#include <linux/debugfs.h> + +void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); +static inline void irq_remove_debugfs_entry(struct irq_desc *desc) +{ + debugfs_remove(desc->debugfs_file); +} +# ifdef CONFIG_IRQ_DOMAIN +void irq_domain_debugfs_init(struct dentry *root); +# else +static inline void irq_domain_debugfs_init(struct dentry *root); +# endif +#else /* CONFIG_GENERIC_IRQ_DEBUGFS */ +static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) +{ +} +static inline void irq_remove_debugfs_entry(struct irq_desc *d) +{ +} +#endif /* CONFIG_GENERIC_IRQ_DEBUGFS */ diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 00bb0aeea1d0..8bbd06405e60 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -4,7 +4,7 @@ * * This file contains the interrupt descriptor management code * - * Detailed information is available in Documentation/DocBook/genericirq + * Detailed information is available in Documentation/core-api/genericirq.rst * */ #include <linux/irq.h> @@ -54,14 +54,25 @@ static void __init init_irq_default_affinity(void) #endif #ifdef CONFIG_SMP -static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) +static int alloc_masks(struct irq_desc *desc, int node) { if (!zalloc_cpumask_var_node(&desc->irq_common_data.affinity, - gfp, node)) + GFP_KERNEL, node)) return -ENOMEM; +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + if (!zalloc_cpumask_var_node(&desc->irq_common_data.effective_affinity, + GFP_KERNEL, node)) { + free_cpumask_var(desc->irq_common_data.affinity); + return -ENOMEM; + } +#endif + #ifdef CONFIG_GENERIC_PENDING_IRQ - if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) { + if (!zalloc_cpumask_var_node(&desc->pending_mask, GFP_KERNEL, node)) { +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + free_cpumask_var(desc->irq_common_data.effective_affinity); +#endif free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } @@ -86,7 +97,7 @@ static void desc_smp_init(struct irq_desc *desc, int node, #else static inline int -alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; } +alloc_masks(struct irq_desc *desc, int node) { return 0; } static inline void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { } #endif @@ -105,6 +116,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, desc->irq_data.chip_data = NULL; irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); + irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); desc->handle_irq = handle_bad_irq; desc->depth = 1; desc->irq_count = 0; @@ -324,6 +336,9 @@ static void free_masks(struct irq_desc *desc) free_cpumask_var(desc->pending_mask); #endif free_cpumask_var(desc->irq_common_data.affinity); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + free_cpumask_var(desc->irq_common_data.effective_affinity); +#endif } #else static inline void free_masks(struct irq_desc *desc) { } @@ -344,9 +359,8 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, struct module *owner) { struct irq_desc *desc; - gfp_t gfp = GFP_KERNEL; - desc = kzalloc_node(sizeof(*desc), gfp, node); + desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node); if (!desc) return NULL; /* allocate based on nr_cpu_ids */ @@ -354,7 +368,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, if (!desc->kstat_irqs) goto err_desc; - if (alloc_masks(desc, gfp, node)) + if (alloc_masks(desc, node)) goto err_kstat; raw_spin_lock_init(&desc->lock); @@ -394,6 +408,7 @@ static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); + irq_remove_debugfs_entry(desc); unregister_irq_proc(irq, desc); /* @@ -480,7 +495,8 @@ int __init early_irq_init(void) /* Let arch update nr_irqs and return the nr of preallocated irqs */ initcnt = arch_probe_nr_irqs(); - printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt); + printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n", + NR_IRQS, nr_irqs, initcnt); if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS)) nr_irqs = IRQ_BITMAP_BITS; @@ -516,14 +532,14 @@ int __init early_irq_init(void) init_irq_default_affinity(); - printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS); + printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS); desc = irq_desc; count = ARRAY_SIZE(irq_desc); for (i = 0; i < count; i++) { desc[i].kstat_irqs = alloc_percpu(unsigned int); - alloc_masks(&desc[i], GFP_KERNEL, node); + alloc_masks(&desc[i], node); raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); desc_set_defaults(i, &desc[i], node, NULL, NULL); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 31805f237396..14fe862aa2e3 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -26,39 +26,69 @@ static struct irq_domain *irq_default_domain; static void irq_domain_check_hierarchy(struct irq_domain *domain); struct irqchip_fwid { - struct fwnode_handle fwnode; - char *name; + struct fwnode_handle fwnode; + unsigned int type; + char *name; void *data; }; +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +static void debugfs_add_domain_dir(struct irq_domain *d); +static void debugfs_remove_domain_dir(struct irq_domain *d); +#else +static inline void debugfs_add_domain_dir(struct irq_domain *d) { } +static inline void debugfs_remove_domain_dir(struct irq_domain *d) { } +#endif + /** * irq_domain_alloc_fwnode - Allocate a fwnode_handle suitable for * identifying an irq domain - * @data: optional user-provided data + * @type: Type of irqchip_fwnode. See linux/irqdomain.h + * @name: Optional user provided domain name + * @id: Optional user provided id if name != NULL + * @data: Optional user-provided data * - * Allocate a struct device_node, and return a poiner to the embedded + * Allocate a struct irqchip_fwid, and return a poiner to the embedded * fwnode_handle (or NULL on failure). + * + * Note: The types IRQCHIP_FWNODE_NAMED and IRQCHIP_FWNODE_NAMED_ID are + * solely to transport name information to irqdomain creation code. The + * node is not stored. For other types the pointer is kept in the irq + * domain struct. */ -struct fwnode_handle *irq_domain_alloc_fwnode(void *data) +struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, + const char *name, void *data) { struct irqchip_fwid *fwid; - char *name; + char *n; fwid = kzalloc(sizeof(*fwid), GFP_KERNEL); - name = kasprintf(GFP_KERNEL, "irqchip@%p", data); - if (!fwid || !name) { + switch (type) { + case IRQCHIP_FWNODE_NAMED: + n = kasprintf(GFP_KERNEL, "%s", name); + break; + case IRQCHIP_FWNODE_NAMED_ID: + n = kasprintf(GFP_KERNEL, "%s-%d", name, id); + break; + default: + n = kasprintf(GFP_KERNEL, "irqchip@%p", data); + break; + } + + if (!fwid || !n) { kfree(fwid); - kfree(name); + kfree(n); return NULL; } - fwid->name = name; + fwid->type = type; + fwid->name = n; fwid->data = data; fwid->fwnode.type = FWNODE_IRQCHIP; return &fwid->fwnode; } -EXPORT_SYMBOL_GPL(irq_domain_alloc_fwnode); +EXPORT_SYMBOL_GPL(__irq_domain_alloc_fwnode); /** * irq_domain_free_fwnode - Free a non-OF-backed fwnode_handle @@ -97,26 +127,82 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, void *host_data) { struct device_node *of_node = to_of_node(fwnode); + struct irqchip_fwid *fwid; struct irq_domain *domain; + static atomic_t unknown_domains; + domain = kzalloc_node(sizeof(*domain) + (sizeof(unsigned int) * size), GFP_KERNEL, of_node_to_nid(of_node)); if (WARN_ON(!domain)) return NULL; + if (fwnode && is_fwnode_irqchip(fwnode)) { + fwid = container_of(fwnode, struct irqchip_fwid, fwnode); + + switch (fwid->type) { + case IRQCHIP_FWNODE_NAMED: + case IRQCHIP_FWNODE_NAMED_ID: + domain->name = kstrdup(fwid->name, GFP_KERNEL); + if (!domain->name) { + kfree(domain); + return NULL; + } + domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + break; + default: + domain->fwnode = fwnode; + domain->name = fwid->name; + break; + } + } else if (of_node) { + char *name; + + /* + * DT paths contain '/', which debugfs is legitimately + * unhappy about. Replace them with ':', which does + * the trick and is not as offensive as '\'... + */ + name = kstrdup(of_node_full_name(of_node), GFP_KERNEL); + if (!name) { + kfree(domain); + return NULL; + } + + strreplace(name, '/', ':'); + + domain->name = name; + domain->fwnode = fwnode; + domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + } + + if (!domain->name) { + if (fwnode) { + pr_err("Invalid fwnode type (%d) for irqdomain\n", + fwnode->type); + } + domain->name = kasprintf(GFP_KERNEL, "unknown-%d", + atomic_inc_return(&unknown_domains)); + if (!domain->name) { + kfree(domain); + return NULL; + } + domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + } + of_node_get(of_node); /* Fill structure */ INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); domain->ops = ops; domain->host_data = host_data; - domain->fwnode = fwnode; domain->hwirq_max = hwirq_max; domain->revmap_size = size; domain->revmap_direct_max_irq = direct_max; irq_domain_check_hierarchy(domain); mutex_lock(&irq_domain_mutex); + debugfs_add_domain_dir(domain); list_add(&domain->link, &irq_domain_list); mutex_unlock(&irq_domain_mutex); @@ -136,6 +222,7 @@ EXPORT_SYMBOL_GPL(__irq_domain_add); void irq_domain_remove(struct irq_domain *domain) { mutex_lock(&irq_domain_mutex); + debugfs_remove_domain_dir(domain); WARN_ON(!radix_tree_empty(&domain->revmap_tree)); @@ -152,10 +239,43 @@ void irq_domain_remove(struct irq_domain *domain) pr_debug("Removed domain %s\n", domain->name); of_node_put(irq_domain_get_of_node(domain)); + if (domain->flags & IRQ_DOMAIN_NAME_ALLOCATED) + kfree(domain->name); kfree(domain); } EXPORT_SYMBOL_GPL(irq_domain_remove); +void irq_domain_update_bus_token(struct irq_domain *domain, + enum irq_domain_bus_token bus_token) +{ + char *name; + + if (domain->bus_token == bus_token) + return; + + mutex_lock(&irq_domain_mutex); + + domain->bus_token = bus_token; + + name = kasprintf(GFP_KERNEL, "%s-%d", domain->name, bus_token); + if (!name) { + mutex_unlock(&irq_domain_mutex); + return; + } + + debugfs_remove_domain_dir(domain); + + if (domain->flags & IRQ_DOMAIN_NAME_ALLOCATED) + kfree(domain->name); + else + domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + + domain->name = name; + debugfs_add_domain_dir(domain); + + mutex_unlock(&irq_domain_mutex); +} + /** * irq_domain_add_simple() - Register an irq_domain and optionally map a range of irqs * @of_node: pointer to interrupt controller's device tree node. @@ -344,6 +464,7 @@ void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) irq_data->domain = NULL; irq_data->hwirq = 0; + domain->mapcount--; /* Clear reverse map for this hwirq */ if (hwirq < domain->revmap_size) { @@ -395,6 +516,7 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq, domain->name = irq_data->chip->name; } + domain->mapcount++; if (hwirq < domain->revmap_size) { domain->linear_revmap[hwirq] = virq; } else { @@ -746,13 +868,54 @@ unsigned int irq_find_mapping(struct irq_domain *domain, EXPORT_SYMBOL_GPL(irq_find_mapping); #ifdef CONFIG_IRQ_DOMAIN_DEBUG +static void virq_debug_show_one(struct seq_file *m, struct irq_desc *desc) +{ + struct irq_domain *domain; + struct irq_data *data; + + domain = desc->irq_data.domain; + data = &desc->irq_data; + + while (domain) { + unsigned int irq = data->irq; + unsigned long hwirq = data->hwirq; + struct irq_chip *chip; + bool direct; + + if (data == &desc->irq_data) + seq_printf(m, "%5d ", irq); + else + seq_printf(m, "%5d+ ", irq); + seq_printf(m, "0x%05lx ", hwirq); + + chip = irq_data_get_irq_chip(data); + seq_printf(m, "%-15s ", (chip && chip->name) ? chip->name : "none"); + + seq_printf(m, data ? "0x%p " : " %p ", + irq_data_get_irq_chip_data(data)); + + seq_printf(m, " %c ", (desc->action && desc->action->handler) ? '*' : ' '); + direct = (irq == hwirq) && (irq < domain->revmap_direct_max_irq); + seq_printf(m, "%6s%-8s ", + (hwirq < domain->revmap_size) ? "LINEAR" : "RADIX", + direct ? "(DIRECT)" : ""); + seq_printf(m, "%s\n", domain->name); +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + domain = domain->parent; + data = data->parent_data; +#else + domain = NULL; +#endif + } +} + static int virq_debug_show(struct seq_file *m, void *private) { unsigned long flags; struct irq_desc *desc; struct irq_domain *domain; struct radix_tree_iter iter; - void *data, **slot; + void **slot; int i; seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", @@ -760,15 +923,26 @@ static int virq_debug_show(struct seq_file *m, void *private) mutex_lock(&irq_domain_mutex); list_for_each_entry(domain, &irq_domain_list, link) { struct device_node *of_node; + const char *name; + int count = 0; + of_node = irq_domain_get_of_node(domain); + if (of_node) + name = of_node_full_name(of_node); + else if (is_fwnode_irqchip(domain->fwnode)) + name = container_of(domain->fwnode, struct irqchip_fwid, + fwnode)->name; + else + name = ""; + radix_tree_for_each_slot(slot, &domain->revmap_tree, &iter, 0) count++; seq_printf(m, "%c%-16s %6u %10u %10u %s\n", domain == irq_default_domain ? '*' : ' ', domain->name, domain->revmap_size + count, domain->revmap_size, domain->revmap_direct_max_irq, - of_node ? of_node_full_name(of_node) : ""); + name); } mutex_unlock(&irq_domain_mutex); @@ -782,30 +956,7 @@ static int virq_debug_show(struct seq_file *m, void *private) continue; raw_spin_lock_irqsave(&desc->lock, flags); - domain = desc->irq_data.domain; - - if (domain) { - struct irq_chip *chip; - int hwirq = desc->irq_data.hwirq; - bool direct; - - seq_printf(m, "%5d ", i); - seq_printf(m, "0x%05x ", hwirq); - - chip = irq_desc_get_chip(desc); - seq_printf(m, "%-15s ", (chip && chip->name) ? chip->name : "none"); - - data = irq_desc_get_chip_data(desc); - seq_printf(m, data ? "0x%p " : " %p ", data); - - seq_printf(m, " %c ", (desc->action && desc->action->handler) ? '*' : ' '); - direct = (i == hwirq) && (i < domain->revmap_direct_max_irq); - seq_printf(m, "%6s%-8s ", - (hwirq < domain->revmap_size) ? "LINEAR" : "RADIX", - direct ? "(DIRECT)" : ""); - seq_printf(m, "%s\n", desc->irq_data.domain->name); - } - + virq_debug_show_one(m, desc); raw_spin_unlock_irqrestore(&desc->lock, flags); } @@ -973,6 +1124,7 @@ static void irq_domain_insert_irq(int virq) struct irq_domain *domain = data->domain; irq_hw_number_t hwirq = data->hwirq; + domain->mapcount++; if (hwirq < domain->revmap_size) { domain->linear_revmap[hwirq] = virq; } else { @@ -1002,6 +1154,7 @@ static void irq_domain_remove_irq(int virq) struct irq_domain *domain = data->domain; irq_hw_number_t hwirq = data->hwirq; + domain->mapcount--; if (hwirq < domain->revmap_size) { domain->linear_revmap[hwirq] = 0; } else { @@ -1189,43 +1342,18 @@ void irq_domain_free_irqs_top(struct irq_domain *domain, unsigned int virq, irq_domain_free_irqs_common(domain, virq, nr_irqs); } -static bool irq_domain_is_auto_recursive(struct irq_domain *domain) -{ - return domain->flags & IRQ_DOMAIN_FLAG_AUTO_RECURSIVE; -} - -static void irq_domain_free_irqs_recursive(struct irq_domain *domain, +static void irq_domain_free_irqs_hierarchy(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs) { domain->ops->free(domain, irq_base, nr_irqs); - if (irq_domain_is_auto_recursive(domain)) { - BUG_ON(!domain->parent); - irq_domain_free_irqs_recursive(domain->parent, irq_base, - nr_irqs); - } } -int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, +int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs, void *arg) { - int ret = 0; - struct irq_domain *parent = domain->parent; - bool recursive = irq_domain_is_auto_recursive(domain); - - BUG_ON(recursive && !parent); - if (recursive) - ret = irq_domain_alloc_irqs_recursive(parent, irq_base, - nr_irqs, arg); - if (ret < 0) - return ret; - - ret = domain->ops->alloc(domain, irq_base, nr_irqs, arg); - if (ret < 0 && recursive) - irq_domain_free_irqs_recursive(parent, irq_base, nr_irqs); - - return ret; + return domain->ops->alloc(domain, irq_base, nr_irqs, arg); } /** @@ -1286,7 +1414,7 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, } mutex_lock(&irq_domain_mutex); - ret = irq_domain_alloc_irqs_recursive(domain, virq, nr_irqs, arg); + ret = irq_domain_alloc_irqs_hierarchy(domain, virq, nr_irqs, arg); if (ret < 0) { mutex_unlock(&irq_domain_mutex); goto out_free_irq_data; @@ -1321,7 +1449,7 @@ void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs) mutex_lock(&irq_domain_mutex); for (i = 0; i < nr_irqs; i++) irq_domain_remove_irq(virq + i); - irq_domain_free_irqs_recursive(data->domain, virq, nr_irqs); + irq_domain_free_irqs_hierarchy(data->domain, virq, nr_irqs); mutex_unlock(&irq_domain_mutex); irq_domain_free_irq_data(virq, nr_irqs); @@ -1341,15 +1469,11 @@ int irq_domain_alloc_irqs_parent(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs, void *arg) { - /* irq_domain_alloc_irqs_recursive() has called parent's alloc() */ - if (irq_domain_is_auto_recursive(domain)) - return 0; + if (!domain->parent) + return -ENOSYS; - domain = domain->parent; - if (domain) - return irq_domain_alloc_irqs_recursive(domain, irq_base, - nr_irqs, arg); - return -ENOSYS; + return irq_domain_alloc_irqs_hierarchy(domain->parent, irq_base, + nr_irqs, arg); } EXPORT_SYMBOL_GPL(irq_domain_alloc_irqs_parent); @@ -1364,10 +1488,10 @@ EXPORT_SYMBOL_GPL(irq_domain_alloc_irqs_parent); void irq_domain_free_irqs_parent(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs) { - /* irq_domain_free_irqs_recursive() will call parent's free */ - if (!irq_domain_is_auto_recursive(domain) && domain->parent) - irq_domain_free_irqs_recursive(domain->parent, irq_base, - nr_irqs); + if (!domain->parent) + return; + + irq_domain_free_irqs_hierarchy(domain->parent, irq_base, nr_irqs); } EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent); @@ -1487,3 +1611,78 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain) { } #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ + +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +static struct dentry *domain_dir; + +static void +irq_domain_debug_show_one(struct seq_file *m, struct irq_domain *d, int ind) +{ + seq_printf(m, "%*sname: %s\n", ind, "", d->name); + seq_printf(m, "%*ssize: %u\n", ind + 1, "", + d->revmap_size + d->revmap_direct_max_irq); + seq_printf(m, "%*smapped: %u\n", ind + 1, "", d->mapcount); + seq_printf(m, "%*sflags: 0x%08x\n", ind +1 , "", d->flags); +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + if (!d->parent) + return; + seq_printf(m, "%*sparent: %s\n", ind + 1, "", d->parent->name); + irq_domain_debug_show_one(m, d->parent, ind + 4); +#endif +} + +static int irq_domain_debug_show(struct seq_file *m, void *p) +{ + struct irq_domain *d = m->private; + + /* Default domain? Might be NULL */ + if (!d) { + if (!irq_default_domain) + return 0; + d = irq_default_domain; + } + irq_domain_debug_show_one(m, d, 0); + return 0; +} + +static int irq_domain_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_domain_debug_show, inode->i_private); +} + +static const struct file_operations dfs_domain_ops = { + .open = irq_domain_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void debugfs_add_domain_dir(struct irq_domain *d) +{ + if (!d->name || !domain_dir || d->debugfs_file) + return; + d->debugfs_file = debugfs_create_file(d->name, 0444, domain_dir, d, + &dfs_domain_ops); +} + +static void debugfs_remove_domain_dir(struct irq_domain *d) +{ + if (d->debugfs_file) + debugfs_remove(d->debugfs_file); +} + +void __init irq_domain_debugfs_init(struct dentry *root) +{ + struct irq_domain *d; + + domain_dir = debugfs_create_dir("domains", root); + if (!domain_dir) + return; + + debugfs_create_file("default", 0444, domain_dir, NULL, &dfs_domain_ops); + mutex_lock(&irq_domain_mutex); + list_for_each_entry(d, &irq_domain_list, link) + debugfs_add_domain_dir(d); + mutex_unlock(&irq_domain_mutex); +} +#endif diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 070be980c37a..5c11c1730ba5 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -168,34 +168,6 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } -#ifdef CONFIG_GENERIC_PENDING_IRQ -static inline bool irq_can_move_pcntxt(struct irq_data *data) -{ - return irqd_can_move_in_process_context(data); -} -static inline bool irq_move_pending(struct irq_data *data) -{ - return irqd_is_setaffinity_pending(data); -} -static inline void -irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) -{ - cpumask_copy(desc->pending_mask, mask); -} -static inline void -irq_get_pending(struct cpumask *mask, struct irq_desc *desc) -{ - cpumask_copy(mask, desc->pending_mask); -} -#else -static inline bool irq_can_move_pcntxt(struct irq_data *data) { return true; } -static inline bool irq_move_pending(struct irq_data *data) { return false; } -static inline void -irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { } -static inline void -irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } -#endif - int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -345,15 +317,18 @@ EXPORT_SYMBOL_GPL(irq_set_affinity_notifier); /* * Generic version of the affinity autoselector. */ -static int setup_affinity(struct irq_desc *desc, struct cpumask *mask) +int irq_setup_affinity(struct irq_desc *desc) { struct cpumask *set = irq_default_affinity; - int node = irq_desc_get_node(desc); + int ret, node = irq_desc_get_node(desc); + static DEFINE_RAW_SPINLOCK(mask_lock); + static struct cpumask mask; /* Excludes PER_CPU and NO_BALANCE interrupts */ if (!__irq_can_set_affinity(desc)) return 0; + raw_spin_lock(&mask_lock); /* * Preserve the managed affinity setting and a userspace affinity * setup, but make sure that one of the targets is online. @@ -367,46 +342,40 @@ static int setup_affinity(struct irq_desc *desc, struct cpumask *mask) irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET); } - cpumask_and(mask, cpu_online_mask, set); + cpumask_and(&mask, cpu_online_mask, set); if (node != NUMA_NO_NODE) { const struct cpumask *nodemask = cpumask_of_node(node); /* make sure at least one of the cpus in nodemask is online */ - if (cpumask_intersects(mask, nodemask)) - cpumask_and(mask, mask, nodemask); + if (cpumask_intersects(&mask, nodemask)) + cpumask_and(&mask, &mask, nodemask); } - irq_do_set_affinity(&desc->irq_data, mask, false); - return 0; + ret = irq_do_set_affinity(&desc->irq_data, &mask, false); + raw_spin_unlock(&mask_lock); + return ret; } #else /* Wrapper for ALPHA specific affinity selector magic */ -static inline int setup_affinity(struct irq_desc *d, struct cpumask *mask) +int irq_setup_affinity(struct irq_desc *desc) { - return irq_select_affinity(irq_desc_get_irq(d)); + return irq_select_affinity(irq_desc_get_irq(desc)); } #endif /* - * Called when affinity is set via /proc/irq + * Called when a bogus affinity is set via /proc/irq */ -int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask) +int irq_select_affinity_usr(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; int ret; raw_spin_lock_irqsave(&desc->lock, flags); - ret = setup_affinity(desc, mask); + ret = irq_setup_affinity(desc); raw_spin_unlock_irqrestore(&desc->lock, flags); return ret; } - -#else -static inline int -setup_affinity(struct irq_desc *desc, struct cpumask *mask) -{ - return 0; -} #endif /** @@ -533,9 +502,15 @@ void __enable_irq(struct irq_desc *desc) goto err_out; /* Prevent probing on this irq: */ irq_settings_set_noprobe(desc); - irq_enable(desc); - check_irq_resend(desc); - /* fall-through */ + /* + * Call irq_startup() not irq_enable() here because the + * interrupt might be marked NOAUTOEN. So irq_startup() + * needs to be invoked when it gets enabled the first + * time. If it was already started up, then irq_startup() + * will invoke irq_enable() under the hood. + */ + irq_startup(desc, IRQ_RESEND, IRQ_START_COND); + break; } default: desc->depth--; @@ -1122,7 +1097,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) struct irqaction *old, **old_ptr; unsigned long flags, thread_mask = 0; int ret, nested, shared = 0; - cpumask_var_t mask; if (!desc) return -EINVAL; @@ -1181,11 +1155,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } } - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { - ret = -ENOMEM; - goto out_thread; - } - /* * Drivers are often written to work w/o knowledge about the * underlying irq chip implementation, so a request for a @@ -1250,7 +1219,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ if (thread_mask == ~0UL) { ret = -EBUSY; - goto out_mask; + goto out_unlock; } /* * The thread_mask for the action is or'ed to @@ -1294,7 +1263,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n", irq); ret = -EINVAL; - goto out_mask; + goto out_unlock; } if (!shared) { @@ -1302,7 +1271,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (ret) { pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", new->name, irq, desc->irq_data.chip->name); - goto out_mask; + goto out_unlock; } init_waitqueue_head(&desc->wait_for_threads); @@ -1312,8 +1281,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) ret = __irq_set_trigger(desc, new->flags & IRQF_TRIGGER_MASK); - if (ret) - goto out_mask; + if (ret) { + irq_release_resources(desc); + goto out_unlock; + } } desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ @@ -1328,20 +1299,25 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (new->flags & IRQF_ONESHOT) desc->istate |= IRQS_ONESHOT; - if (irq_settings_can_autoenable(desc)) - irq_startup(desc, true); - else - /* Undo nested disables: */ - desc->depth = 1; - /* Exclude IRQ from balancing if requested */ if (new->flags & IRQF_NOBALANCING) { irq_settings_set_no_balancing(desc); irqd_set(&desc->irq_data, IRQD_NO_BALANCING); } - /* Set default affinity mask once everything is setup */ - setup_affinity(desc, mask); + if (irq_settings_can_autoenable(desc)) { + irq_startup(desc, IRQ_RESEND, IRQ_START_COND); + } else { + /* + * Shared interrupts do not go well with disabling + * auto enable. The sharing interrupt might request + * it while it's still disabled and then wait for + * interrupts forever. + */ + WARN_ON_ONCE(new->flags & IRQF_SHARED); + /* Undo nested disables: */ + desc->depth = 1; + } } else if (new->flags & IRQF_TRIGGER_MASK) { unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK; @@ -1372,6 +1348,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) raw_spin_unlock_irqrestore(&desc->lock, flags); + irq_setup_timings(desc, new); + /* * Strictly no need to wake it up, but hung_task complains * when no hard interrupt wakes the thread up. @@ -1382,10 +1360,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) wake_up_process(new->secondary->thread); register_irq_proc(irq, desc); + irq_add_debugfs_entry(irq, desc); new->dir = NULL; register_handler_proc(irq, new); - free_cpumask_var(mask); - return 0; mismatch: @@ -1398,9 +1375,8 @@ mismatch: } ret = -EBUSY; -out_mask: +out_unlock: raw_spin_unlock_irqrestore(&desc->lock, flags); - free_cpumask_var(mask); out_thread: if (new->thread) { @@ -1500,6 +1476,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) irq_settings_clr_disable_unlazy(desc); irq_shutdown(desc); irq_release_resources(desc); + irq_remove_timings(desc); } #ifdef CONFIG_SMP diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 37ddb7bda651..6ca054a3f91d 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -4,6 +4,36 @@ #include "internals.h" +/** + * irq_fixup_move_pending - Cleanup irq move pending from a dying CPU + * @desc: Interrupt descpriptor to clean up + * @force_clear: If set clear the move pending bit unconditionally. + * If not set, clear it only when the dying CPU is the + * last one in the pending mask. + * + * Returns true if the pending bit was set and the pending mask contains an + * online CPU other than the dying CPU. + */ +bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear) +{ + struct irq_data *data = irq_desc_get_irq_data(desc); + + if (!irqd_is_setaffinity_pending(data)) + return false; + + /* + * The outgoing CPU might be the last online target in a pending + * interrupt move. If that's the case clear the pending move bit. + */ + if (cpumask_any_and(desc->pending_mask, cpu_online_mask) >= nr_cpu_ids) { + irqd_clr_move_pending(data); + return false; + } + if (force_clear) + irqd_clr_move_pending(data); + return true; +} + void irq_move_masked_irq(struct irq_data *idata) { struct irq_desc *desc = irq_data_to_desc(idata); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index ddc2f5427f75..48eadf416c24 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -265,13 +265,20 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent) { + struct irq_domain *domain; + if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS) msi_domain_update_dom_ops(info); if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) msi_domain_update_chip_ops(info); - return irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0, - fwnode, &msi_domain_ops, info); + domain = irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0, + fwnode, &msi_domain_ops, info); + + if (domain && !domain->name && info->chip) + domain->name = info->chip->name; + + return domain; } int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, @@ -308,7 +315,7 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, ops->set_desc(arg, desc); /* Assumes the domain mutex is held! */ - ret = irq_domain_alloc_irqs_recursive(domain, virq, 1, arg); + ret = irq_domain_alloc_irqs_hierarchy(domain, virq, 1, arg); if (ret) break; diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index c53edad7b459..7f9642a1e267 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -37,19 +37,47 @@ static struct proc_dir_entry *root_irq_dir; #ifdef CONFIG_SMP -static int show_irq_affinity(int type, struct seq_file *m, void *v) +enum { + AFFINITY, + AFFINITY_LIST, + EFFECTIVE, + EFFECTIVE_LIST, +}; + +static int show_irq_affinity(int type, struct seq_file *m) { struct irq_desc *desc = irq_to_desc((long)m->private); - const struct cpumask *mask = desc->irq_common_data.affinity; + const struct cpumask *mask; + switch (type) { + case AFFINITY: + case AFFINITY_LIST: + mask = desc->irq_common_data.affinity; #ifdef CONFIG_GENERIC_PENDING_IRQ - if (irqd_is_setaffinity_pending(&desc->irq_data)) - mask = desc->pending_mask; + if (irqd_is_setaffinity_pending(&desc->irq_data)) + mask = desc->pending_mask; #endif - if (type) + break; + case EFFECTIVE: + case EFFECTIVE_LIST: +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + mask = desc->irq_common_data.effective_affinity; + break; +#else + return -EINVAL; +#endif + }; + + switch (type) { + case AFFINITY_LIST: + case EFFECTIVE_LIST: seq_printf(m, "%*pbl\n", cpumask_pr_args(mask)); - else + break; + case AFFINITY: + case EFFECTIVE: seq_printf(m, "%*pb\n", cpumask_pr_args(mask)); + break; + } return 0; } @@ -80,12 +108,12 @@ static int irq_affinity_hint_proc_show(struct seq_file *m, void *v) int no_irq_affinity; static int irq_affinity_proc_show(struct seq_file *m, void *v) { - return show_irq_affinity(0, m, v); + return show_irq_affinity(AFFINITY, m); } static int irq_affinity_list_proc_show(struct seq_file *m, void *v) { - return show_irq_affinity(1, m, v); + return show_irq_affinity(AFFINITY_LIST, m); } @@ -120,9 +148,11 @@ static ssize_t write_irq_affinity(int type, struct file *file, * one online CPU still has to be targeted. */ if (!cpumask_intersects(new_value, cpu_online_mask)) { - /* Special case for empty set - allow the architecture - code to set default SMP affinity. */ - err = irq_select_affinity_usr(irq, new_value) ? -EINVAL : count; + /* + * Special case for empty set - allow the architecture code + * to set default SMP affinity. + */ + err = irq_select_affinity_usr(irq) ? -EINVAL : count; } else { irq_set_affinity(irq, new_value); err = count; @@ -183,6 +213,44 @@ static const struct file_operations irq_affinity_list_proc_fops = { .write = irq_affinity_list_proc_write, }; +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK +static int irq_effective_aff_proc_show(struct seq_file *m, void *v) +{ + return show_irq_affinity(EFFECTIVE, m); +} + +static int irq_effective_aff_list_proc_show(struct seq_file *m, void *v) +{ + return show_irq_affinity(EFFECTIVE_LIST, m); +} + +static int irq_effective_aff_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_effective_aff_proc_show, PDE_DATA(inode)); +} + +static int irq_effective_aff_list_proc_open(struct inode *inode, + struct file *file) +{ + return single_open(file, irq_effective_aff_list_proc_show, + PDE_DATA(inode)); +} + +static const struct file_operations irq_effective_aff_proc_fops = { + .open = irq_effective_aff_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations irq_effective_aff_list_proc_fops = { + .open = irq_effective_aff_list_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +#endif + static int default_affinity_show(struct seq_file *m, void *v) { seq_printf(m, "%*pb\n", cpumask_pr_args(irq_default_affinity)); @@ -324,6 +392,7 @@ void register_handler_proc(unsigned int irq, struct irqaction *action) void register_irq_proc(unsigned int irq, struct irq_desc *desc) { static DEFINE_MUTEX(register_lock); + void __maybe_unused *irqp = (void *)(unsigned long) irq; char name [MAX_NAMELEN]; if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip)) @@ -349,20 +418,25 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) #ifdef CONFIG_SMP /* create /proc/irq/<irq>/smp_affinity */ proc_create_data("smp_affinity", 0644, desc->dir, - &irq_affinity_proc_fops, (void *)(long)irq); + &irq_affinity_proc_fops, irqp); /* create /proc/irq/<irq>/affinity_hint */ proc_create_data("affinity_hint", 0444, desc->dir, - &irq_affinity_hint_proc_fops, (void *)(long)irq); + &irq_affinity_hint_proc_fops, irqp); /* create /proc/irq/<irq>/smp_affinity_list */ proc_create_data("smp_affinity_list", 0644, desc->dir, - &irq_affinity_list_proc_fops, (void *)(long)irq); + &irq_affinity_list_proc_fops, irqp); proc_create_data("node", 0444, desc->dir, - &irq_node_proc_fops, (void *)(long)irq); + &irq_node_proc_fops, irqp); +# ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + proc_create_data("effective_affinity", 0444, desc->dir, + &irq_effective_aff_proc_fops, irqp); + proc_create_data("effective_affinity_list", 0444, desc->dir, + &irq_effective_aff_list_proc_fops, irqp); +# endif #endif - proc_create_data("spurious", 0444, desc->dir, &irq_spurious_proc_fops, (void *)(long)irq); @@ -381,6 +455,10 @@ void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) remove_proc_entry("affinity_hint", desc->dir); remove_proc_entry("smp_affinity_list", desc->dir); remove_proc_entry("node", desc->dir); +# ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + remove_proc_entry("effective_affinity", desc->dir); + remove_proc_entry("effective_affinity_list", desc->dir); +# endif #endif remove_proc_entry("spurious", desc->dir); diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c new file mode 100644 index 000000000000..c8c1d073fbf1 --- /dev/null +++ b/kernel/irq/timings.c @@ -0,0 +1,369 @@ +/* + * linux/kernel/irq/timings.c + * + * Copyright (C) 2016, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/slab.h> +#include <linux/static_key.h> +#include <linux/interrupt.h> +#include <linux/idr.h> +#include <linux/irq.h> +#include <linux/math64.h> + +#include <trace/events/irq.h> + +#include "internals.h" + +DEFINE_STATIC_KEY_FALSE(irq_timing_enabled); + +DEFINE_PER_CPU(struct irq_timings, irq_timings); + +struct irqt_stat { + u64 next_evt; + u64 last_ts; + u64 variance; + u32 avg; + u32 nr_samples; + int anomalies; + int valid; +}; + +static DEFINE_IDR(irqt_stats); + +void irq_timings_enable(void) +{ + static_branch_enable(&irq_timing_enabled); +} + +void irq_timings_disable(void) +{ + static_branch_disable(&irq_timing_enabled); +} + +/** + * irqs_update - update the irq timing statistics with a new timestamp + * + * @irqs: an irqt_stat struct pointer + * @ts: the new timestamp + * + * The statistics are computed online, in other words, the code is + * designed to compute the statistics on a stream of values rather + * than doing multiple passes on the values to compute the average, + * then the variance. The integer division introduces a loss of + * precision but with an acceptable error margin regarding the results + * we would have with the double floating precision: we are dealing + * with nanosec, so big numbers, consequently the mantisse is + * negligeable, especially when converting the time in usec + * afterwards. + * + * The computation happens at idle time. When the CPU is not idle, the + * interrupts' timestamps are stored in the circular buffer, when the + * CPU goes idle and this routine is called, all the buffer's values + * are injected in the statistical model continuying to extend the + * statistics from the previous busy-idle cycle. + * + * The observations showed a device will trigger a burst of periodic + * interrupts followed by one or two peaks of longer time, for + * instance when a SD card device flushes its cache, then the periodic + * intervals occur again. A one second inactivity period resets the + * stats, that gives us the certitude the statistical values won't + * exceed 1x10^9, thus the computation won't overflow. + * + * Basically, the purpose of the algorithm is to watch the periodic + * interrupts and eliminate the peaks. + * + * An interrupt is considered periodically stable if the interval of + * its occurences follow the normal distribution, thus the values + * comply with: + * + * avg - 3 x stddev < value < avg + 3 x stddev + * + * Which can be simplified to: + * + * -3 x stddev < value - avg < 3 x stddev + * + * abs(value - avg) < 3 x stddev + * + * In order to save a costly square root computation, we use the + * variance. For the record, stddev = sqrt(variance). The equation + * above becomes: + * + * abs(value - avg) < 3 x sqrt(variance) + * + * And finally we square it: + * + * (value - avg) ^ 2 < (3 x sqrt(variance)) ^ 2 + * + * (value - avg) x (value - avg) < 9 x variance + * + * Statistically speaking, any values out of this interval is + * considered as an anomaly and is discarded. However, a normal + * distribution appears when the number of samples is 30 (it is the + * rule of thumb in statistics, cf. "30 samples" on Internet). When + * there are three consecutive anomalies, the statistics are resetted. + * + */ +static void irqs_update(struct irqt_stat *irqs, u64 ts) +{ + u64 old_ts = irqs->last_ts; + u64 variance = 0; + u64 interval; + s64 diff; + + /* + * The timestamps are absolute time values, we need to compute + * the timing interval between two interrupts. + */ + irqs->last_ts = ts; + + /* + * The interval type is u64 in order to deal with the same + * type in our computation, that prevent mindfuck issues with + * overflow, sign and division. + */ + interval = ts - old_ts; + + /* + * The interrupt triggered more than one second apart, that + * ends the sequence as predictible for our purpose. In this + * case, assume we have the beginning of a sequence and the + * timestamp is the first value. As it is impossible to + * predict anything at this point, return. + * + * Note the first timestamp of the sequence will always fall + * in this test because the old_ts is zero. That is what we + * want as we need another timestamp to compute an interval. + */ + if (interval >= NSEC_PER_SEC) { + memset(irqs, 0, sizeof(*irqs)); + irqs->last_ts = ts; + return; + } + + /* + * Pre-compute the delta with the average as the result is + * used several times in this function. + */ + diff = interval - irqs->avg; + + /* + * Increment the number of samples. + */ + irqs->nr_samples++; + + /* + * Online variance divided by the number of elements if there + * is more than one sample. Normally the formula is division + * by nr_samples - 1 but we assume the number of element will be + * more than 32 and dividing by 32 instead of 31 is enough + * precise. + */ + if (likely(irqs->nr_samples > 1)) + variance = irqs->variance >> IRQ_TIMINGS_SHIFT; + + /* + * The rule of thumb in statistics for the normal distribution + * is having at least 30 samples in order to have the model to + * apply. Values outside the interval are considered as an + * anomaly. + */ + if ((irqs->nr_samples >= 30) && ((diff * diff) > (9 * variance))) { + /* + * After three consecutive anomalies, we reset the + * stats as it is no longer stable enough. + */ + if (irqs->anomalies++ >= 3) { + memset(irqs, 0, sizeof(*irqs)); + irqs->last_ts = ts; + return; + } + } else { + /* + * The anomalies must be consecutives, so at this + * point, we reset the anomalies counter. + */ + irqs->anomalies = 0; + } + + /* + * The interrupt is considered stable enough to try to predict + * the next event on it. + */ + irqs->valid = 1; + + /* + * Online average algorithm: + * + * new_average = average + ((value - average) / count) + * + * The variance computation depends on the new average + * to be computed here first. + * + */ + irqs->avg = irqs->avg + (diff >> IRQ_TIMINGS_SHIFT); + + /* + * Online variance algorithm: + * + * new_variance = variance + (value - average) x (value - new_average) + * + * Warning: irqs->avg is updated with the line above, hence + * 'interval - irqs->avg' is no longer equal to 'diff' + */ + irqs->variance = irqs->variance + (diff * (interval - irqs->avg)); + + /* + * Update the next event + */ + irqs->next_evt = ts + irqs->avg; +} + +/** + * irq_timings_next_event - Return when the next event is supposed to arrive + * + * During the last busy cycle, the number of interrupts is incremented + * and stored in the irq_timings structure. This information is + * necessary to: + * + * - know if the index in the table wrapped up: + * + * If more than the array size interrupts happened during the + * last busy/idle cycle, the index wrapped up and we have to + * begin with the next element in the array which is the last one + * in the sequence, otherwise it is a the index 0. + * + * - have an indication of the interrupts activity on this CPU + * (eg. irq/sec) + * + * The values are 'consumed' after inserting in the statistical model, + * thus the count is reinitialized. + * + * The array of values **must** be browsed in the time direction, the + * timestamp must increase between an element and the next one. + * + * Returns a nanosec time based estimation of the earliest interrupt, + * U64_MAX otherwise. + */ +u64 irq_timings_next_event(u64 now) +{ + struct irq_timings *irqts = this_cpu_ptr(&irq_timings); + struct irqt_stat *irqs; + struct irqt_stat __percpu *s; + u64 ts, next_evt = U64_MAX; + int i, irq = 0; + + /* + * This function must be called with the local irq disabled in + * order to prevent the timings circular buffer to be updated + * while we are reading it. + */ + WARN_ON_ONCE(!irqs_disabled()); + + /* + * Number of elements in the circular buffer: If it happens it + * was flushed before, then the number of elements could be + * smaller than IRQ_TIMINGS_SIZE, so the count is used, + * otherwise the array size is used as we wrapped. The index + * begins from zero when we did not wrap. That could be done + * in a nicer way with the proper circular array structure + * type but with the cost of extra computation in the + * interrupt handler hot path. We choose efficiency. + * + * Inject measured irq/timestamp to the statistical model + * while decrementing the counter because we consume the data + * from our circular buffer. + */ + for (i = irqts->count & IRQ_TIMINGS_MASK, + irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count); + irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) { + + irq = irq_timing_decode(irqts->values[i], &ts); + + s = idr_find(&irqt_stats, irq); + if (s) { + irqs = this_cpu_ptr(s); + irqs_update(irqs, ts); + } + } + + /* + * Look in the list of interrupts' statistics, the earliest + * next event. + */ + idr_for_each_entry(&irqt_stats, s, i) { + + irqs = this_cpu_ptr(s); + + if (!irqs->valid) + continue; + + if (irqs->next_evt <= now) { + irq = i; + next_evt = now; + + /* + * This interrupt mustn't use in the future + * until new events occur and update the + * statistics. + */ + irqs->valid = 0; + break; + } + + if (irqs->next_evt < next_evt) { + irq = i; + next_evt = irqs->next_evt; + } + } + + return next_evt; +} + +void irq_timings_free(int irq) +{ + struct irqt_stat __percpu *s; + + s = idr_find(&irqt_stats, irq); + if (s) { + free_percpu(s); + idr_remove(&irqt_stats, irq); + } +} + +int irq_timings_alloc(int irq) +{ + struct irqt_stat __percpu *s; + int id; + + /* + * Some platforms can have the same private interrupt per cpu, + * so this function may be be called several times with the + * same interrupt number. Just bail out in case the per cpu + * stat structure is already allocated. + */ + s = idr_find(&irqt_stats, irq); + if (s) + return 0; + + s = alloc_percpu(*s); + if (!s) + return -ENOMEM; + + idr_preload(GFP_KERNEL); + id = idr_alloc(&irqt_stats, s, irq, irq + 1, GFP_NOWAIT); + idr_preload_end(); + + if (id < 0) { + free_percpu(s); + return id; + } + + return 0; +} diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 6c9cb208ac48..d11c506a6ac3 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -15,6 +15,7 @@ #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/bug.h> +#include <linux/cpu.h> #ifdef HAVE_JUMP_LABEL @@ -124,6 +125,7 @@ void static_key_slow_inc(struct static_key *key) return; } + cpus_read_lock(); jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); @@ -133,12 +135,14 @@ void static_key_slow_inc(struct static_key *key) atomic_inc(&key->enabled); } jump_label_unlock(); + cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_slow_inc); static void __static_key_slow_dec(struct static_key *key, unsigned long rate_limit, struct delayed_work *work) { + cpus_read_lock(); /* * The negative count check is valid even when a negative * key->enabled is in use by static_key_slow_inc(); a @@ -149,6 +153,7 @@ static void __static_key_slow_dec(struct static_key *key, if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) { WARN(atomic_read(&key->enabled) < 0, "jump label: negative count!\n"); + cpus_read_unlock(); return; } @@ -159,6 +164,7 @@ static void __static_key_slow_dec(struct static_key *key, jump_label_update(key); } jump_label_unlock(); + cpus_read_unlock(); } static void jump_label_update_timeout(struct work_struct *work) @@ -334,6 +340,7 @@ void __init jump_label_init(void) if (static_key_initialized) return; + cpus_read_lock(); jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); @@ -353,6 +360,7 @@ void __init jump_label_init(void) } static_key_initialized = true; jump_label_unlock(); + cpus_read_unlock(); } #ifdef CONFIG_MODULES @@ -590,28 +598,28 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val, struct module *mod = data; int ret = 0; + cpus_read_lock(); + jump_label_lock(); + switch (val) { case MODULE_STATE_COMING: - jump_label_lock(); ret = jump_label_add_module(mod); if (ret) { WARN(1, "Failed to allocatote memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } - jump_label_unlock(); break; case MODULE_STATE_GOING: - jump_label_lock(); jump_label_del_module(mod); - jump_label_unlock(); break; case MODULE_STATE_LIVE: - jump_label_lock(); jump_label_invalidate_module_init(mod); - jump_label_unlock(); break; } + jump_label_unlock(); + cpus_read_unlock(); + return notifier_from_errno(ret); } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index ae1a3ba24df5..154ffb489b93 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -38,6 +38,7 @@ #include <linux/syscore_ops.h> #include <linux/compiler.h> #include <linux/hugetlb.h> +#include <linux/frame.h> #include <asm/page.h> #include <asm/sections.h> @@ -874,7 +875,7 @@ int kexec_load_disabled; * only when panic_cpu holds the current CPU number; this is the only CPU * which processes crash_kexec routines. */ -void __crash_kexec(struct pt_regs *regs) +void __noclone __crash_kexec(struct pt_regs *regs) { /* Take the kexec_mutex here to prevent sys_kexec_load * running on one cpu from replacing the crash kernel @@ -896,6 +897,7 @@ void __crash_kexec(struct pt_regs *regs) mutex_unlock(&kexec_mutex); } } +STACK_FRAME_NON_STANDARD(__crash_kexec); void crash_kexec(struct pt_regs *regs) { diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index b118735fea9d..766e7e4d3ad9 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -162,16 +162,10 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, } if (cmdline_len) { - image->cmdline_buf = kzalloc(cmdline_len, GFP_KERNEL); - if (!image->cmdline_buf) { - ret = -ENOMEM; - goto out; - } - - ret = copy_from_user(image->cmdline_buf, cmdline_ptr, - cmdline_len); - if (ret) { - ret = -EFAULT; + image->cmdline_buf = memdup_user(cmdline_ptr, cmdline_len); + if (IS_ERR(image->cmdline_buf)) { + ret = PTR_ERR(image->cmdline_buf); + image->cmdline_buf = NULL; goto out; } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index adfe3b4cfe05..6756d750b31b 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -483,11 +483,6 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); */ static void do_optimize_kprobes(void) { - /* Optimization never be done when disarmed */ - if (kprobes_all_disarmed || !kprobes_allow_optimization || - list_empty(&optimizing_list)) - return; - /* * The optimization/unoptimization refers online_cpus via * stop_machine() and cpu-hotplug modifies online_cpus. @@ -495,14 +490,19 @@ static void do_optimize_kprobes(void) * This combination can cause a deadlock (cpu-hotplug try to lock * text_mutex but stop_machine can not be done because online_cpus * has been changed) - * To avoid this deadlock, we need to call get_online_cpus() + * To avoid this deadlock, caller must have locked cpu hotplug * for preventing cpu-hotplug outside of text_mutex locking. */ - get_online_cpus(); + lockdep_assert_cpus_held(); + + /* Optimization never be done when disarmed */ + if (kprobes_all_disarmed || !kprobes_allow_optimization || + list_empty(&optimizing_list)) + return; + mutex_lock(&text_mutex); arch_optimize_kprobes(&optimizing_list); mutex_unlock(&text_mutex); - put_online_cpus(); } /* @@ -513,12 +513,13 @@ static void do_unoptimize_kprobes(void) { struct optimized_kprobe *op, *tmp; + /* See comment in do_optimize_kprobes() */ + lockdep_assert_cpus_held(); + /* Unoptimization must be done anytime */ if (list_empty(&unoptimizing_list)) return; - /* Ditto to do_optimize_kprobes */ - get_online_cpus(); mutex_lock(&text_mutex); arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop free_list for disarming */ @@ -537,7 +538,6 @@ static void do_unoptimize_kprobes(void) list_del_init(&op->list); } mutex_unlock(&text_mutex); - put_online_cpus(); } /* Reclaim all kprobes on the free_list */ @@ -562,6 +562,7 @@ static void kick_kprobe_optimizer(void) static void kprobe_optimizer(struct work_struct *work) { mutex_lock(&kprobe_mutex); + cpus_read_lock(); /* Lock modules while optimizing kprobes */ mutex_lock(&module_mutex); @@ -587,6 +588,7 @@ static void kprobe_optimizer(struct work_struct *work) do_free_cleaned_kprobes(); mutex_unlock(&module_mutex); + cpus_read_unlock(); mutex_unlock(&kprobe_mutex); /* Step 5: Kick optimizer again if needed */ @@ -650,9 +652,8 @@ static void optimize_kprobe(struct kprobe *p) /* Short cut to direct unoptimizing */ static void force_unoptimize_kprobe(struct optimized_kprobe *op) { - get_online_cpus(); + lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); - put_online_cpus(); if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); } @@ -791,6 +792,7 @@ static void try_to_optimize_kprobe(struct kprobe *p) return; /* For preparing optimization, jump_label_text_reserved() is called */ + cpus_read_lock(); jump_label_lock(); mutex_lock(&text_mutex); @@ -812,6 +814,7 @@ static void try_to_optimize_kprobe(struct kprobe *p) out: mutex_unlock(&text_mutex); jump_label_unlock(); + cpus_read_unlock(); } #ifdef CONFIG_SYSCTL @@ -826,6 +829,7 @@ static void optimize_all_kprobes(void) if (kprobes_allow_optimization) goto out; + cpus_read_lock(); kprobes_allow_optimization = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; @@ -833,6 +837,7 @@ static void optimize_all_kprobes(void) if (!kprobe_disabled(p)) optimize_kprobe(p); } + cpus_read_unlock(); printk(KERN_INFO "Kprobes globally optimized\n"); out: mutex_unlock(&kprobe_mutex); @@ -851,6 +856,7 @@ static void unoptimize_all_kprobes(void) return; } + cpus_read_lock(); kprobes_allow_optimization = false; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; @@ -859,6 +865,7 @@ static void unoptimize_all_kprobes(void) unoptimize_kprobe(p, false); } } + cpus_read_unlock(); mutex_unlock(&kprobe_mutex); /* Wait for unoptimizing completion */ @@ -1010,14 +1017,11 @@ static void arm_kprobe(struct kprobe *kp) arm_kprobe_ftrace(kp); return; } - /* - * Here, since __arm_kprobe() doesn't use stop_machine(), - * this doesn't cause deadlock on text_mutex. So, we don't - * need get_online_cpus(). - */ + cpus_read_lock(); mutex_lock(&text_mutex); __arm_kprobe(kp); mutex_unlock(&text_mutex); + cpus_read_unlock(); } /* Disarm a kprobe with text_mutex */ @@ -1027,10 +1031,12 @@ static void disarm_kprobe(struct kprobe *kp, bool reopt) disarm_kprobe_ftrace(kp); return; } - /* Ditto */ + + cpus_read_lock(); mutex_lock(&text_mutex); __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); + cpus_read_unlock(); } /* @@ -1298,13 +1304,10 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) int ret = 0; struct kprobe *ap = orig_p; + cpus_read_lock(); + /* For preparing optimization, jump_label_text_reserved() is called */ jump_label_lock(); - /* - * Get online CPUs to avoid text_mutex deadlock.with stop machine, - * which is invoked by unoptimize_kprobe() in add_new_kprobe() - */ - get_online_cpus(); mutex_lock(&text_mutex); if (!kprobe_aggrprobe(orig_p)) { @@ -1352,8 +1355,8 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) out: mutex_unlock(&text_mutex); - put_online_cpus(); jump_label_unlock(); + cpus_read_unlock(); if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { ap->flags &= ~KPROBE_FLAG_DISABLED; @@ -1555,9 +1558,12 @@ int register_kprobe(struct kprobe *p) goto out; } - mutex_lock(&text_mutex); /* Avoiding text modification */ + cpus_read_lock(); + /* Prevent text modification */ + mutex_lock(&text_mutex); ret = prepare_kprobe(p); mutex_unlock(&text_mutex); + cpus_read_unlock(); if (ret) goto out; @@ -1570,7 +1576,6 @@ int register_kprobe(struct kprobe *p) /* Try to optimize kprobe */ try_to_optimize_kprobe(p); - out: mutex_unlock(&kprobe_mutex); diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c index f8269036bf0b..52c4e907c14b 100644 --- a/kernel/livepatch/patch.c +++ b/kernel/livepatch/patch.c @@ -59,7 +59,11 @@ static void notrace klp_ftrace_handler(unsigned long ip, ops = container_of(fops, struct klp_ops, fops); - rcu_read_lock(); + /* + * A variant of synchronize_sched() is used to allow patching functions + * where RCU is not watching, see klp_synchronize_transition(). + */ + preempt_disable_notrace(); func = list_first_or_null_rcu(&ops->func_stack, struct klp_func, stack_node); @@ -115,7 +119,7 @@ static void notrace klp_ftrace_handler(unsigned long ip, klp_arch_set_pc(regs, (unsigned long)func->new_func); unlock: - rcu_read_unlock(); + preempt_enable_notrace(); } /* diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index adc0cc64aa4b..b004a1fb6032 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -49,6 +49,28 @@ static void klp_transition_work_fn(struct work_struct *work) static DECLARE_DELAYED_WORK(klp_transition_work, klp_transition_work_fn); /* + * This function is just a stub to implement a hard force + * of synchronize_sched(). This requires synchronizing + * tasks even in userspace and idle. + */ +static void klp_sync(struct work_struct *work) +{ +} + +/* + * We allow to patch also functions where RCU is not watching, + * e.g. before user_exit(). We can not rely on the RCU infrastructure + * to do the synchronization. Instead hard force the sched synchronization. + * + * This approach allows to use RCU functions for manipulating func_stack + * safely. + */ +static void klp_synchronize_transition(void) +{ + schedule_on_each_cpu(klp_sync); +} + +/* * The transition to the target patch state is complete. Clean up the data * structures. */ @@ -73,7 +95,7 @@ static void klp_complete_transition(void) * func->transition gets cleared, the handler may choose a * removed function. */ - synchronize_rcu(); + klp_synchronize_transition(); } if (klp_transition_patch->immediate) @@ -92,7 +114,7 @@ static void klp_complete_transition(void) /* Prevent klp_ftrace_handler() from seeing KLP_UNDEFINED state */ if (klp_target_state == KLP_PATCHED) - synchronize_rcu(); + klp_synchronize_transition(); read_lock(&tasklist_lock); for_each_process_thread(g, task) { @@ -136,7 +158,11 @@ void klp_cancel_transition(void) */ void klp_update_patch_state(struct task_struct *task) { - rcu_read_lock(); + /* + * A variant of synchronize_sched() is used to allow patching functions + * where RCU is not watching, see klp_synchronize_transition(). + */ + preempt_disable_notrace(); /* * This test_and_clear_tsk_thread_flag() call also serves as a read @@ -153,7 +179,7 @@ void klp_update_patch_state(struct task_struct *task) if (test_and_clear_tsk_thread_flag(task, TIF_PATCH_PENDING)) task->patch_state = READ_ONCE(klp_target_state); - rcu_read_unlock(); + preempt_enable_notrace(); } /* @@ -539,7 +565,7 @@ void klp_reverse_transition(void) clear_tsk_thread_flag(idle_task(cpu), TIF_PATCH_PENDING); /* Let any remaining calls to klp_update_patch_state() complete */ - synchronize_rcu(); + klp_synchronize_transition(); klp_start_transition(); } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index c0e31bfee25c..7d2499bec5fe 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1157,18 +1157,18 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth, if (debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("======================================================\n"); pr_warn("WARNING: possible circular locking dependency detected\n"); print_kernel_ident(); pr_warn("------------------------------------------------------\n"); - printk("%s/%d is trying to acquire lock:\n", + pr_warn("%s/%d is trying to acquire lock:\n", curr->comm, task_pid_nr(curr)); print_lock(check_src); - printk("\nbut task is already holding lock:\n"); + pr_warn("\nbut task is already holding lock:\n"); print_lock(check_tgt); - printk("\nwhich lock already depends on the new lock.\n\n"); - printk("\nthe existing dependency chain (in reverse order) is:\n"); + pr_warn("\nwhich lock already depends on the new lock.\n\n"); + pr_warn("\nthe existing dependency chain (in reverse order) is:\n"); print_circular_bug_entry(entry, depth); @@ -1495,13 +1495,13 @@ print_bad_irq_dependency(struct task_struct *curr, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("=====================================================\n"); pr_warn("WARNING: %s-safe -> %s-unsafe lock order detected\n", irqclass, irqclass); print_kernel_ident(); pr_warn("-----------------------------------------------------\n"); - printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", + pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", curr->comm, task_pid_nr(curr), curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT, curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT, @@ -1509,46 +1509,46 @@ print_bad_irq_dependency(struct task_struct *curr, curr->softirqs_enabled); print_lock(next); - printk("\nand this task is already holding:\n"); + pr_warn("\nand this task is already holding:\n"); print_lock(prev); - printk("which would create a new lock dependency:\n"); + pr_warn("which would create a new lock dependency:\n"); print_lock_name(hlock_class(prev)); - printk(KERN_CONT " ->"); + pr_cont(" ->"); print_lock_name(hlock_class(next)); - printk(KERN_CONT "\n"); + pr_cont("\n"); - printk("\nbut this new dependency connects a %s-irq-safe lock:\n", + pr_warn("\nbut this new dependency connects a %s-irq-safe lock:\n", irqclass); print_lock_name(backwards_entry->class); - printk("\n... which became %s-irq-safe at:\n", irqclass); + pr_warn("\n... which became %s-irq-safe at:\n", irqclass); print_stack_trace(backwards_entry->class->usage_traces + bit1, 1); - printk("\nto a %s-irq-unsafe lock:\n", irqclass); + pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass); print_lock_name(forwards_entry->class); - printk("\n... which became %s-irq-unsafe at:\n", irqclass); - printk("..."); + pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass); + pr_warn("..."); print_stack_trace(forwards_entry->class->usage_traces + bit2, 1); - printk("\nother info that might help us debug this:\n\n"); + pr_warn("\nother info that might help us debug this:\n\n"); print_irq_lock_scenario(backwards_entry, forwards_entry, hlock_class(prev), hlock_class(next)); lockdep_print_held_locks(curr); - printk("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass); + pr_warn("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass); if (!save_trace(&prev_root->trace)) return 0; print_shortest_lock_dependencies(backwards_entry, prev_root); - printk("\nthe dependencies between the lock to be acquired"); - printk(" and %s-irq-unsafe lock:\n", irqclass); + pr_warn("\nthe dependencies between the lock to be acquired"); + pr_warn(" and %s-irq-unsafe lock:\n", irqclass); if (!save_trace(&next_root->trace)) return 0; print_shortest_lock_dependencies(forwards_entry, next_root); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -1724,22 +1724,22 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("============================================\n"); pr_warn("WARNING: possible recursive locking detected\n"); print_kernel_ident(); pr_warn("--------------------------------------------\n"); - printk("%s/%d is trying to acquire lock:\n", + pr_warn("%s/%d is trying to acquire lock:\n", curr->comm, task_pid_nr(curr)); print_lock(next); - printk("\nbut task is already holding lock:\n"); + pr_warn("\nbut task is already holding lock:\n"); print_lock(prev); - printk("\nother info that might help us debug this:\n"); + pr_warn("\nother info that might help us debug this:\n"); print_deadlock_scenario(next, prev); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -2074,21 +2074,21 @@ static void print_collision(struct task_struct *curr, struct held_lock *hlock_next, struct lock_chain *chain) { - printk("\n"); + pr_warn("\n"); pr_warn("============================\n"); pr_warn("WARNING: chain_key collision\n"); print_kernel_ident(); pr_warn("----------------------------\n"); - printk("%s/%d: ", current->comm, task_pid_nr(current)); - printk("Hash chain already cached but the contents don't match!\n"); + pr_warn("%s/%d: ", current->comm, task_pid_nr(current)); + pr_warn("Hash chain already cached but the contents don't match!\n"); - printk("Held locks:"); + pr_warn("Held locks:"); print_chain_keys_held_locks(curr, hlock_next); - printk("Locks in cached chain:"); + pr_warn("Locks in cached chain:"); print_chain_keys_chain(chain); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); } #endif @@ -2373,16 +2373,16 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("================================\n"); pr_warn("WARNING: inconsistent lock state\n"); print_kernel_ident(); pr_warn("--------------------------------\n"); - printk("inconsistent {%s} -> {%s} usage.\n", + pr_warn("inconsistent {%s} -> {%s} usage.\n", usage_str[prev_bit], usage_str[new_bit]); - printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n", + pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n", curr->comm, task_pid_nr(curr), trace_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT, trace_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT, @@ -2390,16 +2390,16 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, trace_softirqs_enabled(curr)); print_lock(this); - printk("{%s} state was registered at:\n", usage_str[prev_bit]); + pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]); print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1); print_irqtrace_events(curr); - printk("\nother info that might help us debug this:\n"); + pr_warn("\nother info that might help us debug this:\n"); print_usage_bug_scenario(this); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -2438,28 +2438,28 @@ print_irq_inversion_bug(struct task_struct *curr, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("========================================================\n"); pr_warn("WARNING: possible irq lock inversion dependency detected\n"); print_kernel_ident(); pr_warn("--------------------------------------------------------\n"); - printk("%s/%d just changed the state of lock:\n", + pr_warn("%s/%d just changed the state of lock:\n", curr->comm, task_pid_nr(curr)); print_lock(this); if (forwards) - printk("but this lock took another, %s-unsafe lock in the past:\n", irqclass); + pr_warn("but this lock took another, %s-unsafe lock in the past:\n", irqclass); else - printk("but this lock was taken by another, %s-safe lock in the past:\n", irqclass); + pr_warn("but this lock was taken by another, %s-safe lock in the past:\n", irqclass); print_lock_name(other->class); - printk("\n\nand interrupts could create inverse lock ordering between them.\n\n"); + pr_warn("\n\nand interrupts could create inverse lock ordering between them.\n\n"); - printk("\nother info that might help us debug this:\n"); + pr_warn("\nother info that might help us debug this:\n"); /* Find a middle lock (if one exists) */ depth = get_lock_depth(other); do { if (depth == 0 && (entry != root)) { - printk("lockdep:%s bad path found in chain graph\n", __func__); + pr_warn("lockdep:%s bad path found in chain graph\n", __func__); break; } middle = entry; @@ -2475,12 +2475,12 @@ print_irq_inversion_bug(struct task_struct *curr, lockdep_print_held_locks(curr); - printk("\nthe shortest dependencies between 2nd lock and 1st lock:\n"); + pr_warn("\nthe shortest dependencies between 2nd lock and 1st lock:\n"); if (!save_trace(&root->trace)) return 0; print_shortest_lock_dependencies(other, root); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -3189,25 +3189,25 @@ print_lock_nested_lock_not_held(struct task_struct *curr, if (debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("==================================\n"); pr_warn("WARNING: Nested lock was not taken\n"); print_kernel_ident(); pr_warn("----------------------------------\n"); - printk("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr)); + pr_warn("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr)); print_lock(hlock); - printk("\nbut this task is not holding:\n"); - printk("%s\n", hlock->nest_lock->name); + pr_warn("\nbut this task is not holding:\n"); + pr_warn("%s\n", hlock->nest_lock->name); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); - printk("\nother info that might help us debug this:\n"); + pr_warn("\nother info that might help us debug this:\n"); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -3402,21 +3402,21 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock, if (debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("=====================================\n"); pr_warn("WARNING: bad unlock balance detected!\n"); print_kernel_ident(); pr_warn("-------------------------------------\n"); - printk("%s/%d is trying to release lock (", + pr_warn("%s/%d is trying to release lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(KERN_CONT ") at:\n"); + pr_cont(") at:\n"); print_ip_sym(ip); - printk("but there are no more locks to release!\n"); - printk("\nother info that might help us debug this:\n"); + pr_warn("but there are no more locks to release!\n"); + pr_warn("\nother info that might help us debug this:\n"); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -3974,21 +3974,21 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, if (debug_locks_silent) return 0; - printk("\n"); + pr_warn("\n"); pr_warn("=================================\n"); pr_warn("WARNING: bad contention detected!\n"); print_kernel_ident(); pr_warn("---------------------------------\n"); - printk("%s/%d is trying to contend lock (", + pr_warn("%s/%d is trying to contend lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(KERN_CONT ") at:\n"); + pr_cont(") at:\n"); print_ip_sym(ip); - printk("but there are no locks held!\n"); - printk("\nother info that might help us debug this:\n"); + pr_warn("but there are no locks held!\n"); + pr_warn("\nother info that might help us debug this:\n"); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); return 0; @@ -4318,17 +4318,17 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, if (debug_locks_silent) return; - printk("\n"); + pr_warn("\n"); pr_warn("=========================\n"); pr_warn("WARNING: held lock freed!\n"); print_kernel_ident(); pr_warn("-------------------------\n"); - printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n", + pr_warn("%s/%d is freeing memory %p-%p, with a lock still held there!\n", curr->comm, task_pid_nr(curr), mem_from, mem_to-1); print_lock(hlock); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); } @@ -4376,14 +4376,14 @@ static void print_held_locks_bug(void) if (debug_locks_silent) return; - printk("\n"); + pr_warn("\n"); pr_warn("====================================\n"); pr_warn("WARNING: %s/%d still has locks held!\n", current->comm, task_pid_nr(current)); print_kernel_ident(); pr_warn("------------------------------------\n"); lockdep_print_held_locks(current); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); } @@ -4402,10 +4402,10 @@ void debug_show_all_locks(void) int unlock = 1; if (unlikely(!debug_locks)) { - printk("INFO: lockdep is turned off.\n"); + pr_warn("INFO: lockdep is turned off.\n"); return; } - printk("\nShowing all locks held in the system:\n"); + pr_warn("\nShowing all locks held in the system:\n"); /* * Here we try to get the tasklist_lock as hard as possible, @@ -4416,18 +4416,18 @@ void debug_show_all_locks(void) retry: if (!read_trylock(&tasklist_lock)) { if (count == 10) - printk("hm, tasklist_lock locked, retrying... "); + pr_warn("hm, tasklist_lock locked, retrying... "); if (count) { count--; - printk(" #%d", 10-count); + pr_cont(" #%d", 10-count); mdelay(200); goto retry; } - printk(" ignoring it.\n"); + pr_cont(" ignoring it.\n"); unlock = 0; } else { if (count != 10) - printk(KERN_CONT " locked it.\n"); + pr_cont(" locked it.\n"); } do_each_thread(g, p) { @@ -4445,7 +4445,7 @@ retry: unlock = 1; } while_each_thread(g, p); - printk("\n"); + pr_warn("\n"); pr_warn("=============================================\n\n"); if (unlock) @@ -4475,12 +4475,12 @@ asmlinkage __visible void lockdep_sys_exit(void) if (unlikely(curr->lockdep_depth)) { if (!debug_locks_off()) return; - printk("\n"); + pr_warn("\n"); pr_warn("================================================\n"); pr_warn("WARNING: lock held when returning to user space!\n"); print_kernel_ident(); pr_warn("------------------------------------------------\n"); - printk("%s/%d is leaving the kernel with locks still held!\n", + pr_warn("%s/%d is leaving the kernel with locks still held!\n", curr->comm, curr->pid); lockdep_print_held_locks(curr); } @@ -4490,19 +4490,15 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) { struct task_struct *curr = current; -#ifndef CONFIG_PROVE_RCU_REPEATEDLY - if (!debug_locks_off()) - return; -#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */ /* Note: the following can be executed concurrently, so be careful. */ - printk("\n"); + pr_warn("\n"); pr_warn("=============================\n"); pr_warn("WARNING: suspicious RCU usage\n"); print_kernel_ident(); pr_warn("-----------------------------\n"); - printk("%s:%d %s!\n", file, line, s); - printk("\nother info that might help us debug this:\n\n"); - printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n", + pr_warn("%s:%d %s!\n", file, line, s); + pr_warn("\nother info that might help us debug this:\n\n"); + pr_warn("\n%srcu_scheduler_active = %d, debug_locks = %d\n", !rcu_lockdep_current_cpu_online() ? "RCU used illegally from offline CPU!\n" : !rcu_is_watching() @@ -4529,10 +4525,10 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) * rcu_read_lock_bh() and so on from extended quiescent states. */ if (!rcu_is_watching()) - printk("RCU used illegally from extended quiescent state!\n"); + pr_warn("RCU used illegally from extended quiescent state!\n"); lockdep_print_held_locks(curr); - printk("\nstack backtrace:\n"); + pr_warn("\nstack backtrace:\n"); dump_stack(); } EXPORT_SYMBOL_GPL(lockdep_rcu_suspicious); diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 198527a62149..858a07590e39 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -227,9 +227,9 @@ static void __sched __mutex_lock_slowpath(struct mutex *lock); * (or statically defined) before it can be locked. memset()-ing * the mutex to 0 is not allowed. * - * ( The CONFIG_DEBUG_MUTEXES .config option turns on debugging - * checks that will enforce the restrictions and will also do - * deadlock debugging. ) + * (The CONFIG_DEBUG_MUTEXES .config option turns on debugging + * checks that will enforce the restrictions and will also do + * deadlock debugging) * * This function is similar to (but not equivalent to) down(). */ diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c index 58e366ad36f4..ac35e648b0e5 100644 --- a/kernel/locking/rtmutex-debug.c +++ b/kernel/locking/rtmutex-debug.c @@ -166,12 +166,16 @@ void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) memset(waiter, 0x22, sizeof(*waiter)); } -void debug_rt_mutex_init(struct rt_mutex *lock, const char *name) +void debug_rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key) { /* * Make sure we are not reinitializing a held lock: */ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); lock->name = name; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif } diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h index b585af9a1b50..5078c6ddf4a5 100644 --- a/kernel/locking/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h @@ -11,7 +11,7 @@ extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter); -extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name); +extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void debug_rt_mutex_lock(struct rt_mutex *lock); extern void debug_rt_mutex_unlock(struct rt_mutex *lock); extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock, diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 28cd09e635ed..78069895032a 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1481,6 +1481,7 @@ void __sched rt_mutex_lock(struct rt_mutex *lock) { might_sleep(); + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); } EXPORT_SYMBOL_GPL(rt_mutex_lock); @@ -1496,9 +1497,16 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock); */ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) { + int ret; + might_sleep(); - return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + + return ret; } EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); @@ -1526,11 +1534,18 @@ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) int rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) { + int ret; + might_sleep(); - return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, RT_MUTEX_MIN_CHAINWALK, rt_mutex_slowlock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + + return ret; } EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); @@ -1547,10 +1562,16 @@ EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); */ int __sched rt_mutex_trylock(struct rt_mutex *lock) { + int ret; + if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) return 0; - return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); + ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; } EXPORT_SYMBOL_GPL(rt_mutex_trylock); @@ -1561,6 +1582,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock); */ void __sched rt_mutex_unlock(struct rt_mutex *lock) { + mutex_release(&lock->dep_map, 1, _RET_IP_); rt_mutex_fastunlock(lock, rt_mutex_slowunlock); } EXPORT_SYMBOL_GPL(rt_mutex_unlock); @@ -1620,7 +1642,6 @@ void rt_mutex_destroy(struct rt_mutex *lock) lock->magic = NULL; #endif } - EXPORT_SYMBOL_GPL(rt_mutex_destroy); /** @@ -1632,14 +1653,16 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy); * * Initializing of a locked rt lock is not allowed */ -void __rt_mutex_init(struct rt_mutex *lock, const char *name) +void __rt_mutex_init(struct rt_mutex *lock, const char *name, + struct lock_class_key *key) { lock->owner = NULL; raw_spin_lock_init(&lock->wait_lock); lock->waiters = RB_ROOT; lock->waiters_leftmost = NULL; - debug_rt_mutex_init(lock, name); + if (name && key) + debug_rt_mutex_init(lock, name, key); } EXPORT_SYMBOL_GPL(__rt_mutex_init); @@ -1660,7 +1683,7 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init); void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner) { - __rt_mutex_init(lock, NULL); + __rt_mutex_init(lock, NULL, NULL); debug_rt_mutex_proxy_lock(lock, proxy_owner); rt_mutex_set_owner(lock, proxy_owner); } diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h index 6607802efa8b..5c253caffe91 100644 --- a/kernel/locking/rtmutex.h +++ b/kernel/locking/rtmutex.h @@ -17,7 +17,7 @@ #define debug_rt_mutex_proxy_lock(l,p) do { } while (0) #define debug_rt_mutex_proxy_unlock(l) do { } while (0) #define debug_rt_mutex_unlock(l) do { } while (0) -#define debug_rt_mutex_init(m, n) do { } while (0) +#define debug_rt_mutex_init(m, n, k) do { } while (0) #define debug_rt_mutex_deadlock(d, a ,l) do { } while (0) #define debug_rt_mutex_print_deadlock(w) do { } while (0) #define debug_rt_mutex_reset_waiter(w) do { } while (0) diff --git a/kernel/module.c b/kernel/module.c index df1c4a9e7abb..1d958c6d5c24 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1202,10 +1202,7 @@ static ssize_t store_uevent(struct module_attribute *mattr, struct module_kobject *mk, const char *buffer, size_t count) { - enum kobject_action action; - - if (kobject_action_type(buffer, count, &action) == 0) - kobject_uevent(&mk->kobj, action); + kobject_synth_uevent(&mk->kobj, buffer, count); return count; } diff --git a/kernel/padata.c b/kernel/padata.c index ac8f1e524836..868f947166d7 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -934,29 +934,18 @@ static struct kobj_type padata_attr_type = { }; /** - * padata_alloc_possible - Allocate and initialize padata instance. - * Use the cpu_possible_mask for serial and - * parallel workers. - * - * @wq: workqueue to use for the allocated padata instance - */ -struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq) -{ - return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask); -} -EXPORT_SYMBOL(padata_alloc_possible); - -/** * padata_alloc - allocate and initialize a padata instance and specify * cpumasks for serial and parallel workers. * * @wq: workqueue to use for the allocated padata instance * @pcpumask: cpumask that will be used for padata parallelization * @cbcpumask: cpumask that will be used for padata serialization + * + * Must be called from a cpus_read_lock() protected region */ -struct padata_instance *padata_alloc(struct workqueue_struct *wq, - const struct cpumask *pcpumask, - const struct cpumask *cbcpumask) +static struct padata_instance *padata_alloc(struct workqueue_struct *wq, + const struct cpumask *pcpumask, + const struct cpumask *cbcpumask) { struct padata_instance *pinst; struct parallel_data *pd = NULL; @@ -965,7 +954,6 @@ struct padata_instance *padata_alloc(struct workqueue_struct *wq, if (!pinst) goto err; - get_online_cpus(); if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL)) goto err_free_inst; if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) { @@ -989,14 +977,12 @@ struct padata_instance *padata_alloc(struct workqueue_struct *wq, pinst->flags = 0; - put_online_cpus(); - BLOCKING_INIT_NOTIFIER_HEAD(&pinst->cpumask_change_notifier); kobject_init(&pinst->kobj, &padata_attr_type); mutex_init(&pinst->lock); #ifdef CONFIG_HOTPLUG_CPU - cpuhp_state_add_instance_nocalls(hp_online, &pinst->node); + cpuhp_state_add_instance_nocalls_cpuslocked(hp_online, &pinst->node); #endif return pinst; @@ -1005,12 +991,27 @@ err_free_masks: free_cpumask_var(pinst->cpumask.cbcpu); err_free_inst: kfree(pinst); - put_online_cpus(); err: return NULL; } /** + * padata_alloc_possible - Allocate and initialize padata instance. + * Use the cpu_possible_mask for serial and + * parallel workers. + * + * @wq: workqueue to use for the allocated padata instance + * + * Must be called from a cpus_read_lock() protected region + */ +struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq) +{ + lockdep_assert_cpus_held(); + return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask); +} +EXPORT_SYMBOL(padata_alloc_possible); + +/** * padata_free - free a padata instance * * @padata_inst: padata instance to free diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a8b978c35a6a..e1914c7b85b1 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -1108,7 +1108,7 @@ static struct attribute * g[] = { }; -static struct attribute_group attr_group = { +static const struct attribute_group attr_group = { .attrs = g, }; diff --git a/kernel/power/process.c b/kernel/power/process.c index c7209f060eeb..78672d324a6e 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -132,7 +132,7 @@ int freeze_processes(void) if (!pm_freezing) atomic_inc(&system_freezing_cnt); - pm_wakeup_clear(); + pm_wakeup_clear(true); pr_info("Freezing user space processes ... "); pm_freezing = true; error = try_to_freeze_tasks(true); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index fa46606f3356..b7708e319941 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -36,13 +36,13 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/io.h> -#ifdef CONFIG_STRICT_KERNEL_RWX +#ifdef CONFIG_ARCH_HAS_SET_MEMORY #include <asm/set_memory.h> #endif #include "power.h" -#ifdef CONFIG_STRICT_KERNEL_RWX +#if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_ARCH_HAS_SET_MEMORY) static bool hibernate_restore_protection; static bool hibernate_restore_protection_active; @@ -77,7 +77,7 @@ static inline void hibernate_restore_protection_begin(void) {} static inline void hibernate_restore_protection_end(void) {} static inline void hibernate_restore_protect_page(void *page_address) {} static inline void hibernate_restore_unprotect_page(void *page_address) {} -#endif /* CONFIG_STRICT_KERNEL_RWX */ +#endif /* CONFIG_STRICT_KERNEL_RWX && CONFIG_ARCH_HAS_SET_MEMORY */ static int swsusp_page_is_free(struct page *); static void swsusp_set_page_forbidden(struct page *); @@ -1929,8 +1929,7 @@ static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm, * also be located in the high memory, because of the way in which * copy_data_pages() works. */ -static int swsusp_alloc(struct memory_bitmap *orig_bm, - struct memory_bitmap *copy_bm, +static int swsusp_alloc(struct memory_bitmap *copy_bm, unsigned int nr_pages, unsigned int nr_highmem) { if (nr_highmem > 0) { @@ -1976,7 +1975,7 @@ asmlinkage __visible int swsusp_save(void) return -ENOMEM; } - if (swsusp_alloc(&orig_bm, ©_bm, nr_pages, nr_highmem)) { + if (swsusp_alloc(©_bm, nr_pages, nr_highmem)) { printk(KERN_ERR "PM: Memory allocation failed\n"); return -ENOMEM; } diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 15e6baef5c73..3ecf275d7e44 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -72,6 +72,8 @@ static void freeze_begin(void) static void freeze_enter(void) { + trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, true); + spin_lock_irq(&suspend_freeze_lock); if (pm_wakeup_pending()) goto out; @@ -84,11 +86,9 @@ static void freeze_enter(void) /* Push all the CPUs into the idle loop. */ wake_up_all_idle_cpus(); - pr_debug("PM: suspend-to-idle\n"); /* Make the current CPU wait so it can enter the idle loop too. */ wait_event(suspend_freeze_wait_head, suspend_freeze_state == FREEZE_STATE_WAKE); - pr_debug("PM: resume from suspend-to-idle\n"); cpuidle_pause(); put_online_cpus(); @@ -98,6 +98,31 @@ static void freeze_enter(void) out: suspend_freeze_state = FREEZE_STATE_NONE; spin_unlock_irq(&suspend_freeze_lock); + + trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, false); +} + +static void s2idle_loop(void) +{ + pr_debug("PM: suspend-to-idle\n"); + + do { + freeze_enter(); + + if (freeze_ops && freeze_ops->wake) + freeze_ops->wake(); + + dpm_resume_noirq(PMSG_RESUME); + if (freeze_ops && freeze_ops->sync) + freeze_ops->sync(); + + if (pm_wakeup_pending()) + break; + + pm_wakeup_clear(false); + } while (!dpm_suspend_noirq(PMSG_SUSPEND)); + + pr_debug("PM: resume from suspend-to-idle\n"); } void freeze_wake(void) @@ -371,10 +396,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) * all the devices are suspended. */ if (state == PM_SUSPEND_FREEZE) { - trace_suspend_resume(TPS("machine_suspend"), state, true); - freeze_enter(); - trace_suspend_resume(TPS("machine_suspend"), state, false); - goto Platform_wake; + s2idle_loop(); + goto Platform_early_resume; } error = disable_nonboot_cpus(); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index f80fd33639e0..57d22571f306 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -225,14 +225,14 @@ static struct block_device *hib_resume_bdev; struct hib_bio_batch { atomic_t count; wait_queue_head_t wait; - int error; + blk_status_t error; }; static void hib_init_batch(struct hib_bio_batch *hb) { atomic_set(&hb->count, 0); init_waitqueue_head(&hb->wait); - hb->error = 0; + hb->error = BLK_STS_OK; } static void hib_end_io(struct bio *bio) @@ -240,7 +240,7 @@ static void hib_end_io(struct bio *bio) struct hib_bio_batch *hb = bio->bi_private; struct page *page = bio->bi_io_vec[0].bv_page; - if (bio->bi_error) { + if (bio->bi_status) { printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n", imajor(bio->bi_bdev->bd_inode), iminor(bio->bi_bdev->bd_inode), @@ -253,8 +253,8 @@ static void hib_end_io(struct bio *bio) flush_icache_range((unsigned long)page_address(page), (unsigned long)page_address(page) + PAGE_SIZE); - if (bio->bi_error && !hb->error) - hb->error = bio->bi_error; + if (bio->bi_status && !hb->error) + hb->error = bio->bi_status; if (atomic_dec_and_test(&hb->count)) wake_up(&hb->wait); @@ -293,10 +293,10 @@ static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr, return error; } -static int hib_wait_io(struct hib_bio_batch *hb) +static blk_status_t hib_wait_io(struct hib_bio_batch *hb) { wait_event(hb->wait, atomic_read(&hb->count) == 0); - return hb->error; + return blk_status_to_errno(hb->error); } /* diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 1db044f808b7..2a7d04049af4 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -18,12 +18,14 @@ #ifdef CONFIG_PRINTK -#define PRINTK_SAFE_CONTEXT_MASK 0x7fffffff -#define PRINTK_NMI_CONTEXT_MASK 0x80000000 +#define PRINTK_SAFE_CONTEXT_MASK 0x3fffffff +#define PRINTK_NMI_DEFERRED_CONTEXT_MASK 0x40000000 +#define PRINTK_NMI_CONTEXT_MASK 0x80000000 extern raw_spinlock_t logbuf_lock; __printf(1, 0) int vprintk_default(const char *fmt, va_list args); +__printf(1, 0) int vprintk_deferred(const char *fmt, va_list args); __printf(1, 0) int vprintk_func(const char *fmt, va_list args); void __printk_safe_enter(void); void __printk_safe_exit(void); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a1db38abac5b..fc47863f629c 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1175,7 +1175,7 @@ static void boot_delay_msec(int level) unsigned long long k; unsigned long timeout; - if ((boot_delay == 0 || system_state != SYSTEM_BOOTING) + if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress_message_printing(level)) { return; } @@ -2720,16 +2720,13 @@ void wake_up_klogd(void) preempt_enable(); } -int printk_deferred(const char *fmt, ...) +int vprintk_deferred(const char *fmt, va_list args) { - va_list args; int r; - preempt_disable(); - va_start(args, fmt); r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args); - va_end(args); + preempt_disable(); __this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); preempt_enable(); @@ -2737,6 +2734,18 @@ int printk_deferred(const char *fmt, ...) return r; } +int printk_deferred(const char *fmt, ...) +{ + va_list args; + int r; + + va_start(args, fmt); + r = vprintk_deferred(fmt, args); + va_end(args); + + return r; +} + /* * printk rate limiting, lifted from the networking subsystem. * diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 033e50a7d706..3cdaeaef9ce1 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -80,8 +80,8 @@ static void queue_flush_work(struct printk_safe_seq_buf *s) * happen, printk_safe_log_store() will notice the buffer->len mismatch * and repeat the write. */ -static int printk_safe_log_store(struct printk_safe_seq_buf *s, - const char *fmt, va_list args) +static __printf(2, 0) int printk_safe_log_store(struct printk_safe_seq_buf *s, + const char *fmt, va_list args) { int add; size_t len; @@ -299,7 +299,7 @@ void printk_safe_flush_on_panic(void) * one writer running. But the buffer might get flushed from another * CPU, so we need to be careful. */ -static int vprintk_nmi(const char *fmt, va_list args) +static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) { struct printk_safe_seq_buf *s = this_cpu_ptr(&nmi_print_seq); @@ -308,17 +308,29 @@ static int vprintk_nmi(const char *fmt, va_list args) void printk_nmi_enter(void) { - this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK); + /* + * The size of the extra per-CPU buffer is limited. Use it only when + * the main one is locked. If this CPU is not in the safe context, + * the lock must be taken on another CPU and we could wait for it. + */ + if ((this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) && + raw_spin_is_locked(&logbuf_lock)) { + this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK); + } else { + this_cpu_or(printk_context, PRINTK_NMI_DEFERRED_CONTEXT_MASK); + } } void printk_nmi_exit(void) { - this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK); + this_cpu_and(printk_context, + ~(PRINTK_NMI_CONTEXT_MASK | + PRINTK_NMI_DEFERRED_CONTEXT_MASK)); } #else -static int vprintk_nmi(const char *fmt, va_list args) +static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) { return 0; } @@ -330,7 +342,7 @@ static int vprintk_nmi(const char *fmt, va_list args) * into itself. It uses a per-CPU buffer to store the message, just like * NMI. */ -static int vprintk_safe(const char *fmt, va_list args) +static __printf(1, 0) int vprintk_safe(const char *fmt, va_list args) { struct printk_safe_seq_buf *s = this_cpu_ptr(&safe_print_seq); @@ -351,12 +363,22 @@ void __printk_safe_exit(void) __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { + /* Use extra buffer in NMI when logbuf_lock is taken or in safe mode. */ if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK) return vprintk_nmi(fmt, args); + /* Use extra buffer to prevent a recursion deadlock in safe mode. */ if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) return vprintk_safe(fmt, args); + /* + * Use the main logbuf when logbuf_lock is available in NMI. + * But avoid calling console drivers that might have their own locks. + */ + if (this_cpu_read(printk_context) & PRINTK_NMI_DEFERRED_CONTEXT_MASK) + return vprintk_deferred(fmt, args); + + /* No obstacles. */ return vprintk_default(fmt, args); } diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig new file mode 100644 index 000000000000..be90c945063f --- /dev/null +++ b/kernel/rcu/Kconfig @@ -0,0 +1,242 @@ +# +# RCU-related configuration options +# + +menu "RCU Subsystem" + +config TREE_RCU + bool + default y if !PREEMPT && SMP + help + This option selects the RCU implementation that is + designed for very large SMP system with hundreds or + thousands of CPUs. It also scales down nicely to + smaller systems. + +config PREEMPT_RCU + bool + default y if PREEMPT + help + This option selects the RCU implementation that is + designed for very large SMP systems with hundreds or + thousands of CPUs, but for which real-time response + is also required. It also scales down nicely to + smaller systems. + + Select this option if you are unsure. + +config TINY_RCU + bool + default y if !PREEMPT && !SMP + help + This option selects the RCU implementation that is + designed for UP systems from which real-time response + is not required. This option greatly reduces the + memory footprint of RCU. + +config RCU_EXPERT + bool "Make expert-level adjustments to RCU configuration" + default n + help + This option needs to be enabled if you wish to make + expert-level adjustments to RCU configuration. By default, + no such adjustments can be made, which has the often-beneficial + side-effect of preventing "make oldconfig" from asking you all + sorts of detailed questions about how you would like numerous + obscure RCU options to be set up. + + Say Y if you need to make expert-level adjustments to RCU. + + Say N if you are unsure. + +config SRCU + bool + help + This option selects the sleepable version of RCU. This version + permits arbitrary sleeping or blocking within RCU read-side critical + sections. + +config TINY_SRCU + bool + default y if SRCU && TINY_RCU + help + This option selects the single-CPU non-preemptible version of SRCU. + +config TREE_SRCU + bool + default y if SRCU && !TINY_RCU + help + This option selects the full-fledged version of SRCU. + +config TASKS_RCU + bool + default n + select SRCU + help + This option enables a task-based RCU implementation that uses + only voluntary context switch (not preemption!), idle, and + user-mode execution as quiescent states. + +config RCU_STALL_COMMON + def_bool ( TREE_RCU || PREEMPT_RCU ) + help + This option enables RCU CPU stall code that is common between + the TINY and TREE variants of RCU. The purpose is to allow + the tiny variants to disable RCU CPU stall warnings, while + making these warnings mandatory for the tree variants. + +config RCU_NEED_SEGCBLIST + def_bool ( TREE_RCU || PREEMPT_RCU || TREE_SRCU ) + +config CONTEXT_TRACKING + bool + +config CONTEXT_TRACKING_FORCE + bool "Force context tracking" + depends on CONTEXT_TRACKING + default y if !NO_HZ_FULL + help + The major pre-requirement for full dynticks to work is to + support the context tracking subsystem. But there are also + other dependencies to provide in order to make the full + dynticks working. + + This option stands for testing when an arch implements the + context tracking backend but doesn't yet fullfill all the + requirements to make the full dynticks feature working. + Without the full dynticks, there is no way to test the support + for context tracking and the subsystems that rely on it: RCU + userspace extended quiescent state and tickless cputime + accounting. This option copes with the absence of the full + dynticks subsystem by forcing the context tracking on all + CPUs in the system. + + Say Y only if you're working on the development of an + architecture backend for the context tracking. + + Say N otherwise, this option brings an overhead that you + don't want in production. + + +config RCU_FANOUT + int "Tree-based hierarchical RCU fanout value" + range 2 64 if 64BIT + range 2 32 if !64BIT + depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT + default 64 if 64BIT + default 32 if !64BIT + help + This option controls the fanout of hierarchical implementations + of RCU, allowing RCU to work efficiently on machines with + large numbers of CPUs. This value must be at least the fourth + root of NR_CPUS, which allows NR_CPUS to be insanely large. + The default value of RCU_FANOUT should be used for production + systems, but if you are stress-testing the RCU implementation + itself, small RCU_FANOUT values allow you to test large-system + code paths on small(er) systems. + + Select a specific number if testing RCU itself. + Take the default if unsure. + +config RCU_FANOUT_LEAF + int "Tree-based hierarchical RCU leaf-level fanout value" + range 2 64 if 64BIT + range 2 32 if !64BIT + depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT + default 16 + help + This option controls the leaf-level fanout of hierarchical + implementations of RCU, and allows trading off cache misses + against lock contention. Systems that synchronize their + scheduling-clock interrupts for energy-efficiency reasons will + want the default because the smaller leaf-level fanout keeps + lock contention levels acceptably low. Very large systems + (hundreds or thousands of CPUs) will instead want to set this + value to the maximum value possible in order to reduce the + number of cache misses incurred during RCU's grace-period + initialization. These systems tend to run CPU-bound, and thus + are not helped by synchronized interrupts, and thus tend to + skew them, which reduces lock contention enough that large + leaf-level fanouts work well. That said, setting leaf-level + fanout to a large number will likely cause problematic + lock contention on the leaf-level rcu_node structures unless + you boot with the skew_tick kernel parameter. + + Select a specific number if testing RCU itself. + + Select the maximum permissible value for large systems, but + please understand that you may also need to set the skew_tick + kernel boot parameter to avoid contention on the rcu_node + structure's locks. + + Take the default if unsure. + +config RCU_FAST_NO_HZ + bool "Accelerate last non-dyntick-idle CPU's grace periods" + depends on NO_HZ_COMMON && SMP && RCU_EXPERT + default n + help + This option permits CPUs to enter dynticks-idle state even if + they have RCU callbacks queued, and prevents RCU from waking + these CPUs up more than roughly once every four jiffies (by + default, you can adjust this using the rcutree.rcu_idle_gp_delay + parameter), thus improving energy efficiency. On the other + hand, this option increases the duration of RCU grace periods, + for example, slowing down synchronize_rcu(). + + Say Y if energy efficiency is critically important, and you + don't care about increased grace-period durations. + + Say N if you are unsure. + +config RCU_BOOST + bool "Enable RCU priority boosting" + depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT + default n + help + This option boosts the priority of preempted RCU readers that + block the current preemptible RCU grace period for too long. + This option also prevents heavy loads from blocking RCU + callback invocation for all flavors of RCU. + + Say Y here if you are working with real-time apps or heavy loads + Say N here if you are unsure. + +config RCU_BOOST_DELAY + int "Milliseconds to delay boosting after RCU grace-period start" + range 0 3000 + depends on RCU_BOOST + default 500 + help + This option specifies the time to wait after the beginning of + a given grace period before priority-boosting preempted RCU + readers blocking that grace period. Note that any RCU reader + blocking an expedited RCU grace period is boosted immediately. + + Accept the default if unsure. + +config RCU_NOCB_CPU + bool "Offload RCU callback processing from boot-selected CPUs" + depends on TREE_RCU || PREEMPT_RCU + depends on RCU_EXPERT || NO_HZ_FULL + default n + help + Use this option to reduce OS jitter for aggressive HPC or + real-time workloads. It can also be used to offload RCU + callback invocation to energy-efficient CPUs in battery-powered + asymmetric multiprocessors. + + This option offloads callback invocation from the set of + CPUs specified at boot time by the rcu_nocbs parameter. + For each such CPU, a kthread ("rcuox/N") will be created to + invoke callbacks, where the "N" is the CPU being offloaded, + and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and + "s" for RCU-sched. Nothing prevents this kthread from running + on the specified CPUs, but (1) the kthreads may be preempted + between each callback, and (2) affinity or cgroups can be used + to force the kthreads to run on whatever set of CPUs is desired. + + Say Y here if you want to help to debug reduced OS jitter. + Say N here if you are unsure. + +endmenu # "RCU Subsystem" diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug new file mode 100644 index 000000000000..0ec7d1d33a14 --- /dev/null +++ b/kernel/rcu/Kconfig.debug @@ -0,0 +1,82 @@ +# +# RCU-related debugging configuration options +# + +menu "RCU Debugging" + +config PROVE_RCU + def_bool PROVE_LOCKING + +config TORTURE_TEST + tristate + default n + +config RCU_PERF_TEST + tristate "performance tests for RCU" + depends on DEBUG_KERNEL + select TORTURE_TEST + select SRCU + select TASKS_RCU + default n + help + This option provides a kernel module that runs performance + tests on the RCU infrastructure. The kernel module may be built + after the fact on the running kernel to be tested, if desired. + + Say Y here if you want RCU performance tests to be built into + the kernel. + Say M if you want the RCU performance tests to build as a module. + Say N if you are unsure. + +config RCU_TORTURE_TEST + tristate "torture tests for RCU" + depends on DEBUG_KERNEL + select TORTURE_TEST + select SRCU + select TASKS_RCU + default n + help + This option provides a kernel module that runs torture tests + on the RCU infrastructure. The kernel module may be built + after the fact on the running kernel to be tested, if desired. + + Say Y here if you want RCU torture tests to be built into + the kernel. + Say M if you want the RCU torture tests to build as a module. + Say N if you are unsure. + +config RCU_CPU_STALL_TIMEOUT + int "RCU CPU stall timeout in seconds" + depends on RCU_STALL_COMMON + range 3 300 + default 21 + help + If a given RCU grace period extends more than the specified + number of seconds, a CPU stall warning is printed. If the + RCU grace period persists, additional CPU stall warnings are + printed at more widely spaced intervals. + +config RCU_TRACE + bool "Enable tracing for RCU" + depends on DEBUG_KERNEL + default y if TREE_RCU + select TRACE_CLOCK + help + This option enables additional tracepoints for ftrace-style + event tracing. + + Say Y here if you want to enable RCU tracing + Say N if you are unsure. + +config RCU_EQS_DEBUG + bool "Provide debugging asserts for adding NO_HZ support to an arch" + depends on DEBUG_KERNEL + help + This option provides consistency checks in RCU's handling of + NO_HZ. These checks have proven quite helpful in detecting + bugs in arch-specific NO_HZ code. + + Say N here if you need ultimate kernel/user switch latencies + Say Y if you are unsure + +endmenu # "RCU Debugging" diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 23803c7d5180..13c0fc852767 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -3,13 +3,11 @@ KCOV_INSTRUMENT := n obj-y += update.o sync.o -obj-$(CONFIG_CLASSIC_SRCU) += srcu.o obj-$(CONFIG_TREE_SRCU) += srcutree.o obj-$(CONFIG_TINY_SRCU) += srcutiny.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o obj-$(CONFIG_TREE_RCU) += tree.o obj-$(CONFIG_PREEMPT_RCU) += tree.o -obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o obj-$(CONFIG_TINY_RCU) += tiny.o obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 73e16ec4054b..808b8c85f626 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -212,6 +212,18 @@ int rcu_jiffies_till_stall_check(void); */ #define TPS(x) tracepoint_string(x) +/* + * Dump the ftrace buffer, but only one time per callsite per boot. + */ +#define rcu_ftrace_dump(oops_dump_mode) \ +do { \ + static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \ + \ + if (!atomic_read(&___rfd_beenhere) && \ + !atomic_xchg(&___rfd_beenhere, 1)) \ + ftrace_dump(oops_dump_mode); \ +} while (0) + void rcu_early_boot_tests(void); void rcu_test_sync_prims(void); @@ -291,6 +303,271 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt) cpu <= rnp->grphi; \ cpu = cpumask_next((cpu), cpu_possible_mask)) +/* + * Wrappers for the rcu_node::lock acquire and release. + * + * Because the rcu_nodes form a tree, the tree traversal locking will observe + * different lock values, this in turn means that an UNLOCK of one level + * followed by a LOCK of another level does not imply a full memory barrier; + * and most importantly transitivity is lost. + * + * In order to restore full ordering between tree levels, augment the regular + * lock acquire functions with smp_mb__after_unlock_lock(). + * + * As ->lock of struct rcu_node is a __private field, therefore one should use + * these wrappers rather than directly call raw_spin_{lock,unlock}* on ->lock. + */ +#define raw_spin_lock_rcu_node(p) \ +do { \ + raw_spin_lock(&ACCESS_PRIVATE(p, lock)); \ + smp_mb__after_unlock_lock(); \ +} while (0) + +#define raw_spin_unlock_rcu_node(p) raw_spin_unlock(&ACCESS_PRIVATE(p, lock)) + +#define raw_spin_lock_irq_rcu_node(p) \ +do { \ + raw_spin_lock_irq(&ACCESS_PRIVATE(p, lock)); \ + smp_mb__after_unlock_lock(); \ +} while (0) + +#define raw_spin_unlock_irq_rcu_node(p) \ + raw_spin_unlock_irq(&ACCESS_PRIVATE(p, lock)) + +#define raw_spin_lock_irqsave_rcu_node(p, flags) \ +do { \ + raw_spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ + smp_mb__after_unlock_lock(); \ +} while (0) + +#define raw_spin_unlock_irqrestore_rcu_node(p, flags) \ + raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags) \ + +#define raw_spin_trylock_rcu_node(p) \ +({ \ + bool ___locked = raw_spin_trylock(&ACCESS_PRIVATE(p, lock)); \ + \ + if (___locked) \ + smp_mb__after_unlock_lock(); \ + ___locked; \ +}) + #endif /* #if defined(SRCU) || !defined(TINY_RCU) */ +#ifdef CONFIG_TINY_RCU +/* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ +static inline bool rcu_gp_is_normal(void) /* Internal RCU use. */ +{ + return true; +} +static inline bool rcu_gp_is_expedited(void) /* Internal RCU use. */ +{ + return false; +} + +static inline void rcu_expedite_gp(void) +{ +} + +static inline void rcu_unexpedite_gp(void) +{ +} +#else /* #ifdef CONFIG_TINY_RCU */ +bool rcu_gp_is_normal(void); /* Internal RCU use. */ +bool rcu_gp_is_expedited(void); /* Internal RCU use. */ +void rcu_expedite_gp(void); +void rcu_unexpedite_gp(void); +void rcupdate_announce_bootup_oddness(void); +#endif /* #else #ifdef CONFIG_TINY_RCU */ + +#define RCU_SCHEDULER_INACTIVE 0 +#define RCU_SCHEDULER_INIT 1 +#define RCU_SCHEDULER_RUNNING 2 + +#ifdef CONFIG_TINY_RCU +static inline void rcu_request_urgent_qs_task(struct task_struct *t) { } +#else /* #ifdef CONFIG_TINY_RCU */ +void rcu_request_urgent_qs_task(struct task_struct *t); +#endif /* #else #ifdef CONFIG_TINY_RCU */ + +enum rcutorture_type { + RCU_FLAVOR, + RCU_BH_FLAVOR, + RCU_SCHED_FLAVOR, + RCU_TASKS_FLAVOR, + SRCU_FLAVOR, + INVALID_RCU_FLAVOR +}; + +#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) +void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, + unsigned long *gpnum, unsigned long *completed); +void rcutorture_record_test_transition(void); +void rcutorture_record_progress(unsigned long vernum); +void do_trace_rcu_torture_read(const char *rcutorturename, + struct rcu_head *rhp, + unsigned long secs, + unsigned long c_old, + unsigned long c); +#else +static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, + int *flags, + unsigned long *gpnum, + unsigned long *completed) +{ + *flags = 0; + *gpnum = 0; + *completed = 0; +} +static inline void rcutorture_record_test_transition(void) +{ +} +static inline void rcutorture_record_progress(unsigned long vernum) +{ +} +#ifdef CONFIG_RCU_TRACE +void do_trace_rcu_torture_read(const char *rcutorturename, + struct rcu_head *rhp, + unsigned long secs, + unsigned long c_old, + unsigned long c); +#else +#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ + do { } while (0) +#endif +#endif + +#ifdef CONFIG_TINY_SRCU + +static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, + struct srcu_struct *sp, int *flags, + unsigned long *gpnum, + unsigned long *completed) +{ + if (test_type != SRCU_FLAVOR) + return; + *flags = 0; + *completed = sp->srcu_idx; + *gpnum = *completed; +} + +#elif defined(CONFIG_TREE_SRCU) + +void srcutorture_get_gp_data(enum rcutorture_type test_type, + struct srcu_struct *sp, int *flags, + unsigned long *gpnum, unsigned long *completed); + +#endif + +#ifdef CONFIG_TINY_RCU + +/* + * Return the number of grace periods started. + */ +static inline unsigned long rcu_batches_started(void) +{ + return 0; +} + +/* + * Return the number of bottom-half grace periods started. + */ +static inline unsigned long rcu_batches_started_bh(void) +{ + return 0; +} + +/* + * Return the number of sched grace periods started. + */ +static inline unsigned long rcu_batches_started_sched(void) +{ + return 0; +} + +/* + * Return the number of grace periods completed. + */ +static inline unsigned long rcu_batches_completed(void) +{ + return 0; +} + +/* + * Return the number of bottom-half grace periods completed. + */ +static inline unsigned long rcu_batches_completed_bh(void) +{ + return 0; +} + +/* + * Return the number of sched grace periods completed. + */ +static inline unsigned long rcu_batches_completed_sched(void) +{ + return 0; +} + +/* + * Return the number of expedited grace periods completed. + */ +static inline unsigned long rcu_exp_batches_completed(void) +{ + return 0; +} + +/* + * Return the number of expedited sched grace periods completed. + */ +static inline unsigned long rcu_exp_batches_completed_sched(void) +{ + return 0; +} + +static inline unsigned long srcu_batches_completed(struct srcu_struct *sp) +{ + return 0; +} + +static inline void rcu_force_quiescent_state(void) +{ +} + +static inline void rcu_bh_force_quiescent_state(void) +{ +} + +static inline void rcu_sched_force_quiescent_state(void) +{ +} + +static inline void show_rcu_gp_kthreads(void) +{ +} + +#else /* #ifdef CONFIG_TINY_RCU */ +extern unsigned long rcutorture_testseq; +extern unsigned long rcutorture_vernum; +unsigned long rcu_batches_started(void); +unsigned long rcu_batches_started_bh(void); +unsigned long rcu_batches_started_sched(void); +unsigned long rcu_batches_completed(void); +unsigned long rcu_batches_completed_bh(void); +unsigned long rcu_batches_completed_sched(void); +unsigned long rcu_exp_batches_completed(void); +unsigned long rcu_exp_batches_completed_sched(void); +unsigned long srcu_batches_completed(struct srcu_struct *sp); +void show_rcu_gp_kthreads(void); +void rcu_force_quiescent_state(void); +void rcu_bh_force_quiescent_state(void); +void rcu_sched_force_quiescent_state(void); +#endif /* #else #ifdef CONFIG_TINY_RCU */ + +#ifdef CONFIG_RCU_NOCB_CPU +bool rcu_is_nocb_cpu(int cpu); +#else +static inline bool rcu_is_nocb_cpu(int cpu) { return false; } +#endif + #endif /* __LINUX_RCU_H */ diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index a4a86fb47e4a..3cc18110b612 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -48,6 +48,8 @@ #include <linux/torture.h> #include <linux/vmalloc.h> +#include "rcu.h" + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>"); @@ -59,12 +61,16 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>"); #define VERBOSE_PERFOUT_ERRSTRING(s) \ do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0) +torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives"); +torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader"); torture_param(bool, gp_exp, false, "Use expedited GP wait primitives"); torture_param(int, holdoff, 10, "Holdoff time before test start (s)"); -torture_param(int, nreaders, -1, "Number of RCU reader threads"); +torture_param(int, nreaders, 0, "Number of RCU reader threads"); torture_param(int, nwriters, -1, "Number of RCU updater threads"); -torture_param(bool, shutdown, false, "Shutdown at end of performance tests."); +torture_param(bool, shutdown, !IS_ENABLED(MODULE), + "Shutdown at end of performance tests."); torture_param(bool, verbose, true, "Enable verbose debugging printk()s"); +torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); static char *perf_type = "rcu"; module_param(perf_type, charp, 0444); @@ -86,13 +92,16 @@ static u64 t_rcu_perf_writer_started; static u64 t_rcu_perf_writer_finished; static unsigned long b_rcu_perf_writer_started; static unsigned long b_rcu_perf_writer_finished; +static DEFINE_PER_CPU(atomic_t, n_async_inflight); static int rcu_perf_writer_state; #define RTWS_INIT 0 -#define RTWS_EXP_SYNC 1 -#define RTWS_SYNC 2 -#define RTWS_IDLE 2 -#define RTWS_STOPPING 3 +#define RTWS_ASYNC 1 +#define RTWS_BARRIER 2 +#define RTWS_EXP_SYNC 3 +#define RTWS_SYNC 4 +#define RTWS_IDLE 5 +#define RTWS_STOPPING 6 #define MAX_MEAS 10000 #define MIN_MEAS 100 @@ -114,6 +123,8 @@ struct rcu_perf_ops { unsigned long (*started)(void); unsigned long (*completed)(void); unsigned long (*exp_completed)(void); + void (*async)(struct rcu_head *head, rcu_callback_t func); + void (*gp_barrier)(void); void (*sync)(void); void (*exp_sync)(void); const char *name; @@ -153,6 +164,8 @@ static struct rcu_perf_ops rcu_ops = { .started = rcu_batches_started, .completed = rcu_batches_completed, .exp_completed = rcu_exp_batches_completed, + .async = call_rcu, + .gp_barrier = rcu_barrier, .sync = synchronize_rcu, .exp_sync = synchronize_rcu_expedited, .name = "rcu" @@ -181,6 +194,8 @@ static struct rcu_perf_ops rcu_bh_ops = { .started = rcu_batches_started_bh, .completed = rcu_batches_completed_bh, .exp_completed = rcu_exp_batches_completed_sched, + .async = call_rcu_bh, + .gp_barrier = rcu_barrier_bh, .sync = synchronize_rcu_bh, .exp_sync = synchronize_rcu_bh_expedited, .name = "rcu_bh" @@ -208,6 +223,16 @@ static unsigned long srcu_perf_completed(void) return srcu_batches_completed(srcu_ctlp); } +static void srcu_call_rcu(struct rcu_head *head, rcu_callback_t func) +{ + call_srcu(srcu_ctlp, head, func); +} + +static void srcu_rcu_barrier(void) +{ + srcu_barrier(srcu_ctlp); +} + static void srcu_perf_synchronize(void) { synchronize_srcu(srcu_ctlp); @@ -226,11 +251,42 @@ static struct rcu_perf_ops srcu_ops = { .started = NULL, .completed = srcu_perf_completed, .exp_completed = srcu_perf_completed, + .async = srcu_call_rcu, + .gp_barrier = srcu_rcu_barrier, .sync = srcu_perf_synchronize, .exp_sync = srcu_perf_synchronize_expedited, .name = "srcu" }; +static struct srcu_struct srcud; + +static void srcu_sync_perf_init(void) +{ + srcu_ctlp = &srcud; + init_srcu_struct(srcu_ctlp); +} + +static void srcu_sync_perf_cleanup(void) +{ + cleanup_srcu_struct(srcu_ctlp); +} + +static struct rcu_perf_ops srcud_ops = { + .ptype = SRCU_FLAVOR, + .init = srcu_sync_perf_init, + .cleanup = srcu_sync_perf_cleanup, + .readlock = srcu_perf_read_lock, + .readunlock = srcu_perf_read_unlock, + .started = NULL, + .completed = srcu_perf_completed, + .exp_completed = srcu_perf_completed, + .async = srcu_call_rcu, + .gp_barrier = srcu_rcu_barrier, + .sync = srcu_perf_synchronize, + .exp_sync = srcu_perf_synchronize_expedited, + .name = "srcud" +}; + /* * Definitions for sched perf testing. */ @@ -254,6 +310,8 @@ static struct rcu_perf_ops sched_ops = { .started = rcu_batches_started_sched, .completed = rcu_batches_completed_sched, .exp_completed = rcu_exp_batches_completed_sched, + .async = call_rcu_sched, + .gp_barrier = rcu_barrier_sched, .sync = synchronize_sched, .exp_sync = synchronize_sched_expedited, .name = "sched" @@ -281,6 +339,8 @@ static struct rcu_perf_ops tasks_ops = { .readunlock = tasks_perf_read_unlock, .started = rcu_no_completed, .completed = rcu_no_completed, + .async = call_rcu_tasks, + .gp_barrier = rcu_barrier_tasks, .sync = synchronize_rcu_tasks, .exp_sync = synchronize_rcu_tasks, .name = "tasks" @@ -344,6 +404,15 @@ rcu_perf_reader(void *arg) } /* + * Callback function for asynchronous grace periods from rcu_perf_writer(). + */ +static void rcu_perf_async_cb(struct rcu_head *rhp) +{ + atomic_dec(this_cpu_ptr(&n_async_inflight)); + kfree(rhp); +} + +/* * RCU perf writer kthread. Repeatedly does a grace period. */ static int @@ -352,6 +421,7 @@ rcu_perf_writer(void *arg) int i = 0; int i_max; long me = (long)arg; + struct rcu_head *rhp = NULL; struct sched_param sp; bool started = false, done = false, alldone = false; u64 t; @@ -380,9 +450,27 @@ rcu_perf_writer(void *arg) } do { + if (writer_holdoff) + udelay(writer_holdoff); wdp = &wdpp[i]; *wdp = ktime_get_mono_fast_ns(); - if (gp_exp) { + if (gp_async) { +retry: + if (!rhp) + rhp = kmalloc(sizeof(*rhp), GFP_KERNEL); + if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) { + rcu_perf_writer_state = RTWS_ASYNC; + atomic_inc(this_cpu_ptr(&n_async_inflight)); + cur_ops->async(rhp, rcu_perf_async_cb); + rhp = NULL; + } else if (!kthread_should_stop()) { + rcu_perf_writer_state = RTWS_BARRIER; + cur_ops->gp_barrier(); + goto retry; + } else { + kfree(rhp); /* Because we are stopping. */ + } + } else if (gp_exp) { rcu_perf_writer_state = RTWS_EXP_SYNC; cur_ops->exp_sync(); } else { @@ -429,6 +517,10 @@ rcu_perf_writer(void *arg) i++; rcu_perf_wait_shutdown(); } while (!torture_must_stop()); + if (gp_async) { + rcu_perf_writer_state = RTWS_BARRIER; + cur_ops->gp_barrier(); + } rcu_perf_writer_state = RTWS_STOPPING; writer_n_durations[me] = i_max; torture_kthread_stopping("rcu_perf_writer"); @@ -452,6 +544,17 @@ rcu_perf_cleanup(void) u64 *wdp; u64 *wdpp; + /* + * Would like warning at start, but everything is expedited + * during the mid-boot phase, so have to wait till the end. + */ + if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp) + VERBOSE_PERFOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); + if (rcu_gp_is_normal() && gp_exp) + VERBOSE_PERFOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); + if (gp_exp && gp_async) + VERBOSE_PERFOUT_ERRSTRING("No expedited async GPs, so went with async!"); + if (torture_cleanup_begin()) return; @@ -554,7 +657,7 @@ rcu_perf_init(void) long i; int firsterr = 0; static struct rcu_perf_ops *perf_ops[] = { - &rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops, + &rcu_ops, &rcu_bh_ops, &srcu_ops, &srcud_ops, &sched_ops, RCUPERF_TASKS_OPS }; @@ -624,16 +727,6 @@ rcu_perf_init(void) firsterr = -ENOMEM; goto unwind; } - if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp) { - VERBOSE_PERFOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); - firsterr = -EINVAL; - goto unwind; - } - if (rcu_gp_is_normal() && gp_exp) { - VERBOSE_PERFOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); - firsterr = -EINVAL; - goto unwind; - } for (i = 0; i < nrealwriters; i++) { writer_durations[i] = kcalloc(MAX_MEAS, sizeof(*writer_durations[i]), diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index ae6e574d4cf5..b8f7f8ce8575 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -52,6 +52,8 @@ #include <linux/torture.h> #include <linux/vmalloc.h> +#include "rcu.h" + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>"); @@ -562,31 +564,19 @@ static void srcu_torture_stats(void) int __maybe_unused cpu; int idx; -#if defined(CONFIG_TREE_SRCU) || defined(CONFIG_CLASSIC_SRCU) #ifdef CONFIG_TREE_SRCU idx = srcu_ctlp->srcu_idx & 0x1; -#else /* #ifdef CONFIG_TREE_SRCU */ - idx = srcu_ctlp->completed & 0x1; -#endif /* #else #ifdef CONFIG_TREE_SRCU */ pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", torture_type, TORTURE_FLAG, idx); for_each_possible_cpu(cpu) { unsigned long l0, l1; unsigned long u0, u1; long c0, c1; -#ifdef CONFIG_TREE_SRCU struct srcu_data *counts; counts = per_cpu_ptr(srcu_ctlp->sda, cpu); u0 = counts->srcu_unlock_count[!idx]; u1 = counts->srcu_unlock_count[idx]; -#else /* #ifdef CONFIG_TREE_SRCU */ - struct srcu_array *counts; - - counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu); - u0 = counts->unlock_count[!idx]; - u1 = counts->unlock_count[idx]; -#endif /* #else #ifdef CONFIG_TREE_SRCU */ /* * Make sure that a lock is always counted if the corresponding @@ -594,13 +584,8 @@ static void srcu_torture_stats(void) */ smp_rmb(); -#ifdef CONFIG_TREE_SRCU l0 = counts->srcu_lock_count[!idx]; l1 = counts->srcu_lock_count[idx]; -#else /* #ifdef CONFIG_TREE_SRCU */ - l0 = counts->lock_count[!idx]; - l1 = counts->lock_count[idx]; -#endif /* #else #ifdef CONFIG_TREE_SRCU */ c0 = l0 - u0; c1 = l1 - u1; @@ -609,7 +594,7 @@ static void srcu_torture_stats(void) pr_cont("\n"); #elif defined(CONFIG_TINY_SRCU) idx = READ_ONCE(srcu_ctlp->srcu_idx) & 0x1; - pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%d,%d)\n", + pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n", torture_type, TORTURE_FLAG, idx, READ_ONCE(srcu_ctlp->srcu_lock_nesting[!idx]), READ_ONCE(srcu_ctlp->srcu_lock_nesting[idx])); diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c deleted file mode 100644 index dea03614263f..000000000000 --- a/kernel/rcu/srcu.c +++ /dev/null @@ -1,661 +0,0 @@ -/* - * Sleepable Read-Copy Update mechanism for mutual exclusion. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, you can access it online at - * http://www.gnu.org/licenses/gpl-2.0.html. - * - * Copyright (C) IBM Corporation, 2006 - * Copyright (C) Fujitsu, 2012 - * - * Author: Paul McKenney <paulmck@us.ibm.com> - * Lai Jiangshan <laijs@cn.fujitsu.com> - * - * For detailed explanation of Read-Copy Update mechanism see - - * Documentation/RCU/ *.txt - * - */ - -#include <linux/export.h> -#include <linux/mutex.h> -#include <linux/percpu.h> -#include <linux/preempt.h> -#include <linux/rcupdate_wait.h> -#include <linux/sched.h> -#include <linux/smp.h> -#include <linux/delay.h> -#include <linux/srcu.h> - -#include "rcu.h" - -/* - * Initialize an rcu_batch structure to empty. - */ -static inline void rcu_batch_init(struct rcu_batch *b) -{ - b->head = NULL; - b->tail = &b->head; -} - -/* - * Enqueue a callback onto the tail of the specified rcu_batch structure. - */ -static inline void rcu_batch_queue(struct rcu_batch *b, struct rcu_head *head) -{ - *b->tail = head; - b->tail = &head->next; -} - -/* - * Is the specified rcu_batch structure empty? - */ -static inline bool rcu_batch_empty(struct rcu_batch *b) -{ - return b->tail == &b->head; -} - -/* - * Remove the callback at the head of the specified rcu_batch structure - * and return a pointer to it, or return NULL if the structure is empty. - */ -static inline struct rcu_head *rcu_batch_dequeue(struct rcu_batch *b) -{ - struct rcu_head *head; - - if (rcu_batch_empty(b)) - return NULL; - - head = b->head; - b->head = head->next; - if (b->tail == &head->next) - rcu_batch_init(b); - - return head; -} - -/* - * Move all callbacks from the rcu_batch structure specified by "from" to - * the structure specified by "to". - */ -static inline void rcu_batch_move(struct rcu_batch *to, struct rcu_batch *from) -{ - if (!rcu_batch_empty(from)) { - *to->tail = from->head; - to->tail = from->tail; - rcu_batch_init(from); - } -} - -static int init_srcu_struct_fields(struct srcu_struct *sp) -{ - sp->completed = 0; - spin_lock_init(&sp->queue_lock); - sp->running = false; - rcu_batch_init(&sp->batch_queue); - rcu_batch_init(&sp->batch_check0); - rcu_batch_init(&sp->batch_check1); - rcu_batch_init(&sp->batch_done); - INIT_DELAYED_WORK(&sp->work, process_srcu); - sp->per_cpu_ref = alloc_percpu(struct srcu_array); - return sp->per_cpu_ref ? 0 : -ENOMEM; -} - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - -int __init_srcu_struct(struct srcu_struct *sp, const char *name, - struct lock_class_key *key) -{ - /* Don't re-initialize a lock while it is held. */ - debug_check_no_locks_freed((void *)sp, sizeof(*sp)); - lockdep_init_map(&sp->dep_map, name, key, 0); - return init_srcu_struct_fields(sp); -} -EXPORT_SYMBOL_GPL(__init_srcu_struct); - -#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - -/** - * init_srcu_struct - initialize a sleep-RCU structure - * @sp: structure to initialize. - * - * Must invoke this on a given srcu_struct before passing that srcu_struct - * to any other function. Each srcu_struct represents a separate domain - * of SRCU protection. - */ -int init_srcu_struct(struct srcu_struct *sp) -{ - return init_srcu_struct_fields(sp); -} -EXPORT_SYMBOL_GPL(init_srcu_struct); - -#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - -/* - * Returns approximate total of the readers' ->lock_count[] values for the - * rank of per-CPU counters specified by idx. - */ -static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx) -{ - int cpu; - unsigned long sum = 0; - - for_each_possible_cpu(cpu) { - struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu); - - sum += READ_ONCE(cpuc->lock_count[idx]); - } - return sum; -} - -/* - * Returns approximate total of the readers' ->unlock_count[] values for the - * rank of per-CPU counters specified by idx. - */ -static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx) -{ - int cpu; - unsigned long sum = 0; - - for_each_possible_cpu(cpu) { - struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu); - - sum += READ_ONCE(cpuc->unlock_count[idx]); - } - return sum; -} - -/* - * Return true if the number of pre-existing readers is determined to - * be zero. - */ -static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx) -{ - unsigned long unlocks; - - unlocks = srcu_readers_unlock_idx(sp, idx); - - /* - * Make sure that a lock is always counted if the corresponding unlock - * is counted. Needs to be a smp_mb() as the read side may contain a - * read from a variable that is written to before the synchronize_srcu() - * in the write side. In this case smp_mb()s A and B act like the store - * buffering pattern. - * - * This smp_mb() also pairs with smp_mb() C to prevent accesses after the - * synchronize_srcu() from being executed before the grace period ends. - */ - smp_mb(); /* A */ - - /* - * If the locks are the same as the unlocks, then there must have - * been no readers on this index at some time in between. This does not - * mean that there are no more readers, as one could have read the - * current index but not have incremented the lock counter yet. - * - * Possible bug: There is no guarantee that there haven't been ULONG_MAX - * increments of ->lock_count[] since the unlocks were counted, meaning - * that this could return true even if there are still active readers. - * Since there are no memory barriers around srcu_flip(), the CPU is not - * required to increment ->completed before running - * srcu_readers_unlock_idx(), which means that there could be an - * arbitrarily large number of critical sections that execute after - * srcu_readers_unlock_idx() but use the old value of ->completed. - */ - return srcu_readers_lock_idx(sp, idx) == unlocks; -} - -/** - * srcu_readers_active - returns true if there are readers. and false - * otherwise - * @sp: which srcu_struct to count active readers (holding srcu_read_lock). - * - * Note that this is not an atomic primitive, and can therefore suffer - * severe errors when invoked on an active srcu_struct. That said, it - * can be useful as an error check at cleanup time. - */ -static bool srcu_readers_active(struct srcu_struct *sp) -{ - int cpu; - unsigned long sum = 0; - - for_each_possible_cpu(cpu) { - struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu); - - sum += READ_ONCE(cpuc->lock_count[0]); - sum += READ_ONCE(cpuc->lock_count[1]); - sum -= READ_ONCE(cpuc->unlock_count[0]); - sum -= READ_ONCE(cpuc->unlock_count[1]); - } - return sum; -} - -/** - * cleanup_srcu_struct - deconstruct a sleep-RCU structure - * @sp: structure to clean up. - * - * Must invoke this only after you are finished using a given srcu_struct - * that was initialized via init_srcu_struct(). This code does some - * probabalistic checking, spotting late uses of srcu_read_lock(), - * synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu(). - * If any such late uses are detected, the per-CPU memory associated with - * the srcu_struct is simply leaked and WARN_ON() is invoked. If the - * caller frees the srcu_struct itself, a use-after-free crash will likely - * ensue, but at least there will be a warning printed. - */ -void cleanup_srcu_struct(struct srcu_struct *sp) -{ - if (WARN_ON(srcu_readers_active(sp))) - return; /* Leakage unless caller handles error. */ - free_percpu(sp->per_cpu_ref); - sp->per_cpu_ref = NULL; -} -EXPORT_SYMBOL_GPL(cleanup_srcu_struct); - -/* - * Counts the new reader in the appropriate per-CPU element of the - * srcu_struct. - * Returns an index that must be passed to the matching srcu_read_unlock(). - */ -int __srcu_read_lock(struct srcu_struct *sp) -{ - int idx; - - idx = READ_ONCE(sp->completed) & 0x1; - this_cpu_inc(sp->per_cpu_ref->lock_count[idx]); - smp_mb(); /* B */ /* Avoid leaking the critical section. */ - return idx; -} -EXPORT_SYMBOL_GPL(__srcu_read_lock); - -/* - * Removes the count for the old reader from the appropriate per-CPU - * element of the srcu_struct. Note that this may well be a different - * CPU than that which was incremented by the corresponding srcu_read_lock(). - */ -void __srcu_read_unlock(struct srcu_struct *sp, int idx) -{ - smp_mb(); /* C */ /* Avoid leaking the critical section. */ - this_cpu_inc(sp->per_cpu_ref->unlock_count[idx]); -} -EXPORT_SYMBOL_GPL(__srcu_read_unlock); - -/* - * We use an adaptive strategy for synchronize_srcu() and especially for - * synchronize_srcu_expedited(). We spin for a fixed time period - * (defined below) to allow SRCU readers to exit their read-side critical - * sections. If there are still some readers after 10 microseconds, - * we repeatedly block for 1-millisecond time periods. This approach - * has done well in testing, so there is no need for a config parameter. - */ -#define SRCU_RETRY_CHECK_DELAY 5 -#define SYNCHRONIZE_SRCU_TRYCOUNT 2 -#define SYNCHRONIZE_SRCU_EXP_TRYCOUNT 12 - -/* - * @@@ Wait until all pre-existing readers complete. Such readers - * will have used the index specified by "idx". - * the caller should ensures the ->completed is not changed while checking - * and idx = (->completed & 1) ^ 1 - */ -static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount) -{ - for (;;) { - if (srcu_readers_active_idx_check(sp, idx)) - return true; - if (--trycount <= 0) - return false; - udelay(SRCU_RETRY_CHECK_DELAY); - } -} - -/* - * Increment the ->completed counter so that future SRCU readers will - * use the other rank of the ->(un)lock_count[] arrays. This allows - * us to wait for pre-existing readers in a starvation-free manner. - */ -static void srcu_flip(struct srcu_struct *sp) -{ - WRITE_ONCE(sp->completed, sp->completed + 1); - - /* - * Ensure that if the updater misses an __srcu_read_unlock() - * increment, that task's next __srcu_read_lock() will see the - * above counter update. Note that both this memory barrier - * and the one in srcu_readers_active_idx_check() provide the - * guarantee for __srcu_read_lock(). - */ - smp_mb(); /* D */ /* Pairs with C. */ -} - -/* - * Enqueue an SRCU callback on the specified srcu_struct structure, - * initiating grace-period processing if it is not already running. - * - * Note that all CPUs must agree that the grace period extended beyond - * all pre-existing SRCU read-side critical section. On systems with - * more than one CPU, this means that when "func()" is invoked, each CPU - * is guaranteed to have executed a full memory barrier since the end of - * its last corresponding SRCU read-side critical section whose beginning - * preceded the call to call_rcu(). It also means that each CPU executing - * an SRCU read-side critical section that continues beyond the start of - * "func()" must have executed a memory barrier after the call_rcu() - * but before the beginning of that SRCU read-side critical section. - * Note that these guarantees include CPUs that are offline, idle, or - * executing in user mode, as well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the - * resulting SRCU callback function "func()", then both CPU A and CPU - * B are guaranteed to execute a full memory barrier during the time - * interval between the call to call_rcu() and the invocation of "func()". - * This guarantee applies even if CPU A and CPU B are the same CPU (but - * again only if the system has more than one CPU). - * - * Of course, these guarantees apply only for invocations of call_srcu(), - * srcu_read_lock(), and srcu_read_unlock() that are all passed the same - * srcu_struct structure. - */ -void call_srcu(struct srcu_struct *sp, struct rcu_head *head, - rcu_callback_t func) -{ - unsigned long flags; - - head->next = NULL; - head->func = func; - spin_lock_irqsave(&sp->queue_lock, flags); - smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */ - rcu_batch_queue(&sp->batch_queue, head); - if (!sp->running) { - sp->running = true; - queue_delayed_work(system_power_efficient_wq, &sp->work, 0); - } - spin_unlock_irqrestore(&sp->queue_lock, flags); -} -EXPORT_SYMBOL_GPL(call_srcu); - -static void srcu_advance_batches(struct srcu_struct *sp, int trycount); -static void srcu_reschedule(struct srcu_struct *sp); - -/* - * Helper function for synchronize_srcu() and synchronize_srcu_expedited(). - */ -static void __synchronize_srcu(struct srcu_struct *sp, int trycount) -{ - struct rcu_synchronize rcu; - struct rcu_head *head = &rcu.head; - bool done = false; - - RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) || - lock_is_held(&rcu_bh_lock_map) || - lock_is_held(&rcu_lock_map) || - lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_srcu() in same-type SRCU (or in RCU) read-side critical section"); - - might_sleep(); - init_completion(&rcu.completion); - - head->next = NULL; - head->func = wakeme_after_rcu; - spin_lock_irq(&sp->queue_lock); - smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */ - if (!sp->running) { - /* steal the processing owner */ - sp->running = true; - rcu_batch_queue(&sp->batch_check0, head); - spin_unlock_irq(&sp->queue_lock); - - srcu_advance_batches(sp, trycount); - if (!rcu_batch_empty(&sp->batch_done)) { - BUG_ON(sp->batch_done.head != head); - rcu_batch_dequeue(&sp->batch_done); - done = true; - } - /* give the processing owner to work_struct */ - srcu_reschedule(sp); - } else { - rcu_batch_queue(&sp->batch_queue, head); - spin_unlock_irq(&sp->queue_lock); - } - - if (!done) { - wait_for_completion(&rcu.completion); - smp_mb(); /* Caller's later accesses after GP. */ - } - -} - -/** - * synchronize_srcu - wait for prior SRCU read-side critical-section completion - * @sp: srcu_struct with which to synchronize. - * - * Wait for the count to drain to zero of both indexes. To avoid the - * possible starvation of synchronize_srcu(), it waits for the count of - * the index=((->completed & 1) ^ 1) to drain to zero at first, - * and then flip the completed and wait for the count of the other index. - * - * Can block; must be called from process context. - * - * Note that it is illegal to call synchronize_srcu() from the corresponding - * SRCU read-side critical section; doing so will result in deadlock. - * However, it is perfectly legal to call synchronize_srcu() on one - * srcu_struct from some other srcu_struct's read-side critical section, - * as long as the resulting graph of srcu_structs is acyclic. - * - * There are memory-ordering constraints implied by synchronize_srcu(). - * On systems with more than one CPU, when synchronize_srcu() returns, - * each CPU is guaranteed to have executed a full memory barrier since - * the end of its last corresponding SRCU-sched read-side critical section - * whose beginning preceded the call to synchronize_srcu(). In addition, - * each CPU having an SRCU read-side critical section that extends beyond - * the return from synchronize_srcu() is guaranteed to have executed a - * full memory barrier after the beginning of synchronize_srcu() and before - * the beginning of that SRCU read-side critical section. Note that these - * guarantees include CPUs that are offline, idle, or executing in user mode, - * as well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked synchronize_srcu(), which returned - * to its caller on CPU B, then both CPU A and CPU B are guaranteed - * to have executed a full memory barrier during the execution of - * synchronize_srcu(). This guarantee applies even if CPU A and CPU B - * are the same CPU, but again only if the system has more than one CPU. - * - * Of course, these memory-ordering guarantees apply only when - * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are - * passed the same srcu_struct structure. - */ -void synchronize_srcu(struct srcu_struct *sp) -{ - __synchronize_srcu(sp, (rcu_gp_is_expedited() && !rcu_gp_is_normal()) - ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT - : SYNCHRONIZE_SRCU_TRYCOUNT); -} -EXPORT_SYMBOL_GPL(synchronize_srcu); - -/** - * synchronize_srcu_expedited - Brute-force SRCU grace period - * @sp: srcu_struct with which to synchronize. - * - * Wait for an SRCU grace period to elapse, but be more aggressive about - * spinning rather than blocking when waiting. - * - * Note that synchronize_srcu_expedited() has the same deadlock and - * memory-ordering properties as does synchronize_srcu(). - */ -void synchronize_srcu_expedited(struct srcu_struct *sp) -{ - __synchronize_srcu(sp, SYNCHRONIZE_SRCU_EXP_TRYCOUNT); -} -EXPORT_SYMBOL_GPL(synchronize_srcu_expedited); - -/** - * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete. - * @sp: srcu_struct on which to wait for in-flight callbacks. - */ -void srcu_barrier(struct srcu_struct *sp) -{ - synchronize_srcu(sp); -} -EXPORT_SYMBOL_GPL(srcu_barrier); - -/** - * srcu_batches_completed - return batches completed. - * @sp: srcu_struct on which to report batch completion. - * - * Report the number of batches, correlated with, but not necessarily - * precisely the same as, the number of grace periods that have elapsed. - */ -unsigned long srcu_batches_completed(struct srcu_struct *sp) -{ - return sp->completed; -} -EXPORT_SYMBOL_GPL(srcu_batches_completed); - -#define SRCU_CALLBACK_BATCH 10 -#define SRCU_INTERVAL 1 - -/* - * Move any new SRCU callbacks to the first stage of the SRCU grace - * period pipeline. - */ -static void srcu_collect_new(struct srcu_struct *sp) -{ - if (!rcu_batch_empty(&sp->batch_queue)) { - spin_lock_irq(&sp->queue_lock); - rcu_batch_move(&sp->batch_check0, &sp->batch_queue); - spin_unlock_irq(&sp->queue_lock); - } -} - -/* - * Core SRCU state machine. Advance callbacks from ->batch_check0 to - * ->batch_check1 and then to ->batch_done as readers drain. - */ -static void srcu_advance_batches(struct srcu_struct *sp, int trycount) -{ - int idx = 1 ^ (sp->completed & 1); - - /* - * Because readers might be delayed for an extended period after - * fetching ->completed for their index, at any point in time there - * might well be readers using both idx=0 and idx=1. We therefore - * need to wait for readers to clear from both index values before - * invoking a callback. - */ - - if (rcu_batch_empty(&sp->batch_check0) && - rcu_batch_empty(&sp->batch_check1)) - return; /* no callbacks need to be advanced */ - - if (!try_check_zero(sp, idx, trycount)) - return; /* failed to advance, will try after SRCU_INTERVAL */ - - /* - * The callbacks in ->batch_check1 have already done with their - * first zero check and flip back when they were enqueued on - * ->batch_check0 in a previous invocation of srcu_advance_batches(). - * (Presumably try_check_zero() returned false during that - * invocation, leaving the callbacks stranded on ->batch_check1.) - * They are therefore ready to invoke, so move them to ->batch_done. - */ - rcu_batch_move(&sp->batch_done, &sp->batch_check1); - - if (rcu_batch_empty(&sp->batch_check0)) - return; /* no callbacks need to be advanced */ - srcu_flip(sp); - - /* - * The callbacks in ->batch_check0 just finished their - * first check zero and flip, so move them to ->batch_check1 - * for future checking on the other idx. - */ - rcu_batch_move(&sp->batch_check1, &sp->batch_check0); - - /* - * SRCU read-side critical sections are normally short, so check - * at least twice in quick succession after a flip. - */ - trycount = trycount < 2 ? 2 : trycount; - if (!try_check_zero(sp, idx^1, trycount)) - return; /* failed to advance, will try after SRCU_INTERVAL */ - - /* - * The callbacks in ->batch_check1 have now waited for all - * pre-existing readers using both idx values. They are therefore - * ready to invoke, so move them to ->batch_done. - */ - rcu_batch_move(&sp->batch_done, &sp->batch_check1); -} - -/* - * Invoke a limited number of SRCU callbacks that have passed through - * their grace period. If there are more to do, SRCU will reschedule - * the workqueue. Note that needed memory barriers have been executed - * in this task's context by srcu_readers_active_idx_check(). - */ -static void srcu_invoke_callbacks(struct srcu_struct *sp) -{ - int i; - struct rcu_head *head; - - for (i = 0; i < SRCU_CALLBACK_BATCH; i++) { - head = rcu_batch_dequeue(&sp->batch_done); - if (!head) - break; - local_bh_disable(); - head->func(head); - local_bh_enable(); - } -} - -/* - * Finished one round of SRCU grace period. Start another if there are - * more SRCU callbacks queued, otherwise put SRCU into not-running state. - */ -static void srcu_reschedule(struct srcu_struct *sp) -{ - bool pending = true; - - if (rcu_batch_empty(&sp->batch_done) && - rcu_batch_empty(&sp->batch_check1) && - rcu_batch_empty(&sp->batch_check0) && - rcu_batch_empty(&sp->batch_queue)) { - spin_lock_irq(&sp->queue_lock); - if (rcu_batch_empty(&sp->batch_done) && - rcu_batch_empty(&sp->batch_check1) && - rcu_batch_empty(&sp->batch_check0) && - rcu_batch_empty(&sp->batch_queue)) { - sp->running = false; - pending = false; - } - spin_unlock_irq(&sp->queue_lock); - } - - if (pending) - queue_delayed_work(system_power_efficient_wq, - &sp->work, SRCU_INTERVAL); -} - -/* - * This is the work-queue function that handles SRCU grace periods. - */ -void process_srcu(struct work_struct *work) -{ - struct srcu_struct *sp; - - sp = container_of(work, struct srcu_struct, work.work); - - srcu_collect_new(sp); - srcu_advance_batches(sp, 1); - srcu_invoke_callbacks(sp); - srcu_reschedule(sp); -} -EXPORT_SYMBOL_GPL(process_srcu); diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 32798eb14853..1a1c1047d2ed 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -38,8 +38,8 @@ static int init_srcu_struct_fields(struct srcu_struct *sp) sp->srcu_lock_nesting[0] = 0; sp->srcu_lock_nesting[1] = 0; init_swait_queue_head(&sp->srcu_wq); - sp->srcu_gp_seq = 0; - rcu_segcblist_init(&sp->srcu_cblist); + sp->srcu_cb_head = NULL; + sp->srcu_cb_tail = &sp->srcu_cb_head; sp->srcu_gp_running = false; sp->srcu_gp_waiting = false; sp->srcu_idx = 0; @@ -88,30 +88,14 @@ void cleanup_srcu_struct(struct srcu_struct *sp) { WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]); flush_work(&sp->srcu_work); - WARN_ON(rcu_seq_state(sp->srcu_gp_seq)); WARN_ON(sp->srcu_gp_running); WARN_ON(sp->srcu_gp_waiting); - WARN_ON(!rcu_segcblist_empty(&sp->srcu_cblist)); + WARN_ON(sp->srcu_cb_head); + WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail); } EXPORT_SYMBOL_GPL(cleanup_srcu_struct); /* - * Counts the new reader in the appropriate per-CPU element of the - * srcu_struct. Can be invoked from irq/bh handlers, but the matching - * __srcu_read_unlock() must be in the same handler instance. Returns an - * index that must be passed to the matching srcu_read_unlock(). - */ -int __srcu_read_lock(struct srcu_struct *sp) -{ - int idx; - - idx = READ_ONCE(sp->srcu_idx); - WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1); - return idx; -} -EXPORT_SYMBOL_GPL(__srcu_read_lock); - -/* * Removes the count for the old reader from the appropriate element of * the srcu_struct. */ @@ -133,52 +117,44 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock); void srcu_drive_gp(struct work_struct *wp) { int idx; - struct rcu_cblist ready_cbs; - struct srcu_struct *sp; + struct rcu_head *lh; struct rcu_head *rhp; + struct srcu_struct *sp; sp = container_of(wp, struct srcu_struct, srcu_work); - if (sp->srcu_gp_running || rcu_segcblist_empty(&sp->srcu_cblist)) + if (sp->srcu_gp_running || !READ_ONCE(sp->srcu_cb_head)) return; /* Already running or nothing to do. */ - /* Tag recently arrived callbacks and wait for readers. */ + /* Remove recently arrived callbacks and wait for readers. */ WRITE_ONCE(sp->srcu_gp_running, true); - rcu_segcblist_accelerate(&sp->srcu_cblist, - rcu_seq_snap(&sp->srcu_gp_seq)); - rcu_seq_start(&sp->srcu_gp_seq); + local_irq_disable(); + lh = sp->srcu_cb_head; + sp->srcu_cb_head = NULL; + sp->srcu_cb_tail = &sp->srcu_cb_head; + local_irq_enable(); idx = sp->srcu_idx; WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx); WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */ swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */ - rcu_seq_end(&sp->srcu_gp_seq); - - /* Update callback list based on GP, and invoke ready callbacks. */ - rcu_segcblist_advance(&sp->srcu_cblist, - rcu_seq_current(&sp->srcu_gp_seq)); - if (rcu_segcblist_ready_cbs(&sp->srcu_cblist)) { - rcu_cblist_init(&ready_cbs); - local_irq_disable(); - rcu_segcblist_extract_done_cbs(&sp->srcu_cblist, &ready_cbs); - local_irq_enable(); - rhp = rcu_cblist_dequeue(&ready_cbs); - for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) { - local_bh_disable(); - rhp->func(rhp); - local_bh_enable(); - } - local_irq_disable(); - rcu_segcblist_insert_count(&sp->srcu_cblist, &ready_cbs); - local_irq_enable(); + + /* Invoke the callbacks we removed above. */ + while (lh) { + rhp = lh; + lh = lh->next; + local_bh_disable(); + rhp->func(rhp); + local_bh_enable(); } - WRITE_ONCE(sp->srcu_gp_running, false); /* - * If more callbacks, reschedule ourselves. This can race with - * a call_srcu() at interrupt level, but the ->srcu_gp_running - * checks will straighten that out. + * Enable rescheduling, and if there are more callbacks, + * reschedule ourselves. This can race with a call_srcu() + * at interrupt level, but the ->srcu_gp_running checks will + * straighten that out. */ - if (!rcu_segcblist_empty(&sp->srcu_cblist)) + WRITE_ONCE(sp->srcu_gp_running, false); + if (READ_ONCE(sp->srcu_cb_head)) schedule_work(&sp->srcu_work); } EXPORT_SYMBOL_GPL(srcu_drive_gp); @@ -187,14 +163,16 @@ EXPORT_SYMBOL_GPL(srcu_drive_gp); * Enqueue an SRCU callback on the specified srcu_struct structure, * initiating grace-period processing if it is not already running. */ -void call_srcu(struct srcu_struct *sp, struct rcu_head *head, +void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, rcu_callback_t func) { unsigned long flags; - head->func = func; + rhp->func = func; + rhp->next = NULL; local_irq_save(flags); - rcu_segcblist_enqueue(&sp->srcu_cblist, head, false); + *sp->srcu_cb_tail = rhp; + sp->srcu_cb_tail = &rhp->next; local_irq_restore(flags); if (!READ_ONCE(sp->srcu_gp_running)) schedule_work(&sp->srcu_work); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 157654fa436a..d0ca524bf042 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -40,9 +40,15 @@ #include "rcu.h" #include "rcu_segcblist.h" -ulong exp_holdoff = 25 * 1000; /* Holdoff (ns) for auto-expediting. */ +/* Holdoff in nanoseconds for auto-expediting. */ +#define DEFAULT_SRCU_EXP_HOLDOFF (25 * 1000) +static ulong exp_holdoff = DEFAULT_SRCU_EXP_HOLDOFF; module_param(exp_holdoff, ulong, 0444); +/* Overflow-check frequency. N bits roughly says every 2**N grace periods. */ +static ulong counter_wrap_check = (ULONG_MAX >> 2); +module_param(counter_wrap_check, ulong, 0444); + static void srcu_invoke_callbacks(struct work_struct *work); static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay); @@ -70,7 +76,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static) /* Each pass through this loop initializes one srcu_node structure. */ rcu_for_each_node_breadth_first(sp, snp) { - spin_lock_init(&snp->lock); + raw_spin_lock_init(&ACCESS_PRIVATE(snp, lock)); WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) != ARRAY_SIZE(snp->srcu_data_have_cbs)); for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) { @@ -104,7 +110,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static) snp_first = sp->level[level]; for_each_possible_cpu(cpu) { sdp = per_cpu_ptr(sp->sda, cpu); - spin_lock_init(&sdp->lock); + raw_spin_lock_init(&ACCESS_PRIVATE(sdp, lock)); rcu_segcblist_init(&sdp->srcu_cblist); sdp->srcu_cblist_invoking = false; sdp->srcu_gp_seq_needed = sp->srcu_gp_seq; @@ -163,7 +169,7 @@ int __init_srcu_struct(struct srcu_struct *sp, const char *name, /* Don't re-initialize a lock while it is held. */ debug_check_no_locks_freed((void *)sp, sizeof(*sp)); lockdep_init_map(&sp->dep_map, name, key, 0); - spin_lock_init(&sp->gp_lock); + raw_spin_lock_init(&ACCESS_PRIVATE(sp, lock)); return init_srcu_struct_fields(sp, false); } EXPORT_SYMBOL_GPL(__init_srcu_struct); @@ -180,7 +186,7 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct); */ int init_srcu_struct(struct srcu_struct *sp) { - spin_lock_init(&sp->gp_lock); + raw_spin_lock_init(&ACCESS_PRIVATE(sp, lock)); return init_srcu_struct_fields(sp, false); } EXPORT_SYMBOL_GPL(init_srcu_struct); @@ -191,7 +197,7 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); * First-use initialization of statically allocated srcu_struct * structure. Wiring up the combining tree is more than can be * done with compile-time initialization, so this check is added - * to each update-side SRCU primitive. Use ->gp_lock, which -is- + * to each update-side SRCU primitive. Use sp->lock, which -is- * compile-time initialized, to resolve races involving multiple * CPUs trying to garner first-use privileges. */ @@ -203,13 +209,13 @@ static void check_init_srcu_struct(struct srcu_struct *sp) /* The smp_load_acquire() pairs with the smp_store_release(). */ if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/ return; /* Already initialized. */ - spin_lock_irqsave(&sp->gp_lock, flags); + raw_spin_lock_irqsave_rcu_node(sp, flags); if (!rcu_seq_state(sp->srcu_gp_seq_needed)) { - spin_unlock_irqrestore(&sp->gp_lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sp, flags); return; } init_srcu_struct_fields(sp, true); - spin_unlock_irqrestore(&sp->gp_lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sp, flags); } /* @@ -275,15 +281,20 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx) * not mean that there are no more readers, as one could have read * the current index but not have incremented the lock counter yet. * - * Possible bug: There is no guarantee that there haven't been - * ULONG_MAX increments of ->srcu_lock_count[] since the unlocks were - * counted, meaning that this could return true even if there are - * still active readers. Since there are no memory barriers around - * srcu_flip(), the CPU is not required to increment ->srcu_idx - * before running srcu_readers_unlock_idx(), which means that there - * could be an arbitrarily large number of critical sections that - * execute after srcu_readers_unlock_idx() but use the old value - * of ->srcu_idx. + * So suppose that the updater is preempted here for so long + * that more than ULONG_MAX non-nested readers come and go in + * the meantime. It turns out that this cannot result in overflow + * because if a reader modifies its unlock count after we read it + * above, then that reader's next load of ->srcu_idx is guaranteed + * to get the new value, which will cause it to operate on the + * other bank of counters, where it cannot contribute to the + * overflow of these counters. This means that there is a maximum + * of 2*NR_CPUS increments, which cannot overflow given current + * systems, especially not on 64-bit systems. + * + * OK, how about nesting? This does impose a limit on nesting + * of floor(ULONG_MAX/NR_CPUS/2), which should be sufficient, + * especially on 64-bit systems. */ return srcu_readers_lock_idx(sp, idx) == unlocks; } @@ -400,8 +411,7 @@ static void srcu_gp_start(struct srcu_struct *sp) struct srcu_data *sdp = this_cpu_ptr(sp->sda); int state; - RCU_LOCKDEP_WARN(!lockdep_is_held(&sp->gp_lock), - "Invoked srcu_gp_start() without ->gp_lock!"); + lockdep_assert_held(&sp->lock); WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&sp->srcu_gp_seq)); @@ -489,17 +499,20 @@ static void srcu_gp_end(struct srcu_struct *sp) { unsigned long cbdelay; bool cbs; + int cpu; + unsigned long flags; unsigned long gpseq; int idx; int idxnext; unsigned long mask; + struct srcu_data *sdp; struct srcu_node *snp; /* Prevent more than one additional grace period. */ mutex_lock(&sp->srcu_cb_mutex); /* End the current grace period. */ - spin_lock_irq(&sp->gp_lock); + raw_spin_lock_irq_rcu_node(sp); idx = rcu_seq_state(sp->srcu_gp_seq); WARN_ON_ONCE(idx != SRCU_STATE_SCAN2); cbdelay = srcu_get_delay(sp); @@ -508,7 +521,7 @@ static void srcu_gp_end(struct srcu_struct *sp) gpseq = rcu_seq_current(&sp->srcu_gp_seq); if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, gpseq)) sp->srcu_gp_seq_needed_exp = gpseq; - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); mutex_unlock(&sp->srcu_gp_mutex); /* A new grace period can start at this point. But only one. */ @@ -516,7 +529,7 @@ static void srcu_gp_end(struct srcu_struct *sp) idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs); idxnext = (idx + 1) % ARRAY_SIZE(snp->srcu_have_cbs); rcu_for_each_node_breadth_first(sp, snp) { - spin_lock_irq(&snp->lock); + raw_spin_lock_irq_rcu_node(snp); cbs = false; if (snp >= sp->level[rcu_num_lvls - 1]) cbs = snp->srcu_have_cbs[idx] == gpseq; @@ -526,28 +539,37 @@ static void srcu_gp_end(struct srcu_struct *sp) snp->srcu_gp_seq_needed_exp = gpseq; mask = snp->srcu_data_have_cbs[idx]; snp->srcu_data_have_cbs[idx] = 0; - spin_unlock_irq(&snp->lock); - if (cbs) { - smp_mb(); /* GP end before CB invocation. */ + raw_spin_unlock_irq_rcu_node(snp); + if (cbs) srcu_schedule_cbs_snp(sp, snp, mask, cbdelay); - } + + /* Occasionally prevent srcu_data counter wrap. */ + if (!(gpseq & counter_wrap_check)) + for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) { + sdp = per_cpu_ptr(sp->sda, cpu); + raw_spin_lock_irqsave_rcu_node(sdp, flags); + if (ULONG_CMP_GE(gpseq, + sdp->srcu_gp_seq_needed + 100)) + sdp->srcu_gp_seq_needed = gpseq; + raw_spin_unlock_irqrestore_rcu_node(sdp, flags); + } } /* Callback initiation done, allow grace periods after next. */ mutex_unlock(&sp->srcu_cb_mutex); /* Start a new grace period if needed. */ - spin_lock_irq(&sp->gp_lock); + raw_spin_lock_irq_rcu_node(sp); gpseq = rcu_seq_current(&sp->srcu_gp_seq); if (!rcu_seq_state(gpseq) && ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) { srcu_gp_start(sp); - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); /* Throttle expedited grace periods: Should be rare! */ srcu_reschedule(sp, rcu_seq_ctr(gpseq) & 0x3ff ? 0 : SRCU_INTERVAL); } else { - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); } } @@ -567,18 +589,18 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp, if (rcu_seq_done(&sp->srcu_gp_seq, s) || ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s)) return; - spin_lock_irqsave(&snp->lock, flags); + raw_spin_lock_irqsave_rcu_node(snp, flags); if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) { - spin_unlock_irqrestore(&snp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); return; } WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); - spin_unlock_irqrestore(&snp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); } - spin_lock_irqsave(&sp->gp_lock, flags); + raw_spin_lock_irqsave_rcu_node(sp, flags); if (!ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s)) sp->srcu_gp_seq_needed_exp = s; - spin_unlock_irqrestore(&sp->gp_lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sp, flags); } /* @@ -600,14 +622,13 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, for (; snp != NULL; snp = snp->srcu_parent) { if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode) return; /* GP already done and CBs recorded. */ - spin_lock_irqsave(&snp->lock, flags); + raw_spin_lock_irqsave_rcu_node(snp, flags); if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) { snp_seq = snp->srcu_have_cbs[idx]; if (snp == sdp->mynode && snp_seq == s) snp->srcu_data_have_cbs[idx] |= sdp->grpmask; - spin_unlock_irqrestore(&snp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); if (snp == sdp->mynode && snp_seq != s) { - smp_mb(); /* CBs after GP! */ srcu_schedule_cbs_sdp(sdp, do_norm ? SRCU_INTERVAL : 0); @@ -622,11 +643,11 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, snp->srcu_data_have_cbs[idx] |= sdp->grpmask; if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s)) snp->srcu_gp_seq_needed_exp = s; - spin_unlock_irqrestore(&snp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(snp, flags); } /* Top of tree, must ensure the grace period will be started. */ - spin_lock_irqsave(&sp->gp_lock, flags); + raw_spin_lock_irqsave_rcu_node(sp, flags); if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) { /* * Record need for grace period s. Pair with load @@ -645,7 +666,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, queue_delayed_work(system_power_efficient_wq, &sp->work, srcu_get_delay(sp)); } - spin_unlock_irqrestore(&sp->gp_lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sp, flags); } /* @@ -671,6 +692,16 @@ static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount) */ static void srcu_flip(struct srcu_struct *sp) { + /* + * Ensure that if this updater saw a given reader's increment + * from __srcu_read_lock(), that reader was using an old value + * of ->srcu_idx. Also ensure that if a given reader sees the + * new value of ->srcu_idx, this updater's earlier scans cannot + * have seen that reader's increments (which is OK, because this + * grace period need not wait on that reader). + */ + smp_mb(); /* E */ /* Pairs with B and C. */ + WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1); /* @@ -745,6 +776,13 @@ static bool srcu_might_be_idle(struct srcu_struct *sp) } /* + * SRCU callback function to leak a callback. + */ +static void srcu_leak_callback(struct rcu_head *rhp) +{ +} + +/* * Enqueue an SRCU callback on the srcu_data structure associated with * the current CPU and the specified srcu_struct structure, initiating * grace-period processing if it is not already running. @@ -782,10 +820,16 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, struct srcu_data *sdp; check_init_srcu_struct(sp); + if (debug_rcu_head_queue(rhp)) { + /* Probable double call_srcu(), so leak the callback. */ + WRITE_ONCE(rhp->func, srcu_leak_callback); + WARN_ONCE(1, "call_srcu(): Leaked duplicate callback\n"); + return; + } rhp->func = func; local_irq_save(flags); sdp = this_cpu_ptr(sp->sda); - spin_lock(&sdp->lock); + raw_spin_lock_rcu_node(sdp); rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&sp->srcu_gp_seq)); @@ -799,13 +843,30 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, sdp->srcu_gp_seq_needed_exp = s; needexp = true; } - spin_unlock_irqrestore(&sdp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(sdp, flags); if (needgp) srcu_funnel_gp_start(sp, sdp, s, do_norm); else if (needexp) srcu_funnel_exp_start(sp, sdp->mynode, s); } +/** + * call_srcu() - Queue a callback for invocation after an SRCU grace period + * @sp: srcu_struct in queue the callback + * @head: structure to be used for queueing the SRCU callback. + * @func: function to be invoked after the SRCU grace period + * + * The callback function will be invoked some time after a full SRCU + * grace period elapses, in other words after all pre-existing SRCU + * read-side critical sections have completed. However, the callback + * function might well execute concurrently with other SRCU read-side + * critical sections that started after call_srcu() was invoked. SRCU + * read-side critical sections are delimited by srcu_read_lock() and + * srcu_read_unlock(), and may be nested. + * + * The callback will be invoked from process context, but must nevertheless + * be fast and must not block. + */ void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, rcu_callback_t func) { @@ -953,13 +1014,16 @@ void srcu_barrier(struct srcu_struct *sp) */ for_each_possible_cpu(cpu) { sdp = per_cpu_ptr(sp->sda, cpu); - spin_lock_irq(&sdp->lock); + raw_spin_lock_irq_rcu_node(sdp); atomic_inc(&sp->srcu_barrier_cpu_cnt); sdp->srcu_barrier_head.func = srcu_barrier_cb; + debug_rcu_head_queue(&sdp->srcu_barrier_head); if (!rcu_segcblist_entrain(&sdp->srcu_cblist, - &sdp->srcu_barrier_head, 0)) + &sdp->srcu_barrier_head, 0)) { + debug_rcu_head_unqueue(&sdp->srcu_barrier_head); atomic_dec(&sp->srcu_barrier_cpu_cnt); - spin_unlock_irq(&sdp->lock); + } + raw_spin_unlock_irq_rcu_node(sdp); } /* Remove the initial count, at which point reaching zero can happen. */ @@ -1008,17 +1072,17 @@ static void srcu_advance_state(struct srcu_struct *sp) */ idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */ if (idx == SRCU_STATE_IDLE) { - spin_lock_irq(&sp->gp_lock); + raw_spin_lock_irq_rcu_node(sp); if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) { WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq)); - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); mutex_unlock(&sp->srcu_gp_mutex); return; } idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)); if (idx == SRCU_STATE_IDLE) srcu_gp_start(sp); - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); if (idx != SRCU_STATE_IDLE) { mutex_unlock(&sp->srcu_gp_mutex); return; /* Someone else started the grace period. */ @@ -1067,22 +1131,22 @@ static void srcu_invoke_callbacks(struct work_struct *work) sdp = container_of(work, struct srcu_data, work.work); sp = sdp->sp; rcu_cblist_init(&ready_cbs); - spin_lock_irq(&sdp->lock); - smp_mb(); /* Old grace periods before callback invocation! */ + raw_spin_lock_irq_rcu_node(sdp); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&sp->srcu_gp_seq)); if (sdp->srcu_cblist_invoking || !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) { - spin_unlock_irq(&sdp->lock); + raw_spin_unlock_irq_rcu_node(sdp); return; /* Someone else on the job or nothing to do. */ } /* We are on the job! Extract and invoke ready callbacks. */ sdp->srcu_cblist_invoking = true; rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs); - spin_unlock_irq(&sdp->lock); + raw_spin_unlock_irq_rcu_node(sdp); rhp = rcu_cblist_dequeue(&ready_cbs); for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) { + debug_rcu_head_unqueue(rhp); local_bh_disable(); rhp->func(rhp); local_bh_enable(); @@ -1092,13 +1156,13 @@ static void srcu_invoke_callbacks(struct work_struct *work) * Update counts, accelerate new callbacks, and if needed, * schedule another round of callback invocation. */ - spin_lock_irq(&sdp->lock); + raw_spin_lock_irq_rcu_node(sdp); rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs); (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, rcu_seq_snap(&sp->srcu_gp_seq)); sdp->srcu_cblist_invoking = false; more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist); - spin_unlock_irq(&sdp->lock); + raw_spin_unlock_irq_rcu_node(sdp); if (more) srcu_schedule_cbs_sdp(sdp, 0); } @@ -1111,7 +1175,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay) { bool pushgp = true; - spin_lock_irq(&sp->gp_lock); + raw_spin_lock_irq_rcu_node(sp); if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) { if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) { /* All requests fulfilled, time to go idle. */ @@ -1121,7 +1185,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay) /* Outstanding request and no GP. Start one. */ srcu_gp_start(sp); } - spin_unlock_irq(&sp->gp_lock); + raw_spin_unlock_irq_rcu_node(sp); if (pushgp) queue_delayed_work(system_power_efficient_wq, &sp->work, delay); @@ -1152,3 +1216,12 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type, *gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed); } EXPORT_SYMBOL_GPL(srcutorture_get_gp_data); + +static int __init srcu_bootup_announce(void) +{ + pr_info("Hierarchical SRCU implementation.\n"); + if (exp_holdoff != DEFAULT_SRCU_EXP_HOLDOFF) + pr_info("\tNon-default auto-expedite holdoff of %lu ns.\n", exp_holdoff); + return 0; +} +early_initcall(srcu_bootup_announce); diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index e5385731e391..f8488965250f 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -35,15 +35,26 @@ #include <linux/time.h> #include <linux/cpu.h> #include <linux/prefetch.h> -#include <linux/trace_events.h> #include "rcu.h" -/* Forward declarations for tiny_plugin.h. */ -struct rcu_ctrlblk; -static void __call_rcu(struct rcu_head *head, - rcu_callback_t func, - struct rcu_ctrlblk *rcp); +/* Global control variables for rcupdate callback mechanism. */ +struct rcu_ctrlblk { + struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */ + struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ + struct rcu_head **curtail; /* ->next pointer of last CB. */ +}; + +/* Definition for rcupdate control block. */ +static struct rcu_ctrlblk rcu_sched_ctrlblk = { + .donetail = &rcu_sched_ctrlblk.rcucblist, + .curtail = &rcu_sched_ctrlblk.rcucblist, +}; + +static struct rcu_ctrlblk rcu_bh_ctrlblk = { + .donetail = &rcu_bh_ctrlblk.rcucblist, + .curtail = &rcu_bh_ctrlblk.rcucblist, +}; #include "tiny_plugin.h" @@ -59,19 +70,6 @@ void rcu_barrier_sched(void) } EXPORT_SYMBOL(rcu_barrier_sched); -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) - -/* - * Test whether RCU thinks that the current CPU is idle. - */ -bool notrace __rcu_is_watching(void) -{ - return true; -} -EXPORT_SYMBOL(__rcu_is_watching); - -#endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ - /* * Helper function for rcu_sched_qs() and rcu_bh_qs(). * Also irqs are disabled to avoid confusion due to interrupt handlers @@ -79,7 +77,6 @@ EXPORT_SYMBOL(__rcu_is_watching); */ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) { - RCU_TRACE(reset_cpu_stall_ticks(rcp);) if (rcp->donetail != rcp->curtail) { rcp->donetail = rcp->curtail; return 1; @@ -125,7 +122,6 @@ void rcu_bh_qs(void) */ void rcu_check_callbacks(int user) { - RCU_TRACE(check_cpu_stalls();) if (user) rcu_sched_qs(); else if (!in_softirq()) @@ -140,10 +136,8 @@ void rcu_check_callbacks(int user) */ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) { - const char *rn = NULL; struct rcu_head *next, *list; unsigned long flags; - RCU_TRACE(int cb_count = 0;) /* Move the ready-to-invoke callbacks to a local list. */ local_irq_save(flags); @@ -152,7 +146,6 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) local_irq_restore(flags); return; } - RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1);) list = rcp->rcucblist; rcp->rcucblist = *rcp->donetail; *rcp->donetail = NULL; @@ -162,22 +155,15 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) local_irq_restore(flags); /* Invoke the callbacks on the local list. */ - RCU_TRACE(rn = rcp->name;) while (list) { next = list->next; prefetch(next); debug_rcu_head_unqueue(list); local_bh_disable(); - __rcu_reclaim(rn, list); + __rcu_reclaim("", list); local_bh_enable(); list = next; - RCU_TRACE(cb_count++;) } - RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count);) - RCU_TRACE(trace_rcu_batch_end(rcp->name, - cb_count, 0, need_resched(), - is_idle_task(current), - false)); } static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) @@ -221,7 +207,6 @@ static void __call_rcu(struct rcu_head *head, local_irq_save(flags); *rcp->curtail = head; rcp->curtail = &head->next; - RCU_TRACE(rcp->qlen++;) local_irq_restore(flags); if (unlikely(is_idle_task(current))) { @@ -254,8 +239,5 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); void __init rcu_init(void) { open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); - RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk);) - RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk);) - rcu_early_boot_tests(); } diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h index 371034e77f87..f0a01b2a3062 100644 --- a/kernel/rcu/tiny_plugin.h +++ b/kernel/rcu/tiny_plugin.h @@ -22,36 +22,6 @@ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ -#include <linux/kthread.h> -#include <linux/init.h> -#include <linux/debugfs.h> -#include <linux/seq_file.h> - -/* Global control variables for rcupdate callback mechanism. */ -struct rcu_ctrlblk { - struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */ - struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ - struct rcu_head **curtail; /* ->next pointer of last CB. */ - RCU_TRACE(long qlen); /* Number of pending CBs. */ - RCU_TRACE(unsigned long gp_start); /* Start time for stalls. */ - RCU_TRACE(unsigned long ticks_this_gp); /* Statistic for stalls. */ - RCU_TRACE(unsigned long jiffies_stall); /* Jiffies at next stall. */ - RCU_TRACE(const char *name); /* Name of RCU type. */ -}; - -/* Definition for rcupdate control block. */ -static struct rcu_ctrlblk rcu_sched_ctrlblk = { - .donetail = &rcu_sched_ctrlblk.rcucblist, - .curtail = &rcu_sched_ctrlblk.rcucblist, - RCU_TRACE(.name = "rcu_sched") -}; - -static struct rcu_ctrlblk rcu_bh_ctrlblk = { - .donetail = &rcu_bh_ctrlblk.rcucblist, - .curtail = &rcu_bh_ctrlblk.rcucblist, - RCU_TRACE(.name = "rcu_bh") -}; - #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) #include <linux/kernel_stat.h> @@ -75,96 +45,3 @@ void __init rcu_scheduler_starting(void) } #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ - -#ifdef CONFIG_RCU_TRACE - -static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n) -{ - unsigned long flags; - - local_irq_save(flags); - rcp->qlen -= n; - local_irq_restore(flags); -} - -/* - * Dump statistics for TINY_RCU, such as they are. - */ -static int show_tiny_stats(struct seq_file *m, void *unused) -{ - seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen); - seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen); - return 0; -} - -static int show_tiny_stats_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_tiny_stats, NULL); -} - -static const struct file_operations show_tiny_stats_fops = { - .owner = THIS_MODULE, - .open = show_tiny_stats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static struct dentry *rcudir; - -static int __init rcutiny_trace_init(void) -{ - struct dentry *retval; - - rcudir = debugfs_create_dir("rcu", NULL); - if (!rcudir) - goto free_out; - retval = debugfs_create_file("rcudata", 0444, rcudir, - NULL, &show_tiny_stats_fops); - if (!retval) - goto free_out; - return 0; -free_out: - debugfs_remove_recursive(rcudir); - return 1; -} -device_initcall(rcutiny_trace_init); - -static void check_cpu_stall(struct rcu_ctrlblk *rcp) -{ - unsigned long j; - unsigned long js; - - if (rcu_cpu_stall_suppress) - return; - rcp->ticks_this_gp++; - j = jiffies; - js = READ_ONCE(rcp->jiffies_stall); - if (rcp->rcucblist && ULONG_CMP_GE(j, js)) { - pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n", - rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE, - jiffies - rcp->gp_start, rcp->qlen); - dump_stack(); - WRITE_ONCE(rcp->jiffies_stall, - jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - } else if (ULONG_CMP_GE(j, js)) { - WRITE_ONCE(rcp->jiffies_stall, - jiffies + rcu_jiffies_till_stall_check()); - } -} - -static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp) -{ - rcp->ticks_this_gp = 0; - rcp->gp_start = jiffies; - WRITE_ONCE(rcp->jiffies_stall, - jiffies + rcu_jiffies_till_stall_check()); -} - -static void check_cpu_stalls(void) -{ - RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk);) - RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk);) -} - -#endif /* #ifdef CONFIG_RCU_TRACE */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e354e475e645..51d4c3acf32d 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -168,35 +168,17 @@ static void rcu_report_exp_rdp(struct rcu_state *rsp, static void sync_sched_exp_online_cleanup(int cpu); /* rcuc/rcub kthread realtime priority */ -#ifdef CONFIG_RCU_KTHREAD_PRIO -static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO; -#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */ static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0; -#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */ module_param(kthread_prio, int, 0644); /* Delay in jiffies for grace-period initialization delays, debug only. */ -#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT -static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY; -module_param(gp_preinit_delay, int, 0644); -#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */ -static const int gp_preinit_delay; -#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */ - -#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT -static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY; -module_param(gp_init_delay, int, 0644); -#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ -static const int gp_init_delay; -#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ - -#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP -static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY; -module_param(gp_cleanup_delay, int, 0644); -#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */ -static const int gp_cleanup_delay; -#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */ +static int gp_preinit_delay; +module_param(gp_preinit_delay, int, 0444); +static int gp_init_delay; +module_param(gp_init_delay, int, 0444); +static int gp_cleanup_delay; +module_param(gp_cleanup_delay, int, 0444); /* * Number of grace periods between delays, normalized by the duration of @@ -250,6 +232,7 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) */ void rcu_sched_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_sched_qs() invoked with preemption enabled!!!"); if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) return; trace_rcu_grace_period(TPS("rcu_sched"), @@ -265,6 +248,7 @@ void rcu_sched_qs(void) void rcu_bh_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_bh"), __this_cpu_read(rcu_bh_data.gpnum), @@ -286,10 +270,6 @@ void rcu_bh_qs(void) static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - .dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE, - .dynticks_idle = ATOMIC_INIT(1), -#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ }; /* @@ -478,7 +458,7 @@ void rcu_note_context_switch(bool preempt) barrier(); /* Avoid RCU read-side critical sections leaking down. */ trace_rcu_utilization(TPS("Start context switch")); rcu_sched_qs(); - rcu_preempt_note_context_switch(); + rcu_preempt_note_context_switch(preempt); /* Load rcu_urgent_qs before other flags. */ if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) goto out; @@ -534,9 +514,12 @@ void rcu_all_qs(void) } EXPORT_SYMBOL_GPL(rcu_all_qs); -static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ -static long qhimark = 10000; /* If this many pending, ignore blimit. */ -static long qlowmark = 100; /* Once only this many pending, use blimit. */ +#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch. */ +static long blimit = DEFAULT_RCU_BLIMIT; +#define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */ +static long qhimark = DEFAULT_RCU_QHIMARK; +#define DEFAULT_RCU_QLOMARK 100 /* Once only this many pending, use blimit. */ +static long qlowmark = DEFAULT_RCU_QLOMARK; module_param(blimit, long, 0444); module_param(qhimark, long, 0444); @@ -559,10 +542,7 @@ module_param(jiffies_till_sched_qs, ulong, 0644); static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); -static void force_qs_rnp(struct rcu_state *rsp, - int (*f)(struct rcu_data *rsp, bool *isidle, - unsigned long *maxj), - bool *isidle, unsigned long *maxj); +static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)); static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(void); @@ -757,6 +737,7 @@ static int rcu_future_needs_gp(struct rcu_state *rsp) int idx = (READ_ONCE(rnp->completed) + 1) & 0x1; int *fp = &rnp->need_future_gp[idx]; + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_future_needs_gp() invoked with irqs enabled!!!"); return READ_ONCE(*fp); } @@ -768,6 +749,7 @@ static int rcu_future_needs_gp(struct rcu_state *rsp) static bool cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) { + RCU_LOCKDEP_WARN(!irqs_disabled(), "cpu_needs_another_gp() invoked with irqs enabled!!!"); if (rcu_gp_in_progress(rsp)) return false; /* No, a grace period is already in progress. */ if (rcu_future_needs_gp(rsp)) @@ -794,6 +776,7 @@ static void rcu_eqs_enter_common(bool user) struct rcu_data *rdp; struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_enter_common() invoked with irqs enabled!!!"); trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0); if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)) { @@ -864,7 +847,6 @@ void rcu_idle_enter(void) local_irq_save(flags); rcu_eqs_enter(false); - rcu_sysidle_enter(0); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_idle_enter); @@ -914,7 +896,6 @@ void rcu_irq_exit(void) trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nesting, rdtp->dynticks_nesting - 1); rdtp->dynticks_nesting--; } - rcu_sysidle_enter(1); } /* @@ -967,6 +948,7 @@ static void rcu_eqs_exit(bool user) struct rcu_dynticks *rdtp; long long oldval; + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); @@ -995,7 +977,6 @@ void rcu_idle_exit(void) local_irq_save(flags); rcu_eqs_exit(false); - rcu_sysidle_exit(0); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_idle_exit); @@ -1047,7 +1028,6 @@ void rcu_irq_enter(void) trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting); else rcu_eqs_exit_common(oldval, true); - rcu_sysidle_exit(1); } /* @@ -1130,22 +1110,11 @@ void rcu_nmi_exit(void) } /** - * __rcu_is_watching - are RCU read-side critical sections safe? - * - * Return true if RCU is watching the running CPU, which means that - * this CPU can safely enter RCU read-side critical sections. Unlike - * rcu_is_watching(), the caller of __rcu_is_watching() must have at - * least disabled preemption. - */ -bool notrace __rcu_is_watching(void) -{ - return !rcu_dynticks_curr_cpu_in_eqs(); -} - -/** * rcu_is_watching - see if RCU thinks that the current CPU is idle * - * If the current CPU is in its idle loop and is neither in an interrupt + * Return true if RCU is watching the running CPU, which means that this + * CPU can safely enter RCU read-side critical sections. In other words, + * if the current CPU is in its idle loop and is neither in an interrupt * or NMI handler, return true. */ bool notrace rcu_is_watching(void) @@ -1153,7 +1122,7 @@ bool notrace rcu_is_watching(void) bool ret; preempt_disable_notrace(); - ret = __rcu_is_watching(); + ret = !rcu_dynticks_curr_cpu_in_eqs(); preempt_enable_notrace(); return ret; } @@ -1237,11 +1206,9 @@ static int rcu_is_cpu_rrupt_from_idle(void) * credit them with an implicit quiescent state. Return 1 if this CPU * is in dynticks idle mode, which is an extended quiescent state. */ -static int dyntick_save_progress_counter(struct rcu_data *rdp, - bool *isidle, unsigned long *maxj) +static int dyntick_save_progress_counter(struct rcu_data *rdp) { rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); - rcu_sysidle_check_cpu(rdp, isidle, maxj); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, @@ -1258,8 +1225,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, * idle state since the last call to dyntick_save_progress_counter() * for this same CPU, or by virtue of having been offline. */ -static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, - bool *isidle, unsigned long *maxj) +static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { unsigned long jtsq; bool *rnhqp; @@ -1674,6 +1640,8 @@ void rcu_cpu_stall_reset(void) static unsigned long rcu_cbs_completed(struct rcu_state *rsp, struct rcu_node *rnp) { + lockdep_assert_held(&rnp->lock); + /* * If RCU is idle, we just wait for the next grace period. * But we can only be sure that RCU is idle if we are looking @@ -1719,6 +1687,8 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, bool ret = false; struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); + lockdep_assert_held(&rnp->lock); + /* * Pick up grace-period number for new callbacks. If this * grace period is already marked as needed, return to the caller. @@ -1845,6 +1815,8 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, { bool ret = false; + lockdep_assert_held(&rnp->lock); + /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ if (!rcu_segcblist_pend_cbs(&rdp->cblist)) return false; @@ -1883,6 +1855,8 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { + lockdep_assert_held(&rnp->lock); + /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ if (!rcu_segcblist_pend_cbs(&rdp->cblist)) return false; @@ -1909,6 +1883,8 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, bool ret; bool need_gp; + lockdep_assert_held(&rnp->lock); + /* Handle the ends of any preceding grace periods first. */ if (rdp->completed == rnp->completed && !unlikely(READ_ONCE(rdp->gpwrap))) { @@ -2115,25 +2091,16 @@ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) */ static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time) { - bool isidle = false; - unsigned long maxj; struct rcu_node *rnp = rcu_get_root(rsp); WRITE_ONCE(rsp->gp_activity, jiffies); rsp->n_force_qs++; if (first_time) { /* Collect dyntick-idle snapshots. */ - if (is_sysidle_rcu_state(rsp)) { - isidle = true; - maxj = jiffies - ULONG_MAX / 4; - } - force_qs_rnp(rsp, dyntick_save_progress_counter, - &isidle, &maxj); - rcu_sysidle_report_gp(rsp, isidle, maxj); + force_qs_rnp(rsp, dyntick_save_progress_counter); } else { /* Handle dyntick-idle and offline CPUs. */ - isidle = true; - force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj); + force_qs_rnp(rsp, rcu_implicit_dynticks_qs); } /* Clear flag to prevent immediate re-entry. */ if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { @@ -2341,6 +2308,7 @@ static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { + lockdep_assert_held(&rnp->lock); if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) { /* * Either we have not yet spawned the grace-period @@ -2402,6 +2370,7 @@ static bool rcu_start_gp(struct rcu_state *rsp) static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { + lockdep_assert_held(&rcu_get_root(rsp)->lock); WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); @@ -2426,6 +2395,8 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, unsigned long oldmask = 0; struct rcu_node *rnp_c; + lockdep_assert_held(&rnp->lock); + /* Walk up the rcu_node hierarchy. */ for (;;) { if (!(rnp->qsmask & mask) || rnp->gpnum != gps) { @@ -2486,6 +2457,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, unsigned long mask; struct rcu_node *rnp_p; + lockdep_assert_held(&rnp->lock); if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2599,6 +2571,8 @@ static void rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { + lockdep_assert_held(&rsp->orphan_lock); + /* No-CBs CPUs do not have orphanable callbacks. */ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu)) return; @@ -2639,6 +2613,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags) { struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + lockdep_assert_held(&rsp->orphan_lock); + /* No-CBs CPUs are handled specially. */ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags)) @@ -2705,6 +2681,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; + lockdep_assert_held(&rnp->lock); if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) return; @@ -2895,10 +2872,7 @@ void rcu_check_callbacks(int user) * * The caller must have suppressed start of new grace periods. */ -static void force_qs_rnp(struct rcu_state *rsp, - int (*f)(struct rcu_data *rsp, bool *isidle, - unsigned long *maxj), - bool *isidle, unsigned long *maxj) +static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) { int cpu; unsigned long flags; @@ -2937,7 +2911,7 @@ static void force_qs_rnp(struct rcu_state *rsp, for_each_leaf_node_possible_cpu(rnp, cpu) { unsigned long bit = leaf_node_cpu_bit(rnp, cpu); if ((rnp->qsmask & bit) != 0) { - if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) + if (f(per_cpu_ptr(rsp->rda, cpu))) mask |= bit; } } @@ -3143,9 +3117,14 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1)); if (debug_rcu_head_queue(head)) { - /* Probable double call_rcu(), so leak the callback. */ + /* + * Probable double call_rcu(), so leak the callback. + * Use rcu:rcu_callback trace event to find the previous + * time callback was passed to __call_rcu(). + */ + WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pF()!!!\n", + head, head->func); WRITE_ONCE(head->func, rcu_leak_callback); - WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n"); return; } head->func = func; @@ -3194,8 +3173,24 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, local_irq_restore(flags); } -/* - * Queue an RCU-sched callback for invocation after a grace period. +/** + * call_rcu_sched() - Queue an RCU for invocation after sched grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_sched() assumes + * that the read-side critical sections end on enabling of preemption + * or on voluntary preemption. + * RCU read-side critical sections are delimited by : + * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR + * - anything that disables preemption. + * + * These may be nested. + * + * See the description of call_rcu() for more detailed information on + * memory ordering guarantees. */ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) { @@ -3203,8 +3198,26 @@ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) } EXPORT_SYMBOL_GPL(call_rcu_sched); -/* - * Queue an RCU callback for invocation after a quicker grace period. +/** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_bh() assumes + * that the read-side critical sections end on completion of a softirq + * handler. This means that read-side critical sections in process + * context must not be interrupted by softirqs. This interface is to be + * used when most of the read-side critical sections are in softirq context. + * RCU read-side critical sections are delimited by : + * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. + * OR + * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. + * These may be nested. + * + * See the description of call_rcu() for more detailed information on + * memory ordering guarantees. */ void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) { @@ -3280,12 +3293,6 @@ static inline int rcu_blocking_is_gp(void) * to have executed a full memory barrier during the execution of * synchronize_sched() -- even if CPU A and CPU B are the same CPU (but * again only if the system has more than one CPU). - * - * This primitive provides the guarantees made by the (now removed) - * synchronize_kernel() API. In contrast, synchronize_rcu() only - * guarantees that rcu_read_lock() sections will have completed. - * In "classic RCU", these two guarantees happen to be one and - * the same, but can differ in realtime RCU implementations. */ void synchronize_sched(void) { @@ -3578,8 +3585,14 @@ static void rcu_barrier_func(void *type) struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); _rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence); - atomic_inc(&rsp->barrier_cpu_count); - rsp->call(&rdp->barrier_head, rcu_barrier_callback); + rdp->barrier_head.func = rcu_barrier_callback; + debug_rcu_head_queue(&rdp->barrier_head); + if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) { + atomic_inc(&rsp->barrier_cpu_count); + } else { + debug_rcu_head_unqueue(&rdp->barrier_head); + _rcu_barrier_trace(rsp, "IRQNQ", -1, rsp->barrier_sequence); + } } /* @@ -3698,6 +3711,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; + lockdep_assert_held(&rnp->lock); for (;;) { mask = rnp->grpmask; rnp = rnp->parent; @@ -3753,7 +3767,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) !init_nocb_callback_list(rdp)) rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; - rcu_sysidle_init_percpu_data(rdp->dynticks); rcu_dynticks_eqs_online(); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index ba38262c3554..9af0f31d6847 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -45,14 +45,6 @@ struct rcu_dynticks { bool rcu_need_heavy_qs; /* GP old, need heavy quiescent state. */ unsigned long rcu_qs_ctr; /* Light universal quiescent state ctr. */ bool rcu_urgent_qs; /* GP old need light quiescent state. */ -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - long long dynticks_idle_nesting; - /* irq/process nesting level from idle. */ - atomic_t dynticks_idle; /* Even value for idle, else odd. */ - /* "Idle" excludes userspace execution. */ - unsigned long dynticks_idle_jiffies; - /* End of last non-NMI non-idle period. */ -#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ #ifdef CONFIG_RCU_FAST_NO_HZ bool all_lazy; /* Are all CPU's CBs lazy? */ unsigned long nonlazy_posted; @@ -160,19 +152,6 @@ struct rcu_node { /* Number of tasks boosted for expedited GP. */ unsigned long n_normal_boosts; /* Number of tasks boosted for normal GP. */ - unsigned long n_balk_blkd_tasks; - /* Refused to boost: no blocked tasks. */ - unsigned long n_balk_exp_gp_tasks; - /* Refused to boost: nothing blocking GP. */ - unsigned long n_balk_boost_tasks; - /* Refused to boost: already boosting. */ - unsigned long n_balk_notblocked; - /* Refused to boost: RCU RS CS still running. */ - unsigned long n_balk_notyet; - /* Refused to boost: not yet time. */ - unsigned long n_balk_nos; - /* Refused to boost: not sure why, though. */ - /* This can happen due to race conditions. */ #ifdef CONFIG_RCU_NOCB_CPU struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ @@ -312,9 +291,9 @@ struct rcu_data { }; /* Values for nocb_defer_wakeup field in struct rcu_data. */ -#define RCU_NOGP_WAKE_NOT 0 -#define RCU_NOGP_WAKE 1 -#define RCU_NOGP_WAKE_FORCE 2 +#define RCU_NOCB_WAKE_NOT 0 +#define RCU_NOCB_WAKE 1 +#define RCU_NOCB_WAKE_FORCE 2 #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500)) /* For jiffies_till_first_fqs and */ @@ -477,7 +456,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work); /* Forward declarations for rcutree_plugin.h */ static void rcu_bootup_announce(void); -static void rcu_preempt_note_context_switch(void); +static void rcu_preempt_note_context_switch(bool preempt); static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static bool rcu_preempt_has_tasks(struct rcu_node *rnp); @@ -529,15 +508,7 @@ static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp); #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ static void __maybe_unused rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); -static void rcu_sysidle_enter(int irq); -static void rcu_sysidle_exit(int irq); -static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, - unsigned long *maxj); -static bool is_sysidle_rcu_state(struct rcu_state *rsp); -static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, - unsigned long maxj); static void rcu_bind_gp_kthread(void); -static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp); static bool rcu_nohz_full_cpu(struct rcu_state *rsp); static void rcu_dynticks_task_enter(void); static void rcu_dynticks_task_exit(void); @@ -551,75 +522,3 @@ void srcu_offline_cpu(unsigned int cpu) { } #endif /* #else #ifdef CONFIG_SRCU */ #endif /* #ifndef RCU_TREE_NONCORE */ - -#ifdef CONFIG_RCU_TRACE -/* Read out queue lengths for tracing. */ -static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) -{ -#ifdef CONFIG_RCU_NOCB_CPU - *ql = atomic_long_read(&rdp->nocb_q_count); - *qll = atomic_long_read(&rdp->nocb_q_count_lazy); -#else /* #ifdef CONFIG_RCU_NOCB_CPU */ - *ql = 0; - *qll = 0; -#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ -} -#endif /* #ifdef CONFIG_RCU_TRACE */ - -/* - * Wrappers for the rcu_node::lock acquire and release. - * - * Because the rcu_nodes form a tree, the tree traversal locking will observe - * different lock values, this in turn means that an UNLOCK of one level - * followed by a LOCK of another level does not imply a full memory barrier; - * and most importantly transitivity is lost. - * - * In order to restore full ordering between tree levels, augment the regular - * lock acquire functions with smp_mb__after_unlock_lock(). - * - * As ->lock of struct rcu_node is a __private field, therefore one should use - * these wrappers rather than directly call raw_spin_{lock,unlock}* on ->lock. - */ -static inline void raw_spin_lock_rcu_node(struct rcu_node *rnp) -{ - raw_spin_lock(&ACCESS_PRIVATE(rnp, lock)); - smp_mb__after_unlock_lock(); -} - -static inline void raw_spin_unlock_rcu_node(struct rcu_node *rnp) -{ - raw_spin_unlock(&ACCESS_PRIVATE(rnp, lock)); -} - -static inline void raw_spin_lock_irq_rcu_node(struct rcu_node *rnp) -{ - raw_spin_lock_irq(&ACCESS_PRIVATE(rnp, lock)); - smp_mb__after_unlock_lock(); -} - -static inline void raw_spin_unlock_irq_rcu_node(struct rcu_node *rnp) -{ - raw_spin_unlock_irq(&ACCESS_PRIVATE(rnp, lock)); -} - -#define raw_spin_lock_irqsave_rcu_node(rnp, flags) \ -do { \ - typecheck(unsigned long, flags); \ - raw_spin_lock_irqsave(&ACCESS_PRIVATE(rnp, lock), flags); \ - smp_mb__after_unlock_lock(); \ -} while (0) - -#define raw_spin_unlock_irqrestore_rcu_node(rnp, flags) \ -do { \ - typecheck(unsigned long, flags); \ - raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(rnp, lock), flags); \ -} while (0) - -static inline bool raw_spin_trylock_rcu_node(struct rcu_node *rnp) -{ - bool locked = raw_spin_trylock(&ACCESS_PRIVATE(rnp, lock)); - - if (locked) - smp_mb__after_unlock_lock(); - return locked; -} diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index e513b4ab1197..dd21ca47e4b4 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -147,7 +147,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) * * Caller must hold the rcu_state's exp_mutex. */ -static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) +static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp) { return rnp->exp_tasks == NULL && READ_ONCE(rnp->expmask) == 0; diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index c9a48657512a..908b309d60d7 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -70,7 +70,7 @@ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ static void __init rcu_bootup_announce_oddness(void) { if (IS_ENABLED(CONFIG_RCU_TRACE)) - pr_info("\tRCU debugfs-based tracing is enabled.\n"); + pr_info("\tRCU event tracing is enabled.\n"); if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) || (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32)) pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", @@ -90,8 +90,32 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); - if (IS_ENABLED(CONFIG_RCU_BOOST)) - pr_info("\tRCU kthread priority: %d.\n", kthread_prio); +#ifdef CONFIG_RCU_BOOST + pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY); +#endif + if (blimit != DEFAULT_RCU_BLIMIT) + pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit); + if (qhimark != DEFAULT_RCU_QHIMARK) + pr_info("\tBoot-time adjustment of callback high-water mark to %ld.\n", qhimark); + if (qlowmark != DEFAULT_RCU_QLOMARK) + pr_info("\tBoot-time adjustment of callback low-water mark to %ld.\n", qlowmark); + if (jiffies_till_first_fqs != ULONG_MAX) + pr_info("\tBoot-time adjustment of first FQS scan delay to %ld jiffies.\n", jiffies_till_first_fqs); + if (jiffies_till_next_fqs != ULONG_MAX) + pr_info("\tBoot-time adjustment of subsequent FQS scan delay to %ld jiffies.\n", jiffies_till_next_fqs); + if (rcu_kick_kthreads) + pr_info("\tKick kthreads if too-long grace period.\n"); + if (IS_ENABLED(CONFIG_DEBUG_OBJECTS_RCU_HEAD)) + pr_info("\tRCU callback double-/use-after-free debug enabled.\n"); + if (gp_preinit_delay) + pr_info("\tRCU debug GP pre-init slowdown %d jiffies.\n", gp_preinit_delay); + if (gp_init_delay) + pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_init_delay); + if (gp_cleanup_delay) + pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_cleanup_delay); + if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG)) + pr_info("\tRCU debug extended QS entry/exit.\n"); + rcupdate_announce_bootup_oddness(); } #ifdef CONFIG_PREEMPT_RCU @@ -155,6 +179,8 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0); struct task_struct *t = current; + lockdep_assert_held(&rnp->lock); + /* * Decide where to queue the newly blocked task. In theory, * this could be an if-statement. In practice, when I tried @@ -263,6 +289,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) */ static void rcu_preempt_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n"); if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data_p->gpnum), @@ -286,12 +313,14 @@ static void rcu_preempt_qs(void) * * Caller must disable interrupts. */ -static void rcu_preempt_note_context_switch(void) +static void rcu_preempt_note_context_switch(bool preempt) { struct task_struct *t = current; struct rcu_data *rdp; struct rcu_node *rnp; + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_preempt_note_context_switch() invoked with interrupts enabled!!!\n"); + WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); if (t->rcu_read_lock_nesting > 0 && !t->rcu_read_unlock_special.b.blocked) { @@ -607,6 +636,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) */ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n"); WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); if (rcu_preempt_has_tasks(rnp)) rnp->gp_tasks = rnp->blkd_tasks.next; @@ -643,8 +673,37 @@ static void rcu_preempt_do_callbacks(void) #endif /* #ifdef CONFIG_RCU_BOOST */ -/* - * Queue a preemptible-RCU callback for invocation after a grace period. +/** + * call_rcu() - Queue an RCU callback for invocation after a grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. However, the callback function + * might well execute concurrently with RCU read-side critical sections + * that started after call_rcu() was invoked. RCU read-side critical + * sections are delimited by rcu_read_lock() and rcu_read_unlock(), + * and may be nested. + * + * Note that all CPUs must agree that the grace period extended beyond + * all pre-existing RCU read-side critical section. On systems with more + * than one CPU, this means that when "func()" is invoked, each CPU is + * guaranteed to have executed a full memory barrier since the end of its + * last RCU read-side critical section whose beginning preceded the call + * to call_rcu(). It also means that each CPU executing an RCU read-side + * critical section that continues beyond the start of "func()" must have + * executed a memory barrier after the call_rcu() but before the beginning + * of that RCU read-side critical section. Note that these guarantees + * include CPUs that are offline, idle, or executing in user mode, as + * well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * resulting RCU callback function "func()", then both CPU A and CPU B are + * guaranteed to execute a full memory barrier during the time interval + * between the call to call_rcu() and the invocation of "func()" -- even + * if CPU A and CPU B are the same CPU (but again only if the system has + * more than one CPU). */ void call_rcu(struct rcu_head *head, rcu_callback_t func) { @@ -663,8 +722,13 @@ EXPORT_SYMBOL_GPL(call_rcu); * synchronize_rcu() was waiting. RCU read-side critical sections are * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested. * - * See the description of synchronize_sched() for more detailed information - * on memory ordering guarantees. + * See the description of synchronize_sched() for more detailed + * information on memory-ordering guarantees. However, please note + * that -only- the memory-ordering guarantees apply. For example, + * synchronize_rcu() is -not- guaranteed to wait on things like code + * protected by preempt_disable(), instead, synchronize_rcu() is -only- + * guaranteed to wait on RCU read-side critical sections, that is, sections + * of code protected by rcu_read_lock(). */ void synchronize_rcu(void) { @@ -738,7 +802,7 @@ static void __init rcu_bootup_announce(void) * Because preemptible RCU does not exist, we never have to check for * CPUs being in quiescent states. */ -static void rcu_preempt_note_context_switch(void) +static void rcu_preempt_note_context_switch(bool preempt) { } @@ -835,33 +899,6 @@ void exit_rcu(void) #include "../locking/rtmutex_common.h" -#ifdef CONFIG_RCU_TRACE - -static void rcu_initiate_boost_trace(struct rcu_node *rnp) -{ - if (!rcu_preempt_has_tasks(rnp)) - rnp->n_balk_blkd_tasks++; - else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL) - rnp->n_balk_exp_gp_tasks++; - else if (rnp->gp_tasks != NULL && rnp->boost_tasks != NULL) - rnp->n_balk_boost_tasks++; - else if (rnp->gp_tasks != NULL && rnp->qsmask != 0) - rnp->n_balk_notblocked++; - else if (rnp->gp_tasks != NULL && - ULONG_CMP_LT(jiffies, rnp->boost_time)) - rnp->n_balk_notyet++; - else - rnp->n_balk_nos++; -} - -#else /* #ifdef CONFIG_RCU_TRACE */ - -static void rcu_initiate_boost_trace(struct rcu_node *rnp) -{ -} - -#endif /* #else #ifdef CONFIG_RCU_TRACE */ - static void rcu_wake_cond(struct task_struct *t, int status) { /* @@ -992,8 +1029,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) { struct task_struct *t; + lockdep_assert_held(&rnp->lock); if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { - rnp->n_balk_exp_gp_tasks++; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } @@ -1009,7 +1046,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) if (t) rcu_wake_cond(t, rnp->boost_kthread_status); } else { - rcu_initiate_boost_trace(rnp); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -1260,8 +1296,7 @@ static void rcu_prepare_kthreads(int cpu) int rcu_needs_cpu(u64 basemono, u64 *nextevt) { *nextevt = KTIME_MAX; - return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) - ? 0 : rcu_cpu_has_callbacks(NULL); + return rcu_cpu_has_callbacks(NULL); } /* @@ -1372,10 +1407,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); unsigned long dj; - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) { - *nextevt = KTIME_MAX; - return 0; - } + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_needs_cpu() invoked with irqs enabled!!!"); /* Snapshot to detect later posting of non-lazy callback. */ rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted; @@ -1424,8 +1456,8 @@ static void rcu_prepare_for_idle(void) struct rcu_state *rsp; int tne; - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) || - rcu_is_nocb_cpu(smp_processor_id())) + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_prepare_for_idle() invoked with irqs enabled!!!"); + if (rcu_is_nocb_cpu(smp_processor_id())) return; /* Handle nohz enablement switches conservatively. */ @@ -1479,8 +1511,8 @@ static void rcu_prepare_for_idle(void) */ static void rcu_cleanup_after_idle(void) { - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) || - rcu_is_nocb_cpu(smp_processor_id())) + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_cleanup_after_idle() invoked with irqs enabled!!!"); + if (rcu_is_nocb_cpu(smp_processor_id())) return; if (rcu_try_advance_all_cbs()) invoke_rcu_core(); @@ -1747,7 +1779,6 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) init_swait_queue_head(&rnp->nocb_gp_wq[1]); } -#ifndef CONFIG_RCU_NOCB_CPU_ALL /* Is the specified CPU a no-CBs CPU? */ bool rcu_is_nocb_cpu(int cpu) { @@ -1755,7 +1786,6 @@ bool rcu_is_nocb_cpu(int cpu) return cpumask_test_cpu(cpu, rcu_nocb_mask); return false; } -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ /* * Kick the leader kthread for this NOCB group. @@ -1769,6 +1799,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { /* Prior smp_mb__after_atomic() orders against prior enqueue. */ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); + smp_mb(); /* ->nocb_leader_sleep before swake_up(). */ swake_up(&rdp_leader->nocb_wq); } } @@ -1860,7 +1891,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty")); } else { - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE); + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE); /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, @@ -1874,7 +1905,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf")); } else { - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_FORCE); + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_FORCE); /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, @@ -2023,6 +2054,7 @@ wait_again: * nocb_gp_head, where they await a grace period. */ gotcbs = false; + smp_mb(); /* wakeup before ->nocb_head reads. */ for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head); if (!rdp->nocb_gp_head) @@ -2201,8 +2233,8 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) if (!rcu_nocb_need_deferred_wakeup(rdp)) return; ndw = READ_ONCE(rdp->nocb_defer_wakeup); - WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_NOT); - wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE); + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); + wake_nocb_leader(rdp, ndw == RCU_NOCB_WAKE_FORCE); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake")); } @@ -2212,10 +2244,6 @@ void __init rcu_init_nohz(void) bool need_rcu_nocb_mask = true; struct rcu_state *rsp; -#ifdef CONFIG_RCU_NOCB_CPU_NONE - need_rcu_nocb_mask = false; -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ - #if defined(CONFIG_NO_HZ_FULL) if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) need_rcu_nocb_mask = true; @@ -2231,14 +2259,6 @@ void __init rcu_init_nohz(void) if (!have_rcu_nocb_mask) return; -#ifdef CONFIG_RCU_NOCB_CPU_ZERO - pr_info("\tOffload RCU callbacks from CPU 0\n"); - cpumask_set_cpu(0, rcu_nocb_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ -#ifdef CONFIG_RCU_NOCB_CPU_ALL - pr_info("\tOffload RCU callbacks from all CPUs\n"); - cpumask_copy(rcu_nocb_mask, cpu_possible_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ #if defined(CONFIG_NO_HZ_FULL) if (tick_nohz_full_running) cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); @@ -2491,421 +2511,6 @@ static void __maybe_unused rcu_kick_nohz_cpu(int cpu) #endif /* #ifdef CONFIG_NO_HZ_FULL */ } - -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - -static int full_sysidle_state; /* Current system-idle state. */ -#define RCU_SYSIDLE_NOT 0 /* Some CPU is not idle. */ -#define RCU_SYSIDLE_SHORT 1 /* All CPUs idle for brief period. */ -#define RCU_SYSIDLE_LONG 2 /* All CPUs idle for long enough. */ -#define RCU_SYSIDLE_FULL 3 /* All CPUs idle, ready for sysidle. */ -#define RCU_SYSIDLE_FULL_NOTED 4 /* Actually entered sysidle state. */ - -/* - * Invoked to note exit from irq or task transition to idle. Note that - * usermode execution does -not- count as idle here! After all, we want - * to detect full-system idle states, not RCU quiescent states and grace - * periods. The caller must have disabled interrupts. - */ -static void rcu_sysidle_enter(int irq) -{ - unsigned long j; - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - /* If there are no nohz_full= CPUs, no need to track this. */ - if (!tick_nohz_full_enabled()) - return; - - /* Adjust nesting, check for fully idle. */ - if (irq) { - rdtp->dynticks_idle_nesting--; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0); - if (rdtp->dynticks_idle_nesting != 0) - return; /* Still not fully idle. */ - } else { - if ((rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) == - DYNTICK_TASK_NEST_VALUE) { - rdtp->dynticks_idle_nesting = 0; - } else { - rdtp->dynticks_idle_nesting -= DYNTICK_TASK_NEST_VALUE; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0); - return; /* Still not fully idle. */ - } - } - - /* Record start of fully idle period. */ - j = jiffies; - WRITE_ONCE(rdtp->dynticks_idle_jiffies, j); - smp_mb__before_atomic(); - atomic_inc(&rdtp->dynticks_idle); - smp_mb__after_atomic(); - WARN_ON_ONCE(atomic_read(&rdtp->dynticks_idle) & 0x1); -} - -/* - * Unconditionally force exit from full system-idle state. This is - * invoked when a normal CPU exits idle, but must be called separately - * for the timekeeping CPU (tick_do_timer_cpu). The reason for this - * is that the timekeeping CPU is permitted to take scheduling-clock - * interrupts while the system is in system-idle state, and of course - * rcu_sysidle_exit() has no way of distinguishing a scheduling-clock - * interrupt from any other type of interrupt. - */ -void rcu_sysidle_force_exit(void) -{ - int oldstate = READ_ONCE(full_sysidle_state); - int newoldstate; - - /* - * Each pass through the following loop attempts to exit full - * system-idle state. If contention proves to be a problem, - * a trylock-based contention tree could be used here. - */ - while (oldstate > RCU_SYSIDLE_SHORT) { - newoldstate = cmpxchg(&full_sysidle_state, - oldstate, RCU_SYSIDLE_NOT); - if (oldstate == newoldstate && - oldstate == RCU_SYSIDLE_FULL_NOTED) { - rcu_kick_nohz_cpu(tick_do_timer_cpu); - return; /* We cleared it, done! */ - } - oldstate = newoldstate; - } - smp_mb(); /* Order initial oldstate fetch vs. later non-idle work. */ -} - -/* - * Invoked to note entry to irq or task transition from idle. Note that - * usermode execution does -not- count as idle here! The caller must - * have disabled interrupts. - */ -static void rcu_sysidle_exit(int irq) -{ - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - /* If there are no nohz_full= CPUs, no need to track this. */ - if (!tick_nohz_full_enabled()) - return; - - /* Adjust nesting, check for already non-idle. */ - if (irq) { - rdtp->dynticks_idle_nesting++; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0); - if (rdtp->dynticks_idle_nesting != 1) - return; /* Already non-idle. */ - } else { - /* - * Allow for irq misnesting. Yes, it really is possible - * to enter an irq handler then never leave it, and maybe - * also vice versa. Handle both possibilities. - */ - if (rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) { - rdtp->dynticks_idle_nesting += DYNTICK_TASK_NEST_VALUE; - WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0); - return; /* Already non-idle. */ - } else { - rdtp->dynticks_idle_nesting = DYNTICK_TASK_EXIT_IDLE; - } - } - - /* Record end of idle period. */ - smp_mb__before_atomic(); - atomic_inc(&rdtp->dynticks_idle); - smp_mb__after_atomic(); - WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks_idle) & 0x1)); - - /* - * If we are the timekeeping CPU, we are permitted to be non-idle - * during a system-idle state. This must be the case, because - * the timekeeping CPU has to take scheduling-clock interrupts - * during the time that the system is transitioning to full - * system-idle state. This means that the timekeeping CPU must - * invoke rcu_sysidle_force_exit() directly if it does anything - * more than take a scheduling-clock interrupt. - */ - if (smp_processor_id() == tick_do_timer_cpu) - return; - - /* Update system-idle state: We are clearly no longer fully idle! */ - rcu_sysidle_force_exit(); -} - -/* - * Check to see if the current CPU is idle. Note that usermode execution - * does not count as idle. The caller must have disabled interrupts, - * and must be running on tick_do_timer_cpu. - */ -static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, - unsigned long *maxj) -{ - int cur; - unsigned long j; - struct rcu_dynticks *rdtp = rdp->dynticks; - - /* If there are no nohz_full= CPUs, don't check system-wide idleness. */ - if (!tick_nohz_full_enabled()) - return; - - /* - * If some other CPU has already reported non-idle, if this is - * not the flavor of RCU that tracks sysidle state, or if this - * is an offline or the timekeeping CPU, nothing to do. - */ - if (!*isidle || rdp->rsp != rcu_state_p || - cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu) - return; - /* Verify affinity of current kthread. */ - WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu); - - /* Pick up current idle and NMI-nesting counter and check. */ - cur = atomic_read(&rdtp->dynticks_idle); - if (cur & 0x1) { - *isidle = false; /* We are not idle! */ - return; - } - smp_mb(); /* Read counters before timestamps. */ - - /* Pick up timestamps. */ - j = READ_ONCE(rdtp->dynticks_idle_jiffies); - /* If this CPU entered idle more recently, update maxj timestamp. */ - if (ULONG_CMP_LT(*maxj, j)) - *maxj = j; -} - -/* - * Is this the flavor of RCU that is handling full-system idle? - */ -static bool is_sysidle_rcu_state(struct rcu_state *rsp) -{ - return rsp == rcu_state_p; -} - -/* - * Return a delay in jiffies based on the number of CPUs, rcu_node - * leaf fanout, and jiffies tick rate. The idea is to allow larger - * systems more time to transition to full-idle state in order to - * avoid the cache thrashing that otherwise occur on the state variable. - * Really small systems (less than a couple of tens of CPUs) should - * instead use a single global atomically incremented counter, and later - * versions of this will automatically reconfigure themselves accordingly. - */ -static unsigned long rcu_sysidle_delay(void) -{ - if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) - return 0; - return DIV_ROUND_UP(nr_cpu_ids * HZ, rcu_fanout_leaf * 1000); -} - -/* - * Advance the full-system-idle state. This is invoked when all of - * the non-timekeeping CPUs are idle. - */ -static void rcu_sysidle(unsigned long j) -{ - /* Check the current state. */ - switch (READ_ONCE(full_sysidle_state)) { - case RCU_SYSIDLE_NOT: - - /* First time all are idle, so note a short idle period. */ - WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_SHORT); - break; - - case RCU_SYSIDLE_SHORT: - - /* - * Idle for a bit, time to advance to next state? - * cmpxchg failure means race with non-idle, let them win. - */ - if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) - (void)cmpxchg(&full_sysidle_state, - RCU_SYSIDLE_SHORT, RCU_SYSIDLE_LONG); - break; - - case RCU_SYSIDLE_LONG: - - /* - * Do an additional check pass before advancing to full. - * cmpxchg failure means race with non-idle, let them win. - */ - if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) - (void)cmpxchg(&full_sysidle_state, - RCU_SYSIDLE_LONG, RCU_SYSIDLE_FULL); - break; - - default: - break; - } -} - -/* - * Found a non-idle non-timekeeping CPU, so kick the system-idle state - * back to the beginning. - */ -static void rcu_sysidle_cancel(void) -{ - smp_mb(); - if (full_sysidle_state > RCU_SYSIDLE_SHORT) - WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_NOT); -} - -/* - * Update the sysidle state based on the results of a force-quiescent-state - * scan of the CPUs' dyntick-idle state. - */ -static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, - unsigned long maxj, bool gpkt) -{ - if (rsp != rcu_state_p) - return; /* Wrong flavor, ignore. */ - if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) - return; /* Running state machine from timekeeping CPU. */ - if (isidle) - rcu_sysidle(maxj); /* More idle! */ - else - rcu_sysidle_cancel(); /* Idle is over. */ -} - -/* - * Wrapper for rcu_sysidle_report() when called from the grace-period - * kthread's context. - */ -static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, - unsigned long maxj) -{ - /* If there are no nohz_full= CPUs, no need to track this. */ - if (!tick_nohz_full_enabled()) - return; - - rcu_sysidle_report(rsp, isidle, maxj, true); -} - -/* Callback and function for forcing an RCU grace period. */ -struct rcu_sysidle_head { - struct rcu_head rh; - int inuse; -}; - -static void rcu_sysidle_cb(struct rcu_head *rhp) -{ - struct rcu_sysidle_head *rshp; - - /* - * The following memory barrier is needed to replace the - * memory barriers that would normally be in the memory - * allocator. - */ - smp_mb(); /* grace period precedes setting inuse. */ - - rshp = container_of(rhp, struct rcu_sysidle_head, rh); - WRITE_ONCE(rshp->inuse, 0); -} - -/* - * Check to see if the system is fully idle, other than the timekeeping CPU. - * The caller must have disabled interrupts. This is not intended to be - * called unless tick_nohz_full_enabled(). - */ -bool rcu_sys_is_idle(void) -{ - static struct rcu_sysidle_head rsh; - int rss = READ_ONCE(full_sysidle_state); - - if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu)) - return false; - - /* Handle small-system case by doing a full scan of CPUs. */ - if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) { - int oldrss = rss - 1; - - /* - * One pass to advance to each state up to _FULL. - * Give up if any pass fails to advance the state. - */ - while (rss < RCU_SYSIDLE_FULL && oldrss < rss) { - int cpu; - bool isidle = true; - unsigned long maxj = jiffies - ULONG_MAX / 4; - struct rcu_data *rdp; - - /* Scan all the CPUs looking for nonidle CPUs. */ - for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rcu_state_p->rda, cpu); - rcu_sysidle_check_cpu(rdp, &isidle, &maxj); - if (!isidle) - break; - } - rcu_sysidle_report(rcu_state_p, isidle, maxj, false); - oldrss = rss; - rss = READ_ONCE(full_sysidle_state); - } - } - - /* If this is the first observation of an idle period, record it. */ - if (rss == RCU_SYSIDLE_FULL) { - rss = cmpxchg(&full_sysidle_state, - RCU_SYSIDLE_FULL, RCU_SYSIDLE_FULL_NOTED); - return rss == RCU_SYSIDLE_FULL; - } - - smp_mb(); /* ensure rss load happens before later caller actions. */ - - /* If already fully idle, tell the caller (in case of races). */ - if (rss == RCU_SYSIDLE_FULL_NOTED) - return true; - - /* - * If we aren't there yet, and a grace period is not in flight, - * initiate a grace period. Either way, tell the caller that - * we are not there yet. We use an xchg() rather than an assignment - * to make up for the memory barriers that would otherwise be - * provided by the memory allocator. - */ - if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL && - !rcu_gp_in_progress(rcu_state_p) && - !rsh.inuse && xchg(&rsh.inuse, 1) == 0) - call_rcu(&rsh.rh, rcu_sysidle_cb); - return false; -} - -/* - * Initialize dynticks sysidle state for CPUs coming online. - */ -static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) -{ - rdtp->dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE; -} - -#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - -static void rcu_sysidle_enter(int irq) -{ -} - -static void rcu_sysidle_exit(int irq) -{ -} - -static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, - unsigned long *maxj) -{ -} - -static bool is_sysidle_rcu_state(struct rcu_state *rsp) -{ - return false; -} - -static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, - unsigned long maxj) -{ -} - -static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) -{ -} - -#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - /* * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the * grace-period kthread will do force_quiescent_state() processing? @@ -2936,13 +2541,7 @@ static void rcu_bind_gp_kthread(void) if (!tick_nohz_full_enabled()) return; -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE - cpu = tick_do_timer_cpu; - if (cpu >= 0 && cpu < nr_cpu_ids) - set_cpus_allowed_ptr(current, cpumask_of(cpu)); -#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ housekeeping_affine(current); -#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ } /* Record the current task on dyntick-idle entry. */ diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c deleted file mode 100644 index 6cea17a1ea30..000000000000 --- a/kernel/rcu/tree_trace.c +++ /dev/null @@ -1,494 +0,0 @@ -/* - * Read-Copy Update tracing for hierarchical implementation. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, you can access it online at - * http://www.gnu.org/licenses/gpl-2.0.html. - * - * Copyright IBM Corporation, 2008 - * Author: Paul E. McKenney - * - * Papers: http://www.rdrop.com/users/paulmck/RCU - * - * For detailed explanation of Read-Copy Update mechanism see - - * Documentation/RCU - * - */ -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/spinlock.h> -#include <linux/smp.h> -#include <linux/rcupdate.h> -#include <linux/interrupt.h> -#include <linux/sched.h> -#include <linux/atomic.h> -#include <linux/bitops.h> -#include <linux/completion.h> -#include <linux/percpu.h> -#include <linux/notifier.h> -#include <linux/cpu.h> -#include <linux/mutex.h> -#include <linux/debugfs.h> -#include <linux/seq_file.h> -#include <linux/prefetch.h> - -#define RCU_TREE_NONCORE -#include "tree.h" -#include "rcu.h" - -static int r_open(struct inode *inode, struct file *file, - const struct seq_operations *op) -{ - int ret = seq_open(file, op); - if (!ret) { - struct seq_file *m = (struct seq_file *)file->private_data; - m->private = inode->i_private; - } - return ret; -} - -static void *r_start(struct seq_file *m, loff_t *pos) -{ - struct rcu_state *rsp = (struct rcu_state *)m->private; - *pos = cpumask_next(*pos - 1, cpu_possible_mask); - if ((*pos) < nr_cpu_ids) - return per_cpu_ptr(rsp->rda, *pos); - return NULL; -} - -static void *r_next(struct seq_file *m, void *v, loff_t *pos) -{ - (*pos)++; - return r_start(m, pos); -} - -static void r_stop(struct seq_file *m, void *v) -{ -} - -static int show_rcubarrier(struct seq_file *m, void *v) -{ - struct rcu_state *rsp = (struct rcu_state *)m->private; - seq_printf(m, "bcc: %d bseq: %lu\n", - atomic_read(&rsp->barrier_cpu_count), - rsp->barrier_sequence); - return 0; -} - -static int rcubarrier_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcubarrier, inode->i_private); -} - -static const struct file_operations rcubarrier_fops = { - .owner = THIS_MODULE, - .open = rcubarrier_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -#ifdef CONFIG_RCU_BOOST - -static char convert_kthread_status(unsigned int kthread_status) -{ - if (kthread_status > RCU_KTHREAD_MAX) - return '?'; - return "SRWOY"[kthread_status]; -} - -#endif /* #ifdef CONFIG_RCU_BOOST */ - -static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) -{ - long ql, qll; - - if (!rdp->beenonline) - return; - seq_printf(m, "%3d%cc=%ld g=%ld cnq=%d/%d:%d", - rdp->cpu, - cpu_is_offline(rdp->cpu) ? '!' : ' ', - ulong2long(rdp->completed), ulong2long(rdp->gpnum), - rdp->cpu_no_qs.b.norm, - rdp->rcu_qs_ctr_snap == per_cpu(rdp->dynticks->rcu_qs_ctr, rdp->cpu), - rdp->core_needs_qs); - seq_printf(m, " dt=%d/%llx/%d df=%lu", - rcu_dynticks_snap(rdp->dynticks), - rdp->dynticks->dynticks_nesting, - rdp->dynticks->dynticks_nmi_nesting, - rdp->dynticks_fqs); - seq_printf(m, " of=%lu", rdp->offline_fqs); - rcu_nocb_q_lengths(rdp, &ql, &qll); - qll += rcu_segcblist_n_lazy_cbs(&rdp->cblist); - ql += rcu_segcblist_n_cbs(&rdp->cblist); - seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c", - qll, ql, - ".N"[!rcu_segcblist_segempty(&rdp->cblist, RCU_NEXT_TAIL)], - ".R"[!rcu_segcblist_segempty(&rdp->cblist, - RCU_NEXT_READY_TAIL)], - ".W"[!rcu_segcblist_segempty(&rdp->cblist, RCU_WAIT_TAIL)], - ".D"[!rcu_segcblist_segempty(&rdp->cblist, RCU_DONE_TAIL)]); -#ifdef CONFIG_RCU_BOOST - seq_printf(m, " kt=%d/%c ktl=%x", - per_cpu(rcu_cpu_has_work, rdp->cpu), - convert_kthread_status(per_cpu(rcu_cpu_kthread_status, - rdp->cpu)), - per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff); -#endif /* #ifdef CONFIG_RCU_BOOST */ - seq_printf(m, " b=%ld", rdp->blimit); - seq_printf(m, " ci=%lu nci=%lu co=%lu ca=%lu\n", - rdp->n_cbs_invoked, rdp->n_nocbs_invoked, - rdp->n_cbs_orphaned, rdp->n_cbs_adopted); -} - -static int show_rcudata(struct seq_file *m, void *v) -{ - print_one_rcu_data(m, (struct rcu_data *)v); - return 0; -} - -static const struct seq_operations rcudate_op = { - .start = r_start, - .next = r_next, - .stop = r_stop, - .show = show_rcudata, -}; - -static int rcudata_open(struct inode *inode, struct file *file) -{ - return r_open(inode, file, &rcudate_op); -} - -static const struct file_operations rcudata_fops = { - .owner = THIS_MODULE, - .open = rcudata_open, - .read = seq_read, - .llseek = no_llseek, - .release = seq_release, -}; - -static int show_rcuexp(struct seq_file *m, void *v) -{ - int cpu; - struct rcu_state *rsp = (struct rcu_state *)m->private; - struct rcu_data *rdp; - unsigned long s0 = 0, s1 = 0, s2 = 0, s3 = 0; - - for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - s0 += atomic_long_read(&rdp->exp_workdone0); - s1 += atomic_long_read(&rdp->exp_workdone1); - s2 += atomic_long_read(&rdp->exp_workdone2); - s3 += atomic_long_read(&rdp->exp_workdone3); - } - seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu enq=%d sc=%lu\n", - rsp->expedited_sequence, s0, s1, s2, s3, - atomic_read(&rsp->expedited_need_qs), - rsp->expedited_sequence / 2); - return 0; -} - -static int rcuexp_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcuexp, inode->i_private); -} - -static const struct file_operations rcuexp_fops = { - .owner = THIS_MODULE, - .open = rcuexp_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -#ifdef CONFIG_RCU_BOOST - -static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) -{ - seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu ", - rnp->grplo, rnp->grphi, - "T."[list_empty(&rnp->blkd_tasks)], - "N."[!rnp->gp_tasks], - "E."[!rnp->exp_tasks], - "B."[!rnp->boost_tasks], - convert_kthread_status(rnp->boost_kthread_status), - rnp->n_tasks_boosted, rnp->n_exp_boosts, - rnp->n_normal_boosts); - seq_printf(m, "j=%04x bt=%04x\n", - (int)(jiffies & 0xffff), - (int)(rnp->boost_time & 0xffff)); - seq_printf(m, " balk: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", - rnp->n_balk_blkd_tasks, - rnp->n_balk_exp_gp_tasks, - rnp->n_balk_boost_tasks, - rnp->n_balk_notblocked, - rnp->n_balk_notyet, - rnp->n_balk_nos); -} - -static int show_rcu_node_boost(struct seq_file *m, void *unused) -{ - struct rcu_node *rnp; - - rcu_for_each_leaf_node(&rcu_preempt_state, rnp) - print_one_rcu_node_boost(m, rnp); - return 0; -} - -static int rcu_node_boost_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcu_node_boost, NULL); -} - -static const struct file_operations rcu_node_boost_fops = { - .owner = THIS_MODULE, - .open = rcu_node_boost_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -#endif /* #ifdef CONFIG_RCU_BOOST */ - -static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) -{ - unsigned long gpnum; - int level = 0; - struct rcu_node *rnp; - - gpnum = rsp->gpnum; - seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x ", - ulong2long(rsp->completed), ulong2long(gpnum), - rsp->gp_state, - (long)(rsp->jiffies_force_qs - jiffies), - (int)(jiffies & 0xffff)); - seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", - rsp->n_force_qs, rsp->n_force_qs_ngp, - rsp->n_force_qs - rsp->n_force_qs_ngp, - READ_ONCE(rsp->n_force_qs_lh), - rsp->orphan_done.len_lazy, - rsp->orphan_done.len); - for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) { - if (rnp->level != level) { - seq_puts(m, "\n"); - level = rnp->level; - } - seq_printf(m, "%lx/%lx->%lx %c%c>%c %d:%d ^%d ", - rnp->qsmask, rnp->qsmaskinit, rnp->qsmaskinitnext, - ".G"[rnp->gp_tasks != NULL], - ".E"[rnp->exp_tasks != NULL], - ".T"[!list_empty(&rnp->blkd_tasks)], - rnp->grplo, rnp->grphi, rnp->grpnum); - } - seq_puts(m, "\n"); -} - -static int show_rcuhier(struct seq_file *m, void *v) -{ - struct rcu_state *rsp = (struct rcu_state *)m->private; - print_one_rcu_state(m, rsp); - return 0; -} - -static int rcuhier_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcuhier, inode->i_private); -} - -static const struct file_operations rcuhier_fops = { - .owner = THIS_MODULE, - .open = rcuhier_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) -{ - unsigned long flags; - unsigned long completed; - unsigned long gpnum; - unsigned long gpage; - unsigned long gpmax; - struct rcu_node *rnp = &rsp->node[0]; - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - completed = READ_ONCE(rsp->completed); - gpnum = READ_ONCE(rsp->gpnum); - if (completed == gpnum) - gpage = 0; - else - gpage = jiffies - rsp->gp_start; - gpmax = rsp->gp_max; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - seq_printf(m, "completed=%ld gpnum=%ld age=%ld max=%ld\n", - ulong2long(completed), ulong2long(gpnum), gpage, gpmax); -} - -static int show_rcugp(struct seq_file *m, void *v) -{ - struct rcu_state *rsp = (struct rcu_state *)m->private; - show_one_rcugp(m, rsp); - return 0; -} - -static int rcugp_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcugp, inode->i_private); -} - -static const struct file_operations rcugp_fops = { - .owner = THIS_MODULE, - .open = rcugp_open, - .read = seq_read, - .llseek = no_llseek, - .release = single_release, -}; - -static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) -{ - if (!rdp->beenonline) - return; - seq_printf(m, "%3d%cnp=%ld ", - rdp->cpu, - cpu_is_offline(rdp->cpu) ? '!' : ' ', - rdp->n_rcu_pending); - seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ", - rdp->n_rp_core_needs_qs, - rdp->n_rp_report_qs, - rdp->n_rp_cb_ready, - rdp->n_rp_cpu_needs_gp); - seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n", - rdp->n_rp_gp_completed, - rdp->n_rp_gp_started, - rdp->n_rp_nocb_defer_wakeup, - rdp->n_rp_need_nothing); -} - -static int show_rcu_pending(struct seq_file *m, void *v) -{ - print_one_rcu_pending(m, (struct rcu_data *)v); - return 0; -} - -static const struct seq_operations rcu_pending_op = { - .start = r_start, - .next = r_next, - .stop = r_stop, - .show = show_rcu_pending, -}; - -static int rcu_pending_open(struct inode *inode, struct file *file) -{ - return r_open(inode, file, &rcu_pending_op); -} - -static const struct file_operations rcu_pending_fops = { - .owner = THIS_MODULE, - .open = rcu_pending_open, - .read = seq_read, - .llseek = no_llseek, - .release = seq_release, -}; - -static int show_rcutorture(struct seq_file *m, void *unused) -{ - seq_printf(m, "rcutorture test sequence: %lu %s\n", - rcutorture_testseq >> 1, - (rcutorture_testseq & 0x1) ? "(test in progress)" : ""); - seq_printf(m, "rcutorture update version number: %lu\n", - rcutorture_vernum); - return 0; -} - -static int rcutorture_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_rcutorture, NULL); -} - -static const struct file_operations rcutorture_fops = { - .owner = THIS_MODULE, - .open = rcutorture_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static struct dentry *rcudir; - -static int __init rcutree_trace_init(void) -{ - struct rcu_state *rsp; - struct dentry *retval; - struct dentry *rspdir; - - rcudir = debugfs_create_dir("rcu", NULL); - if (!rcudir) - goto free_out; - - for_each_rcu_flavor(rsp) { - rspdir = debugfs_create_dir(rsp->name, rcudir); - if (!rspdir) - goto free_out; - - retval = debugfs_create_file("rcudata", 0444, - rspdir, rsp, &rcudata_fops); - if (!retval) - goto free_out; - - retval = debugfs_create_file("rcuexp", 0444, - rspdir, rsp, &rcuexp_fops); - if (!retval) - goto free_out; - - retval = debugfs_create_file("rcu_pending", 0444, - rspdir, rsp, &rcu_pending_fops); - if (!retval) - goto free_out; - - retval = debugfs_create_file("rcubarrier", 0444, - rspdir, rsp, &rcubarrier_fops); - if (!retval) - goto free_out; - -#ifdef CONFIG_RCU_BOOST - if (rsp == &rcu_preempt_state) { - retval = debugfs_create_file("rcuboost", 0444, - rspdir, NULL, &rcu_node_boost_fops); - if (!retval) - goto free_out; - } -#endif - - retval = debugfs_create_file("rcugp", 0444, - rspdir, rsp, &rcugp_fops); - if (!retval) - goto free_out; - - retval = debugfs_create_file("rcuhier", 0444, - rspdir, rsp, &rcuhier_fops); - if (!retval) - goto free_out; - } - - retval = debugfs_create_file("rcutorture", 0444, rcudir, - NULL, &rcutorture_fops); - if (!retval) - goto free_out; - return 0; -free_out: - debugfs_remove_recursive(rcudir); - return 1; -} -device_initcall(rcutree_trace_init); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 273e869ca21d..00e77c470017 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -62,7 +62,9 @@ #define MODULE_PARAM_PREFIX "rcupdate." #ifndef CONFIG_TINY_RCU +extern int rcu_expedited; /* from sysctl */ module_param(rcu_expedited, int, 0); +extern int rcu_normal; /* from sysctl */ module_param(rcu_normal, int, 0); static int rcu_normal_after_boot; module_param(rcu_normal_after_boot, int, 0); @@ -379,6 +381,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array) { int i; + int j; /* Initialize and register callbacks for each flavor specified. */ for (i = 0; i < n; i++) { @@ -390,7 +393,11 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, } init_rcu_head_on_stack(&rs_array[i].head); init_completion(&rs_array[i].completion); - (crcu_array[i])(&rs_array[i].head, wakeme_after_rcu); + for (j = 0; j < i; j++) + if (crcu_array[j] == crcu_array[i]) + break; + if (j == i) + (crcu_array[i])(&rs_array[i].head, wakeme_after_rcu); } /* Wait for all callbacks to be invoked. */ @@ -399,7 +406,11 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, (crcu_array[i] == call_rcu || crcu_array[i] == call_rcu_bh)) continue; - wait_for_completion(&rs_array[i].completion); + for (j = 0; j < i; j++) + if (crcu_array[j] == crcu_array[i]) + break; + if (j == i) + wait_for_completion(&rs_array[i].completion); destroy_rcu_head_on_stack(&rs_array[i].head); } } @@ -560,15 +571,30 @@ static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock); DEFINE_SRCU(tasks_rcu_exit_srcu); /* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */ -static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10; +#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10) +static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT; module_param(rcu_task_stall_timeout, int, 0644); static void rcu_spawn_tasks_kthread(void); static struct task_struct *rcu_tasks_kthread_ptr; -/* - * Post an RCU-tasks callback. First call must be from process context - * after the scheduler if fully operational. +/** + * call_rcu_tasks() - Queue an RCU for invocation task-based grace period + * @rhp: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_tasks() assumes + * that the read-side critical sections end at a voluntary context + * switch (not a preemption!), entry into idle, or transition to usermode + * execution. As such, there are no read-side primitives analogous to + * rcu_read_lock() and rcu_read_unlock() because this primitive is intended + * to determine that all tasks have passed through a safe state, not so + * much for data-strcuture synchronization. + * + * See the description of call_rcu() for more detailed information on + * memory ordering guarantees. */ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func) { @@ -851,6 +877,23 @@ static void rcu_spawn_tasks_kthread(void) #endif /* #ifdef CONFIG_TASKS_RCU */ +#ifndef CONFIG_TINY_RCU + +/* + * Print any non-default Tasks RCU settings. + */ +static void __init rcu_tasks_bootup_oddness(void) +{ +#ifdef CONFIG_TASKS_RCU + if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT) + pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout); + else + pr_info("\tTasks RCU enabled.\n"); +#endif /* #ifdef CONFIG_TASKS_RCU */ +} + +#endif /* #ifndef CONFIG_TINY_RCU */ + #ifdef CONFIG_PROVE_RCU /* @@ -935,3 +978,25 @@ late_initcall(rcu_verify_early_boot_tests); #else void rcu_early_boot_tests(void) {} #endif /* CONFIG_PROVE_RCU */ + +#ifndef CONFIG_TINY_RCU + +/* + * Print any significant non-default boot-time settings. + */ +void __init rcupdate_announce_bootup_oddness(void) +{ + if (rcu_normal) + pr_info("\tNo expedited grace period (rcu_normal).\n"); + else if (rcu_normal_after_boot) + pr_info("\tNo expedited grace period (rcu_normal_after_boot).\n"); + else if (rcu_expedited) + pr_info("\tAll grace periods are expedited (rcu_expedited).\n"); + if (rcu_cpu_stall_suppress) + pr_info("\tRCU CPU stall warnings suppressed (rcu_cpu_stall_suppress).\n"); + if (rcu_cpu_stall_timeout != CONFIG_RCU_CPU_STALL_TIMEOUT) + pr_info("\tRCU CPU stall warnings timeout set to %d (rcu_cpu_stall_timeout).\n", rcu_cpu_stall_timeout); + rcu_tasks_bootup_oddness(); +} + +#endif /* #ifndef CONFIG_TINY_RCU */ diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 89ab6758667b..53f0164ed362 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -16,9 +16,9 @@ CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif obj-y += core.o loadavg.o clock.o cputime.o -obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o -obj-y += wait.o swait.o completion.o idle.o -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o +obj-y += idle_task.o fair.o rt.o deadline.o +obj-y += wait.o wait_bit.o swait.o completion.o idle.o +obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index 00a45c45beca..ca0f8fc945c6 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -64,6 +64,7 @@ #include <linux/workqueue.h> #include <linux/compiler.h> #include <linux/tick.h> +#include <linux/init.h> /* * Scheduler clock - returns current time in nanosec units. @@ -124,14 +125,27 @@ int sched_clock_stable(void) return static_branch_likely(&__sched_clock_stable); } +static void __scd_stamp(struct sched_clock_data *scd) +{ + scd->tick_gtod = ktime_get_ns(); + scd->tick_raw = sched_clock(); +} + static void __set_sched_clock_stable(void) { - struct sched_clock_data *scd = this_scd(); + struct sched_clock_data *scd; /* + * Since we're still unstable and the tick is already running, we have + * to disable IRQs in order to get a consistent scd->tick* reading. + */ + local_irq_disable(); + scd = this_scd(); + /* * Attempt to make the (initial) unstable->stable transition continuous. */ __sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw); + local_irq_enable(); printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n", scd->tick_gtod, __gtod_offset, @@ -141,8 +155,38 @@ static void __set_sched_clock_stable(void) tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); } +/* + * If we ever get here, we're screwed, because we found out -- typically after + * the fact -- that TSC wasn't good. This means all our clocksources (including + * ktime) could have reported wrong values. + * + * What we do here is an attempt to fix up and continue sort of where we left + * off in a coherent manner. + * + * The only way to fully avoid random clock jumps is to boot with: + * "tsc=unstable". + */ static void __sched_clock_work(struct work_struct *work) { + struct sched_clock_data *scd; + int cpu; + + /* take a current timestamp and set 'now' */ + preempt_disable(); + scd = this_scd(); + __scd_stamp(scd); + scd->clock = scd->tick_gtod + __gtod_offset; + preempt_enable(); + + /* clone to all CPUs */ + for_each_possible_cpu(cpu) + per_cpu(sched_clock_data, cpu) = *scd; + + printk(KERN_WARNING "TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'.\n"); + printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n", + scd->tick_gtod, __gtod_offset, + scd->tick_raw, __sched_clock_offset); + static_branch_disable(&__sched_clock_stable); } @@ -150,27 +194,11 @@ static DECLARE_WORK(sched_clock_work, __sched_clock_work); static void __clear_sched_clock_stable(void) { - struct sched_clock_data *scd = this_scd(); - - /* - * Attempt to make the stable->unstable transition continuous. - * - * Trouble is, this is typically called from the TSC watchdog - * timer, which is late per definition. This means the tick - * values can already be screwy. - * - * Still do what we can. - */ - __gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod); - - printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n", - scd->tick_gtod, __gtod_offset, - scd->tick_raw, __sched_clock_offset); + if (!sched_clock_stable()) + return; tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); - - if (sched_clock_stable()) - schedule_work(&sched_clock_work); + schedule_work(&sched_clock_work); } void clear_sched_clock_stable(void) @@ -183,7 +211,11 @@ void clear_sched_clock_stable(void) __clear_sched_clock_stable(); } -void sched_clock_init_late(void) +/* + * We run this as late_initcall() such that it runs after all built-in drivers, + * notably: acpi_processor and intel_idle, which can mark the TSC as unstable. + */ +static int __init sched_clock_init_late(void) { sched_clock_running = 2; /* @@ -197,7 +229,10 @@ void sched_clock_init_late(void) if (__sched_clock_stable_early) __set_sched_clock_stable(); + + return 0; } +late_initcall(sched_clock_init_late); /* * min, max except they take wrapping into account @@ -347,21 +382,38 @@ void sched_clock_tick(void) { struct sched_clock_data *scd; + if (sched_clock_stable()) + return; + + if (unlikely(!sched_clock_running)) + return; + WARN_ON_ONCE(!irqs_disabled()); + scd = this_scd(); + __scd_stamp(scd); + sched_clock_local(scd); +} + +void sched_clock_tick_stable(void) +{ + u64 gtod, clock; + + if (!sched_clock_stable()) + return; + /* - * Update these values even if sched_clock_stable(), because it can - * become unstable at any point in time at which point we need some - * values to fall back on. + * Called under watchdog_lock. * - * XXX arguably we can skip this if we expose tsc_clocksource_reliable + * The watchdog just found this TSC to (still) be stable, so now is a + * good moment to update our __gtod_offset. Because once we find the + * TSC to be unstable, any computation will be computing crap. */ - scd = this_scd(); - scd->tick_raw = sched_clock(); - scd->tick_gtod = ktime_get_ns(); - - if (!sched_clock_stable() && likely(sched_clock_running)) - sched_clock_local(scd); + local_irq_disable(); + gtod = ktime_get_ns(); + clock = sched_clock(); + __gtod_offset = (clock + __sched_clock_offset) - gtod; + local_irq_enable(); } /* @@ -374,15 +426,21 @@ void sched_clock_idle_sleep_event(void) EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event); /* - * We just idled delta nanoseconds (called with irqs disabled): + * We just idled; resync with ktime. */ -void sched_clock_idle_wakeup_event(u64 delta_ns) +void sched_clock_idle_wakeup_event(void) { - if (timekeeping_suspended) + unsigned long flags; + + if (sched_clock_stable()) + return; + + if (unlikely(timekeeping_suspended)) return; + local_irq_save(flags); sched_clock_tick(); - touch_softlockup_watchdog_sched(); + local_irq_restore(flags); } EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index 53f9558fa925..13fc5ae9bf2f 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -66,7 +66,7 @@ do_wait_for_common(struct completion *x, if (!x->done) { DECLARE_WAITQUEUE(wait, current); - __add_wait_queue_tail_exclusive(&x->wait, &wait); + __add_wait_queue_entry_tail_exclusive(&x->wait, &wait); do { if (signal_pending_state(state, current)) { timeout = -ERESTARTSYS; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 803c3bc274c4..17c667b427b4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10,6 +10,7 @@ #include <uapi/linux/sched/types.h> #include <linux/sched/loadavg.h> #include <linux/sched/hotplug.h> +#include <linux/wait_bit.h> #include <linux/cpuset.h> #include <linux/delayacct.h> #include <linux/init_task.h> @@ -788,36 +789,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -void sched_set_stop_task(int cpu, struct task_struct *stop) -{ - struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; - struct task_struct *old_stop = cpu_rq(cpu)->stop; - - if (stop) { - /* - * Make it appear like a SCHED_FIFO task, its something - * userspace knows about and won't get confused about. - * - * Also, it will make PI more or less work without too - * much confusion -- but then, stop work should not - * rely on PI working anyway. - */ - sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); - - stop->sched_class = &stop_sched_class; - } - - cpu_rq(cpu)->stop = stop; - - if (old_stop) { - /* - * Reset it back to a normal scheduling class so that - * it can die in pieces. - */ - old_stop->sched_class = &rt_sched_class; - } -} - /* * __normal_prio - return the priority that is based on the static prio */ @@ -1588,6 +1559,36 @@ static void update_avg(u64 *avg, u64 sample) *avg += diff >> 3; } +void sched_set_stop_task(int cpu, struct task_struct *stop) +{ + struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; + struct task_struct *old_stop = cpu_rq(cpu)->stop; + + if (stop) { + /* + * Make it appear like a SCHED_FIFO task, its something + * userspace knows about and won't get confused about. + * + * Also, it will make PI more or less work without too + * much confusion -- but then, stop work should not + * rely on PI working anyway. + */ + sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); + + stop->sched_class = &stop_sched_class; + } + + cpu_rq(cpu)->stop = stop; + + if (old_stop) { + /* + * Reset it back to a normal scheduling class so that + * it can die in pieces. + */ + old_stop->sched_class = &rt_sched_class; + } +} + #else static inline int __set_cpus_allowed_ptr(struct task_struct *p, @@ -1731,7 +1732,7 @@ void sched_ttwu_pending(void) { struct rq *rq = this_rq(); struct llist_node *llist = llist_del_all(&rq->wake_list); - struct task_struct *p; + struct task_struct *p, *t; struct rq_flags rf; if (!llist) @@ -1740,17 +1741,8 @@ void sched_ttwu_pending(void) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - while (llist) { - int wake_flags = 0; - - p = llist_entry(llist, struct task_struct, wake_entry); - llist = llist_next(llist); - - if (p->sched_remote_wakeup) - wake_flags = WF_MIGRATED; - - ttwu_do_activate(rq, p, wake_flags, &rf); - } + llist_for_each_entry_safe(p, t, llist, wake_entry) + ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf); rq_unlock_irqrestore(rq, &rf); } @@ -2148,23 +2140,6 @@ int wake_up_state(struct task_struct *p, unsigned int state) } /* - * This function clears the sched_dl_entity static params. - */ -void __dl_clear_params(struct task_struct *p) -{ - struct sched_dl_entity *dl_se = &p->dl; - - dl_se->dl_runtime = 0; - dl_se->dl_deadline = 0; - dl_se->dl_period = 0; - dl_se->flags = 0; - dl_se->dl_bw = 0; - - dl_se->dl_throttled = 0; - dl_se->dl_yielded = 0; -} - -/* * Perform scheduler related setup for a newly forked process p. * p is forked by current. * @@ -2193,6 +2168,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) RB_CLEAR_NODE(&p->dl.rb_node); init_dl_task_timer(&p->dl); + init_dl_inactive_task_timer(&p->dl); __dl_clear_params(p); INIT_LIST_HEAD(&p->rt.run_list); @@ -2430,7 +2406,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) unsigned long to_ratio(u64 period, u64 runtime) { if (runtime == RUNTIME_INF) - return 1ULL << 20; + return BW_UNIT; /* * Doing this here saves a lot of checks in all @@ -2440,93 +2416,9 @@ unsigned long to_ratio(u64 period, u64 runtime) if (period == 0) return 0; - return div64_u64(runtime << 20, period); -} - -#ifdef CONFIG_SMP -inline struct dl_bw *dl_bw_of(int i) -{ - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), - "sched RCU must be held"); - return &cpu_rq(i)->rd->dl_bw; -} - -static inline int dl_bw_cpus(int i) -{ - struct root_domain *rd = cpu_rq(i)->rd; - int cpus = 0; - - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), - "sched RCU must be held"); - for_each_cpu_and(i, rd->span, cpu_active_mask) - cpus++; - - return cpus; -} -#else -inline struct dl_bw *dl_bw_of(int i) -{ - return &cpu_rq(i)->dl.dl_bw; -} - -static inline int dl_bw_cpus(int i) -{ - return 1; -} -#endif - -/* - * We must be sure that accepting a new task (or allowing changing the - * parameters of an existing one) is consistent with the bandwidth - * constraints. If yes, this function also accordingly updates the currently - * allocated bandwidth to reflect the new situation. - * - * This function is called while holding p's rq->lock. - * - * XXX we should delay bw change until the task's 0-lag point, see - * __setparam_dl(). - */ -static int dl_overflow(struct task_struct *p, int policy, - const struct sched_attr *attr) -{ - - struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); - u64 period = attr->sched_period ?: attr->sched_deadline; - u64 runtime = attr->sched_runtime; - u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; - int cpus, err = -1; - - /* !deadline task may carry old deadline bandwidth */ - if (new_bw == p->dl.dl_bw && task_has_dl_policy(p)) - return 0; - - /* - * Either if a task, enters, leave, or stays -deadline but changes - * its parameters, we may need to update accordingly the total - * allocated bandwidth of the container. - */ - raw_spin_lock(&dl_b->lock); - cpus = dl_bw_cpus(task_cpu(p)); - if (dl_policy(policy) && !task_has_dl_policy(p) && - !__dl_overflow(dl_b, cpus, 0, new_bw)) { - __dl_add(dl_b, new_bw); - err = 0; - } else if (dl_policy(policy) && task_has_dl_policy(p) && - !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) { - __dl_clear(dl_b, p->dl.dl_bw); - __dl_add(dl_b, new_bw); - err = 0; - } else if (!dl_policy(policy) && task_has_dl_policy(p)) { - __dl_clear(dl_b, p->dl.dl_bw); - err = 0; - } - raw_spin_unlock(&dl_b->lock); - - return err; + return div64_u64(runtime << BW_SHIFT, period); } -extern void init_dl_bw(struct dl_bw *dl_b); - /* * wake_up_new_task - wake up a newly created task for the first time. * @@ -3687,7 +3579,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void) exception_exit(prev_state); } -int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, +int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags, void *key) { return try_to_wake_up(curr->private, mode, wake_flags); @@ -4009,46 +3901,6 @@ static struct task_struct *find_process_by_pid(pid_t pid) } /* - * This function initializes the sched_dl_entity of a newly becoming - * SCHED_DEADLINE task. - * - * Only the static values are considered here, the actual runtime and the - * absolute deadline will be properly calculated when the task is enqueued - * for the first time with its new policy. - */ -static void -__setparam_dl(struct task_struct *p, const struct sched_attr *attr) -{ - struct sched_dl_entity *dl_se = &p->dl; - - dl_se->dl_runtime = attr->sched_runtime; - dl_se->dl_deadline = attr->sched_deadline; - dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline; - dl_se->flags = attr->sched_flags; - dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); - - /* - * Changing the parameters of a task is 'tricky' and we're not doing - * the correct thing -- also see task_dead_dl() and switched_from_dl(). - * - * What we SHOULD do is delay the bandwidth release until the 0-lag - * point. This would include retaining the task_struct until that time - * and change dl_overflow() to not immediately decrement the current - * amount. - * - * Instead we retain the current runtime/deadline and let the new - * parameters take effect after the current reservation period lapses. - * This is safe (albeit pessimistic) because the 0-lag point is always - * before the current scheduling deadline. - * - * We can still have temporary overloads because we do not delay the - * change in bandwidth until that time; so admission control is - * not on the safe side. It does however guarantee tasks will never - * consume more than promised. - */ -} - -/* * sched_setparam() passes in -1 for its policy, to let the functions * it calls know not to change it. */ @@ -4101,59 +3953,6 @@ static void __setscheduler(struct rq *rq, struct task_struct *p, p->sched_class = &fair_sched_class; } -static void -__getparam_dl(struct task_struct *p, struct sched_attr *attr) -{ - struct sched_dl_entity *dl_se = &p->dl; - - attr->sched_priority = p->rt_priority; - attr->sched_runtime = dl_se->dl_runtime; - attr->sched_deadline = dl_se->dl_deadline; - attr->sched_period = dl_se->dl_period; - attr->sched_flags = dl_se->flags; -} - -/* - * This function validates the new parameters of a -deadline task. - * We ask for the deadline not being zero, and greater or equal - * than the runtime, as well as the period of being zero or - * greater than deadline. Furthermore, we have to be sure that - * user parameters are above the internal resolution of 1us (we - * check sched_runtime only since it is always the smaller one) and - * below 2^63 ns (we have to check both sched_deadline and - * sched_period, as the latter can be zero). - */ -static bool -__checkparam_dl(const struct sched_attr *attr) -{ - /* deadline != 0 */ - if (attr->sched_deadline == 0) - return false; - - /* - * Since we truncate DL_SCALE bits, make sure we're at least - * that big. - */ - if (attr->sched_runtime < (1ULL << DL_SCALE)) - return false; - - /* - * Since we use the MSB for wrap-around and sign issues, make - * sure it's not set (mind that period can be equal to zero). - */ - if (attr->sched_deadline & (1ULL << 63) || - attr->sched_period & (1ULL << 63)) - return false; - - /* runtime <= deadline <= period (if period != 0) */ - if ((attr->sched_period != 0 && - attr->sched_period < attr->sched_deadline) || - attr->sched_deadline < attr->sched_runtime) - return false; - - return true; -} - /* * Check the target process has a UID that matches the current process's: */ @@ -4170,19 +3969,6 @@ static bool check_same_owner(struct task_struct *p) return match; } -static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) -{ - struct sched_dl_entity *dl_se = &p->dl; - - if (dl_se->dl_runtime != attr->sched_runtime || - dl_se->dl_deadline != attr->sched_deadline || - dl_se->dl_period != attr->sched_period || - dl_se->flags != attr->sched_flags) - return true; - - return false; -} - static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi) @@ -4197,8 +3983,8 @@ static int __sched_setscheduler(struct task_struct *p, int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; struct rq *rq; - /* May grab non-irq protected spin_locks: */ - BUG_ON(in_interrupt()); + /* The pi code expects interrupts enabled */ + BUG_ON(pi && in_interrupt()); recheck: /* Double check policy once rq lock held: */ if (policy < 0) { @@ -4211,7 +3997,8 @@ recheck: return -EINVAL; } - if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK)) + if (attr->sched_flags & + ~(SCHED_FLAG_RESET_ON_FORK | SCHED_FLAG_RECLAIM)) return -EINVAL; /* @@ -4362,7 +4149,7 @@ change: * of a SCHED_DEADLINE task) we need to check if enough bandwidth * is available. */ - if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) { + if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) { task_rq_unlock(rq, p, &rf); return -EBUSY; } @@ -5463,26 +5250,17 @@ void init_idle(struct task_struct *idle, int cpu) #endif } +#ifdef CONFIG_SMP + int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial) { - int ret = 1, trial_cpus; - struct dl_bw *cur_dl_b; - unsigned long flags; + int ret = 1; if (!cpumask_weight(cur)) return ret; - rcu_read_lock_sched(); - cur_dl_b = dl_bw_of(cpumask_any(cur)); - trial_cpus = cpumask_weight(trial); - - raw_spin_lock_irqsave(&cur_dl_b->lock, flags); - if (cur_dl_b->bw != -1 && - cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw) - ret = 0; - raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags); - rcu_read_unlock_sched(); + ret = dl_cpuset_cpumask_can_shrink(cur, trial); return ret; } @@ -5506,43 +5284,14 @@ int task_can_attach(struct task_struct *p, goto out; } -#ifdef CONFIG_SMP if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_cpus_allowed)) { - unsigned int dest_cpu = cpumask_any_and(cpu_active_mask, - cs_cpus_allowed); - struct dl_bw *dl_b; - bool overflow; - int cpus; - unsigned long flags; - - rcu_read_lock_sched(); - dl_b = dl_bw_of(dest_cpu); - raw_spin_lock_irqsave(&dl_b->lock, flags); - cpus = dl_bw_cpus(dest_cpu); - overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw); - if (overflow) - ret = -EBUSY; - else { - /* - * We reserve space for this task in the destination - * root_domain, as we can't fail after this point. - * We will free resources in the source root_domain - * later on (see set_cpus_allowed_dl()). - */ - __dl_add(dl_b, p->dl.dl_bw); - } - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - rcu_read_unlock_sched(); + cs_cpus_allowed)) + ret = dl_task_can_attach(p, cs_cpus_allowed); - } -#endif out: return ret; } -#ifdef CONFIG_SMP - bool sched_smp_initialized __read_mostly; #ifdef CONFIG_NUMA_BALANCING @@ -5605,7 +5354,7 @@ void idle_task_exit(void) BUG_ON(cpu_online(smp_processor_id())); if (mm != &init_mm) { - switch_mm_irqs_off(mm, &init_mm, current); + switch_mm(mm, &init_mm, current); finish_arch_post_lock_switch(); } mmdrop(mm); @@ -5805,23 +5554,8 @@ static void cpuset_cpu_active(void) static int cpuset_cpu_inactive(unsigned int cpu) { - unsigned long flags; - struct dl_bw *dl_b; - bool overflow; - int cpus; - if (!cpuhp_tasks_frozen) { - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - cpus = dl_bw_cpus(cpu); - overflow = __dl_overflow(dl_b, cpus, 0, 0); - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - - if (overflow) + if (dl_cpu_busy(cpu)) return -EBUSY; cpuset_update_active_cpus(); } else { @@ -5874,15 +5608,9 @@ int sched_cpu_deactivate(unsigned int cpu) * users of this state to go away such that all new such users will * observe it. * - * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might - * not imply sync_sched(), so wait for both. - * * Do sync before park smpboot threads to take care the rcu boost case. */ - if (IS_ENABLED(CONFIG_PREEMPT)) - synchronize_rcu_mult(call_rcu, call_rcu_sched); - else - synchronize_rcu(); + synchronize_rcu_mult(call_rcu, call_rcu_sched); if (!sched_smp_initialized) return 0; @@ -5958,7 +5686,6 @@ void __init sched_init_smp(void) cpumask_var_t non_isolated_cpus; alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); - alloc_cpumask_var(&fallback_doms, GFP_KERNEL); sched_init_numa(); @@ -5968,7 +5695,7 @@ void __init sched_init_smp(void) * happen. */ mutex_lock(&sched_domains_mutex); - init_sched_domains(cpu_active_mask); + sched_init_domains(cpu_active_mask); cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); if (cpumask_empty(non_isolated_cpus)) cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); @@ -5984,7 +5711,6 @@ void __init sched_init_smp(void) init_sched_dl_class(); sched_init_smt(); - sched_clock_init_late(); sched_smp_initialized = true; } @@ -6000,7 +5726,6 @@ early_initcall(migration_init); void __init sched_init_smp(void) { sched_init_granularity(); - sched_clock_init_late(); } #endif /* CONFIG_SMP */ @@ -6026,28 +5751,13 @@ static struct kmem_cache *task_group_cache __read_mostly; DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); DECLARE_PER_CPU(cpumask_var_t, select_idle_mask); -#define WAIT_TABLE_BITS 8 -#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS) -static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned; - -wait_queue_head_t *bit_waitqueue(void *word, int bit) -{ - const int shift = BITS_PER_LONG == 32 ? 5 : 6; - unsigned long val = (unsigned long)word << shift | bit; - - return bit_wait_table + hash_long(val, WAIT_TABLE_BITS); -} -EXPORT_SYMBOL(bit_waitqueue); - void __init sched_init(void) { int i, j; unsigned long alloc_size = 0, ptr; sched_clock_init(); - - for (i = 0; i < WAIT_TABLE_SIZE; i++) - init_waitqueue_head(bit_wait_table + i); + wait_bit_init(); #ifdef CONFIG_FAIR_GROUP_SCHED alloc_size += 2 * nr_cpu_ids * sizeof(void **); @@ -6199,7 +5909,6 @@ void __init sched_init(void) calc_load_update = jiffies + LOAD_FREQ; #ifdef CONFIG_SMP - zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT); /* May be allocated at isolcpus cmdline parse time */ if (cpu_isolated_map == NULL) zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); @@ -6251,8 +5960,10 @@ void ___might_sleep(const char *file, int line, int preempt_offset) if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && !is_idle_task(current)) || - system_state != SYSTEM_RUNNING || oops_in_progress) + system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING || + oops_in_progress) return; + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) return; prev_jiffy = jiffies; @@ -6507,385 +6218,6 @@ void sched_move_task(struct task_struct *tsk) task_rq_unlock(rq, tsk, &rf); } -#endif /* CONFIG_CGROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -/* - * Ensure that the real time constraints are schedulable. - */ -static DEFINE_MUTEX(rt_constraints_mutex); - -/* Must be called with tasklist_lock held */ -static inline int tg_has_rt_tasks(struct task_group *tg) -{ - struct task_struct *g, *p; - - /* - * Autogroups do not have RT tasks; see autogroup_create(). - */ - if (task_group_is_autogroup(tg)) - return 0; - - for_each_process_thread(g, p) { - if (rt_task(p) && task_group(p) == tg) - return 1; - } - - return 0; -} - -struct rt_schedulable_data { - struct task_group *tg; - u64 rt_period; - u64 rt_runtime; -}; - -static int tg_rt_schedulable(struct task_group *tg, void *data) -{ - struct rt_schedulable_data *d = data; - struct task_group *child; - unsigned long total, sum = 0; - u64 period, runtime; - - period = ktime_to_ns(tg->rt_bandwidth.rt_period); - runtime = tg->rt_bandwidth.rt_runtime; - - if (tg == d->tg) { - period = d->rt_period; - runtime = d->rt_runtime; - } - - /* - * Cannot have more runtime than the period. - */ - if (runtime > period && runtime != RUNTIME_INF) - return -EINVAL; - - /* - * Ensure we don't starve existing RT tasks. - */ - if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) - return -EBUSY; - - total = to_ratio(period, runtime); - - /* - * Nobody can have more than the global setting allows. - */ - if (total > to_ratio(global_rt_period(), global_rt_runtime())) - return -EINVAL; - - /* - * The sum of our children's runtime should not exceed our own. - */ - list_for_each_entry_rcu(child, &tg->children, siblings) { - period = ktime_to_ns(child->rt_bandwidth.rt_period); - runtime = child->rt_bandwidth.rt_runtime; - - if (child == d->tg) { - period = d->rt_period; - runtime = d->rt_runtime; - } - - sum += to_ratio(period, runtime); - } - - if (sum > total) - return -EINVAL; - - return 0; -} - -static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) -{ - int ret; - - struct rt_schedulable_data data = { - .tg = tg, - .rt_period = period, - .rt_runtime = runtime, - }; - - rcu_read_lock(); - ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data); - rcu_read_unlock(); - - return ret; -} - -static int tg_set_rt_bandwidth(struct task_group *tg, - u64 rt_period, u64 rt_runtime) -{ - int i, err = 0; - - /* - * Disallowing the root group RT runtime is BAD, it would disallow the - * kernel creating (and or operating) RT threads. - */ - if (tg == &root_task_group && rt_runtime == 0) - return -EINVAL; - - /* No period doesn't make any sense. */ - if (rt_period == 0) - return -EINVAL; - - mutex_lock(&rt_constraints_mutex); - read_lock(&tasklist_lock); - err = __rt_schedulable(tg, rt_period, rt_runtime); - if (err) - goto unlock; - - raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); - tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); - tg->rt_bandwidth.rt_runtime = rt_runtime; - - for_each_possible_cpu(i) { - struct rt_rq *rt_rq = tg->rt_rq[i]; - - raw_spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_runtime = rt_runtime; - raw_spin_unlock(&rt_rq->rt_runtime_lock); - } - raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); -unlock: - read_unlock(&tasklist_lock); - mutex_unlock(&rt_constraints_mutex); - - return err; -} - -static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) -{ - u64 rt_runtime, rt_period; - - rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); - rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; - if (rt_runtime_us < 0) - rt_runtime = RUNTIME_INF; - - return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); -} - -static long sched_group_rt_runtime(struct task_group *tg) -{ - u64 rt_runtime_us; - - if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) - return -1; - - rt_runtime_us = tg->rt_bandwidth.rt_runtime; - do_div(rt_runtime_us, NSEC_PER_USEC); - return rt_runtime_us; -} - -static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us) -{ - u64 rt_runtime, rt_period; - - rt_period = rt_period_us * NSEC_PER_USEC; - rt_runtime = tg->rt_bandwidth.rt_runtime; - - return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); -} - -static long sched_group_rt_period(struct task_group *tg) -{ - u64 rt_period_us; - - rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); - do_div(rt_period_us, NSEC_PER_USEC); - return rt_period_us; -} -#endif /* CONFIG_RT_GROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -static int sched_rt_global_constraints(void) -{ - int ret = 0; - - mutex_lock(&rt_constraints_mutex); - read_lock(&tasklist_lock); - ret = __rt_schedulable(NULL, 0, 0); - read_unlock(&tasklist_lock); - mutex_unlock(&rt_constraints_mutex); - - return ret; -} - -static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) -{ - /* Don't accept realtime tasks when there is no way for them to run */ - if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) - return 0; - - return 1; -} - -#else /* !CONFIG_RT_GROUP_SCHED */ -static int sched_rt_global_constraints(void) -{ - unsigned long flags; - int i; - - raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); - for_each_possible_cpu(i) { - struct rt_rq *rt_rq = &cpu_rq(i)->rt; - - raw_spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_runtime = global_rt_runtime(); - raw_spin_unlock(&rt_rq->rt_runtime_lock); - } - raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); - - return 0; -} -#endif /* CONFIG_RT_GROUP_SCHED */ - -static int sched_dl_global_validate(void) -{ - u64 runtime = global_rt_runtime(); - u64 period = global_rt_period(); - u64 new_bw = to_ratio(period, runtime); - struct dl_bw *dl_b; - int cpu, ret = 0; - unsigned long flags; - - /* - * Here we want to check the bandwidth not being set to some - * value smaller than the currently allocated bandwidth in - * any of the root_domains. - * - * FIXME: Cycling on all the CPUs is overdoing, but simpler than - * cycling on root_domains... Discussion on different/better - * solutions is welcome! - */ - for_each_possible_cpu(cpu) { - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - if (new_bw < dl_b->total_bw) - ret = -EBUSY; - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - - if (ret) - break; - } - - return ret; -} - -static void sched_dl_do_global(void) -{ - u64 new_bw = -1; - struct dl_bw *dl_b; - int cpu; - unsigned long flags; - - def_dl_bandwidth.dl_period = global_rt_period(); - def_dl_bandwidth.dl_runtime = global_rt_runtime(); - - if (global_rt_runtime() != RUNTIME_INF) - new_bw = to_ratio(global_rt_period(), global_rt_runtime()); - - /* - * FIXME: As above... - */ - for_each_possible_cpu(cpu) { - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - dl_b->bw = new_bw; - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - } -} - -static int sched_rt_global_validate(void) -{ - if (sysctl_sched_rt_period <= 0) - return -EINVAL; - - if ((sysctl_sched_rt_runtime != RUNTIME_INF) && - (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) - return -EINVAL; - - return 0; -} - -static void sched_rt_do_global(void) -{ - def_rt_bandwidth.rt_runtime = global_rt_runtime(); - def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period()); -} - -int sched_rt_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int old_period, old_runtime; - static DEFINE_MUTEX(mutex); - int ret; - - mutex_lock(&mutex); - old_period = sysctl_sched_rt_period; - old_runtime = sysctl_sched_rt_runtime; - - ret = proc_dointvec(table, write, buffer, lenp, ppos); - - if (!ret && write) { - ret = sched_rt_global_validate(); - if (ret) - goto undo; - - ret = sched_dl_global_validate(); - if (ret) - goto undo; - - ret = sched_rt_global_constraints(); - if (ret) - goto undo; - - sched_rt_do_global(); - sched_dl_do_global(); - } - if (0) { -undo: - sysctl_sched_rt_period = old_period; - sysctl_sched_rt_runtime = old_runtime; - } - mutex_unlock(&mutex); - - return ret; -} - -int sched_rr_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int ret; - static DEFINE_MUTEX(mutex); - - mutex_lock(&mutex); - ret = proc_dointvec(table, write, buffer, lenp, ppos); - /* - * Make sure that internally we keep jiffies. - * Also, writing zero resets the timeslice to default: - */ - if (!ret && write) { - sched_rr_timeslice = - sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE : - msecs_to_jiffies(sysctl_sched_rr_timeslice); - } - mutex_unlock(&mutex); - return ret; -} - -#ifdef CONFIG_CGROUP_SCHED static inline struct task_group *css_tg(struct cgroup_subsys_state *css) { diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 622eed1b7658..076a2e31951c 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -101,9 +101,6 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, if (sg_policy->next_freq == next_freq) return; - if (sg_policy->next_freq > next_freq) - next_freq = (sg_policy->next_freq + next_freq) >> 1; - sg_policy->next_freq = next_freq; sg_policy->last_freq_update_time = time; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index aea3135c5d90..67c70e287647 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -615,19 +615,13 @@ static void cputime_adjust(struct task_cputime *curr, * userspace. Once a task gets some ticks, the monotonicy code at * 'update' will ensure things converge to the observed ratio. */ - if (stime == 0) { - utime = rtime; - goto update; + if (stime != 0) { + if (utime == 0) + stime = rtime; + else + stime = scale_stime(stime, rtime, stime + utime); } - if (utime == 0) { - stime = rtime; - goto update; - } - - stime = scale_stime(stime, rtime, stime + utime); - -update: /* * Make sure stime doesn't go backwards; this preserves monotonicity * for utime because rtime is monotonic. diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index a2ce59015642..a84299f44b5d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -17,6 +17,7 @@ #include "sched.h" #include <linux/slab.h> +#include <uapi/linux/sched/types.h> struct dl_bandwidth def_dl_bandwidth; @@ -43,6 +44,254 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se) return !RB_EMPTY_NODE(&dl_se->rb_node); } +#ifdef CONFIG_SMP +static inline struct dl_bw *dl_bw_of(int i) +{ + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); + return &cpu_rq(i)->rd->dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + struct root_domain *rd = cpu_rq(i)->rd; + int cpus = 0; + + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); + for_each_cpu_and(i, rd->span, cpu_active_mask) + cpus++; + + return cpus; +} +#else +static inline struct dl_bw *dl_bw_of(int i) +{ + return &cpu_rq(i)->dl.dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + return 1; +} +#endif + +static inline +void add_running_bw(u64 dl_bw, struct dl_rq *dl_rq) +{ + u64 old = dl_rq->running_bw; + + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); + dl_rq->running_bw += dl_bw; + SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */ + SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw); +} + +static inline +void sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq) +{ + u64 old = dl_rq->running_bw; + + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); + dl_rq->running_bw -= dl_bw; + SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */ + if (dl_rq->running_bw > old) + dl_rq->running_bw = 0; +} + +static inline +void add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq) +{ + u64 old = dl_rq->this_bw; + + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); + dl_rq->this_bw += dl_bw; + SCHED_WARN_ON(dl_rq->this_bw < old); /* overflow */ +} + +static inline +void sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq) +{ + u64 old = dl_rq->this_bw; + + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); + dl_rq->this_bw -= dl_bw; + SCHED_WARN_ON(dl_rq->this_bw > old); /* underflow */ + if (dl_rq->this_bw > old) + dl_rq->this_bw = 0; + SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw); +} + +void dl_change_utilization(struct task_struct *p, u64 new_bw) +{ + struct rq *rq; + + if (task_on_rq_queued(p)) + return; + + rq = task_rq(p); + if (p->dl.dl_non_contending) { + sub_running_bw(p->dl.dl_bw, &rq->dl); + p->dl.dl_non_contending = 0; + /* + * If the timer handler is currently running and the + * timer cannot be cancelled, inactive_task_timer() + * will see that dl_not_contending is not set, and + * will not touch the rq's active utilization, + * so we are still safe. + */ + if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) + put_task_struct(p); + } + sub_rq_bw(p->dl.dl_bw, &rq->dl); + add_rq_bw(new_bw, &rq->dl); +} + +/* + * The utilization of a task cannot be immediately removed from + * the rq active utilization (running_bw) when the task blocks. + * Instead, we have to wait for the so called "0-lag time". + * + * If a task blocks before the "0-lag time", a timer (the inactive + * timer) is armed, and running_bw is decreased when the timer + * fires. + * + * If the task wakes up again before the inactive timer fires, + * the timer is cancelled, whereas if the task wakes up after the + * inactive timer fired (and running_bw has been decreased) the + * task's utilization has to be added to running_bw again. + * A flag in the deadline scheduling entity (dl_non_contending) + * is used to avoid race conditions between the inactive timer handler + * and task wakeups. + * + * The following diagram shows how running_bw is updated. A task is + * "ACTIVE" when its utilization contributes to running_bw; an + * "ACTIVE contending" task is in the TASK_RUNNING state, while an + * "ACTIVE non contending" task is a blocked task for which the "0-lag time" + * has not passed yet. An "INACTIVE" task is a task for which the "0-lag" + * time already passed, which does not contribute to running_bw anymore. + * +------------------+ + * wakeup | ACTIVE | + * +------------------>+ contending | + * | add_running_bw | | + * | +----+------+------+ + * | | ^ + * | dequeue | | + * +--------+-------+ | | + * | | t >= 0-lag | | wakeup + * | INACTIVE |<---------------+ | + * | | sub_running_bw | | + * +--------+-------+ | | + * ^ | | + * | t < 0-lag | | + * | | | + * | V | + * | +----+------+------+ + * | sub_running_bw | ACTIVE | + * +-------------------+ | + * inactive timer | non contending | + * fired +------------------+ + * + * The task_non_contending() function is invoked when a task + * blocks, and checks if the 0-lag time already passed or + * not (in the first case, it directly updates running_bw; + * in the second case, it arms the inactive timer). + * + * The task_contending() function is invoked when a task wakes + * up, and checks if the task is still in the "ACTIVE non contending" + * state or not (in the second case, it updates running_bw). + */ +static void task_non_contending(struct task_struct *p) +{ + struct sched_dl_entity *dl_se = &p->dl; + struct hrtimer *timer = &dl_se->inactive_timer; + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + s64 zerolag_time; + + /* + * If this is a non-deadline task that has been boosted, + * do nothing + */ + if (dl_se->dl_runtime == 0) + return; + + WARN_ON(hrtimer_active(&dl_se->inactive_timer)); + WARN_ON(dl_se->dl_non_contending); + + zerolag_time = dl_se->deadline - + div64_long((dl_se->runtime * dl_se->dl_period), + dl_se->dl_runtime); + + /* + * Using relative times instead of the absolute "0-lag time" + * allows to simplify the code + */ + zerolag_time -= rq_clock(rq); + + /* + * If the "0-lag time" already passed, decrease the active + * utilization now, instead of starting a timer + */ + if (zerolag_time < 0) { + if (dl_task(p)) + sub_running_bw(dl_se->dl_bw, dl_rq); + if (!dl_task(p) || p->state == TASK_DEAD) { + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + + if (p->state == TASK_DEAD) + sub_rq_bw(p->dl.dl_bw, &rq->dl); + raw_spin_lock(&dl_b->lock); + __dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p))); + __dl_clear_params(p); + raw_spin_unlock(&dl_b->lock); + } + + return; + } + + dl_se->dl_non_contending = 1; + get_task_struct(p); + hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL); +} + +static void task_contending(struct sched_dl_entity *dl_se, int flags) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + + /* + * If this is a non-deadline task that has been boosted, + * do nothing + */ + if (dl_se->dl_runtime == 0) + return; + + if (flags & ENQUEUE_MIGRATED) + add_rq_bw(dl_se->dl_bw, dl_rq); + + if (dl_se->dl_non_contending) { + dl_se->dl_non_contending = 0; + /* + * If the timer handler is currently running and the + * timer cannot be cancelled, inactive_task_timer() + * will see that dl_not_contending is not set, and + * will not touch the rq's active utilization, + * so we are still safe. + */ + if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) + put_task_struct(dl_task_of(dl_se)); + } else { + /* + * Since "dl_non_contending" is not set, the + * task's utilization has already been removed from + * active utilization (either when the task blocked, + * when the "inactive timer" fired). + * So, add it back. + */ + add_running_bw(dl_se->dl_bw, dl_rq); + } +} + static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq) { struct sched_dl_entity *dl_se = &p->dl; @@ -83,6 +332,10 @@ void init_dl_rq(struct dl_rq *dl_rq) #else init_dl_bw(&dl_rq->dl_bw); #endif + + dl_rq->running_bw = 0; + dl_rq->this_bw = 0; + init_dl_rq_bw_ratio(dl_rq); } #ifdef CONFIG_SMP @@ -484,13 +737,84 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, } /* - * When a -deadline entity is queued back on the runqueue, its runtime and - * deadline might need updating. + * Revised wakeup rule [1]: For self-suspending tasks, rather then + * re-initializing task's runtime and deadline, the revised wakeup + * rule adjusts the task's runtime to avoid the task to overrun its + * density. + * + * Reasoning: a task may overrun the density if: + * runtime / (deadline - t) > dl_runtime / dl_deadline + * + * Therefore, runtime can be adjusted to: + * runtime = (dl_runtime / dl_deadline) * (deadline - t) + * + * In such way that runtime will be equal to the maximum density + * the task can use without breaking any rule. + * + * [1] Luca Abeni, Giuseppe Lipari, and Juri Lelli. 2015. Constant + * bandwidth server revisited. SIGBED Rev. 11, 4 (January 2015), 19-24. + */ +static void +update_dl_revised_wakeup(struct sched_dl_entity *dl_se, struct rq *rq) +{ + u64 laxity = dl_se->deadline - rq_clock(rq); + + /* + * If the task has deadline < period, and the deadline is in the past, + * it should already be throttled before this check. + * + * See update_dl_entity() comments for further details. + */ + WARN_ON(dl_time_before(dl_se->deadline, rq_clock(rq))); + + dl_se->runtime = (dl_se->dl_density * laxity) >> BW_SHIFT; +} + +/* + * Regarding the deadline, a task with implicit deadline has a relative + * deadline == relative period. A task with constrained deadline has a + * relative deadline <= relative period. + * + * We support constrained deadline tasks. However, there are some restrictions + * applied only for tasks which do not have an implicit deadline. See + * update_dl_entity() to know more about such restrictions. + * + * The dl_is_implicit() returns true if the task has an implicit deadline. + */ +static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_deadline == dl_se->dl_period; +} + +/* + * When a deadline entity is placed in the runqueue, its runtime and deadline + * might need to be updated. This is done by a CBS wake up rule. There are two + * different rules: 1) the original CBS; and 2) the Revisited CBS. + * + * When the task is starting a new period, the Original CBS is used. In this + * case, the runtime is replenished and a new absolute deadline is set. + * + * When a task is queued before the begin of the next period, using the + * remaining runtime and deadline could make the entity to overflow, see + * dl_entity_overflow() to find more about runtime overflow. When such case + * is detected, the runtime and deadline need to be updated. + * + * If the task has an implicit deadline, i.e., deadline == period, the Original + * CBS is applied. the runtime is replenished and a new absolute deadline is + * set, as in the previous cases. + * + * However, the Original CBS does not work properly for tasks with + * deadline < period, which are said to have a constrained deadline. By + * applying the Original CBS, a constrained deadline task would be able to run + * runtime/deadline in a period. With deadline < period, the task would + * overrun the runtime/period allowed bandwidth, breaking the admission test. * - * The policy here is that we update the deadline of the entity only if: - * - the current deadline is in the past, - * - using the remaining runtime with the current deadline would make - * the entity exceed its bandwidth. + * In order to prevent this misbehave, the Revisited CBS is used for + * constrained deadline tasks when a runtime overflow is detected. In the + * Revisited CBS, rather than replenishing & setting a new absolute deadline, + * the remaining runtime of the task is reduced to avoid runtime overflow. + * Please refer to the comments update_dl_revised_wakeup() function to find + * more about the Revised CBS rule. */ static void update_dl_entity(struct sched_dl_entity *dl_se, struct sched_dl_entity *pi_se) @@ -500,6 +824,14 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, if (dl_time_before(dl_se->deadline, rq_clock(rq)) || dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + + if (unlikely(!dl_is_implicit(dl_se) && + !dl_time_before(dl_se->deadline, rq_clock(rq)) && + !dl_se->dl_boosted)){ + update_dl_revised_wakeup(dl_se, rq); + return; + } + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; } @@ -593,10 +925,8 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * The task might have changed its scheduling policy to something * different than SCHED_DEADLINE (through switched_from_dl()). */ - if (!dl_task(p)) { - __dl_clear_params(p); + if (!dl_task(p)) goto unlock; - } /* * The task might have been boosted by someone else and might be in the @@ -723,6 +1053,8 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) return; dl_se->dl_throttled = 1; + if (dl_se->runtime > 0) + dl_se->runtime = 0; } } @@ -735,6 +1067,47 @@ int dl_runtime_exceeded(struct sched_dl_entity *dl_se) extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); /* + * This function implements the GRUB accounting rule: + * according to the GRUB reclaiming algorithm, the runtime is + * not decreased as "dq = -dt", but as + * "dq = -max{u / Umax, (1 - Uinact - Uextra)} dt", + * where u is the utilization of the task, Umax is the maximum reclaimable + * utilization, Uinact is the (per-runqueue) inactive utilization, computed + * as the difference between the "total runqueue utilization" and the + * runqueue active utilization, and Uextra is the (per runqueue) extra + * reclaimable utilization. + * Since rq->dl.running_bw and rq->dl.this_bw contain utilizations + * multiplied by 2^BW_SHIFT, the result has to be shifted right by + * BW_SHIFT. + * Since rq->dl.bw_ratio contains 1 / Umax multipled by 2^RATIO_SHIFT, + * dl_bw is multiped by rq->dl.bw_ratio and shifted right by RATIO_SHIFT. + * Since delta is a 64 bit variable, to have an overflow its value + * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds. + * So, overflow is not an issue here. + */ +u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se) +{ + u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */ + u64 u_act; + u64 u_act_min = (dl_se->dl_bw * rq->dl.bw_ratio) >> RATIO_SHIFT; + + /* + * Instead of computing max{u * bw_ratio, (1 - u_inact - u_extra)}, + * we compare u_inact + rq->dl.extra_bw with + * 1 - (u * rq->dl.bw_ratio >> RATIO_SHIFT), because + * u_inact + rq->dl.extra_bw can be larger than + * 1 * (so, 1 - u_inact - rq->dl.extra_bw would be negative + * leading to wrong results) + */ + if (u_inact + rq->dl.extra_bw > BW_UNIT - u_act_min) + u_act = u_act_min; + else + u_act = BW_UNIT - u_inact - rq->dl.extra_bw; + + return (delta * u_act) >> BW_SHIFT; +} + +/* * Update the current task's runtime statistics (provided it is still * a -deadline task and has not been removed from the dl_rq). */ @@ -776,6 +1149,8 @@ static void update_curr_dl(struct rq *rq) sched_rt_avg_update(rq, delta_exec); + if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM)) + delta_exec = grub_reclaim(delta_exec, rq, &curr->dl); dl_se->runtime -= delta_exec; throttle: @@ -815,6 +1190,56 @@ throttle: } } +static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer) +{ + struct sched_dl_entity *dl_se = container_of(timer, + struct sched_dl_entity, + inactive_timer); + struct task_struct *p = dl_task_of(dl_se); + struct rq_flags rf; + struct rq *rq; + + rq = task_rq_lock(p, &rf); + + if (!dl_task(p) || p->state == TASK_DEAD) { + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + + if (p->state == TASK_DEAD && dl_se->dl_non_contending) { + sub_running_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl)); + sub_rq_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl)); + dl_se->dl_non_contending = 0; + } + + raw_spin_lock(&dl_b->lock); + __dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p))); + raw_spin_unlock(&dl_b->lock); + __dl_clear_params(p); + + goto unlock; + } + if (dl_se->dl_non_contending == 0) + goto unlock; + + sched_clock_tick(); + update_rq_clock(rq); + + sub_running_bw(dl_se->dl_bw, &rq->dl); + dl_se->dl_non_contending = 0; +unlock: + task_rq_unlock(rq, p, &rf); + put_task_struct(p); + + return HRTIMER_NORESTART; +} + +void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se) +{ + struct hrtimer *timer = &dl_se->inactive_timer; + + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + timer->function = inactive_task_timer; +} + #ifdef CONFIG_SMP static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) @@ -946,10 +1371,12 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, * parameters of the task might need updating. Otherwise, * we want a replenishment of its runtime. */ - if (flags & ENQUEUE_WAKEUP) + if (flags & ENQUEUE_WAKEUP) { + task_contending(dl_se, flags); update_dl_entity(dl_se, pi_se); - else if (flags & ENQUEUE_REPLENISH) + } else if (flags & ENQUEUE_REPLENISH) { replenish_dl_entity(dl_se, pi_se); + } __enqueue_dl_entity(dl_se); } @@ -959,11 +1386,6 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) __dequeue_dl_entity(dl_se); } -static inline bool dl_is_constrained(struct sched_dl_entity *dl_se) -{ - return dl_se->dl_deadline < dl_se->dl_period; -} - static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { struct task_struct *pi_task = rt_mutex_get_top_task(p); @@ -995,17 +1417,32 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * If that is the case, the task will be throttled and * the replenishment timer will be set to the next period. */ - if (!p->dl.dl_throttled && dl_is_constrained(&p->dl)) + if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl)) dl_check_constrained_dl(&p->dl); + if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) { + add_rq_bw(p->dl.dl_bw, &rq->dl); + add_running_bw(p->dl.dl_bw, &rq->dl); + } + /* - * If p is throttled, we do nothing. In fact, if it exhausted + * If p is throttled, we do not enqueue it. In fact, if it exhausted * its budget it needs a replenishment and, since it now is on * its rq, the bandwidth timer callback (which clearly has not * run yet) will take care of this. + * However, the active utilization does not depend on the fact + * that the task is on the runqueue or not (but depends on the + * task's state - in GRUB parlance, "inactive" vs "active contending"). + * In other words, even if a task is throttled its utilization must + * be counted in the active utilization; hence, we need to call + * add_running_bw(). */ - if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) + if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) { + if (flags & ENQUEUE_WAKEUP) + task_contending(&p->dl, flags); + return; + } enqueue_dl_entity(&p->dl, pi_se, flags); @@ -1023,6 +1460,23 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) { update_curr_dl(rq); __dequeue_task_dl(rq, p, flags); + + if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) { + sub_running_bw(p->dl.dl_bw, &rq->dl); + sub_rq_bw(p->dl.dl_bw, &rq->dl); + } + + /* + * This check allows to start the inactive timer (or to immediately + * decrease the active utilization, if needed) in two cases: + * when the task blocks and when it is terminating + * (p->state == TASK_DEAD). We can handle the two cases in the same + * way, because from GRUB's point of view the same thing is happening + * (the task moves from "active contending" to "active non contending" + * or "inactive") + */ + if (flags & DEQUEUE_SLEEP) + task_non_contending(p); } /* @@ -1100,6 +1554,37 @@ out: return cpu; } +static void migrate_task_rq_dl(struct task_struct *p) +{ + struct rq *rq; + + if (p->state != TASK_WAKING) + return; + + rq = task_rq(p); + /* + * Since p->state == TASK_WAKING, set_task_cpu() has been called + * from try_to_wake_up(). Hence, p->pi_lock is locked, but + * rq->lock is not... So, lock it + */ + raw_spin_lock(&rq->lock); + if (p->dl.dl_non_contending) { + sub_running_bw(p->dl.dl_bw, &rq->dl); + p->dl.dl_non_contending = 0; + /* + * If the timer handler is currently running and the + * timer cannot be cancelled, inactive_task_timer() + * will see that dl_not_contending is not set, and + * will not touch the rq's active utilization, + * so we are still safe. + */ + if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) + put_task_struct(p); + } + sub_rq_bw(p->dl.dl_bw, &rq->dl); + raw_spin_unlock(&rq->lock); +} + static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) { /* @@ -1255,19 +1740,6 @@ static void task_fork_dl(struct task_struct *p) */ } -static void task_dead_dl(struct task_struct *p) -{ - struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); - - /* - * Since we are TASK_DEAD we won't slip out of the domain! - */ - raw_spin_lock_irq(&dl_b->lock); - /* XXX we should retain the bw until 0-lag */ - dl_b->total_bw -= p->dl.dl_bw; - raw_spin_unlock_irq(&dl_b->lock); -} - static void set_curr_task_dl(struct rq *rq) { struct task_struct *p = rq->curr; @@ -1533,7 +2005,7 @@ retry: * then possible that next_task has migrated. */ task = pick_next_pushable_dl_task(rq); - if (task_cpu(next_task) == rq->cpu && task == next_task) { + if (task == next_task) { /* * The task is still there. We don't try * again, some other cpu will pull it when ready. @@ -1551,7 +2023,11 @@ retry: } deactivate_task(rq, next_task, 0); + sub_running_bw(next_task->dl.dl_bw, &rq->dl); + sub_rq_bw(next_task->dl.dl_bw, &rq->dl); set_task_cpu(next_task, later_rq->cpu); + add_rq_bw(next_task->dl.dl_bw, &later_rq->dl); + add_running_bw(next_task->dl.dl_bw, &later_rq->dl); activate_task(later_rq, next_task, 0); ret = 1; @@ -1639,7 +2115,11 @@ static void pull_dl_task(struct rq *this_rq) resched = true; deactivate_task(src_rq, p, 0); + sub_running_bw(p->dl.dl_bw, &src_rq->dl); + sub_rq_bw(p->dl.dl_bw, &src_rq->dl); set_task_cpu(p, this_cpu); + add_rq_bw(p->dl.dl_bw, &this_rq->dl); + add_running_bw(p->dl.dl_bw, &this_rq->dl); activate_task(this_rq, p, 0); dmin = p->dl.deadline; @@ -1695,7 +2175,7 @@ static void set_cpus_allowed_dl(struct task_struct *p, * until we complete the update. */ raw_spin_lock(&src_dl_b->lock); - __dl_clear(src_dl_b, p->dl.dl_bw); + __dl_clear(src_dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p))); raw_spin_unlock(&src_dl_b->lock); } @@ -1737,13 +2217,26 @@ void __init init_sched_dl_class(void) static void switched_from_dl(struct rq *rq, struct task_struct *p) { /* - * Start the deadline timer; if we switch back to dl before this we'll - * continue consuming our current CBS slice. If we stay outside of - * SCHED_DEADLINE until the deadline passes, the timer will reset the - * task. + * task_non_contending() can start the "inactive timer" (if the 0-lag + * time is in the future). If the task switches back to dl before + * the "inactive timer" fires, it can continue to consume its current + * runtime using its current deadline. If it stays outside of + * SCHED_DEADLINE until the 0-lag time passes, inactive_task_timer() + * will reset the task parameters. */ - if (!start_dl_timer(p)) - __dl_clear_params(p); + if (task_on_rq_queued(p) && p->dl.dl_runtime) + task_non_contending(p); + + if (!task_on_rq_queued(p)) + sub_rq_bw(p->dl.dl_bw, &rq->dl); + + /* + * We cannot use inactive_task_timer() to invoke sub_running_bw() + * at the 0-lag time, because the task could have been migrated + * while SCHED_OTHER in the meanwhile. + */ + if (p->dl.dl_non_contending) + p->dl.dl_non_contending = 0; /* * Since this might be the only -deadline task on the rq, @@ -1762,11 +2255,15 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) */ static void switched_to_dl(struct rq *rq, struct task_struct *p) { + if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) + put_task_struct(p); /* If p is not queued we will update its parameters at next wakeup. */ - if (!task_on_rq_queued(p)) - return; + if (!task_on_rq_queued(p)) { + add_rq_bw(p->dl.dl_bw, &rq->dl); + return; + } /* * If p is boosted we already updated its params in * rt_mutex_setprio()->enqueue_task(..., ENQUEUE_REPLENISH), @@ -1836,6 +2333,7 @@ const struct sched_class dl_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_dl, + .migrate_task_rq = migrate_task_rq_dl, .set_cpus_allowed = set_cpus_allowed_dl, .rq_online = rq_online_dl, .rq_offline = rq_offline_dl, @@ -1845,7 +2343,6 @@ const struct sched_class dl_sched_class = { .set_curr_task = set_curr_task_dl, .task_tick = task_tick_dl, .task_fork = task_fork_dl, - .task_dead = task_dead_dl, .prio_changed = prio_changed_dl, .switched_from = switched_from_dl, @@ -1854,6 +2351,317 @@ const struct sched_class dl_sched_class = { .update_curr = update_curr_dl, }; +int sched_dl_global_validate(void) +{ + u64 runtime = global_rt_runtime(); + u64 period = global_rt_period(); + u64 new_bw = to_ratio(period, runtime); + struct dl_bw *dl_b; + int cpu, ret = 0; + unsigned long flags; + + /* + * Here we want to check the bandwidth not being set to some + * value smaller than the currently allocated bandwidth in + * any of the root_domains. + * + * FIXME: Cycling on all the CPUs is overdoing, but simpler than + * cycling on root_domains... Discussion on different/better + * solutions is welcome! + */ + for_each_possible_cpu(cpu) { + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + if (new_bw < dl_b->total_bw) + ret = -EBUSY; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (ret) + break; + } + + return ret; +} + +void init_dl_rq_bw_ratio(struct dl_rq *dl_rq) +{ + if (global_rt_runtime() == RUNTIME_INF) { + dl_rq->bw_ratio = 1 << RATIO_SHIFT; + dl_rq->extra_bw = 1 << BW_SHIFT; + } else { + dl_rq->bw_ratio = to_ratio(global_rt_runtime(), + global_rt_period()) >> (BW_SHIFT - RATIO_SHIFT); + dl_rq->extra_bw = to_ratio(global_rt_period(), + global_rt_runtime()); + } +} + +void sched_dl_do_global(void) +{ + u64 new_bw = -1; + struct dl_bw *dl_b; + int cpu; + unsigned long flags; + + def_dl_bandwidth.dl_period = global_rt_period(); + def_dl_bandwidth.dl_runtime = global_rt_runtime(); + + if (global_rt_runtime() != RUNTIME_INF) + new_bw = to_ratio(global_rt_period(), global_rt_runtime()); + + /* + * FIXME: As above... + */ + for_each_possible_cpu(cpu) { + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + dl_b->bw = new_bw; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl); + } +} + +/* + * We must be sure that accepting a new task (or allowing changing the + * parameters of an existing one) is consistent with the bandwidth + * constraints. If yes, this function also accordingly updates the currently + * allocated bandwidth to reflect the new situation. + * + * This function is called while holding p's rq->lock. + */ +int sched_dl_overflow(struct task_struct *p, int policy, + const struct sched_attr *attr) +{ + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + u64 period = attr->sched_period ?: attr->sched_deadline; + u64 runtime = attr->sched_runtime; + u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; + int cpus, err = -1; + + /* !deadline task may carry old deadline bandwidth */ + if (new_bw == p->dl.dl_bw && task_has_dl_policy(p)) + return 0; + + /* + * Either if a task, enters, leave, or stays -deadline but changes + * its parameters, we may need to update accordingly the total + * allocated bandwidth of the container. + */ + raw_spin_lock(&dl_b->lock); + cpus = dl_bw_cpus(task_cpu(p)); + if (dl_policy(policy) && !task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, 0, new_bw)) { + if (hrtimer_active(&p->dl.inactive_timer)) + __dl_clear(dl_b, p->dl.dl_bw, cpus); + __dl_add(dl_b, new_bw, cpus); + err = 0; + } else if (dl_policy(policy) && task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) { + /* + * XXX this is slightly incorrect: when the task + * utilization decreases, we should delay the total + * utilization change until the task's 0-lag point. + * But this would require to set the task's "inactive + * timer" when the task is not inactive. + */ + __dl_clear(dl_b, p->dl.dl_bw, cpus); + __dl_add(dl_b, new_bw, cpus); + dl_change_utilization(p, new_bw); + err = 0; + } else if (!dl_policy(policy) && task_has_dl_policy(p)) { + /* + * Do not decrease the total deadline utilization here, + * switched_from_dl() will take care to do it at the correct + * (0-lag) time. + */ + err = 0; + } + raw_spin_unlock(&dl_b->lock); + + return err; +} + +/* + * This function initializes the sched_dl_entity of a newly becoming + * SCHED_DEADLINE task. + * + * Only the static values are considered here, the actual runtime and the + * absolute deadline will be properly calculated when the task is enqueued + * for the first time with its new policy. + */ +void __setparam_dl(struct task_struct *p, const struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + dl_se->dl_runtime = attr->sched_runtime; + dl_se->dl_deadline = attr->sched_deadline; + dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline; + dl_se->flags = attr->sched_flags; + dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); + dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime); +} + +void __getparam_dl(struct task_struct *p, struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + attr->sched_priority = p->rt_priority; + attr->sched_runtime = dl_se->dl_runtime; + attr->sched_deadline = dl_se->dl_deadline; + attr->sched_period = dl_se->dl_period; + attr->sched_flags = dl_se->flags; +} + +/* + * This function validates the new parameters of a -deadline task. + * We ask for the deadline not being zero, and greater or equal + * than the runtime, as well as the period of being zero or + * greater than deadline. Furthermore, we have to be sure that + * user parameters are above the internal resolution of 1us (we + * check sched_runtime only since it is always the smaller one) and + * below 2^63 ns (we have to check both sched_deadline and + * sched_period, as the latter can be zero). + */ +bool __checkparam_dl(const struct sched_attr *attr) +{ + /* deadline != 0 */ + if (attr->sched_deadline == 0) + return false; + + /* + * Since we truncate DL_SCALE bits, make sure we're at least + * that big. + */ + if (attr->sched_runtime < (1ULL << DL_SCALE)) + return false; + + /* + * Since we use the MSB for wrap-around and sign issues, make + * sure it's not set (mind that period can be equal to zero). + */ + if (attr->sched_deadline & (1ULL << 63) || + attr->sched_period & (1ULL << 63)) + return false; + + /* runtime <= deadline <= period (if period != 0) */ + if ((attr->sched_period != 0 && + attr->sched_period < attr->sched_deadline) || + attr->sched_deadline < attr->sched_runtime) + return false; + + return true; +} + +/* + * This function clears the sched_dl_entity static params. + */ +void __dl_clear_params(struct task_struct *p) +{ + struct sched_dl_entity *dl_se = &p->dl; + + dl_se->dl_runtime = 0; + dl_se->dl_deadline = 0; + dl_se->dl_period = 0; + dl_se->flags = 0; + dl_se->dl_bw = 0; + dl_se->dl_density = 0; + + dl_se->dl_throttled = 0; + dl_se->dl_yielded = 0; + dl_se->dl_non_contending = 0; +} + +bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + if (dl_se->dl_runtime != attr->sched_runtime || + dl_se->dl_deadline != attr->sched_deadline || + dl_se->dl_period != attr->sched_period || + dl_se->flags != attr->sched_flags) + return true; + + return false; +} + +#ifdef CONFIG_SMP +int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed) +{ + unsigned int dest_cpu = cpumask_any_and(cpu_active_mask, + cs_cpus_allowed); + struct dl_bw *dl_b; + bool overflow; + int cpus, ret; + unsigned long flags; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(dest_cpu); + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(dest_cpu); + overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw); + if (overflow) + ret = -EBUSY; + else { + /* + * We reserve space for this task in the destination + * root_domain, as we can't fail after this point. + * We will free resources in the source root_domain + * later on (see set_cpus_allowed_dl()). + */ + __dl_add(dl_b, p->dl.dl_bw, cpus); + ret = 0; + } + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + rcu_read_unlock_sched(); + return ret; +} + +int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, + const struct cpumask *trial) +{ + int ret = 1, trial_cpus; + struct dl_bw *cur_dl_b; + unsigned long flags; + + rcu_read_lock_sched(); + cur_dl_b = dl_bw_of(cpumask_any(cur)); + trial_cpus = cpumask_weight(trial); + + raw_spin_lock_irqsave(&cur_dl_b->lock, flags); + if (cur_dl_b->bw != -1 && + cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw) + ret = 0; + raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags); + rcu_read_unlock_sched(); + return ret; +} + +bool dl_cpu_busy(unsigned int cpu) +{ + unsigned long flags; + struct dl_bw *dl_b; + bool overflow; + int cpus; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + rcu_read_unlock_sched(); + return overflow; +} +#endif + #ifdef CONFIG_SCHED_DEBUG extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 38f019324f1a..4fa66de52bd6 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -552,15 +552,21 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) #define P(x) \ SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x)) +#define PU(x) \ + SEQ_printf(m, " .%-30s: %lu\n", #x, (unsigned long)(rt_rq->x)) #define PN(x) \ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x)) - P(rt_nr_running); + PU(rt_nr_running); +#ifdef CONFIG_SMP + PU(rt_nr_migratory); +#endif P(rt_throttled); PN(rt_time); PN(rt_runtime); #undef PN +#undef PU #undef P } @@ -569,14 +575,21 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) struct dl_bw *dl_bw; SEQ_printf(m, "\ndl_rq[%d]:\n", cpu); - SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running); + +#define PU(x) \ + SEQ_printf(m, " .%-30s: %lu\n", #x, (unsigned long)(dl_rq->x)) + + PU(dl_nr_running); #ifdef CONFIG_SMP + PU(dl_nr_migratory); dl_bw = &cpu_rq(cpu)->rd->dl_bw; #else dl_bw = &dl_rq->dl_bw; #endif SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw); SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw); + +#undef PU } extern __read_mostly int sched_clock_running; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d71109321841..008c514dc241 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -369,8 +369,9 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) } /* Iterate thr' all leaf cfs_rq's on a runqueue */ -#define for_each_leaf_cfs_rq(rq, cfs_rq) \ - list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) +#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \ + list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list, \ + leaf_cfs_rq_list) /* Do the two (enqueued) entities belong to the same group ? */ static inline struct cfs_rq * @@ -463,8 +464,8 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) { } -#define for_each_leaf_cfs_rq(rq, cfs_rq) \ - for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL) +#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \ + for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos) static inline struct sched_entity *parent_entity(struct sched_entity *se) { @@ -1381,7 +1382,6 @@ static unsigned long weighted_cpuload(const int cpu); static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); static unsigned long capacity_of(int cpu); -static long effective_load(struct task_group *tg, int cpu, long wl, long wg); /* Cached statistics for all CPUs within a node */ struct numa_stats { @@ -2469,7 +2469,8 @@ void task_numa_work(struct callback_head *work) return; - down_read(&mm->mmap_sem); + if (!down_read_trylock(&mm->mmap_sem)) + return; vma = find_vma(mm, start); if (!vma) { reset_ptenuma_scan(p); @@ -2584,6 +2585,60 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr) } } } + +/* + * Can a task be moved from prev_cpu to this_cpu without causing a load + * imbalance that would trigger the load balancer? + */ +static inline bool numa_wake_affine(struct sched_domain *sd, + struct task_struct *p, int this_cpu, + int prev_cpu, int sync) +{ + struct numa_stats prev_load, this_load; + s64 this_eff_load, prev_eff_load; + + update_numa_stats(&prev_load, cpu_to_node(prev_cpu)); + update_numa_stats(&this_load, cpu_to_node(this_cpu)); + + /* + * If sync wakeup then subtract the (maximum possible) + * effect of the currently running task from the load + * of the current CPU: + */ + if (sync) { + unsigned long current_load = task_h_load(current); + + if (this_load.load > current_load) + this_load.load -= current_load; + else + this_load.load = 0; + } + + /* + * In low-load situations, where this_cpu's node is idle due to the + * sync cause above having dropped this_load.load to 0, move the task. + * Moving to an idle socket will not create a bad imbalance. + * + * Otherwise check if the nodes are near enough in load to allow this + * task to be woken on this_cpu's node. + */ + if (this_load.load > 0) { + unsigned long task_load = task_h_load(p); + + this_eff_load = 100; + this_eff_load *= prev_load.compute_capacity; + + prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= this_load.compute_capacity; + + this_eff_load *= this_load.load + task_load; + prev_eff_load *= prev_load.load - task_load; + + return this_eff_load <= prev_eff_load; + } + + return true; +} #else static void task_tick_numa(struct rq *rq, struct task_struct *curr) { @@ -2596,6 +2651,15 @@ static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p) static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p) { } + +#ifdef CONFIG_SMP +static inline bool numa_wake_affine(struct sched_domain *sd, + struct task_struct *p, int this_cpu, + int prev_cpu, int sync) +{ + return true; +} +#endif /* !SMP */ #endif /* CONFIG_NUMA_BALANCING */ static void @@ -2916,12 +2980,12 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa, /* * Step 2: update *_avg. */ - sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX); + sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib); if (cfs_rq) { cfs_rq->runnable_load_avg = - div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX); + div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib); } - sa->util_avg = sa->util_sum / LOAD_AVG_MAX; + sa->util_avg = sa->util_sum / (LOAD_AVG_MAX - 1024 + sa->period_contrib); return 1; } @@ -2982,8 +3046,7 @@ __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) * differential update where we store the last value we propagated. This in * turn allows skipping updates if the differential is 'small'. * - * Updating tg's load_avg is necessary before update_cfs_share() (which is - * done) and effective_load() (which is not done because it is too costly). + * Updating tg's load_avg is necessary before update_cfs_share(). */ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) { @@ -3563,7 +3626,7 @@ static inline void check_schedstat_required(void) trace_sched_stat_runtime_enabled()) { printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, " "stat_blocked and stat_runtime require the " - "kernel parameter schedstats=enabled or " + "kernel parameter schedstats=enable or " "kernel.sched_schedstats=1\n"); } #endif @@ -4642,24 +4705,43 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) hrtimer_cancel(&cfs_b->slack_timer); } +/* + * Both these cpu hotplug callbacks race against unregister_fair_sched_group() + * + * The race is harmless, since modifying bandwidth settings of unhooked group + * bits doesn't do much. + */ + +/* cpu online calback */ static void __maybe_unused update_runtime_enabled(struct rq *rq) { - struct cfs_rq *cfs_rq; + struct task_group *tg; - for_each_leaf_cfs_rq(rq, cfs_rq) { - struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth; + lockdep_assert_held(&rq->lock); + + rcu_read_lock(); + list_for_each_entry_rcu(tg, &task_groups, list) { + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; raw_spin_lock(&cfs_b->lock); cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF; raw_spin_unlock(&cfs_b->lock); } + rcu_read_unlock(); } +/* cpu offline callback */ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) { - struct cfs_rq *cfs_rq; + struct task_group *tg; + + lockdep_assert_held(&rq->lock); + + rcu_read_lock(); + list_for_each_entry_rcu(tg, &task_groups, list) { + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; - for_each_leaf_cfs_rq(rq, cfs_rq) { if (!cfs_rq->runtime_enabled) continue; @@ -4677,6 +4759,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) if (cfs_rq_throttled(cfs_rq)) unthrottle_cfs_rq(cfs_rq); } + rcu_read_unlock(); } #else /* CONFIG_CFS_BANDWIDTH */ @@ -5215,126 +5298,6 @@ static unsigned long cpu_avg_load_per_task(int cpu) return 0; } -#ifdef CONFIG_FAIR_GROUP_SCHED -/* - * effective_load() calculates the load change as seen from the root_task_group - * - * Adding load to a group doesn't make a group heavier, but can cause movement - * of group shares between cpus. Assuming the shares were perfectly aligned one - * can calculate the shift in shares. - * - * Calculate the effective load difference if @wl is added (subtracted) to @tg - * on this @cpu and results in a total addition (subtraction) of @wg to the - * total group weight. - * - * Given a runqueue weight distribution (rw_i) we can compute a shares - * distribution (s_i) using: - * - * s_i = rw_i / \Sum rw_j (1) - * - * Suppose we have 4 CPUs and our @tg is a direct child of the root group and - * has 7 equal weight tasks, distributed as below (rw_i), with the resulting - * shares distribution (s_i): - * - * rw_i = { 2, 4, 1, 0 } - * s_i = { 2/7, 4/7, 1/7, 0 } - * - * As per wake_affine() we're interested in the load of two CPUs (the CPU the - * task used to run on and the CPU the waker is running on), we need to - * compute the effect of waking a task on either CPU and, in case of a sync - * wakeup, compute the effect of the current task going to sleep. - * - * So for a change of @wl to the local @cpu with an overall group weight change - * of @wl we can compute the new shares distribution (s'_i) using: - * - * s'_i = (rw_i + @wl) / (@wg + \Sum rw_j) (2) - * - * Suppose we're interested in CPUs 0 and 1, and want to compute the load - * differences in waking a task to CPU 0. The additional task changes the - * weight and shares distributions like: - * - * rw'_i = { 3, 4, 1, 0 } - * s'_i = { 3/8, 4/8, 1/8, 0 } - * - * We can then compute the difference in effective weight by using: - * - * dw_i = S * (s'_i - s_i) (3) - * - * Where 'S' is the group weight as seen by its parent. - * - * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7) - * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 - - * 4/7) times the weight of the group. - */ -static long effective_load(struct task_group *tg, int cpu, long wl, long wg) -{ - struct sched_entity *se = tg->se[cpu]; - - if (!tg->parent) /* the trivial, non-cgroup case */ - return wl; - - for_each_sched_entity(se) { - struct cfs_rq *cfs_rq = se->my_q; - long W, w = cfs_rq_load_avg(cfs_rq); - - tg = cfs_rq->tg; - - /* - * W = @wg + \Sum rw_j - */ - W = wg + atomic_long_read(&tg->load_avg); - - /* Ensure \Sum rw_j >= rw_i */ - W -= cfs_rq->tg_load_avg_contrib; - W += w; - - /* - * w = rw_i + @wl - */ - w += wl; - - /* - * wl = S * s'_i; see (2) - */ - if (W > 0 && w < W) - wl = (w * (long)scale_load_down(tg->shares)) / W; - else - wl = scale_load_down(tg->shares); - - /* - * Per the above, wl is the new se->load.weight value; since - * those are clipped to [MIN_SHARES, ...) do so now. See - * calc_cfs_shares(). - */ - if (wl < MIN_SHARES) - wl = MIN_SHARES; - - /* - * wl = dw_i = S * (s'_i - s_i); see (3) - */ - wl -= se->avg.load_avg; - - /* - * Recursively apply this logic to all parent groups to compute - * the final effective load change on the root group. Since - * only the @tg group gets extra weight, all parent groups can - * only redistribute existing shares. @wl is the shift in shares - * resulting from this level per the above. - */ - wg = 0; - } - - return wl; -} -#else - -static long effective_load(struct task_group *tg, int cpu, long wl, long wg) -{ - return wl; -} - -#endif - static void record_wakee(struct task_struct *p) { /* @@ -5385,67 +5348,25 @@ static int wake_wide(struct task_struct *p) static int wake_affine(struct sched_domain *sd, struct task_struct *p, int prev_cpu, int sync) { - s64 this_load, load; - s64 this_eff_load, prev_eff_load; - int idx, this_cpu; - struct task_group *tg; - unsigned long weight; - int balanced; - - idx = sd->wake_idx; - this_cpu = smp_processor_id(); - load = source_load(prev_cpu, idx); - this_load = target_load(this_cpu, idx); - - /* - * If sync wakeup then subtract the (maximum possible) - * effect of the currently running task from the load - * of the current CPU: - */ - if (sync) { - tg = task_group(current); - weight = current->se.avg.load_avg; - - this_load += effective_load(tg, this_cpu, -weight, -weight); - load += effective_load(tg, prev_cpu, 0, -weight); - } - - tg = task_group(p); - weight = p->se.avg.load_avg; + int this_cpu = smp_processor_id(); + bool affine = false; /* - * In low-load situations, where prev_cpu is idle and this_cpu is idle - * due to the sync cause above having dropped this_load to 0, we'll - * always have an imbalance, but there's really nothing you can do - * about that, so that's good too. - * - * Otherwise check if either cpus are near enough in load to allow this - * task to be woken on this_cpu. + * Common case: CPUs are in the same socket, and select_idle_sibling() + * will do its thing regardless of what we return: */ - this_eff_load = 100; - this_eff_load *= capacity_of(prev_cpu); - - prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= capacity_of(this_cpu); - - if (this_load > 0) { - this_eff_load *= this_load + - effective_load(tg, this_cpu, weight, weight); - - prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight); - } - - balanced = this_eff_load <= prev_eff_load; + if (cpus_share_cache(prev_cpu, this_cpu)) + affine = true; + else + affine = numa_wake_affine(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); + if (affine) { + schedstat_inc(sd->ttwu_move_affine); + schedstat_inc(p->se.statistics.nr_wakeups_affine); + } - if (!balanced) - return 0; - - schedstat_inc(sd->ttwu_move_affine); - schedstat_inc(p->se.statistics.nr_wakeups_affine); - - return 1; + return affine; } static inline int task_util(struct task_struct *p); @@ -5484,12 +5405,12 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int i; /* Skip over this group if it has no CPUs allowed */ - if (!cpumask_intersects(sched_group_cpus(group), + if (!cpumask_intersects(sched_group_span(group), &p->cpus_allowed)) continue; local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); + sched_group_span(group)); /* * Tally up the load of all CPUs in the group and find @@ -5499,7 +5420,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, runnable_load = 0; max_spare_cap = 0; - for_each_cpu(i, sched_group_cpus(group)) { + for_each_cpu(i, sched_group_span(group)) { /* Bias balancing toward cpus of our domain */ if (local_group) load = source_load(i, load_idx); @@ -5602,10 +5523,10 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) /* Check if we have any choice: */ if (group->group_weight == 1) - return cpumask_first(sched_group_cpus(group)); + return cpumask_first(sched_group_span(group)); /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) { + for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) { if (idle_cpu(i)) { struct rq *rq = cpu_rq(i); struct cpuidle_state *idle = idle_get_state(rq); @@ -5640,43 +5561,6 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; } -/* - * Implement a for_each_cpu() variant that starts the scan at a given cpu - * (@start), and wraps around. - * - * This is used to scan for idle CPUs; such that not all CPUs looking for an - * idle CPU find the same CPU. The down-side is that tasks tend to cycle - * through the LLC domain. - * - * Especially tbench is found sensitive to this. - */ - -static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped) -{ - int next; - -again: - next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1); - - if (*wrapped) { - if (next >= start) - return nr_cpumask_bits; - } else { - if (next >= nr_cpumask_bits) { - *wrapped = 1; - n = -1; - goto again; - } - } - - return next; -} - -#define for_each_cpu_wrap(cpu, mask, start, wrap) \ - for ((wrap) = 0, (cpu) = (start)-1; \ - (cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)), \ - (cpu) < nr_cpumask_bits; ) - #ifdef CONFIG_SCHED_SMT static inline void set_idle_cores(int cpu, int val) @@ -5736,7 +5620,7 @@ unlock: static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target) { struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); - int core, cpu, wrap; + int core, cpu; if (!static_branch_likely(&sched_smt_present)) return -1; @@ -5746,7 +5630,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); - for_each_cpu_wrap(core, cpus, target, wrap) { + for_each_cpu_wrap(core, cpus, target) { bool idle = true; for_each_cpu(cpu, cpu_smt_mask(core)) { @@ -5809,27 +5693,38 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target) { struct sched_domain *this_sd; - u64 avg_cost, avg_idle = this_rq()->avg_idle; + u64 avg_cost, avg_idle; u64 time, cost; s64 delta; - int cpu, wrap; + int cpu, nr = INT_MAX; this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); if (!this_sd) return -1; - avg_cost = this_sd->avg_scan_cost; - /* * Due to large variance we need a large fuzz factor; hackbench in * particularly is sensitive here. */ - if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost) + avg_idle = this_rq()->avg_idle / 512; + avg_cost = this_sd->avg_scan_cost + 1; + + if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost) return -1; + if (sched_feat(SIS_PROP)) { + u64 span_avg = sd->span_weight * avg_idle; + if (span_avg > 4*avg_cost) + nr = div_u64(span_avg, avg_cost); + else + nr = 4; + } + time = local_clock(); - for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) { + for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { + if (!--nr) + return -1; if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) continue; if (idle_cpu(cpu)) @@ -6011,11 +5906,15 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (affine_sd) { sd = NULL; /* Prefer wake_affine over balance flags */ - if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync)) + if (cpu == prev_cpu) + goto pick_cpu; + + if (wake_affine(affine_sd, p, prev_cpu, sync)) new_cpu = cpu; } if (!sd) { + pick_cpu: if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */ new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); @@ -6168,8 +6067,11 @@ static void set_last_buddy(struct sched_entity *se) if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) return; - for_each_sched_entity(se) + for_each_sched_entity(se) { + if (SCHED_WARN_ON(!se->on_rq)) + return; cfs_rq_of(se)->last = se; + } } static void set_next_buddy(struct sched_entity *se) @@ -6177,8 +6079,11 @@ static void set_next_buddy(struct sched_entity *se) if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) return; - for_each_sched_entity(se) + for_each_sched_entity(se) { + if (SCHED_WARN_ON(!se->on_rq)) + return; cfs_rq_of(se)->next = se; + } } static void set_skip_buddy(struct sched_entity *se) @@ -6686,6 +6591,10 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) if (dst_nid == p->numa_preferred_nid) return 0; + /* Leaving a core idle is often worse than degrading locality. */ + if (env->idle != CPU_NOT_IDLE) + return -1; + if (numa_group) { src_faults = group_faults(p, src_nid); dst_faults = group_faults(p, dst_nid); @@ -6970,10 +6879,28 @@ static void attach_tasks(struct lb_env *env) } #ifdef CONFIG_FAIR_GROUP_SCHED + +static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->load.weight) + return false; + + if (cfs_rq->avg.load_sum) + return false; + + if (cfs_rq->avg.util_sum) + return false; + + if (cfs_rq->runnable_load_sum) + return false; + + return true; +} + static void update_blocked_averages(int cpu) { struct rq *rq = cpu_rq(cpu); - struct cfs_rq *cfs_rq; + struct cfs_rq *cfs_rq, *pos; struct rq_flags rf; rq_lock_irqsave(rq, &rf); @@ -6983,7 +6910,7 @@ static void update_blocked_averages(int cpu) * Iterates the task_group tree in a bottom up fashion, see * list_add_leaf_cfs_rq() for details. */ - for_each_leaf_cfs_rq(rq, cfs_rq) { + for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) { struct sched_entity *se; /* throttled entities do not contribute to load */ @@ -6997,6 +6924,13 @@ static void update_blocked_averages(int cpu) se = cfs_rq->tg->se[cpu]; if (se && !skip_blocked_update(se)) update_load_avg(se, 0); + + /* + * There can be a lot of idle CPU cgroups. Don't let fully + * decayed cfs_rqs linger on the list. + */ + if (cfs_rq_is_decayed(cfs_rq)) + list_del_leaf_cfs_rq(cfs_rq); } rq_unlock_irqrestore(rq, &rf); } @@ -7229,7 +7163,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) * span the current group. */ - for_each_cpu(cpu, sched_group_cpus(sdg)) { + for_each_cpu(cpu, sched_group_span(sdg)) { struct sched_group_capacity *sgc; struct rq *rq = cpu_rq(cpu); @@ -7408,7 +7342,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, memset(sgs, 0, sizeof(*sgs)); - for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { + for_each_cpu_and(i, sched_group_span(group), env->cpus) { struct rq *rq = cpu_rq(i); /* Bias balancing toward cpus of our domain */ @@ -7572,7 +7506,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sg_lb_stats *sgs = &tmp_sgs; int local_group; - local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg)); + local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg)); if (local_group) { sds->local = sg; sgs = local; @@ -7927,7 +7861,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, unsigned long busiest_load = 0, busiest_capacity = 1; int i; - for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { + for_each_cpu_and(i, sched_group_span(group), env->cpus) { unsigned long capacity, wl; enum fbq_type rt; @@ -8033,7 +7967,6 @@ static int active_load_balance_cpu_stop(void *data); static int should_we_balance(struct lb_env *env) { struct sched_group *sg = env->sd->groups; - struct cpumask *sg_cpus, *sg_mask; int cpu, balance_cpu = -1; /* @@ -8043,11 +7976,9 @@ static int should_we_balance(struct lb_env *env) if (env->idle == CPU_NEWLY_IDLE) return 1; - sg_cpus = sched_group_cpus(sg); - sg_mask = sched_group_mask(sg); /* Try to find first idle cpu */ - for_each_cpu_and(cpu, sg_cpus, env->cpus) { - if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu)) + for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) { + if (!idle_cpu(cpu)) continue; balance_cpu = cpu; @@ -8083,7 +8014,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, .sd = sd, .dst_cpu = this_cpu, .dst_rq = this_rq, - .dst_grpmask = sched_group_cpus(sd->groups), + .dst_grpmask = sched_group_span(sd->groups), .idle = idle, .loop_break = sched_nr_migrate_break, .cpus = cpus, @@ -8659,6 +8590,10 @@ void nohz_balance_enter_idle(int cpu) if (!cpu_active(cpu)) return; + /* Spare idle load balancing on CPUs that don't want to be disturbed: */ + if (!is_housekeeping_cpu(cpu)) + return; + if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) return; @@ -9523,10 +9458,10 @@ const struct sched_class fair_sched_class = { #ifdef CONFIG_SCHED_DEBUG void print_cfs_stats(struct seq_file *m, int cpu) { - struct cfs_rq *cfs_rq; + struct cfs_rq *cfs_rq, *pos; rcu_read_lock(); - for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq) + for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos) print_cfs_rq(m, cpu, cfs_rq); rcu_read_unlock(); } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 11192e0cb122..d3fb15555291 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -55,6 +55,7 @@ SCHED_FEAT(TTWU_QUEUE, true) * When doing wakeups, attempt to limit superfluous scans of the LLC domain. */ SCHED_FEAT(SIS_AVG_CPU, false) +SCHED_FEAT(SIS_PROP, true) /* * Issue a WARN when we do multiple update_rq_clock() calls @@ -76,7 +77,6 @@ SCHED_FEAT(WARN_DOUBLE_CLOCK, false) SCHED_FEAT(RT_PUSH_IPI, true) #endif -SCHED_FEAT(FORCE_SD_OVERLAP, false) SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) SCHED_FEAT(ATTACH_AGE_LOAD, true) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index ef63adce0c9c..6c23e30c0e5c 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -219,6 +219,7 @@ static void do_idle(void) */ __current_set_polling(); + quiet_vmstat(); tick_nohz_idle_enter(); while (!need_resched()) { diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index f15fb2bdbc0d..f14716a3522f 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -117,7 +117,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) * load-average relies on per-cpu sampling from the tick, it is affected by * NO_HZ. * - * The basic idea is to fold the nr_active delta into a global idle-delta upon + * The basic idea is to fold the nr_active delta into a global NO_HZ-delta upon * entering NO_HZ state such that we can include this as an 'extra' cpu delta * when we read the global state. * @@ -126,7 +126,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) * - When we go NO_HZ idle during the window, we can negate our sample * contribution, causing under-accounting. * - * We avoid this by keeping two idle-delta counters and flipping them + * We avoid this by keeping two NO_HZ-delta counters and flipping them * when the window starts, thus separating old and new NO_HZ load. * * The only trick is the slight shift in index flip for read vs write. @@ -137,22 +137,22 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) * r:0 0 1 1 0 0 1 1 0 * w:0 1 1 0 0 1 1 0 0 * - * This ensures we'll fold the old idle contribution in this window while + * This ensures we'll fold the old NO_HZ contribution in this window while * accumlating the new one. * - * - When we wake up from NO_HZ idle during the window, we push up our + * - When we wake up from NO_HZ during the window, we push up our * contribution, since we effectively move our sample point to a known * busy state. * * This is solved by pushing the window forward, and thus skipping the - * sample, for this cpu (effectively using the idle-delta for this cpu which + * sample, for this cpu (effectively using the NO_HZ-delta for this cpu which * was in effect at the time the window opened). This also solves the issue - * of having to deal with a cpu having been in NOHZ idle for multiple - * LOAD_FREQ intervals. + * of having to deal with a cpu having been in NO_HZ for multiple LOAD_FREQ + * intervals. * * When making the ILB scale, we should try to pull this in as well. */ -static atomic_long_t calc_load_idle[2]; +static atomic_long_t calc_load_nohz[2]; static int calc_load_idx; static inline int calc_load_write_idx(void) @@ -167,7 +167,7 @@ static inline int calc_load_write_idx(void) /* * If the folding window started, make sure we start writing in the - * next idle-delta. + * next NO_HZ-delta. */ if (!time_before(jiffies, READ_ONCE(calc_load_update))) idx++; @@ -180,24 +180,24 @@ static inline int calc_load_read_idx(void) return calc_load_idx & 1; } -void calc_load_enter_idle(void) +void calc_load_nohz_start(void) { struct rq *this_rq = this_rq(); long delta; /* - * We're going into NOHZ mode, if there's any pending delta, fold it - * into the pending idle delta. + * We're going into NO_HZ mode, if there's any pending delta, fold it + * into the pending NO_HZ delta. */ delta = calc_load_fold_active(this_rq, 0); if (delta) { int idx = calc_load_write_idx(); - atomic_long_add(delta, &calc_load_idle[idx]); + atomic_long_add(delta, &calc_load_nohz[idx]); } } -void calc_load_exit_idle(void) +void calc_load_nohz_stop(void) { struct rq *this_rq = this_rq(); @@ -217,13 +217,13 @@ void calc_load_exit_idle(void) this_rq->calc_load_update += LOAD_FREQ; } -static long calc_load_fold_idle(void) +static long calc_load_nohz_fold(void) { int idx = calc_load_read_idx(); long delta = 0; - if (atomic_long_read(&calc_load_idle[idx])) - delta = atomic_long_xchg(&calc_load_idle[idx], 0); + if (atomic_long_read(&calc_load_nohz[idx])) + delta = atomic_long_xchg(&calc_load_nohz[idx], 0); return delta; } @@ -299,9 +299,9 @@ calc_load_n(unsigned long load, unsigned long exp, /* * NO_HZ can leave us missing all per-cpu ticks calling - * calc_load_account_active(), but since an idle CPU folds its delta into - * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold - * in the pending idle delta if our idle period crossed a load cycle boundary. + * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into + * calc_load_nohz per calc_load_nohz_start(), all we need to do is fold + * in the pending NO_HZ delta if our NO_HZ period crossed a load cycle boundary. * * Once we've updated the global active value, we need to apply the exponential * weights adjusted to the number of cycles missed. @@ -330,7 +330,7 @@ static void calc_global_nohz(void) } /* - * Flip the idle index... + * Flip the NO_HZ index... * * Make sure we first write the new time then flip the index, so that * calc_load_write_idx() will see the new time when it reads the new @@ -341,7 +341,7 @@ static void calc_global_nohz(void) } #else /* !CONFIG_NO_HZ_COMMON */ -static inline long calc_load_fold_idle(void) { return 0; } +static inline long calc_load_nohz_fold(void) { return 0; } static inline void calc_global_nohz(void) { } #endif /* CONFIG_NO_HZ_COMMON */ @@ -362,9 +362,9 @@ void calc_global_load(unsigned long ticks) return; /* - * Fold the 'old' idle-delta to include all NO_HZ cpus. + * Fold the 'old' NO_HZ-delta to include all NO_HZ cpus. */ - delta = calc_load_fold_idle(); + delta = calc_load_nohz_fold(); if (delta) atomic_long_add(delta, &calc_load_tasks); @@ -378,7 +378,8 @@ void calc_global_load(unsigned long ticks) WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ); /* - * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk. + * In case we went to NO_HZ for multiple LOAD_FREQ intervals + * catch up in bulk. */ calc_global_nohz(); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 979b7341008a..45caf937ef90 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -840,6 +840,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) int enqueue = 0; struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); struct rq *rq = rq_of_rt_rq(rt_rq); + int skip; + + /* + * When span == cpu_online_mask, taking each rq->lock + * can be time-consuming. Try to avoid it when possible. + */ + raw_spin_lock(&rt_rq->rt_runtime_lock); + skip = !rt_rq->rt_time && !rt_rq->rt_nr_running; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + if (skip) + continue; raw_spin_lock(&rq->lock); if (rt_rq->rt_time) { @@ -1819,7 +1830,7 @@ retry: * pushing. */ task = pick_next_pushable_task(rq); - if (task_cpu(next_task) == rq->cpu && task == next_task) { + if (task == next_task) { /* * The task hasn't migrated, and is still the next * eligible task, but we failed to find a run-queue @@ -2438,6 +2449,316 @@ const struct sched_class rt_sched_class = { .update_curr = update_curr_rt, }; +#ifdef CONFIG_RT_GROUP_SCHED +/* + * Ensure that the real time constraints are schedulable. + */ +static DEFINE_MUTEX(rt_constraints_mutex); + +/* Must be called with tasklist_lock held */ +static inline int tg_has_rt_tasks(struct task_group *tg) +{ + struct task_struct *g, *p; + + /* + * Autogroups do not have RT tasks; see autogroup_create(). + */ + if (task_group_is_autogroup(tg)) + return 0; + + for_each_process_thread(g, p) { + if (rt_task(p) && task_group(p) == tg) + return 1; + } + + return 0; +} + +struct rt_schedulable_data { + struct task_group *tg; + u64 rt_period; + u64 rt_runtime; +}; + +static int tg_rt_schedulable(struct task_group *tg, void *data) +{ + struct rt_schedulable_data *d = data; + struct task_group *child; + unsigned long total, sum = 0; + u64 period, runtime; + + period = ktime_to_ns(tg->rt_bandwidth.rt_period); + runtime = tg->rt_bandwidth.rt_runtime; + + if (tg == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; + } + + /* + * Cannot have more runtime than the period. + */ + if (runtime > period && runtime != RUNTIME_INF) + return -EINVAL; + + /* + * Ensure we don't starve existing RT tasks. + */ + if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) + return -EBUSY; + + total = to_ratio(period, runtime); + + /* + * Nobody can have more than the global setting allows. + */ + if (total > to_ratio(global_rt_period(), global_rt_runtime())) + return -EINVAL; + + /* + * The sum of our children's runtime should not exceed our own. + */ + list_for_each_entry_rcu(child, &tg->children, siblings) { + period = ktime_to_ns(child->rt_bandwidth.rt_period); + runtime = child->rt_bandwidth.rt_runtime; + + if (child == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; + } + + sum += to_ratio(period, runtime); + } + + if (sum > total) + return -EINVAL; + + return 0; +} + +static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) +{ + int ret; + + struct rt_schedulable_data data = { + .tg = tg, + .rt_period = period, + .rt_runtime = runtime, + }; + + rcu_read_lock(); + ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data); + rcu_read_unlock(); + + return ret; +} + +static int tg_set_rt_bandwidth(struct task_group *tg, + u64 rt_period, u64 rt_runtime) +{ + int i, err = 0; + + /* + * Disallowing the root group RT runtime is BAD, it would disallow the + * kernel creating (and or operating) RT threads. + */ + if (tg == &root_task_group && rt_runtime == 0) + return -EINVAL; + + /* No period doesn't make any sense. */ + if (rt_period == 0) + return -EINVAL; + + mutex_lock(&rt_constraints_mutex); + read_lock(&tasklist_lock); + err = __rt_schedulable(tg, rt_period, rt_runtime); + if (err) + goto unlock; + + raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); + tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); + tg->rt_bandwidth.rt_runtime = rt_runtime; + + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = tg->rt_rq[i]; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = rt_runtime; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); +unlock: + read_unlock(&tasklist_lock); + mutex_unlock(&rt_constraints_mutex); + + return err; +} + +int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) +{ + u64 rt_runtime, rt_period; + + rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); + rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; + if (rt_runtime_us < 0) + rt_runtime = RUNTIME_INF; + + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); +} + +long sched_group_rt_runtime(struct task_group *tg) +{ + u64 rt_runtime_us; + + if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) + return -1; + + rt_runtime_us = tg->rt_bandwidth.rt_runtime; + do_div(rt_runtime_us, NSEC_PER_USEC); + return rt_runtime_us; +} + +int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us) +{ + u64 rt_runtime, rt_period; + + rt_period = rt_period_us * NSEC_PER_USEC; + rt_runtime = tg->rt_bandwidth.rt_runtime; + + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); +} + +long sched_group_rt_period(struct task_group *tg) +{ + u64 rt_period_us; + + rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); + do_div(rt_period_us, NSEC_PER_USEC); + return rt_period_us; +} + +static int sched_rt_global_constraints(void) +{ + int ret = 0; + + mutex_lock(&rt_constraints_mutex); + read_lock(&tasklist_lock); + ret = __rt_schedulable(NULL, 0, 0); + read_unlock(&tasklist_lock); + mutex_unlock(&rt_constraints_mutex); + + return ret; +} + +int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +{ + /* Don't accept realtime tasks when there is no way for them to run */ + if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) + return 0; + + return 1; +} + +#else /* !CONFIG_RT_GROUP_SCHED */ +static int sched_rt_global_constraints(void) +{ + unsigned long flags; + int i; + + raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = &cpu_rq(i)->rt; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = global_rt_runtime(); + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); + + return 0; +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +static int sched_rt_global_validate(void) +{ + if (sysctl_sched_rt_period <= 0) + return -EINVAL; + + if ((sysctl_sched_rt_runtime != RUNTIME_INF) && + (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) + return -EINVAL; + + return 0; +} + +static void sched_rt_do_global(void) +{ + def_rt_bandwidth.rt_runtime = global_rt_runtime(); + def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period()); +} + +int sched_rt_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old_period, old_runtime; + static DEFINE_MUTEX(mutex); + int ret; + + mutex_lock(&mutex); + old_period = sysctl_sched_rt_period; + old_runtime = sysctl_sched_rt_runtime; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (!ret && write) { + ret = sched_rt_global_validate(); + if (ret) + goto undo; + + ret = sched_dl_global_validate(); + if (ret) + goto undo; + + ret = sched_rt_global_constraints(); + if (ret) + goto undo; + + sched_rt_do_global(); + sched_dl_do_global(); + } + if (0) { +undo: + sysctl_sched_rt_period = old_period; + sysctl_sched_rt_runtime = old_runtime; + } + mutex_unlock(&mutex); + + return ret; +} + +int sched_rr_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + static DEFINE_MUTEX(mutex); + + mutex_lock(&mutex); + ret = proc_dointvec(table, write, buffer, lenp, ppos); + /* + * Make sure that internally we keep jiffies. + * Also, writing zero resets the timeslice to default: + */ + if (!ret && write) { + sched_rr_timeslice = + sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE : + msecs_to_jiffies(sysctl_sched_rr_timeslice); + } + mutex_unlock(&mutex); + return ret; +} + #ifdef CONFIG_SCHED_DEBUG extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 6dda2aab731e..eeef1a3086d1 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -39,9 +39,9 @@ #include "cpuacct.h" #ifdef CONFIG_SCHED_DEBUG -#define SCHED_WARN_ON(x) WARN_ONCE(x, #x) +# define SCHED_WARN_ON(x) WARN_ONCE(x, #x) #else -#define SCHED_WARN_ON(x) ((void)(x)) +# define SCHED_WARN_ON(x) ({ (void)(x), 0; }) #endif struct rq; @@ -218,23 +218,25 @@ static inline int dl_bandwidth_enabled(void) return sysctl_sched_rt_runtime >= 0; } -extern struct dl_bw *dl_bw_of(int i); - struct dl_bw { raw_spinlock_t lock; u64 bw, total_bw; }; +static inline void __dl_update(struct dl_bw *dl_b, s64 bw); + static inline -void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw) +void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw, int cpus) { dl_b->total_bw -= tsk_bw; + __dl_update(dl_b, (s32)tsk_bw / cpus); } static inline -void __dl_add(struct dl_bw *dl_b, u64 tsk_bw) +void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus) { dl_b->total_bw += tsk_bw; + __dl_update(dl_b, -((s32)tsk_bw / cpus)); } static inline @@ -244,7 +246,22 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw) dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw; } +void dl_change_utilization(struct task_struct *p, u64 new_bw); extern void init_dl_bw(struct dl_bw *dl_b); +extern int sched_dl_global_validate(void); +extern void sched_dl_do_global(void); +extern int sched_dl_overflow(struct task_struct *p, int policy, + const struct sched_attr *attr); +extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr); +extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr); +extern bool __checkparam_dl(const struct sched_attr *attr); +extern void __dl_clear_params(struct task_struct *p); +extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); +extern int dl_task_can_attach(struct task_struct *p, + const struct cpumask *cs_cpus_allowed); +extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, + const struct cpumask *trial); +extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED @@ -366,6 +383,11 @@ extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int cpu, struct sched_rt_entity *parent); +extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us); +extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us); +extern long sched_group_rt_runtime(struct task_group *tg); +extern long sched_group_rt_period(struct task_group *tg); +extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); extern struct task_group *sched_create_group(struct task_group *parent); extern void sched_online_group(struct task_group *tg, @@ -558,6 +580,30 @@ struct dl_rq { #else struct dl_bw dl_bw; #endif + /* + * "Active utilization" for this runqueue: increased when a + * task wakes up (becomes TASK_RUNNING) and decreased when a + * task blocks + */ + u64 running_bw; + + /* + * Utilization of the tasks "assigned" to this runqueue (including + * the tasks that are in runqueue and the tasks that executed on this + * CPU and blocked). Increased when a task moves to this runqueue, and + * decreased when the task moves away (migrates, changes scheduling + * policy, or terminates). + * This is needed to compute the "inactive utilization" for the + * runqueue (inactive utilization = this_bw - running_bw). + */ + u64 this_bw; + u64 extra_bw; + + /* + * Inverse of the fraction of CPU utilization that can be reclaimed + * by the GRUB algorithm. + */ + u64 bw_ratio; }; #ifdef CONFIG_SMP @@ -606,11 +652,9 @@ struct root_domain { extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; -extern cpumask_var_t fallback_doms; -extern cpumask_var_t sched_domains_tmpmask; extern void init_defrootdomain(void); -extern int init_sched_domains(const struct cpumask *cpu_map); +extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); #endif /* CONFIG_SMP */ @@ -1025,7 +1069,11 @@ struct sched_group_capacity { unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ - unsigned long cpumask[0]; /* iteration mask */ +#ifdef CONFIG_SCHED_DEBUG + int id; +#endif + + unsigned long cpumask[0]; /* balance mask */ }; struct sched_group { @@ -1046,16 +1094,15 @@ struct sched_group { unsigned long cpumask[0]; }; -static inline struct cpumask *sched_group_cpus(struct sched_group *sg) +static inline struct cpumask *sched_group_span(struct sched_group *sg) { return to_cpumask(sg->cpumask); } /* - * cpumask masking which cpus in the group are allowed to iterate up the domain - * tree. + * See build_balance_mask(). */ -static inline struct cpumask *sched_group_mask(struct sched_group *sg) +static inline struct cpumask *group_balance_mask(struct sched_group *sg) { return to_cpumask(sg->sgc->cpumask); } @@ -1066,7 +1113,7 @@ static inline struct cpumask *sched_group_mask(struct sched_group *sg) */ static inline unsigned int group_first_cpu(struct sched_group *group) { - return cpumask_first(sched_group_cpus(group)); + return cpumask_first(sched_group_span(group)); } extern int group_balance_cpu(struct sched_group *sg); @@ -1422,7 +1469,11 @@ static inline void set_curr_task(struct rq *rq, struct task_struct *curr) curr->sched_class->set_curr_task(rq); } +#ifdef CONFIG_SMP #define sched_class_highest (&stop_sched_class) +#else +#define sched_class_highest (&dl_sched_class) +#endif #define for_each_class(class) \ for (class = sched_class_highest; class; class = class->next) @@ -1486,7 +1537,12 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime extern struct dl_bandwidth def_dl_bandwidth; extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); extern void init_dl_task_timer(struct sched_dl_entity *dl_se); +extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se); +extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq); +#define BW_SHIFT 20 +#define BW_UNIT (1 << BW_SHIFT) +#define RATIO_SHIFT 8 unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); @@ -1928,6 +1984,33 @@ extern void nohz_balance_exit_idle(unsigned int cpu); static inline void nohz_balance_exit_idle(unsigned int cpu) { } #endif + +#ifdef CONFIG_SMP +static inline +void __dl_update(struct dl_bw *dl_b, s64 bw) +{ + struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw); + int i; + + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); + for_each_cpu_and(i, rd->span, cpu_active_mask) { + struct rq *rq = cpu_rq(i); + + rq->dl.extra_bw += bw; + } +} +#else +static inline +void __dl_update(struct dl_bw *dl_b, s64 bw) +{ + struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw); + + dl->extra_bw += bw; +} +#endif + + #ifdef CONFIG_IRQ_TIME_ACCOUNTING struct irqtime { u64 total; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 1b0b4fb12837..79895aec281e 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -10,6 +10,7 @@ DEFINE_MUTEX(sched_domains_mutex); /* Protected by sched_domains_mutex: */ cpumask_var_t sched_domains_tmpmask; +cpumask_var_t sched_domains_tmpmask2; #ifdef CONFIG_SCHED_DEBUG @@ -35,7 +36,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpumask_clear(groupmask); - printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + printk(KERN_DEBUG "%*s domain-%d: ", level, "", level); if (!(sd->flags & SD_LOAD_BALANCE)) { printk("does not load-balance\n"); @@ -45,14 +46,14 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, return -1; } - printk(KERN_CONT "span %*pbl level %s\n", + printk(KERN_CONT "span=%*pbl level=%s\n", cpumask_pr_args(sched_domain_span(sd)), sd->name); 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_cpus(group))) { + if (!cpumask_test_cpu(cpu, sched_group_span(group))) { printk(KERN_ERR "ERROR: domain->groups does not contain" " CPU%d\n", cpu); } @@ -65,29 +66,47 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (!cpumask_weight(sched_group_cpus(group))) { + if (!cpumask_weight(sched_group_span(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: empty group\n"); break; } if (!(sd->flags & SD_OVERLAP) && - cpumask_intersects(groupmask, sched_group_cpus(group))) { + cpumask_intersects(groupmask, sched_group_span(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: repeated CPUs\n"); break; } - cpumask_or(groupmask, groupmask, sched_group_cpus(group)); + cpumask_or(groupmask, groupmask, sched_group_span(group)); - printk(KERN_CONT " %*pbl", - cpumask_pr_args(sched_group_cpus(group))); - if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { - printk(KERN_CONT " (cpu_capacity = %lu)", - group->sgc->capacity); + printk(KERN_CONT " %d:{ span=%*pbl", + group->sgc->id, + cpumask_pr_args(sched_group_span(group))); + + if ((sd->flags & SD_OVERLAP) && + !cpumask_equal(group_balance_mask(group), sched_group_span(group))) { + printk(KERN_CONT " mask=%*pbl", + cpumask_pr_args(group_balance_mask(group))); + } + + if (group->sgc->capacity != SCHED_CAPACITY_SCALE) + printk(KERN_CONT " cap=%lu", group->sgc->capacity); + + if (group == sd->groups && sd->child && + !cpumask_equal(sched_domain_span(sd->child), + sched_group_span(group))) { + printk(KERN_ERR "ERROR: domain->groups does not match domain->child\n"); } + printk(KERN_CONT " }"); + group = group->next; + + if (group != sd->groups) + printk(KERN_CONT ","); + } while (group != sd->groups); printk(KERN_CONT "\n"); @@ -113,7 +132,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) return; } - printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + printk(KERN_DEBUG "CPU%d attaching sched-domain(s):\n", cpu); for (;;) { if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) @@ -477,46 +496,214 @@ enum s_alloc { }; /* - * Build an iteration mask that can exclude certain CPUs from the upwards - * domain traversal. + * Return the canonical balance CPU for this group, this is the first CPU + * of this group that's also in the balance mask. * - * Asymmetric node setups can result in situations where the domain tree is of - * unequal depth, make sure to skip domains that already cover the entire - * range. + * The balance mask are all those CPUs that could actually end up at this + * group. See build_balance_mask(). * - * In that case build_sched_domains() will have terminated the iteration early - * and our sibling sd spans will be empty. Domains should always include the - * CPU they're built on, so check that. + * Also see should_we_balance(). */ -static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) +int group_balance_cpu(struct sched_group *sg) { - const struct cpumask *span = sched_domain_span(sd); + return cpumask_first(group_balance_mask(sg)); +} + + +/* + * NUMA topology (first read the regular topology blurb below) + * + * Given a node-distance table, for example: + * + * node 0 1 2 3 + * 0: 10 20 30 20 + * 1: 20 10 20 30 + * 2: 30 20 10 20 + * 3: 20 30 20 10 + * + * which represents a 4 node ring topology like: + * + * 0 ----- 1 + * | | + * | | + * | | + * 3 ----- 2 + * + * We want to construct domains and groups to represent this. The way we go + * about doing this is to build the domains on 'hops'. For each NUMA level we + * construct the mask of all nodes reachable in @level hops. + * + * For the above NUMA topology that gives 3 levels: + * + * NUMA-2 0-3 0-3 0-3 0-3 + * groups: {0-1,3},{1-3} {0-2},{0,2-3} {1-3},{0-1,3} {0,2-3},{0-2} + * + * NUMA-1 0-1,3 0-2 1-3 0,2-3 + * groups: {0},{1},{3} {0},{1},{2} {1},{2},{3} {0},{2},{3} + * + * NUMA-0 0 1 2 3 + * + * + * As can be seen; things don't nicely line up as with the regular topology. + * When we iterate a domain in child domain chunks some nodes can be + * represented multiple times -- hence the "overlap" naming for this part of + * the topology. + * + * In order to minimize this overlap, we only build enough groups to cover the + * domain. For instance Node-0 NUMA-2 would only get groups: 0-1,3 and 1-3. + * + * Because: + * + * - the first group of each domain is its child domain; this + * gets us the first 0-1,3 + * - the only uncovered node is 2, who's child domain is 1-3. + * + * However, because of the overlap, computing a unique CPU for each group is + * more complicated. Consider for instance the groups of NODE-1 NUMA-2, both + * groups include the CPUs of Node-0, while those CPUs would not in fact ever + * end up at those groups (they would end up in group: 0-1,3). + * + * To correct this we have to introduce the group balance mask. This mask + * will contain those CPUs in the group that can reach this group given the + * (child) domain tree. + * + * With this we can once again compute balance_cpu and sched_group_capacity + * relations. + * + * XXX include words on how balance_cpu is unique and therefore can be + * used for sched_group_capacity links. + * + * + * Another 'interesting' topology is: + * + * node 0 1 2 3 + * 0: 10 20 20 30 + * 1: 20 10 20 20 + * 2: 20 20 10 20 + * 3: 30 20 20 10 + * + * Which looks a little like: + * + * 0 ----- 1 + * | / | + * | / | + * | / | + * 2 ----- 3 + * + * This topology is asymmetric, nodes 1,2 are fully connected, but nodes 0,3 + * are not. + * + * This leads to a few particularly weird cases where the sched_domain's are + * not of the same number for each cpu. Consider: + * + * NUMA-2 0-3 0-3 + * groups: {0-2},{1-3} {1-3},{0-2} + * + * NUMA-1 0-2 0-3 0-3 1-3 + * + * NUMA-0 0 1 2 3 + * + */ + + +/* + * Build the balance mask; it contains only those CPUs that can arrive at this + * group and should be considered to continue balancing. + * + * We do this during the group creation pass, therefore the group information + * isn't complete yet, however since each group represents a (child) domain we + * can fully construct this using the sched_domain bits (which are already + * complete). + */ +static void +build_balance_mask(struct sched_domain *sd, struct sched_group *sg, struct cpumask *mask) +{ + const struct cpumask *sg_span = sched_group_span(sg); struct sd_data *sdd = sd->private; struct sched_domain *sibling; int i; - for_each_cpu(i, span) { + cpumask_clear(mask); + + for_each_cpu(i, sg_span) { sibling = *per_cpu_ptr(sdd->sd, i); - if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + + /* + * Can happen in the asymmetric case, where these siblings are + * unused. The mask will not be empty because those CPUs that + * do have the top domain _should_ span the domain. + */ + if (!sibling->child) continue; - cpumask_set_cpu(i, sched_group_mask(sg)); + /* If we would not end up here, we can't continue from here */ + if (!cpumask_equal(sg_span, sched_domain_span(sibling->child))) + continue; + + cpumask_set_cpu(i, mask); } + + /* We must not have empty masks here */ + WARN_ON_ONCE(cpumask_empty(mask)); } /* - * Return the canonical balance CPU for this group, this is the first CPU - * of this group that's also in the iteration mask. + * XXX: This creates per-node group entries; since the load-balancer will + * immediately access remote memory to construct this group's load-balance + * statistics having the groups node local is of dubious benefit. */ -int group_balance_cpu(struct sched_group *sg) +static struct sched_group * +build_group_from_child_sched_domain(struct sched_domain *sd, int cpu) { - return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg)); + struct sched_group *sg; + struct cpumask *sg_span; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(cpu)); + + if (!sg) + return NULL; + + sg_span = sched_group_span(sg); + if (sd->child) + cpumask_copy(sg_span, sched_domain_span(sd->child)); + else + cpumask_copy(sg_span, sched_domain_span(sd)); + + return sg; +} + +static void init_overlap_sched_group(struct sched_domain *sd, + struct sched_group *sg) +{ + struct cpumask *mask = sched_domains_tmpmask2; + struct sd_data *sdd = sd->private; + struct cpumask *sg_span; + int cpu; + + build_balance_mask(sd, sg, mask); + cpu = cpumask_first_and(sched_group_span(sg), mask); + + sg->sgc = *per_cpu_ptr(sdd->sgc, cpu); + if (atomic_inc_return(&sg->sgc->ref) == 1) + cpumask_copy(group_balance_mask(sg), mask); + else + WARN_ON_ONCE(!cpumask_equal(group_balance_mask(sg), mask)); + + /* + * Initialize sgc->capacity such that even if we mess up the + * domains and no possible iteration will get us here, we won't + * die on a /0 trap. + */ + sg_span = sched_group_span(sg); + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); + sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; } static int build_overlap_sched_groups(struct sched_domain *sd, int cpu) { - struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; + struct sched_group *first = NULL, *last = NULL, *sg; const struct cpumask *span = sched_domain_span(sd); struct cpumask *covered = sched_domains_tmpmask; struct sd_data *sdd = sd->private; @@ -525,7 +712,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) cpumask_clear(covered); - for_each_cpu(i, span) { + for_each_cpu_wrap(i, span, cpu) { struct cpumask *sg_span; if (cpumask_test_cpu(i, covered)) @@ -533,44 +720,27 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) sibling = *per_cpu_ptr(sdd->sd, i); - /* See the comment near build_group_mask(). */ + /* + * Asymmetric node setups can result in situations where the + * domain tree is of unequal depth, make sure to skip domains + * that already cover the entire range. + * + * In that case build_sched_domains() will have terminated the + * iteration early and our sibling sd spans will be empty. + * Domains should always include the CPU they're built on, so + * check that. + */ if (!cpumask_test_cpu(i, sched_domain_span(sibling))) continue; - sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, cpu_to_node(cpu)); - + sg = build_group_from_child_sched_domain(sibling, cpu); if (!sg) goto fail; - sg_span = sched_group_cpus(sg); - if (sibling->child) - cpumask_copy(sg_span, sched_domain_span(sibling->child)); - else - cpumask_set_cpu(i, sg_span); - + sg_span = sched_group_span(sg); cpumask_or(covered, covered, sg_span); - sg->sgc = *per_cpu_ptr(sdd->sgc, i); - if (atomic_inc_return(&sg->sgc->ref) == 1) - build_group_mask(sd, sg); - - /* - * Initialize sgc->capacity such that even if we mess up the - * domains and no possible iteration will get us here, we won't - * die on a /0 trap. - */ - sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); - sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; - - /* - * Make sure the first group of this domain contains the - * canonical balance CPU. Otherwise the sched_domain iteration - * breaks. See update_sg_lb_stats(). - */ - if ((!groups && cpumask_test_cpu(cpu, sg_span)) || - group_balance_cpu(sg) == cpu) - groups = sg; + init_overlap_sched_group(sd, sg); if (!first) first = sg; @@ -579,7 +749,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) last = sg; last->next = first; } - sd->groups = groups; + sd->groups = first; return 0; @@ -589,23 +759,106 @@ fail: return -ENOMEM; } -static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) + +/* + * Package topology (also see the load-balance blurb in fair.c) + * + * The scheduler builds a tree structure to represent a number of important + * topology features. By default (default_topology[]) these include: + * + * - Simultaneous multithreading (SMT) + * - Multi-Core Cache (MC) + * - Package (DIE) + * + * Where the last one more or less denotes everything up to a NUMA node. + * + * The tree consists of 3 primary data structures: + * + * sched_domain -> sched_group -> sched_group_capacity + * ^ ^ ^ ^ + * `-' `-' + * + * The sched_domains are per-cpu and have a two way link (parent & child) and + * denote the ever growing mask of CPUs belonging to that level of topology. + * + * Each sched_domain has a circular (double) linked list of sched_group's, each + * denoting the domains of the level below (or individual CPUs in case of the + * first domain level). The sched_group linked by a sched_domain includes the + * CPU of that sched_domain [*]. + * + * Take for instance a 2 threaded, 2 core, 2 cache cluster part: + * + * CPU 0 1 2 3 4 5 6 7 + * + * DIE [ ] + * MC [ ] [ ] + * SMT [ ] [ ] [ ] [ ] + * + * - or - + * + * DIE 0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7 + * MC 0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7 + * SMT 0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7 + * + * CPU 0 1 2 3 4 5 6 7 + * + * One way to think about it is: sched_domain moves you up and down among these + * topology levels, while sched_group moves you sideways through it, at child + * domain granularity. + * + * sched_group_capacity ensures each unique sched_group has shared storage. + * + * There are two related construction problems, both require a CPU that + * uniquely identify each group (for a given domain): + * + * - The first is the balance_cpu (see should_we_balance() and the + * load-balance blub in fair.c); for each group we only want 1 CPU to + * continue balancing at a higher domain. + * + * - The second is the sched_group_capacity; we want all identical groups + * to share a single sched_group_capacity. + * + * Since these topologies are exclusive by construction. That is, its + * impossible for an SMT thread to belong to multiple cores, and cores to + * be part of multiple caches. There is a very clear and unique location + * for each CPU in the hierarchy. + * + * Therefore computing a unique CPU for each group is trivial (the iteration + * mask is redundant and set all 1s; all CPUs in a group will end up at _that_ + * group), we can simply pick the first CPU in each group. + * + * + * [*] in other words, the first group of each domain is its child domain. + */ + +static struct sched_group *get_group(int cpu, struct sd_data *sdd) { struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); struct sched_domain *child = sd->child; + struct sched_group *sg; if (child) cpu = cpumask_first(sched_domain_span(child)); - if (sg) { - *sg = *per_cpu_ptr(sdd->sg, cpu); - (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); + sg = *per_cpu_ptr(sdd->sg, cpu); + sg->sgc = *per_cpu_ptr(sdd->sgc, cpu); + + /* For claim_allocations: */ + atomic_inc(&sg->ref); + atomic_inc(&sg->sgc->ref); - /* For claim_allocations: */ - atomic_set(&(*sg)->sgc->ref, 1); + if (child) { + cpumask_copy(sched_group_span(sg), sched_domain_span(child)); + cpumask_copy(group_balance_mask(sg), sched_group_span(sg)); + } else { + cpumask_set_cpu(cpu, sched_group_span(sg)); + cpumask_set_cpu(cpu, group_balance_mask(sg)); } - return cpu; + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg)); + sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; + + return sg; } /* @@ -624,34 +877,20 @@ build_sched_groups(struct sched_domain *sd, int cpu) struct cpumask *covered; int i; - get_group(cpu, sdd, &sd->groups); - atomic_inc(&sd->groups->ref); - - if (cpu != cpumask_first(span)) - return 0; - lockdep_assert_held(&sched_domains_mutex); covered = sched_domains_tmpmask; cpumask_clear(covered); - for_each_cpu(i, span) { + for_each_cpu_wrap(i, span, cpu) { struct sched_group *sg; - int group, j; if (cpumask_test_cpu(i, covered)) continue; - group = get_group(i, sdd, &sg); - cpumask_setall(sched_group_mask(sg)); + sg = get_group(i, sdd); - for_each_cpu(j, span) { - if (get_group(j, sdd, NULL) != group) - continue; - - cpumask_set_cpu(j, covered); - cpumask_set_cpu(j, sched_group_cpus(sg)); - } + cpumask_or(covered, covered, sched_group_span(sg)); if (!first) first = sg; @@ -660,6 +899,7 @@ build_sched_groups(struct sched_domain *sd, int cpu) last = sg; } last->next = first; + sd->groups = first; return 0; } @@ -683,12 +923,12 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) do { int cpu, max_cpu = -1; - sg->group_weight = cpumask_weight(sched_group_cpus(sg)); + sg->group_weight = cpumask_weight(sched_group_span(sg)); if (!(sd->flags & SD_ASYM_PACKING)) goto next; - for_each_cpu(cpu, sched_group_cpus(sg)) { + for_each_cpu(cpu, sched_group_span(sg)) { if (max_cpu < 0) max_cpu = cpu; else if (sched_asym_prefer(cpu, max_cpu)) @@ -1308,6 +1548,10 @@ static int __sdt_alloc(const struct cpumask *cpu_map) if (!sgc) return -ENOMEM; +#ifdef CONFIG_SCHED_DEBUG + sgc->id = j; +#endif + *per_cpu_ptr(sdd->sgc, j) = sgc; } } @@ -1407,7 +1651,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att sd = build_sched_domain(tl, cpu_map, attr, sd, i); if (tl == sched_domain_topology) *per_cpu_ptr(d.sd, i) = sd; - if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) + if (tl->flags & SDTL_OVERLAP) sd->flags |= SD_OVERLAP; if (cpumask_equal(cpu_map, sched_domain_span(sd))) break; @@ -1478,7 +1722,7 @@ static struct sched_domain_attr *dattr_cur; * cpumask) fails, then fallback to a single sched domain, * as determined by the single cpumask fallback_doms. */ -cpumask_var_t fallback_doms; +static cpumask_var_t fallback_doms; /* * arch_update_cpu_topology lets virtualized architectures update the @@ -1520,10 +1764,14 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) * For now this just excludes isolated CPUs, but could be used to * exclude other special cases in the future. */ -int init_sched_domains(const struct cpumask *cpu_map) +int sched_init_domains(const struct cpumask *cpu_map) { int err; + zalloc_cpumask_var(&sched_domains_tmpmask, GFP_KERNEL); + zalloc_cpumask_var(&sched_domains_tmpmask2, GFP_KERNEL); + zalloc_cpumask_var(&fallback_doms, GFP_KERNEL); + arch_update_cpu_topology(); ndoms_cur = 1; doms_cur = alloc_sched_domains(ndoms_cur); diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index b8c84c6dee64..17f11c6b0a9f 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -12,44 +12,44 @@ #include <linux/hash.h> #include <linux/kthread.h> -void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key) +void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key) { - spin_lock_init(&q->lock); - lockdep_set_class_and_name(&q->lock, key, name); - INIT_LIST_HEAD(&q->task_list); + spin_lock_init(&wq_head->lock); + lockdep_set_class_and_name(&wq_head->lock, key, name); + INIT_LIST_HEAD(&wq_head->head); } EXPORT_SYMBOL(__init_waitqueue_head); -void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; - wait->flags &= ~WQ_FLAG_EXCLUSIVE; - spin_lock_irqsave(&q->lock, flags); - __add_wait_queue(q, wait); - spin_unlock_irqrestore(&q->lock, flags); + wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&wq_head->lock, flags); + __add_wait_queue_entry_tail(wq_head, wq_entry); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(add_wait_queue); -void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; - wait->flags |= WQ_FLAG_EXCLUSIVE; - spin_lock_irqsave(&q->lock, flags); - __add_wait_queue_tail(q, wait); - spin_unlock_irqrestore(&q->lock, flags); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&wq_head->lock, flags); + __add_wait_queue_entry_tail(wq_head, wq_entry); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(add_wait_queue_exclusive); -void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; - spin_lock_irqsave(&q->lock, flags); - __remove_wait_queue(q, wait); - spin_unlock_irqrestore(&q->lock, flags); + spin_lock_irqsave(&wq_head->lock, flags); + __remove_wait_queue(wq_head, wq_entry); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(remove_wait_queue); @@ -63,12 +63,12 @@ EXPORT_SYMBOL(remove_wait_queue); * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns * zero in this (rare) case, and we handle it by continuing to scan the queue. */ -static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, +static void __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, int wake_flags, void *key) { - wait_queue_t *curr, *next; + wait_queue_entry_t *curr, *next; - list_for_each_entry_safe(curr, next, &q->task_list, task_list) { + list_for_each_entry_safe(curr, next, &wq_head->head, entry) { unsigned flags = curr->flags; if (curr->func(curr, mode, wake_flags, key) && @@ -79,7 +79,7 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, /** * __wake_up - wake up threads blocked on a waitqueue. - * @q: the waitqueue + * @wq_head: the waitqueue * @mode: which threads * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: is directly passed to the wakeup function @@ -87,35 +87,35 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, * It may be assumed that this function implies a write memory barrier before * changing the task state if and only if any tasks are woken up. */ -void __wake_up(wait_queue_head_t *q, unsigned int mode, +void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) { unsigned long flags; - spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, 0, key); - spin_unlock_irqrestore(&q->lock, flags); + spin_lock_irqsave(&wq_head->lock, flags); + __wake_up_common(wq_head, mode, nr_exclusive, 0, key); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(__wake_up); /* * Same as __wake_up but called with the spinlock in wait_queue_head_t held. */ -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) +void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr) { - __wake_up_common(q, mode, nr, 0, NULL); + __wake_up_common(wq_head, mode, nr, 0, NULL); } EXPORT_SYMBOL_GPL(__wake_up_locked); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) +void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key) { - __wake_up_common(q, mode, 1, 0, key); + __wake_up_common(wq_head, mode, 1, 0, key); } EXPORT_SYMBOL_GPL(__wake_up_locked_key); /** * __wake_up_sync_key - wake up threads blocked on a waitqueue. - * @q: the waitqueue + * @wq_head: the waitqueue * @mode: which threads * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: opaque value to be passed to wakeup targets @@ -130,30 +130,30 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key); * It may be assumed that this function implies a write memory barrier before * changing the task state if and only if any tasks are woken up. */ -void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, +void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) { unsigned long flags; int wake_flags = 1; /* XXX WF_SYNC */ - if (unlikely(!q)) + if (unlikely(!wq_head)) return; if (unlikely(nr_exclusive != 1)) wake_flags = 0; - spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, wake_flags, key); - spin_unlock_irqrestore(&q->lock, flags); + spin_lock_irqsave(&wq_head->lock, flags); + __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL_GPL(__wake_up_sync_key); /* * __wake_up_sync - see __wake_up_sync_key() */ -void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive) { - __wake_up_sync_key(q, mode, nr_exclusive, NULL); + __wake_up_sync_key(wq_head, mode, nr_exclusive, NULL); } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ @@ -170,48 +170,48 @@ EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ * loads to move into the critical region). */ void -prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state) +prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state) { unsigned long flags; - wait->flags &= ~WQ_FLAG_EXCLUSIVE; - spin_lock_irqsave(&q->lock, flags); - if (list_empty(&wait->task_list)) - __add_wait_queue(q, wait); + wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&wq_head->lock, flags); + if (list_empty(&wq_entry->entry)) + __add_wait_queue(wq_head, wq_entry); set_current_state(state); - spin_unlock_irqrestore(&q->lock, flags); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(prepare_to_wait); void -prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state) +prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state) { unsigned long flags; - wait->flags |= WQ_FLAG_EXCLUSIVE; - spin_lock_irqsave(&q->lock, flags); - if (list_empty(&wait->task_list)) - __add_wait_queue_tail(q, wait); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&wq_head->lock, flags); + if (list_empty(&wq_entry->entry)) + __add_wait_queue_entry_tail(wq_head, wq_entry); set_current_state(state); - spin_unlock_irqrestore(&q->lock, flags); + spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(prepare_to_wait_exclusive); -void init_wait_entry(wait_queue_t *wait, int flags) +void init_wait_entry(struct wait_queue_entry *wq_entry, int flags) { - wait->flags = flags; - wait->private = current; - wait->func = autoremove_wake_function; - INIT_LIST_HEAD(&wait->task_list); + wq_entry->flags = flags; + wq_entry->private = current; + wq_entry->func = autoremove_wake_function; + INIT_LIST_HEAD(&wq_entry->entry); } EXPORT_SYMBOL(init_wait_entry); -long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) +long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state) { unsigned long flags; long ret = 0; - spin_lock_irqsave(&q->lock, flags); + spin_lock_irqsave(&wq_head->lock, flags); if (unlikely(signal_pending_state(state, current))) { /* * Exclusive waiter must not fail if it was selected by wakeup, @@ -219,24 +219,24 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) * * The caller will recheck the condition and return success if * we were already woken up, we can not miss the event because - * wakeup locks/unlocks the same q->lock. + * wakeup locks/unlocks the same wq_head->lock. * * But we need to ensure that set-condition + wakeup after that * can't see us, it should wake up another exclusive waiter if * we fail. */ - list_del_init(&wait->task_list); + list_del_init(&wq_entry->entry); ret = -ERESTARTSYS; } else { - if (list_empty(&wait->task_list)) { - if (wait->flags & WQ_FLAG_EXCLUSIVE) - __add_wait_queue_tail(q, wait); + if (list_empty(&wq_entry->entry)) { + if (wq_entry->flags & WQ_FLAG_EXCLUSIVE) + __add_wait_queue_entry_tail(wq_head, wq_entry); else - __add_wait_queue(q, wait); + __add_wait_queue(wq_head, wq_entry); } set_current_state(state); } - spin_unlock_irqrestore(&q->lock, flags); + spin_unlock_irqrestore(&wq_head->lock, flags); return ret; } @@ -249,10 +249,10 @@ EXPORT_SYMBOL(prepare_to_wait_event); * condition in the caller before they add the wait * entry to the wake queue. */ -int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait) +int do_wait_intr(wait_queue_head_t *wq, wait_queue_entry_t *wait) { - if (likely(list_empty(&wait->task_list))) - __add_wait_queue_tail(wq, wait); + if (likely(list_empty(&wait->entry))) + __add_wait_queue_entry_tail(wq, wait); set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) @@ -265,10 +265,10 @@ int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait) } EXPORT_SYMBOL(do_wait_intr); -int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait) +int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_entry_t *wait) { - if (likely(list_empty(&wait->task_list))) - __add_wait_queue_tail(wq, wait); + if (likely(list_empty(&wait->entry))) + __add_wait_queue_entry_tail(wq, wait); set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) @@ -283,14 +283,14 @@ EXPORT_SYMBOL(do_wait_intr_irq); /** * finish_wait - clean up after waiting in a queue - * @q: waitqueue waited on - * @wait: wait descriptor + * @wq_head: waitqueue waited on + * @wq_entry: wait descriptor * * Sets current thread back to running state and removes * the wait descriptor from the given waitqueue if still * queued. */ -void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) +void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; @@ -308,20 +308,20 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) * have _one_ other CPU that looks at or modifies * the list). */ - if (!list_empty_careful(&wait->task_list)) { - spin_lock_irqsave(&q->lock, flags); - list_del_init(&wait->task_list); - spin_unlock_irqrestore(&q->lock, flags); + if (!list_empty_careful(&wq_entry->entry)) { + spin_lock_irqsave(&wq_head->lock, flags); + list_del_init(&wq_entry->entry); + spin_unlock_irqrestore(&wq_head->lock, flags); } } EXPORT_SYMBOL(finish_wait); -int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key) { - int ret = default_wake_function(wait, mode, sync, key); + int ret = default_wake_function(wq_entry, mode, sync, key); if (ret) - list_del_init(&wait->task_list); + list_del_init(&wq_entry->entry); return ret; } EXPORT_SYMBOL(autoremove_wake_function); @@ -334,24 +334,24 @@ static inline bool is_kthread_should_stop(void) /* * DEFINE_WAIT_FUNC(wait, woken_wake_func); * - * add_wait_queue(&wq, &wait); + * add_wait_queue(&wq_head, &wait); * for (;;) { * if (condition) * break; * * p->state = mode; condition = true; * smp_mb(); // A smp_wmb(); // C - * if (!wait->flags & WQ_FLAG_WOKEN) wait->flags |= WQ_FLAG_WOKEN; + * if (!wq_entry->flags & WQ_FLAG_WOKEN) wq_entry->flags |= WQ_FLAG_WOKEN; * schedule() try_to_wake_up(); * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~ - * wait->flags &= ~WQ_FLAG_WOKEN; condition = true; + * wq_entry->flags &= ~WQ_FLAG_WOKEN; condition = true; * smp_mb() // B smp_wmb(); // C - * wait->flags |= WQ_FLAG_WOKEN; + * wq_entry->flags |= WQ_FLAG_WOKEN; * } - * remove_wait_queue(&wq, &wait); + * remove_wait_queue(&wq_head, &wait); * */ -long wait_woken(wait_queue_t *wait, unsigned mode, long timeout) +long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout) { set_current_state(mode); /* A */ /* @@ -359,7 +359,7 @@ long wait_woken(wait_queue_t *wait, unsigned mode, long timeout) * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must * also observe all state before the wakeup. */ - if (!(wait->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) + if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) timeout = schedule_timeout(timeout); __set_current_state(TASK_RUNNING); @@ -369,13 +369,13 @@ long wait_woken(wait_queue_t *wait, unsigned mode, long timeout) * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss * an event. */ - smp_store_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */ + smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */ return timeout; } EXPORT_SYMBOL(wait_woken); -int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key) { /* * Although this function is called under waitqueue lock, LOCK @@ -385,267 +385,8 @@ int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) * and is paired with smp_store_mb() in wait_woken(). */ smp_wmb(); /* C */ - wait->flags |= WQ_FLAG_WOKEN; + wq_entry->flags |= WQ_FLAG_WOKEN; - return default_wake_function(wait, mode, sync, key); + return default_wake_function(wq_entry, mode, sync, key); } EXPORT_SYMBOL(woken_wake_function); - -int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg) -{ - struct wait_bit_key *key = arg; - struct wait_bit_queue *wait_bit - = container_of(wait, struct wait_bit_queue, wait); - - if (wait_bit->key.flags != key->flags || - wait_bit->key.bit_nr != key->bit_nr || - test_bit(key->bit_nr, key->flags)) - return 0; - else - return autoremove_wake_function(wait, mode, sync, key); -} -EXPORT_SYMBOL(wake_bit_function); - -/* - * To allow interruptible waiting and asynchronous (i.e. nonblocking) - * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are - * permitted return codes. Nonzero return codes halt waiting and return. - */ -int __sched -__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, - wait_bit_action_f *action, unsigned mode) -{ - int ret = 0; - - do { - prepare_to_wait(wq, &q->wait, mode); - if (test_bit(q->key.bit_nr, q->key.flags)) - ret = (*action)(&q->key, mode); - } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); - finish_wait(wq, &q->wait); - return ret; -} -EXPORT_SYMBOL(__wait_on_bit); - -int __sched out_of_line_wait_on_bit(void *word, int bit, - wait_bit_action_f *action, unsigned mode) -{ - wait_queue_head_t *wq = bit_waitqueue(word, bit); - DEFINE_WAIT_BIT(wait, word, bit); - - return __wait_on_bit(wq, &wait, action, mode); -} -EXPORT_SYMBOL(out_of_line_wait_on_bit); - -int __sched out_of_line_wait_on_bit_timeout( - void *word, int bit, wait_bit_action_f *action, - unsigned mode, unsigned long timeout) -{ - wait_queue_head_t *wq = bit_waitqueue(word, bit); - DEFINE_WAIT_BIT(wait, word, bit); - - wait.key.timeout = jiffies + timeout; - return __wait_on_bit(wq, &wait, action, mode); -} -EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout); - -int __sched -__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, - wait_bit_action_f *action, unsigned mode) -{ - int ret = 0; - - for (;;) { - prepare_to_wait_exclusive(wq, &q->wait, mode); - if (test_bit(q->key.bit_nr, q->key.flags)) { - ret = action(&q->key, mode); - /* - * See the comment in prepare_to_wait_event(). - * finish_wait() does not necessarily takes wq->lock, - * but test_and_set_bit() implies mb() which pairs with - * smp_mb__after_atomic() before wake_up_page(). - */ - if (ret) - finish_wait(wq, &q->wait); - } - if (!test_and_set_bit(q->key.bit_nr, q->key.flags)) { - if (!ret) - finish_wait(wq, &q->wait); - return 0; - } else if (ret) { - return ret; - } - } -} -EXPORT_SYMBOL(__wait_on_bit_lock); - -int __sched out_of_line_wait_on_bit_lock(void *word, int bit, - wait_bit_action_f *action, unsigned mode) -{ - wait_queue_head_t *wq = bit_waitqueue(word, bit); - DEFINE_WAIT_BIT(wait, word, bit); - - return __wait_on_bit_lock(wq, &wait, action, mode); -} -EXPORT_SYMBOL(out_of_line_wait_on_bit_lock); - -void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit) -{ - struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit); - if (waitqueue_active(wq)) - __wake_up(wq, TASK_NORMAL, 1, &key); -} -EXPORT_SYMBOL(__wake_up_bit); - -/** - * wake_up_bit - wake up a waiter on a bit - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that wakes up waiters - * on a bit. For instance, if one were to have waiters on a bitflag, - * one would call wake_up_bit() after clearing the bit. - * - * In order for this to function properly, as it uses waitqueue_active() - * internally, some kind of memory barrier must be done prior to calling - * this. Typically, this will be smp_mb__after_atomic(), but in some - * cases where bitflags are manipulated non-atomically under a lock, one - * may need to use a less regular barrier, such fs/inode.c's smp_mb(), - * because spin_unlock() does not guarantee a memory barrier. - */ -void wake_up_bit(void *word, int bit) -{ - __wake_up_bit(bit_waitqueue(word, bit), word, bit); -} -EXPORT_SYMBOL(wake_up_bit); - -/* - * Manipulate the atomic_t address to produce a better bit waitqueue table hash - * index (we're keying off bit -1, but that would produce a horrible hash - * value). - */ -static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p) -{ - if (BITS_PER_LONG == 64) { - unsigned long q = (unsigned long)p; - return bit_waitqueue((void *)(q & ~1), q & 1); - } - return bit_waitqueue(p, 0); -} - -static int wake_atomic_t_function(wait_queue_t *wait, unsigned mode, int sync, - void *arg) -{ - struct wait_bit_key *key = arg; - struct wait_bit_queue *wait_bit - = container_of(wait, struct wait_bit_queue, wait); - atomic_t *val = key->flags; - - if (wait_bit->key.flags != key->flags || - wait_bit->key.bit_nr != key->bit_nr || - atomic_read(val) != 0) - return 0; - return autoremove_wake_function(wait, mode, sync, key); -} - -/* - * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting, - * the actions of __wait_on_atomic_t() are permitted return codes. Nonzero - * return codes halt waiting and return. - */ -static __sched -int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q, - int (*action)(atomic_t *), unsigned mode) -{ - atomic_t *val; - int ret = 0; - - do { - prepare_to_wait(wq, &q->wait, mode); - val = q->key.flags; - if (atomic_read(val) == 0) - break; - ret = (*action)(val); - } while (!ret && atomic_read(val) != 0); - finish_wait(wq, &q->wait); - return ret; -} - -#define DEFINE_WAIT_ATOMIC_T(name, p) \ - struct wait_bit_queue name = { \ - .key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p), \ - .wait = { \ - .private = current, \ - .func = wake_atomic_t_function, \ - .task_list = \ - LIST_HEAD_INIT((name).wait.task_list), \ - }, \ - } - -__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *), - unsigned mode) -{ - wait_queue_head_t *wq = atomic_t_waitqueue(p); - DEFINE_WAIT_ATOMIC_T(wait, p); - - return __wait_on_atomic_t(wq, &wait, action, mode); -} -EXPORT_SYMBOL(out_of_line_wait_on_atomic_t); - -/** - * wake_up_atomic_t - Wake up a waiter on a atomic_t - * @p: The atomic_t being waited on, a kernel virtual address - * - * Wake up anyone waiting for the atomic_t to go to zero. - * - * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t - * check is done by the waiter's wake function, not the by the waker itself). - */ -void wake_up_atomic_t(atomic_t *p) -{ - __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR); -} -EXPORT_SYMBOL(wake_up_atomic_t); - -__sched int bit_wait(struct wait_bit_key *word, int mode) -{ - schedule(); - if (signal_pending_state(mode, current)) - return -EINTR; - return 0; -} -EXPORT_SYMBOL(bit_wait); - -__sched int bit_wait_io(struct wait_bit_key *word, int mode) -{ - io_schedule(); - if (signal_pending_state(mode, current)) - return -EINTR; - return 0; -} -EXPORT_SYMBOL(bit_wait_io); - -__sched int bit_wait_timeout(struct wait_bit_key *word, int mode) -{ - unsigned long now = READ_ONCE(jiffies); - if (time_after_eq(now, word->timeout)) - return -EAGAIN; - schedule_timeout(word->timeout - now); - if (signal_pending_state(mode, current)) - return -EINTR; - return 0; -} -EXPORT_SYMBOL_GPL(bit_wait_timeout); - -__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode) -{ - unsigned long now = READ_ONCE(jiffies); - if (time_after_eq(now, word->timeout)) - return -EAGAIN; - io_schedule_timeout(word->timeout - now); - if (signal_pending_state(mode, current)) - return -EINTR; - return 0; -} -EXPORT_SYMBOL_GPL(bit_wait_io_timeout); diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c new file mode 100644 index 000000000000..f8159698aa4d --- /dev/null +++ b/kernel/sched/wait_bit.c @@ -0,0 +1,286 @@ +/* + * The implementation of the wait_bit*() and related waiting APIs: + */ +#include <linux/wait_bit.h> +#include <linux/sched/signal.h> +#include <linux/sched/debug.h> +#include <linux/hash.h> + +#define WAIT_TABLE_BITS 8 +#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS) + +static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned; + +wait_queue_head_t *bit_waitqueue(void *word, int bit) +{ + const int shift = BITS_PER_LONG == 32 ? 5 : 6; + unsigned long val = (unsigned long)word << shift | bit; + + return bit_wait_table + hash_long(val, WAIT_TABLE_BITS); +} +EXPORT_SYMBOL(bit_waitqueue); + +int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry); + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + test_bit(key->bit_nr, key->flags)) + return 0; + else + return autoremove_wake_function(wq_entry, mode, sync, key); +} +EXPORT_SYMBOL(wake_bit_function); + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) + * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are + * permitted return codes. Nonzero return codes halt waiting and return. + */ +int __sched +__wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, + wait_bit_action_f *action, unsigned mode) +{ + int ret = 0; + + do { + prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode); + if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) + ret = (*action)(&wbq_entry->key, mode); + } while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret); + finish_wait(wq_head, &wbq_entry->wq_entry); + return ret; +} +EXPORT_SYMBOL(__wait_on_bit); + +int __sched out_of_line_wait_on_bit(void *word, int bit, + wait_bit_action_f *action, unsigned mode) +{ + struct wait_queue_head *wq_head = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wq_entry, word, bit); + + return __wait_on_bit(wq_head, &wq_entry, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit); + +int __sched out_of_line_wait_on_bit_timeout( + void *word, int bit, wait_bit_action_f *action, + unsigned mode, unsigned long timeout) +{ + struct wait_queue_head *wq_head = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wq_entry, word, bit); + + wq_entry.key.timeout = jiffies + timeout; + return __wait_on_bit(wq_head, &wq_entry, action, mode); +} +EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout); + +int __sched +__wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, + wait_bit_action_f *action, unsigned mode) +{ + int ret = 0; + + for (;;) { + prepare_to_wait_exclusive(wq_head, &wbq_entry->wq_entry, mode); + if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) { + ret = action(&wbq_entry->key, mode); + /* + * See the comment in prepare_to_wait_event(). + * finish_wait() does not necessarily takes wwq_head->lock, + * but test_and_set_bit() implies mb() which pairs with + * smp_mb__after_atomic() before wake_up_page(). + */ + if (ret) + finish_wait(wq_head, &wbq_entry->wq_entry); + } + if (!test_and_set_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) { + if (!ret) + finish_wait(wq_head, &wbq_entry->wq_entry); + return 0; + } else if (ret) { + return ret; + } + } +} +EXPORT_SYMBOL(__wait_on_bit_lock); + +int __sched out_of_line_wait_on_bit_lock(void *word, int bit, + wait_bit_action_f *action, unsigned mode) +{ + struct wait_queue_head *wq_head = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wq_entry, word, bit); + + return __wait_on_bit_lock(wq_head, &wq_entry, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit_lock); + +void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit) +{ + struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit); + if (waitqueue_active(wq_head)) + __wake_up(wq_head, TASK_NORMAL, 1, &key); +} +EXPORT_SYMBOL(__wake_up_bit); + +/** + * wake_up_bit - wake up a waiter on a bit + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that wakes up waiters + * on a bit. For instance, if one were to have waiters on a bitflag, + * one would call wake_up_bit() after clearing the bit. + * + * In order for this to function properly, as it uses waitqueue_active() + * internally, some kind of memory barrier must be done prior to calling + * this. Typically, this will be smp_mb__after_atomic(), but in some + * cases where bitflags are manipulated non-atomically under a lock, one + * may need to use a less regular barrier, such fs/inode.c's smp_mb(), + * because spin_unlock() does not guarantee a memory barrier. + */ +void wake_up_bit(void *word, int bit) +{ + __wake_up_bit(bit_waitqueue(word, bit), word, bit); +} +EXPORT_SYMBOL(wake_up_bit); + +/* + * Manipulate the atomic_t address to produce a better bit waitqueue table hash + * index (we're keying off bit -1, but that would produce a horrible hash + * value). + */ +static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p) +{ + if (BITS_PER_LONG == 64) { + unsigned long q = (unsigned long)p; + return bit_waitqueue((void *)(q & ~1), q & 1); + } + return bit_waitqueue(p, 0); +} + +static int wake_atomic_t_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, + void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry); + atomic_t *val = key->flags; + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + atomic_read(val) != 0) + return 0; + return autoremove_wake_function(wq_entry, mode, sync, key); +} + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting, + * the actions of __wait_on_atomic_t() are permitted return codes. Nonzero + * return codes halt waiting and return. + */ +static __sched +int __wait_on_atomic_t(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, + int (*action)(atomic_t *), unsigned mode) +{ + atomic_t *val; + int ret = 0; + + do { + prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode); + val = wbq_entry->key.flags; + if (atomic_read(val) == 0) + break; + ret = (*action)(val); + } while (!ret && atomic_read(val) != 0); + finish_wait(wq_head, &wbq_entry->wq_entry); + return ret; +} + +#define DEFINE_WAIT_ATOMIC_T(name, p) \ + struct wait_bit_queue_entry name = { \ + .key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p), \ + .wq_entry = { \ + .private = current, \ + .func = wake_atomic_t_function, \ + .entry = \ + LIST_HEAD_INIT((name).wq_entry.entry), \ + }, \ + } + +__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *), + unsigned mode) +{ + struct wait_queue_head *wq_head = atomic_t_waitqueue(p); + DEFINE_WAIT_ATOMIC_T(wq_entry, p); + + return __wait_on_atomic_t(wq_head, &wq_entry, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_atomic_t); + +/** + * wake_up_atomic_t - Wake up a waiter on a atomic_t + * @p: The atomic_t being waited on, a kernel virtual address + * + * Wake up anyone waiting for the atomic_t to go to zero. + * + * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t + * check is done by the waiter's wake function, not the by the waker itself). + */ +void wake_up_atomic_t(atomic_t *p) +{ + __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR); +} +EXPORT_SYMBOL(wake_up_atomic_t); + +__sched int bit_wait(struct wait_bit_key *word, int mode) +{ + schedule(); + if (signal_pending_state(mode, current)) + return -EINTR; + return 0; +} +EXPORT_SYMBOL(bit_wait); + +__sched int bit_wait_io(struct wait_bit_key *word, int mode) +{ + io_schedule(); + if (signal_pending_state(mode, current)) + return -EINTR; + return 0; +} +EXPORT_SYMBOL(bit_wait_io); + +__sched int bit_wait_timeout(struct wait_bit_key *word, int mode) +{ + unsigned long now = READ_ONCE(jiffies); + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + schedule_timeout(word->timeout - now); + if (signal_pending_state(mode, current)) + return -EINTR; + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_timeout); + +__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode) +{ + unsigned long now = READ_ONCE(jiffies); + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + io_schedule_timeout(word->timeout - now); + if (signal_pending_state(mode, current)) + return -EINTR; + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_io_timeout); + +void __init wait_bit_init(void) +{ + int i; + + for (i = 0; i < WAIT_TABLE_SIZE; i++) + init_waitqueue_head(bit_wait_table + i); +} diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 65f61077ad50..98b59b5db90b 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -13,7 +13,7 @@ * of Berkeley Packet Filters/Linux Socket Filters. */ -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/audit.h> #include <linux/compat.h> #include <linux/coredump.h> @@ -56,7 +56,7 @@ * to a task_struct (other than @usage). */ struct seccomp_filter { - atomic_t usage; + refcount_t usage; struct seccomp_filter *prev; struct bpf_prog *prog; }; @@ -378,7 +378,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) return ERR_PTR(ret); } - atomic_set(&sfilter->usage, 1); + refcount_set(&sfilter->usage, 1); return sfilter; } @@ -465,7 +465,7 @@ void get_seccomp_filter(struct task_struct *tsk) if (!orig) return; /* Reference count is bounded by the number of total processes. */ - atomic_inc(&orig->usage); + refcount_inc(&orig->usage); } static inline void seccomp_filter_free(struct seccomp_filter *filter) @@ -481,7 +481,7 @@ void put_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; /* Clean up single-reference branches iteratively. */ - while (orig && atomic_dec_and_test(&orig->usage)) { + while (orig && refcount_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; orig = orig->prev; seccomp_filter_free(freeme); @@ -641,11 +641,12 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, return 0; case SECCOMP_RET_KILL: - default: { - siginfo_t info; + default: audit_seccomp(this_syscall, SIGSYS, action); /* Dump core only if this is the last remaining thread. */ if (get_nr_threads(current) == 1) { + siginfo_t info; + /* Show the original registers in the dump. */ syscall_rollback(current, task_pt_regs(current)); /* Trigger a manual coredump since do_exit skips it. */ @@ -654,7 +655,6 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, } do_exit(SIGSYS); } - } unreachable(); diff --git a/kernel/signal.c b/kernel/signal.c index ca92bcfeb322..35a570f71f07 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -39,6 +39,7 @@ #include <linux/compat.h> #include <linux/cn_proc.h> #include <linux/compiler.h> +#include <linux/posix-timers.h> #define CREATE_TRACE_POINTS #include <trace/events/signal.h> @@ -510,7 +511,8 @@ int unhandled_signal(struct task_struct *tsk, int sig) return !tsk->ptrace; } -static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) +static void collect_signal(int sig, struct sigpending *list, siginfo_t *info, + bool *resched_timer) { struct sigqueue *q, *first = NULL; @@ -532,6 +534,12 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); + + *resched_timer = + (first->flags & SIGQUEUE_PREALLOC) && + (info->si_code == SI_TIMER) && + (info->si_sys_private); + __sigqueue_free(first); } else { /* @@ -548,12 +556,12 @@ still_pending: } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - siginfo_t *info) + siginfo_t *info, bool *resched_timer) { int sig = next_signal(pending, mask); if (sig) - collect_signal(sig, pending, info); + collect_signal(sig, pending, info, resched_timer); return sig; } @@ -565,15 +573,16 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, */ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) { + bool resched_timer = false; int signr; /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ - signr = __dequeue_signal(&tsk->pending, mask, info); + signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { signr = __dequeue_signal(&tsk->signal->shared_pending, - mask, info); + mask, info, &resched_timer); #ifdef CONFIG_POSIX_TIMERS /* * itimer signal ? @@ -621,7 +630,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) current->jobctl |= JOBCTL_STOP_DEQUEUED; } #ifdef CONFIG_POSIX_TIMERS - if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) { + if (resched_timer) { /* * Release the siglock to ensure proper locking order * of timer locks outside of siglocks. Note, we leave @@ -629,7 +638,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) * about to disable them again anyway. */ spin_unlock(&tsk->sighand->siglock); - do_schedule_next_timer(info); + posixtimer_rearm(info); spin_lock(&tsk->sighand->siglock); } #endif @@ -2092,7 +2101,6 @@ static void do_jobctl_trap(void) static int ptrace_signal(int signr, siginfo_t *info) { - ptrace_signal_deliver(); /* * We do not check sig_kernel_stop(signr) but set this marker * unconditionally because we do not know whether debugger will diff --git a/kernel/smp.c b/kernel/smp.c index a817769b53c0..3061483cb3ad 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -30,6 +30,7 @@ enum { struct call_function_data { struct call_single_data __percpu *csd; cpumask_var_t cpumask; + cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data); @@ -45,9 +46,15 @@ int smpcfd_prepare_cpu(unsigned int cpu) if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; + if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, + cpu_to_node(cpu))) { + free_cpumask_var(cfd->cpumask); + return -ENOMEM; + } cfd->csd = alloc_percpu(struct call_single_data); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); + free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } @@ -59,6 +66,7 @@ int smpcfd_dead_cpu(unsigned int cpu) struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); + free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } @@ -428,12 +436,13 @@ void smp_call_function_many(const struct cpumask *mask, cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); - cpumask_clear_cpu(this_cpu, cfd->cpumask); + __cpumask_clear_cpu(this_cpu, cfd->cpumask); /* Some callers race with other cpus changing the passed mask */ if (unlikely(!cpumask_weight(cfd->cpumask))) return; + cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu); @@ -442,11 +451,12 @@ void smp_call_function_many(const struct cpumask *mask, csd->flags |= CSD_FLAG_SYNCHRONOUS; csd->func = func; csd->info = info; - llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)); + if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu))) + __cpumask_set_cpu(cpu, cfd->cpumask_ipi); } /* Send a message to all CPUs in the map */ - arch_send_call_function_ipi_mask(cfd->cpumask); + arch_send_call_function_ipi_mask(cfd->cpumask_ipi); if (wait) { for_each_cpu(cpu, cfd->cpumask) { diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 1eb82661ecdb..b7591261652d 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -552,7 +552,8 @@ static int __init cpu_stop_init(void) } early_initcall(cpu_stop_init); -static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) +int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, + const struct cpumask *cpus) { struct multi_stop_data msdata = { .fn = fn, @@ -561,6 +562,8 @@ static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cp .active_cpus = cpus, }; + lockdep_assert_cpus_held(); + if (!stop_machine_initialized) { /* * Handle the case where stop_machine() is called @@ -590,9 +593,9 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) int ret; /* No CPUs can come up or down during this. */ - get_online_cpus(); - ret = __stop_machine(fn, data, cpus); - put_online_cpus(); + cpus_read_lock(); + ret = stop_machine_cpuslocked(fn, data, cpus); + cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(stop_machine); diff --git a/kernel/sys.c b/kernel/sys.c index 8a94b4eabcaa..dab1a0658a92 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1552,7 +1552,7 @@ static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) r->ru_oublock += task_io_get_oublock(t); } -static void k_getrusage(struct task_struct *p, int who, struct rusage *r) +void getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; @@ -1626,20 +1626,16 @@ out: r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ } -int getrusage(struct task_struct *p, int who, struct rusage __user *ru) +SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) { struct rusage r; - k_getrusage(p, who, &r); - return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; -} - -SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) -{ if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; - return getrusage(current, who, ru); + + getrusage(current, who, &r); + return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT @@ -1651,7 +1647,7 @@ COMPAT_SYSCALL_DEFINE2(getrusage, int, who, struct compat_rusage __user *, ru) who != RUSAGE_THREAD) return -EINVAL; - k_getrusage(current, who, &r); + getrusage(current, who, &r); return put_compat_rusage(&r, ru); } #endif diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index ece4b177052b..939a158eab11 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1119,7 +1119,7 @@ static ssize_t bin_uuid(struct file *file, /* Only supports reads */ if (oldval && oldlen) { char buf[UUID_STRING_LEN + 1]; - uuid_be uuid; + uuid_t uuid; result = kernel_read(file, 0, buf, sizeof(buf) - 1); if (result < 0) @@ -1128,7 +1128,7 @@ static ssize_t bin_uuid(struct file *file, buf[result] = '\0'; result = -EIO; - if (uuid_be_to_bin(buf, &uuid)) + if (uuid_parse(buf, &uuid)) goto out; if (oldlen > 16) diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 4008d9f95dd7..ac09bc29eb08 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -126,56 +126,6 @@ config NO_HZ_FULL_ALL Note the boot CPU will still be kept outside the range to handle the timekeeping duty. -config NO_HZ_FULL_SYSIDLE - bool "Detect full-system idle state for full dynticks system" - depends on NO_HZ_FULL - default n - help - At least one CPU must keep the scheduling-clock tick running for - timekeeping purposes whenever there is a non-idle CPU, where - "non-idle" also includes dynticks CPUs as long as they are - running non-idle tasks. Because the underlying adaptive-tick - support cannot distinguish between all CPUs being idle and - all CPUs each running a single task in dynticks mode, the - underlying support simply ensures that there is always a CPU - handling the scheduling-clock tick, whether or not all CPUs - are idle. This Kconfig option enables scalable detection of - the all-CPUs-idle state, thus allowing the scheduling-clock - tick to be disabled when all CPUs are idle. Note that scalable - detection of the all-CPUs-idle state means that larger systems - will be slower to declare the all-CPUs-idle state. - - Say Y if you would like to help debug all-CPUs-idle detection. - - Say N if you are unsure. - -config NO_HZ_FULL_SYSIDLE_SMALL - int "Number of CPUs above which large-system approach is used" - depends on NO_HZ_FULL_SYSIDLE - range 1 NR_CPUS - default 8 - help - The full-system idle detection mechanism takes a lazy approach - on large systems, as is required to attain decent scalability. - However, on smaller systems, scalability is not anywhere near as - large a concern as is energy efficiency. The sysidle subsystem - therefore uses a fast but non-scalable algorithm for small - systems and a lazier but scalable algorithm for large systems. - This Kconfig parameter defines the number of CPUs in the largest - system that will be considered to be "small". - - The default value will be fine in most cases. Battery-powered - systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger - numbers of CPUs, and (3) are suffering from battery-lifetime - problems due to long sysidle latencies might wish to experiment - with larger values for this Kconfig parameter. On the other - hand, they might be even better served by disabling NO_HZ_FULL - entirely, given that NO_HZ_FULL is intended for HPC and - real-time workloads that at present do not tend to be run on - battery-powered systems. - - Take the default if you are unsure. - config NO_HZ bool "Old Idle dynticks config" depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 5cb5b0008d97..0b8ff7d257ea 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -27,6 +27,9 @@ #include <linux/posix-timers.h> #include <linux/workqueue.h> #include <linux/freezer.h> +#include <linux/compat.h> + +#include "posix-timers.h" #define CREATE_TRACE_POINTS #include <trace/events/alarmtimer.h> @@ -45,11 +48,13 @@ static struct alarm_base { clockid_t base_clockid; } alarm_bases[ALARM_NUMTYPE]; +#if defined(CONFIG_POSIX_TIMERS) || defined(CONFIG_RTC_CLASS) /* freezer information to handle clock_nanosleep triggered wakeups */ static enum alarmtimer_type freezer_alarmtype; static ktime_t freezer_expires; static ktime_t freezer_delta; static DEFINE_SPINLOCK(freezer_delta_lock); +#endif static struct wakeup_source *ws; @@ -307,38 +312,6 @@ static int alarmtimer_resume(struct device *dev) } #endif -static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type) -{ - struct alarm_base *base; - unsigned long flags; - ktime_t delta; - - switch(type) { - case ALARM_REALTIME: - base = &alarm_bases[ALARM_REALTIME]; - type = ALARM_REALTIME_FREEZER; - break; - case ALARM_BOOTTIME: - base = &alarm_bases[ALARM_BOOTTIME]; - type = ALARM_BOOTTIME_FREEZER; - break; - default: - WARN_ONCE(1, "Invalid alarm type: %d\n", type); - return; - } - - delta = ktime_sub(absexp, base->gettime()); - - spin_lock_irqsave(&freezer_delta_lock, flags); - if (!freezer_delta || (delta < freezer_delta)) { - freezer_delta = delta; - freezer_expires = absexp; - freezer_alarmtype = type; - } - spin_unlock_irqrestore(&freezer_delta_lock, flags); -} - - /** * alarm_init - Initialize an alarm structure * @alarm: ptr to alarm to be initialized @@ -387,7 +360,7 @@ void alarm_start_relative(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; - start = ktime_add(start, base->gettime()); + start = ktime_add_safe(start, base->gettime()); alarm_start(alarm, start); } EXPORT_SYMBOL_GPL(alarm_start_relative); @@ -475,7 +448,7 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) overrun++; } - alarm->node.expires = ktime_add(alarm->node.expires, interval); + alarm->node.expires = ktime_add_safe(alarm->node.expires, interval); return overrun; } EXPORT_SYMBOL_GPL(alarm_forward); @@ -488,6 +461,38 @@ u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) } EXPORT_SYMBOL_GPL(alarm_forward_now); +#ifdef CONFIG_POSIX_TIMERS + +static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type) +{ + struct alarm_base *base; + unsigned long flags; + ktime_t delta; + + switch(type) { + case ALARM_REALTIME: + base = &alarm_bases[ALARM_REALTIME]; + type = ALARM_REALTIME_FREEZER; + break; + case ALARM_BOOTTIME: + base = &alarm_bases[ALARM_BOOTTIME]; + type = ALARM_BOOTTIME_FREEZER; + break; + default: + WARN_ONCE(1, "Invalid alarm type: %d\n", type); + return; + } + + delta = ktime_sub(absexp, base->gettime()); + + spin_lock_irqsave(&freezer_delta_lock, flags); + if (!freezer_delta || (delta < freezer_delta)) { + freezer_delta = delta; + freezer_expires = absexp; + freezer_alarmtype = type; + } + spin_unlock_irqrestore(&freezer_delta_lock, flags); +} /** * clock2alarm - helper that converts from clockid to alarmtypes @@ -511,22 +516,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, ktime_t now) { - unsigned long flags; struct k_itimer *ptr = container_of(alarm, struct k_itimer, - it.alarm.alarmtimer); + it.alarm.alarmtimer); enum alarmtimer_restart result = ALARMTIMER_NORESTART; + unsigned long flags; + int si_private = 0; spin_lock_irqsave(&ptr->it_lock, flags); - if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) { - if (IS_ENABLED(CONFIG_POSIX_TIMERS) && - posix_timer_event(ptr, 0) != 0) - ptr->it_overrun++; - } - /* Re-add periodic timers */ - if (ptr->it.alarm.interval) { - ptr->it_overrun += alarm_forward(alarm, now, - ptr->it.alarm.interval); + ptr->it_active = 0; + if (ptr->it_interval) + si_private = ++ptr->it_requeue_pending; + + if (posix_timer_event(ptr, si_private) && ptr->it_interval) { + /* + * Handle ignored signals and rearm the timer. This will go + * away once we handle ignored signals proper. + */ + ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval); + ++ptr->it_requeue_pending; + ptr->it_active = 1; result = ALARMTIMER_RESTART; } spin_unlock_irqrestore(&ptr->it_lock, flags); @@ -535,6 +544,72 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, } /** + * alarm_timer_rearm - Posix timer callback for rearming timer + * @timr: Pointer to the posixtimer data struct + */ +static void alarm_timer_rearm(struct k_itimer *timr) +{ + struct alarm *alarm = &timr->it.alarm.alarmtimer; + + timr->it_overrun += alarm_forward_now(alarm, timr->it_interval); + alarm_start(alarm, alarm->node.expires); +} + +/** + * alarm_timer_forward - Posix timer callback for forwarding timer + * @timr: Pointer to the posixtimer data struct + * @now: Current time to forward the timer against + */ +static int alarm_timer_forward(struct k_itimer *timr, ktime_t now) +{ + struct alarm *alarm = &timr->it.alarm.alarmtimer; + + return (int) alarm_forward(alarm, timr->it_interval, now); +} + +/** + * alarm_timer_remaining - Posix timer callback to retrieve remaining time + * @timr: Pointer to the posixtimer data struct + * @now: Current time to calculate against + */ +static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now) +{ + struct alarm *alarm = &timr->it.alarm.alarmtimer; + + return ktime_sub(now, alarm->node.expires); +} + +/** + * alarm_timer_try_to_cancel - Posix timer callback to cancel a timer + * @timr: Pointer to the posixtimer data struct + */ +static int alarm_timer_try_to_cancel(struct k_itimer *timr) +{ + return alarm_try_to_cancel(&timr->it.alarm.alarmtimer); +} + +/** + * alarm_timer_arm - Posix timer callback to arm a timer + * @timr: Pointer to the posixtimer data struct + * @expires: The new expiry time + * @absolute: Expiry value is absolute time + * @sigev_none: Posix timer does not deliver signals + */ +static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires, + bool absolute, bool sigev_none) +{ + struct alarm *alarm = &timr->it.alarm.alarmtimer; + struct alarm_base *base = &alarm_bases[alarm->type]; + + if (!absolute) + expires = ktime_add_safe(expires, base->gettime()); + if (sigev_none) + alarm->node.expires = expires; + else + alarm_start(&timr->it.alarm.alarmtimer, expires); +} + +/** * alarm_clock_getres - posix getres interface * @which_clock: clockid * @tp: timespec to fill @@ -591,89 +666,6 @@ static int alarm_timer_create(struct k_itimer *new_timer) } /** - * alarm_timer_get - posix timer_get interface - * @new_timer: k_itimer pointer - * @cur_setting: itimerspec data to fill - * - * Copies out the current itimerspec data - */ -static void alarm_timer_get(struct k_itimer *timr, - struct itimerspec64 *cur_setting) -{ - ktime_t relative_expiry_time = - alarm_expires_remaining(&(timr->it.alarm.alarmtimer)); - - if (ktime_to_ns(relative_expiry_time) > 0) { - cur_setting->it_value = ktime_to_timespec64(relative_expiry_time); - } else { - cur_setting->it_value.tv_sec = 0; - cur_setting->it_value.tv_nsec = 0; - } - - cur_setting->it_interval = ktime_to_timespec64(timr->it.alarm.interval); -} - -/** - * alarm_timer_del - posix timer_del interface - * @timr: k_itimer pointer to be deleted - * - * Cancels any programmed alarms for the given timer. - */ -static int alarm_timer_del(struct k_itimer *timr) -{ - if (!rtcdev) - return -ENOTSUPP; - - if (alarm_try_to_cancel(&timr->it.alarm.alarmtimer) < 0) - return TIMER_RETRY; - - return 0; -} - -/** - * alarm_timer_set - posix timer_set interface - * @timr: k_itimer pointer to be deleted - * @flags: timer flags - * @new_setting: itimerspec to be used - * @old_setting: itimerspec being replaced - * - * Sets the timer to new_setting, and starts the timer. - */ -static int alarm_timer_set(struct k_itimer *timr, int flags, - struct itimerspec64 *new_setting, - struct itimerspec64 *old_setting) -{ - ktime_t exp; - - if (!rtcdev) - return -ENOTSUPP; - - if (flags & ~TIMER_ABSTIME) - return -EINVAL; - - if (old_setting) - alarm_timer_get(timr, old_setting); - - /* If the timer was already set, cancel it */ - if (alarm_try_to_cancel(&timr->it.alarm.alarmtimer) < 0) - return TIMER_RETRY; - - /* start the timer */ - timr->it.alarm.interval = timespec64_to_ktime(new_setting->it_interval); - exp = timespec64_to_ktime(new_setting->it_value); - /* Convert (if necessary) to absolute time */ - if (flags != TIMER_ABSTIME) { - ktime_t now; - - now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime(); - exp = ktime_add(now, exp); - } - - alarm_start(&timr->it.alarm.alarmtimer, exp); - return 0; -} - -/** * alarmtimer_nsleep_wakeup - Wakeup function for alarm_timer_nsleep * @alarm: ptr to alarm that fired * @@ -697,8 +689,10 @@ static enum alarmtimer_restart alarmtimer_nsleep_wakeup(struct alarm *alarm, * * Sets the alarm timer and sleeps until it is fired or interrupted. */ -static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp) +static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp, + enum alarmtimer_type type) { + struct restart_block *restart; alarm->data = (void *)current; do { set_current_state(TASK_INTERRUPTIBLE); @@ -711,36 +705,25 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp) __set_current_state(TASK_RUNNING); - return (alarm->data == NULL); -} - - -/** - * update_rmtp - Update remaining timespec value - * @exp: expiration time - * @type: timer type - * @rmtp: user pointer to remaining timepsec value - * - * Helper function that fills in rmtp value with time between - * now and the exp value - */ -static int update_rmtp(ktime_t exp, enum alarmtimer_type type, - struct timespec __user *rmtp) -{ - struct timespec rmt; - ktime_t rem; - - rem = ktime_sub(exp, alarm_bases[type].gettime()); - - if (rem <= 0) + if (!alarm->data) return 0; - rmt = ktime_to_timespec(rem); - if (copy_to_user(rmtp, &rmt, sizeof(*rmtp))) - return -EFAULT; + if (freezing(current)) + alarmtimer_freezerset(absexp, type); + restart = ¤t->restart_block; + if (restart->nanosleep.type != TT_NONE) { + struct timespec64 rmt; + ktime_t rem; + + rem = ktime_sub(absexp, alarm_bases[type].gettime()); - return 1; + if (rem <= 0) + return 0; + rmt = ktime_to_timespec64(rem); + return nanosleep_copyout(restart, &rmt); + } + return -ERESTART_RESTARTBLOCK; } /** @@ -752,32 +735,12 @@ static int update_rmtp(ktime_t exp, enum alarmtimer_type type, static long __sched alarm_timer_nsleep_restart(struct restart_block *restart) { enum alarmtimer_type type = restart->nanosleep.clockid; - ktime_t exp; - struct timespec __user *rmtp; + ktime_t exp = restart->nanosleep.expires; struct alarm alarm; - int ret = 0; - exp = restart->nanosleep.expires; alarm_init(&alarm, type, alarmtimer_nsleep_wakeup); - if (alarmtimer_do_nsleep(&alarm, exp)) - goto out; - - if (freezing(current)) - alarmtimer_freezerset(exp, type); - - rmtp = restart->nanosleep.rmtp; - if (rmtp) { - ret = update_rmtp(exp, type, rmtp); - if (ret <= 0) - goto out; - } - - - /* The other values in restart are already filled in */ - ret = -ERESTART_RESTARTBLOCK; -out: - return ret; + return alarmtimer_do_nsleep(&alarm, exp, type); } /** @@ -790,11 +753,10 @@ out: * Handles clock_nanosleep calls against _ALARM clockids */ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, - struct timespec64 *tsreq, - struct timespec __user *rmtp) + const struct timespec64 *tsreq) { enum alarmtimer_type type = clock2alarm(which_clock); - struct restart_block *restart; + struct restart_block *restart = ¤t->restart_block; struct alarm alarm; ktime_t exp; int ret = 0; @@ -817,35 +779,36 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, exp = ktime_add(now, exp); } - if (alarmtimer_do_nsleep(&alarm, exp)) - goto out; - - if (freezing(current)) - alarmtimer_freezerset(exp, type); + ret = alarmtimer_do_nsleep(&alarm, exp, type); + if (ret != -ERESTART_RESTARTBLOCK) + return ret; /* abs timers don't set remaining time or restart */ - if (flags == TIMER_ABSTIME) { - ret = -ERESTARTNOHAND; - goto out; - } + if (flags == TIMER_ABSTIME) + return -ERESTARTNOHAND; - if (rmtp) { - ret = update_rmtp(exp, type, rmtp); - if (ret <= 0) - goto out; - } - - restart = ¤t->restart_block; restart->fn = alarm_timer_nsleep_restart; restart->nanosleep.clockid = type; restart->nanosleep.expires = exp; - restart->nanosleep.rmtp = rmtp; - ret = -ERESTART_RESTARTBLOCK; - -out: return ret; } +const struct k_clock alarm_clock = { + .clock_getres = alarm_clock_getres, + .clock_get = alarm_clock_get, + .timer_create = alarm_timer_create, + .timer_set = common_timer_set, + .timer_del = common_timer_del, + .timer_get = common_timer_get, + .timer_arm = alarm_timer_arm, + .timer_rearm = alarm_timer_rearm, + .timer_forward = alarm_timer_forward, + .timer_remaining = alarm_timer_remaining, + .timer_try_to_cancel = alarm_timer_try_to_cancel, + .nsleep = alarm_timer_nsleep, +}; +#endif /* CONFIG_POSIX_TIMERS */ + /* Suspend hook structures */ static const struct dev_pm_ops alarmtimer_pm_ops = { @@ -871,23 +834,9 @@ static int __init alarmtimer_init(void) struct platform_device *pdev; int error = 0; int i; - struct k_clock alarm_clock = { - .clock_getres = alarm_clock_getres, - .clock_get = alarm_clock_get, - .timer_create = alarm_timer_create, - .timer_set = alarm_timer_set, - .timer_del = alarm_timer_del, - .timer_get = alarm_timer_get, - .nsleep = alarm_timer_nsleep, - }; alarmtimer_rtc_timer_init(); - if (IS_ENABLED(CONFIG_POSIX_TIMERS)) { - posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock); - posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock); - } - /* Initialize alarm bases */ alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME; alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 93621ae718d3..03918a19cf2d 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -233,6 +233,9 @@ static void clocksource_watchdog(unsigned long data) continue; } + if (cs == curr_clocksource && cs->tick_stable) + cs->tick_stable(cs); + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index ac053bb5296e..88f75f92ef36 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -51,6 +51,7 @@ #include <linux/sched/debug.h> #include <linux/timer.h> #include <linux/freezer.h> +#include <linux/compat.h> #include <linux/uaccess.h> @@ -1439,8 +1440,29 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); +int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) +{ + switch(restart->nanosleep.type) { +#ifdef CONFIG_COMPAT + case TT_COMPAT: + if (compat_put_timespec64(ts, restart->nanosleep.compat_rmtp)) + return -EFAULT; + break; +#endif + case TT_NATIVE: + if (put_timespec64(ts, restart->nanosleep.rmtp)) + return -EFAULT; + break; + default: + BUG(); + } + return -ERESTART_RESTARTBLOCK; +} + static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { + struct restart_block *restart; + hrtimer_init_sleeper(t, current); do { @@ -1457,53 +1479,38 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod __set_current_state(TASK_RUNNING); - return t->task == NULL; -} - -static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp) -{ - struct timespec rmt; - ktime_t rem; - - rem = hrtimer_expires_remaining(timer); - if (rem <= 0) + if (!t->task) return 0; - rmt = ktime_to_timespec(rem); - if (copy_to_user(rmtp, &rmt, sizeof(*rmtp))) - return -EFAULT; + restart = ¤t->restart_block; + if (restart->nanosleep.type != TT_NONE) { + ktime_t rem = hrtimer_expires_remaining(&t->timer); + struct timespec64 rmt; + + if (rem <= 0) + return 0; + rmt = ktime_to_timespec64(rem); - return 1; + return nanosleep_copyout(restart, &rmt); + } + return -ERESTART_RESTARTBLOCK; } -long __sched hrtimer_nanosleep_restart(struct restart_block *restart) +static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) { struct hrtimer_sleeper t; - struct timespec __user *rmtp; - int ret = 0; + int ret; hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); - if (do_nanosleep(&t, HRTIMER_MODE_ABS)) - goto out; - - rmtp = restart->nanosleep.rmtp; - if (rmtp) { - ret = update_rmtp(&t.timer, rmtp); - if (ret <= 0) - goto out; - } - - /* The other values in restart are already filled in */ - ret = -ERESTART_RESTARTBLOCK; -out: + ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; } -long hrtimer_nanosleep(struct timespec64 *rqtp, struct timespec __user *rmtp, +long hrtimer_nanosleep(const struct timespec64 *rqtp, const enum hrtimer_mode mode, const clockid_t clockid) { struct restart_block *restart; @@ -1517,7 +1524,8 @@ long hrtimer_nanosleep(struct timespec64 *rqtp, struct timespec __user *rmtp, hrtimer_init_on_stack(&t.timer, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack); - if (do_nanosleep(&t, mode)) + ret = do_nanosleep(&t, mode); + if (ret != -ERESTART_RESTARTBLOCK) goto out; /* Absolute timers do not update the rmtp value and restart: */ @@ -1526,19 +1534,10 @@ long hrtimer_nanosleep(struct timespec64 *rqtp, struct timespec __user *rmtp, goto out; } - if (rmtp) { - ret = update_rmtp(&t.timer, rmtp); - if (ret <= 0) - goto out; - } - restart = ¤t->restart_block; restart->fn = hrtimer_nanosleep_restart; restart->nanosleep.clockid = t.timer.base->clockid; - restart->nanosleep.rmtp = rmtp; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); - - ret = -ERESTART_RESTARTBLOCK; out: destroy_hrtimer_on_stack(&t.timer); return ret; @@ -1547,18 +1546,37 @@ out: SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, struct timespec __user *, rmtp) { - struct timespec64 tu64; - struct timespec tu; + struct timespec64 tu; + + if (get_timespec64(&tu, rqtp)) + return -EFAULT; + + if (!timespec64_valid(&tu)) + return -EINVAL; + + current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; + current->restart_block.nanosleep.rmtp = rmtp; + return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC); +} + +#ifdef CONFIG_COMPAT + +COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, + struct compat_timespec __user *, rmtp) +{ + struct timespec64 tu; - if (copy_from_user(&tu, rqtp, sizeof(tu))) + if (compat_get_timespec64(&tu, rqtp)) return -EFAULT; - tu64 = timespec_to_timespec64(tu); - if (!timespec64_valid(&tu64)) + if (!timespec64_valid(&tu)) return -EINVAL; - return hrtimer_nanosleep(&tu64, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC); + current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; + current->restart_block.nanosleep.compat_rmtp = rmtp; + return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC); } +#endif /* * Functions related to boot-time initialization: diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 087d6a1279b8..2ef98a02376a 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -15,6 +15,7 @@ #include <linux/posix-timers.h> #include <linux/hrtimer.h> #include <trace/events/timer.h> +#include <linux/compat.h> #include <linux/uaccess.h> @@ -116,6 +117,19 @@ SYSCALL_DEFINE2(getitimer, int, which, struct itimerval __user *, value) return error; } +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(getitimer, int, which, + struct compat_itimerval __user *, it) +{ + struct itimerval kit; + int error = do_getitimer(which, &kit); + + if (!error && put_compat_itimerval(it, &kit)) + error = -EFAULT; + return error; +} +#endif + /* * The timer is automagically restarted, when interval != 0 @@ -138,8 +152,12 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, u64 oval, nval, ointerval, ninterval; struct cpu_itimer *it = &tsk->signal->it[clock_id]; - nval = timeval_to_ns(&value->it_value); - ninterval = timeval_to_ns(&value->it_interval); + /* + * Use the to_ktime conversion because that clamps the maximum + * value to KTIME_MAX and avoid multiplication overflows. + */ + nval = ktime_to_ns(timeval_to_ktime(value->it_value)); + ninterval = ktime_to_ns(timeval_to_ktime(value->it_interval)); spin_lock_irq(&tsk->sighand->siglock); @@ -294,3 +312,27 @@ SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value, return -EFAULT; return 0; } + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE3(setitimer, int, which, + struct compat_itimerval __user *, in, + struct compat_itimerval __user *, out) +{ + struct itimerval kin, kout; + int error; + + if (in) { + if (get_compat_itimerval(&kin, in)) + return -EFAULT; + } else { + memset(&kin, 0, sizeof(kin)); + } + + error = do_setitimer(which, &kin, out ? &kout : NULL); + if (error || !out) + return error; + if (put_compat_itimerval(out, &kout)) + return -EFAULT; + return 0; +} +#endif diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 31d588d37a17..17cdc554c9fe 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -25,6 +25,8 @@ #include <linux/syscalls.h> #include <linux/uaccess.h> +#include "posix-timers.h" + static void delete_clock(struct kref *kref); /* @@ -82,38 +84,6 @@ static unsigned int posix_clock_poll(struct file *fp, poll_table *wait) return result; } -static int posix_clock_fasync(int fd, struct file *fp, int on) -{ - struct posix_clock *clk = get_posix_clock(fp); - int err = 0; - - if (!clk) - return -ENODEV; - - if (clk->ops.fasync) - err = clk->ops.fasync(clk, fd, fp, on); - - put_posix_clock(clk); - - return err; -} - -static int posix_clock_mmap(struct file *fp, struct vm_area_struct *vma) -{ - struct posix_clock *clk = get_posix_clock(fp); - int err = -ENODEV; - - if (!clk) - return -ENODEV; - - if (clk->ops.mmap) - err = clk->ops.mmap(clk, vma); - - put_posix_clock(clk); - - return err; -} - static long posix_clock_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) { @@ -199,8 +169,6 @@ static const struct file_operations posix_clock_file_operations = { .unlocked_ioctl = posix_clock_ioctl, .open = posix_clock_open, .release = posix_clock_release, - .fasync = posix_clock_fasync, - .mmap = posix_clock_mmap, #ifdef CONFIG_COMPAT .compat_ioctl = posix_clock_compat_ioctl, #endif @@ -359,88 +327,9 @@ out: return err; } -static int pc_timer_create(struct k_itimer *kit) -{ - clockid_t id = kit->it_clock; - struct posix_clock_desc cd; - int err; - - err = get_clock_desc(id, &cd); - if (err) - return err; - - if (cd.clk->ops.timer_create) - err = cd.clk->ops.timer_create(cd.clk, kit); - else - err = -EOPNOTSUPP; - - put_clock_desc(&cd); - - return err; -} - -static int pc_timer_delete(struct k_itimer *kit) -{ - clockid_t id = kit->it_clock; - struct posix_clock_desc cd; - int err; - - err = get_clock_desc(id, &cd); - if (err) - return err; - - if (cd.clk->ops.timer_delete) - err = cd.clk->ops.timer_delete(cd.clk, kit); - else - err = -EOPNOTSUPP; - - put_clock_desc(&cd); - - return err; -} - -static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec64 *ts) -{ - clockid_t id = kit->it_clock; - struct posix_clock_desc cd; - - if (get_clock_desc(id, &cd)) - return; - - if (cd.clk->ops.timer_gettime) - cd.clk->ops.timer_gettime(cd.clk, kit, ts); - - put_clock_desc(&cd); -} - -static int pc_timer_settime(struct k_itimer *kit, int flags, - struct itimerspec64 *ts, struct itimerspec64 *old) -{ - clockid_t id = kit->it_clock; - struct posix_clock_desc cd; - int err; - - err = get_clock_desc(id, &cd); - if (err) - return err; - - if (cd.clk->ops.timer_settime) - err = cd.clk->ops.timer_settime(cd.clk, kit, flags, ts, old); - else - err = -EOPNOTSUPP; - - put_clock_desc(&cd); - - return err; -} - -struct k_clock clock_posix_dynamic = { +const struct k_clock clock_posix_dynamic = { .clock_getres = pc_clock_getres, .clock_set = pc_clock_settime, .clock_get = pc_clock_gettime, .clock_adj = pc_clock_adjtime, - .timer_create = pc_timer_create, - .timer_set = pc_timer_settime, - .timer_del = pc_timer_delete, - .timer_get = pc_timer_gettime, }; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index d2a1e6dd0291..a3bd5dbe0dc4 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -12,6 +12,11 @@ #include <trace/events/timer.h> #include <linux/tick.h> #include <linux/workqueue.h> +#include <linux/compat.h> + +#include "posix-timers.h" + +static void posix_cpu_timer_rearm(struct k_itimer *timer); /* * Called after updating RLIMIT_CPU to run cpu timer and update @@ -322,6 +327,8 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer) if (CPUCLOCK_WHICH(new_timer->it_clock) >= CPUCLOCK_MAX) return -EINVAL; + new_timer->kclock = &clock_posix_cpu; + INIT_LIST_HEAD(&new_timer->it.cpu.entry); rcu_read_lock(); @@ -524,7 +531,8 @@ static void cpu_timer_fire(struct k_itimer *timer) * reload the timer. But we need to keep it * ticking in case the signal is deliverable next time. */ - posix_cpu_timer_schedule(timer); + posix_cpu_timer_rearm(timer); + ++timer->it_requeue_pending; } } @@ -572,7 +580,11 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, WARN_ON_ONCE(p == NULL); - new_expires = timespec64_to_ns(&new->it_value); + /* + * Use the to_ktime conversion because that clamps the maximum + * value to KTIME_MAX and avoid multiplication overflows. + */ + new_expires = ktime_to_ns(timespec64_to_ktime(new->it_value)); /* * Protect against sighand release/switch in exit/exec and p->cpu_timers @@ -712,10 +724,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp */ itp->it_interval = ns_to_timespec64(timer->it.cpu.incr); - if (timer->it.cpu.expires == 0) { /* Timer not armed at all. */ - itp->it_value.tv_sec = itp->it_value.tv_nsec = 0; + if (!timer->it.cpu.expires) return; - } /* * Sample the clock to take the difference with the expiry time. @@ -739,7 +749,6 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp * Call the timer disarmed, nothing else to do. */ timer->it.cpu.expires = 0; - itp->it_value = ns_to_timespec64(timer->it.cpu.expires); return; } else { cpu_timer_sample_group(timer->it_clock, p, &now); @@ -976,10 +985,10 @@ static void check_process_timers(struct task_struct *tsk, } /* - * This is called from the signal code (via do_schedule_next_timer) + * This is called from the signal code (via posixtimer_rearm) * when the last timer signal was delivered and we have to reload the timer. */ -void posix_cpu_timer_schedule(struct k_itimer *timer) +static void posix_cpu_timer_rearm(struct k_itimer *timer) { struct sighand_struct *sighand; unsigned long flags; @@ -995,12 +1004,12 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) cpu_clock_sample(timer->it_clock, p, &now); bump_cpu_timer(timer, now); if (unlikely(p->exit_state)) - goto out; + return; /* Protect timer list r/w in arm_timer() */ sighand = lock_task_sighand(p, &flags); if (!sighand) - goto out; + return; } else { /* * Protect arm_timer() and timer sampling in case of call to @@ -1013,11 +1022,10 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) * We can't even collect a sample any more. */ timer->it.cpu.expires = 0; - goto out; + return; } else if (unlikely(p->exit_state) && thread_group_empty(p)) { - unlock_task_sighand(p, &flags); - /* Optimizations: if the process is dying, no need to rearm */ - goto out; + /* If the process is dying, no need to rearm */ + goto unlock; } cpu_timer_sample_group(timer->it_clock, p, &now); bump_cpu_timer(timer, now); @@ -1029,12 +1037,8 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) */ WARN_ON_ONCE(!irqs_disabled()); arm_timer(timer); +unlock: unlock_task_sighand(p, &flags); - -out: - timer->it_overrun_last = timer->it_overrun; - timer->it_overrun = -1; - ++timer->it_requeue_pending; } /** @@ -1227,9 +1231,11 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, } static int do_cpu_nanosleep(const clockid_t which_clock, int flags, - struct timespec64 *rqtp, struct itimerspec64 *it) + const struct timespec64 *rqtp) { + struct itimerspec64 it; struct k_itimer timer; + u64 expires; int error; /* @@ -1243,12 +1249,13 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, timer.it_process = current; if (!error) { static struct itimerspec64 zero_it; + struct restart_block *restart; - memset(it, 0, sizeof *it); - it->it_value = *rqtp; + memset(&it, 0, sizeof(it)); + it.it_value = *rqtp; spin_lock_irq(&timer.it_lock); - error = posix_cpu_timer_set(&timer, flags, it, NULL); + error = posix_cpu_timer_set(&timer, flags, &it, NULL); if (error) { spin_unlock_irq(&timer.it_lock); return error; @@ -1277,8 +1284,8 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, /* * We were interrupted by a signal. */ - *rqtp = ns_to_timespec64(timer.it.cpu.expires); - error = posix_cpu_timer_set(&timer, 0, &zero_it, it); + expires = timer.it.cpu.expires; + error = posix_cpu_timer_set(&timer, 0, &zero_it, &it); if (!error) { /* * Timer is now unarmed, deletion can not fail. @@ -1298,7 +1305,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, spin_unlock_irq(&timer.it_lock); } - if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) { + if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) { /* * It actually did fire already. */ @@ -1306,6 +1313,13 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, } error = -ERESTART_RESTARTBLOCK; + /* + * Report back to the user the time still remaining. + */ + restart = ¤t->restart_block; + restart->nanosleep.expires = expires; + if (restart->nanosleep.type != TT_NONE) + error = nanosleep_copyout(restart, &it.it_value); } return error; @@ -1314,11 +1328,9 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, static long posix_cpu_nsleep_restart(struct restart_block *restart_block); static int posix_cpu_nsleep(const clockid_t which_clock, int flags, - struct timespec64 *rqtp, struct timespec __user *rmtp) + const struct timespec64 *rqtp) { struct restart_block *restart_block = ¤t->restart_block; - struct itimerspec64 it; - struct timespec ts; int error; /* @@ -1329,23 +1341,15 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags, CPUCLOCK_PID(which_clock) == task_pid_vnr(current))) return -EINVAL; - error = do_cpu_nanosleep(which_clock, flags, rqtp, &it); + error = do_cpu_nanosleep(which_clock, flags, rqtp); if (error == -ERESTART_RESTARTBLOCK) { if (flags & TIMER_ABSTIME) return -ERESTARTNOHAND; - /* - * Report back to the user the time still remaining. - */ - ts = timespec64_to_timespec(it.it_value); - if (rmtp && copy_to_user(rmtp, &ts, sizeof(*rmtp))) - return -EFAULT; restart_block->fn = posix_cpu_nsleep_restart; restart_block->nanosleep.clockid = which_clock; - restart_block->nanosleep.rmtp = rmtp; - restart_block->nanosleep.expires = timespec64_to_ns(rqtp); } return error; } @@ -1353,28 +1357,11 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags, static long posix_cpu_nsleep_restart(struct restart_block *restart_block) { clockid_t which_clock = restart_block->nanosleep.clockid; - struct itimerspec64 it; struct timespec64 t; - struct timespec tmp; - int error; t = ns_to_timespec64(restart_block->nanosleep.expires); - error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it); - - if (error == -ERESTART_RESTARTBLOCK) { - struct timespec __user *rmtp = restart_block->nanosleep.rmtp; - /* - * Report back to the user the time still remaining. - */ - tmp = timespec64_to_timespec(it.it_value); - if (rmtp && copy_to_user(rmtp, &tmp, sizeof(*rmtp))) - return -EFAULT; - - restart_block->nanosleep.expires = timespec64_to_ns(&t); - } - return error; - + return do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t); } #define PROCESS_CLOCK MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED) @@ -1396,14 +1383,9 @@ static int process_cpu_timer_create(struct k_itimer *timer) return posix_cpu_timer_create(timer); } static int process_cpu_nsleep(const clockid_t which_clock, int flags, - struct timespec64 *rqtp, - struct timespec __user *rmtp) + const struct timespec64 *rqtp) { - return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp); -} -static long process_cpu_nsleep_restart(struct restart_block *restart_block) -{ - return -EINVAL; + return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp); } static int thread_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp) @@ -1421,36 +1403,27 @@ static int thread_cpu_timer_create(struct k_itimer *timer) return posix_cpu_timer_create(timer); } -struct k_clock clock_posix_cpu = { +const struct k_clock clock_posix_cpu = { .clock_getres = posix_cpu_clock_getres, .clock_set = posix_cpu_clock_set, .clock_get = posix_cpu_clock_get, .timer_create = posix_cpu_timer_create, .nsleep = posix_cpu_nsleep, - .nsleep_restart = posix_cpu_nsleep_restart, .timer_set = posix_cpu_timer_set, .timer_del = posix_cpu_timer_del, .timer_get = posix_cpu_timer_get, + .timer_rearm = posix_cpu_timer_rearm, }; -static __init int init_posix_cpu_timers(void) -{ - struct k_clock process = { - .clock_getres = process_cpu_clock_getres, - .clock_get = process_cpu_clock_get, - .timer_create = process_cpu_timer_create, - .nsleep = process_cpu_nsleep, - .nsleep_restart = process_cpu_nsleep_restart, - }; - struct k_clock thread = { - .clock_getres = thread_cpu_clock_getres, - .clock_get = thread_cpu_clock_get, - .timer_create = thread_cpu_timer_create, - }; - - posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process); - posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread); +const struct k_clock clock_process = { + .clock_getres = process_cpu_clock_getres, + .clock_get = process_cpu_clock_get, + .timer_create = process_cpu_timer_create, + .nsleep = process_cpu_nsleep, +}; - return 0; -} -__initcall(init_posix_cpu_timers); +const struct k_clock clock_thread = { + .clock_getres = thread_cpu_clock_getres, + .clock_get = thread_cpu_clock_get, + .timer_create = thread_cpu_timer_create, +}; diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index c0cd53eb018a..06f34feb635e 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -17,6 +17,7 @@ #include <linux/ktime.h> #include <linux/timekeeping.h> #include <linux/posix-timers.h> +#include <linux/compat.h> asmlinkage long sys_ni_posix_timers(void) { @@ -27,6 +28,7 @@ asmlinkage long sys_ni_posix_timers(void) } #define SYS_NI(name) SYSCALL_ALIAS(sys_##name, sys_ni_posix_timers) +#define COMPAT_SYS_NI(name) SYSCALL_ALIAS(compat_sys_##name, sys_ni_posix_timers) SYS_NI(timer_create); SYS_NI(timer_gettime); @@ -49,40 +51,52 @@ SYS_NI(alarm); SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, const struct timespec __user *, tp) { - struct timespec64 new_tp64; - struct timespec new_tp; + struct timespec64 new_tp; if (which_clock != CLOCK_REALTIME) return -EINVAL; - if (copy_from_user(&new_tp, tp, sizeof (*tp))) + if (get_timespec64(&new_tp, tp)) return -EFAULT; - new_tp64 = timespec_to_timespec64(new_tp); - return do_sys_settimeofday64(&new_tp64, NULL); + return do_sys_settimeofday64(&new_tp, NULL); } -SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, - struct timespec __user *,tp) +int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) { - struct timespec64 kernel_tp64; - struct timespec kernel_tp; - switch (which_clock) { - case CLOCK_REALTIME: ktime_get_real_ts64(&kernel_tp64); break; - case CLOCK_MONOTONIC: ktime_get_ts64(&kernel_tp64); break; - case CLOCK_BOOTTIME: get_monotonic_boottime64(&kernel_tp64); break; - default: return -EINVAL; + case CLOCK_REALTIME: + ktime_get_real_ts64(tp); + break; + case CLOCK_MONOTONIC: + ktime_get_ts64(tp); + break; + case CLOCK_BOOTTIME: + get_monotonic_boottime64(tp); + break; + default: + return -EINVAL; } - kernel_tp = timespec64_to_timespec(kernel_tp64); - if (copy_to_user(tp, &kernel_tp, sizeof (kernel_tp))) + return 0; +} +SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, + struct timespec __user *, tp) +{ + int ret; + struct timespec64 kernel_tp; + + ret = do_clock_gettime(which_clock, &kernel_tp); + if (ret) + return ret; + + if (put_timespec64(&kernel_tp, tp)) return -EFAULT; return 0; } SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct timespec __user *, tp) { - struct timespec rtn_tp = { + struct timespec64 rtn_tp = { .tv_sec = 0, .tv_nsec = hrtimer_resolution, }; @@ -91,7 +105,7 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct timespec __us case CLOCK_REALTIME: case CLOCK_MONOTONIC: case CLOCK_BOOTTIME: - if (copy_to_user(tp, &rtn_tp, sizeof(rtn_tp))) + if (put_timespec64(&rtn_tp, tp)) return -EFAULT; return 0; default: @@ -110,22 +124,108 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, case CLOCK_REALTIME: case CLOCK_MONOTONIC: case CLOCK_BOOTTIME: - if (copy_from_user(&t, rqtp, sizeof (struct timespec))) - return -EFAULT; - t64 = timespec_to_timespec64(t); - if (!timespec64_valid(&t64)) - return -EINVAL; - return hrtimer_nanosleep(&t64, rmtp, flags & TIMER_ABSTIME ? - HRTIMER_MODE_ABS : HRTIMER_MODE_REL, - which_clock); + break; default: return -EINVAL; } + + if (copy_from_user(&t, rqtp, sizeof (struct timespec))) + return -EFAULT; + t64 = timespec_to_timespec64(t); + if (!timespec64_valid(&t64)) + return -EINVAL; + if (flags & TIMER_ABSTIME) + rmtp = NULL; + current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; + current->restart_block.nanosleep.rmtp = rmtp; + return hrtimer_nanosleep(&t64, flags & TIMER_ABSTIME ? + HRTIMER_MODE_ABS : HRTIMER_MODE_REL, + which_clock); } #ifdef CONFIG_COMPAT -long clock_nanosleep_restart(struct restart_block *restart_block) +COMPAT_SYS_NI(timer_create); +COMPAT_SYS_NI(clock_adjtime); +COMPAT_SYS_NI(timer_settime); +COMPAT_SYS_NI(timer_gettime); +COMPAT_SYS_NI(getitimer); +COMPAT_SYS_NI(setitimer); + +COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, + struct compat_timespec __user *, tp) { - return hrtimer_nanosleep_restart(restart_block); + struct timespec64 new_tp; + + if (which_clock != CLOCK_REALTIME) + return -EINVAL; + if (compat_get_timespec64(&new_tp, tp)) + return -EFAULT; + + return do_sys_settimeofday64(&new_tp, NULL); +} + +COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, + struct compat_timespec __user *, tp) +{ + int ret; + struct timespec64 kernel_tp; + + ret = do_clock_gettime(which_clock, &kernel_tp); + if (ret) + return ret; + + if (compat_put_timespec64(&kernel_tp, tp)) + return -EFAULT; + return 0; +} + +COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, + struct compat_timespec __user *, tp) +{ + struct timespec64 rtn_tp = { + .tv_sec = 0, + .tv_nsec = hrtimer_resolution, + }; + + switch (which_clock) { + case CLOCK_REALTIME: + case CLOCK_MONOTONIC: + case CLOCK_BOOTTIME: + if (compat_put_timespec64(&rtn_tp, tp)) + return -EFAULT; + return 0; + default: + return -EINVAL; + } +} + +COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, + struct compat_timespec __user *, rqtp, + struct compat_timespec __user *, rmtp) +{ + struct timespec64 t64; + struct timespec t; + + switch (which_clock) { + case CLOCK_REALTIME: + case CLOCK_MONOTONIC: + case CLOCK_BOOTTIME: + break; + default: + return -EINVAL; + } + + if (compat_get_timespec(&t, rqtp)) + return -EFAULT; + t64 = timespec_to_timespec64(t); + if (!timespec64_valid(&t64)) + return -EINVAL; + if (flags & TIMER_ABSTIME) + rmtp = NULL; + current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; + current->restart_block.nanosleep.compat_rmtp = rmtp; + return hrtimer_nanosleep(&t64, flags & TIMER_ABSTIME ? + HRTIMER_MODE_ABS : HRTIMER_MODE_REL, + which_clock); } #endif diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 4d7b2ce09c27..13d6881f908b 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -49,8 +49,10 @@ #include <linux/workqueue.h> #include <linux/export.h> #include <linux/hashtable.h> +#include <linux/compat.h> #include "timekeeping.h" +#include "posix-timers.h" /* * Management arrays for POSIX timers. Timers are now kept in static hash table @@ -69,6 +71,10 @@ static struct kmem_cache *posix_timers_cache; static DEFINE_HASHTABLE(posix_timers_hashtable, 9); static DEFINE_SPINLOCK(hash_lock); +static const struct k_clock * const posix_clocks[]; +static const struct k_clock *clockid_to_kclock(const clockid_t id); +static const struct k_clock clock_realtime, clock_monotonic; + /* * we assume that the new SIGEV_THREAD_ID shares no bits with the other * SIGEV values. Here we put out an error if this assumption fails. @@ -124,22 +130,6 @@ static DEFINE_SPINLOCK(hash_lock); * have is CLOCK_REALTIME and its high res counter part, both of * which we beg off on and pass to do_sys_settimeofday(). */ - -static struct k_clock posix_clocks[MAX_CLOCKS]; - -/* - * These ones are defined below. - */ -static int common_nsleep(const clockid_t, int flags, struct timespec64 *t, - struct timespec __user *rmtp); -static int common_timer_create(struct k_itimer *new_timer); -static void common_timer_get(struct k_itimer *, struct itimerspec64 *); -static int common_timer_set(struct k_itimer *, int, - struct itimerspec64 *, struct itimerspec64 *); -static int common_timer_del(struct k_itimer *timer); - -static enum hrtimer_restart posix_timer_fn(struct hrtimer *data); - static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags); #define lock_timer(tid, flags) \ @@ -285,91 +275,23 @@ static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp) */ static __init int init_posix_timers(void) { - struct k_clock clock_realtime = { - .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_clock_realtime_get, - .clock_set = posix_clock_realtime_set, - .clock_adj = posix_clock_realtime_adj, - .nsleep = common_nsleep, - .nsleep_restart = hrtimer_nanosleep_restart, - .timer_create = common_timer_create, - .timer_set = common_timer_set, - .timer_get = common_timer_get, - .timer_del = common_timer_del, - }; - struct k_clock clock_monotonic = { - .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_ktime_get_ts, - .nsleep = common_nsleep, - .nsleep_restart = hrtimer_nanosleep_restart, - .timer_create = common_timer_create, - .timer_set = common_timer_set, - .timer_get = common_timer_get, - .timer_del = common_timer_del, - }; - struct k_clock clock_monotonic_raw = { - .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_monotonic_raw, - }; - struct k_clock clock_realtime_coarse = { - .clock_getres = posix_get_coarse_res, - .clock_get = posix_get_realtime_coarse, - }; - struct k_clock clock_monotonic_coarse = { - .clock_getres = posix_get_coarse_res, - .clock_get = posix_get_monotonic_coarse, - }; - struct k_clock clock_tai = { - .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_tai, - .nsleep = common_nsleep, - .nsleep_restart = hrtimer_nanosleep_restart, - .timer_create = common_timer_create, - .timer_set = common_timer_set, - .timer_get = common_timer_get, - .timer_del = common_timer_del, - }; - struct k_clock clock_boottime = { - .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_boottime, - .nsleep = common_nsleep, - .nsleep_restart = hrtimer_nanosleep_restart, - .timer_create = common_timer_create, - .timer_set = common_timer_set, - .timer_get = common_timer_get, - .timer_del = common_timer_del, - }; - - posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime); - posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic); - posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw); - posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse); - posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse); - posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime); - posix_timers_register_clock(CLOCK_TAI, &clock_tai); - posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof (struct k_itimer), 0, SLAB_PANIC, NULL); return 0; } - __initcall(init_posix_timers); -static void schedule_next_timer(struct k_itimer *timr) +static void common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; - if (timr->it.real.interval == 0) + if (!timr->it_interval) return; timr->it_overrun += (unsigned int) hrtimer_forward(timer, timer->base->get_time(), - timr->it.real.interval); - - timr->it_overrun_last = timr->it_overrun; - timr->it_overrun = -1; - ++timr->it_requeue_pending; + timr->it_interval); hrtimer_restart(timer); } @@ -384,24 +306,27 @@ static void schedule_next_timer(struct k_itimer *timr) * To protect against the timer going away while the interrupt is queued, * we require that the it_requeue_pending flag be set. */ -void do_schedule_next_timer(struct siginfo *info) +void posixtimer_rearm(struct siginfo *info) { struct k_itimer *timr; unsigned long flags; timr = lock_timer(info->si_tid, &flags); + if (!timr) + return; + + if (timr->it_requeue_pending == info->si_sys_private) { + timr->kclock->timer_rearm(timr); - if (timr && timr->it_requeue_pending == info->si_sys_private) { - if (timr->it_clock < 0) - posix_cpu_timer_schedule(timr); - else - schedule_next_timer(timr); + timr->it_active = 1; + timr->it_overrun_last = timr->it_overrun; + timr->it_overrun = -1; + ++timr->it_requeue_pending; info->si_overrun += timr->it_overrun_last; } - if (timr) - unlock_timer(timr, flags); + unlock_timer(timr, flags); } int posix_timer_event(struct k_itimer *timr, int si_private) @@ -410,12 +335,12 @@ int posix_timer_event(struct k_itimer *timr, int si_private) int shared, ret = -1; /* * FIXME: if ->sigq is queued we can race with - * dequeue_signal()->do_schedule_next_timer(). + * dequeue_signal()->posixtimer_rearm(). * * If dequeue_signal() sees the "right" value of - * si_sys_private it calls do_schedule_next_timer(). + * si_sys_private it calls posixtimer_rearm(). * We re-queue ->sigq and drop ->it_lock(). - * do_schedule_next_timer() locks the timer + * posixtimer_rearm() locks the timer * and re-schedules it while ->sigq is pending. * Not really bad, but not that we want. */ @@ -431,7 +356,6 @@ int posix_timer_event(struct k_itimer *timr, int si_private) /* If we failed to send the signal the timer stops. */ return ret > 0; } -EXPORT_SYMBOL_GPL(posix_timer_event); /* * This function gets called when a POSIX.1b interval timer expires. It @@ -450,7 +374,8 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) timr = container_of(timer, struct k_itimer, it.real.timer); spin_lock_irqsave(&timr->it_lock, flags); - if (timr->it.real.interval != 0) + timr->it_active = 0; + if (timr->it_interval != 0) si_private = ++timr->it_requeue_pending; if (posix_timer_event(timr, si_private)) { @@ -459,7 +384,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) * we will not get a call back to restart it AND * it should be restarted. */ - if (timr->it.real.interval != 0) { + if (timr->it_interval != 0) { ktime_t now = hrtimer_cb_get_time(timer); /* @@ -488,15 +413,16 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) { ktime_t kj = NSEC_PER_SEC / HZ; - if (timr->it.real.interval < kj) + if (timr->it_interval < kj) now = ktime_add(now, kj); } #endif timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, - timr->it.real.interval); + timr->it_interval); ret = HRTIMER_RESTART; ++timr->it_requeue_pending; + timr->it_active = 1; } } @@ -521,30 +447,6 @@ static struct pid *good_sigevent(sigevent_t * event) return task_pid(rtn); } -void posix_timers_register_clock(const clockid_t clock_id, - struct k_clock *new_clock) -{ - if ((unsigned) clock_id >= MAX_CLOCKS) { - printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n", - clock_id); - return; - } - - if (!new_clock->clock_get) { - printk(KERN_WARNING "POSIX clock id %d lacks clock_get()\n", - clock_id); - return; - } - if (!new_clock->clock_getres) { - printk(KERN_WARNING "POSIX clock id %d lacks clock_getres()\n", - clock_id); - return; - } - - posix_clocks[clock_id] = *new_clock; -} -EXPORT_SYMBOL_GPL(posix_timers_register_clock); - static struct k_itimer * alloc_posix_timer(void) { struct k_itimer *tmr; @@ -581,17 +483,6 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set) call_rcu(&tmr->it.rcu, k_itimer_rcu_free); } -static struct k_clock *clockid_to_kclock(const clockid_t id) -{ - if (id < 0) - return (id & CLOCKFD_MASK) == CLOCKFD ? - &clock_posix_dynamic : &clock_posix_cpu; - - if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres) - return NULL; - return &posix_clocks[id]; -} - static int common_timer_create(struct k_itimer *new_timer) { hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0); @@ -599,15 +490,12 @@ static int common_timer_create(struct k_itimer *new_timer) } /* Create a POSIX.1b interval timer. */ - -SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, - struct sigevent __user *, timer_event_spec, - timer_t __user *, created_timer_id) +static int do_timer_create(clockid_t which_clock, struct sigevent *event, + timer_t __user *created_timer_id) { - struct k_clock *kc = clockid_to_kclock(which_clock); + const struct k_clock *kc = clockid_to_kclock(which_clock); struct k_itimer *new_timer; int error, new_timer_id; - sigevent_t event; int it_id_set = IT_ID_NOT_SET; if (!kc) @@ -629,31 +517,28 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, it_id_set = IT_ID_SET; new_timer->it_id = (timer_t) new_timer_id; new_timer->it_clock = which_clock; + new_timer->kclock = kc; new_timer->it_overrun = -1; - if (timer_event_spec) { - if (copy_from_user(&event, timer_event_spec, sizeof (event))) { - error = -EFAULT; - goto out; - } + if (event) { rcu_read_lock(); - new_timer->it_pid = get_pid(good_sigevent(&event)); + new_timer->it_pid = get_pid(good_sigevent(event)); rcu_read_unlock(); if (!new_timer->it_pid) { error = -EINVAL; goto out; } + new_timer->it_sigev_notify = event->sigev_notify; + new_timer->sigq->info.si_signo = event->sigev_signo; + new_timer->sigq->info.si_value = event->sigev_value; } else { - memset(&event.sigev_value, 0, sizeof(event.sigev_value)); - event.sigev_notify = SIGEV_SIGNAL; - event.sigev_signo = SIGALRM; - event.sigev_value.sival_int = new_timer->it_id; + new_timer->it_sigev_notify = SIGEV_SIGNAL; + new_timer->sigq->info.si_signo = SIGALRM; + memset(&new_timer->sigq->info.si_value, 0, sizeof(sigval_t)); + new_timer->sigq->info.si_value.sival_int = new_timer->it_id; new_timer->it_pid = get_pid(task_tgid(current)); } - new_timer->it_sigev_notify = event.sigev_notify; - new_timer->sigq->info.si_signo = event.sigev_signo; - new_timer->sigq->info.si_value = event.sigev_value; new_timer->sigq->info.si_tid = new_timer->it_id; new_timer->sigq->info.si_code = SI_TIMER; @@ -684,6 +569,36 @@ out: return error; } +SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, + struct sigevent __user *, timer_event_spec, + timer_t __user *, created_timer_id) +{ + if (timer_event_spec) { + sigevent_t event; + + if (copy_from_user(&event, timer_event_spec, sizeof (event))) + return -EFAULT; + return do_timer_create(which_clock, &event, created_timer_id); + } + return do_timer_create(which_clock, NULL, created_timer_id); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock, + struct compat_sigevent __user *, timer_event_spec, + timer_t __user *, created_timer_id) +{ + if (timer_event_spec) { + sigevent_t event; + + if (get_compat_sigevent(&event, timer_event_spec)) + return -EFAULT; + return do_timer_create(which_clock, &event, created_timer_id); + } + return do_timer_create(which_clock, NULL, created_timer_id); +} +#endif + /* * Locking issues: We need to protect the result of the id look up until * we get the timer locked down so it is not deleted under us. The @@ -717,6 +632,20 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) return NULL; } +static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now) +{ + struct hrtimer *timer = &timr->it.real.timer; + + return __hrtimer_expires_remaining_adjusted(timer, now); +} + +static int common_hrtimer_forward(struct k_itimer *timr, ktime_t now) +{ + struct hrtimer *timer = &timr->it.real.timer; + + return (int)hrtimer_forward(timer, now, timr->it_interval); +} + /* * Get the time remaining on a POSIX.1b interval timer. This function * is ALWAYS called with spin_lock_irq on the timer, thus it must not @@ -733,55 +662,61 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) * it is the same as a requeue pending timer WRT to what we should * report. */ -static void -common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) +void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) { + const struct k_clock *kc = timr->kclock; ktime_t now, remaining, iv; - struct hrtimer *timer = &timr->it.real.timer; - - memset(cur_setting, 0, sizeof(*cur_setting)); + struct timespec64 ts64; + bool sig_none; - iv = timr->it.real.interval; + sig_none = (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE; + iv = timr->it_interval; /* interval timer ? */ - if (iv) + if (iv) { cur_setting->it_interval = ktime_to_timespec64(iv); - else if (!hrtimer_active(timer) && - (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) - return; + } else if (!timr->it_active) { + /* + * SIGEV_NONE oneshot timers are never queued. Check them + * below. + */ + if (!sig_none) + return; + } - now = timer->base->get_time(); + /* + * The timespec64 based conversion is suboptimal, but it's not + * worth to implement yet another callback. + */ + kc->clock_get(timr->it_clock, &ts64); + now = timespec64_to_ktime(ts64); /* - * When a requeue is pending or this is a SIGEV_NONE - * timer move the expiry time forward by intervals, so - * expiry is > now. + * When a requeue is pending or this is a SIGEV_NONE timer move the + * expiry time forward by intervals, so expiry is > now. */ - if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || - (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) - timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); + if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || sig_none)) + timr->it_overrun += kc->timer_forward(timr, now); - remaining = __hrtimer_expires_remaining_adjusted(timer, now); + remaining = kc->timer_remaining(timr, now); /* Return 0 only, when the timer is expired and not pending */ if (remaining <= 0) { /* * A single shot SIGEV_NONE timer must return 0, when * it is expired ! */ - if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) + if (!sig_none) cur_setting->it_value.tv_nsec = 1; - } else + } else { cur_setting->it_value = ktime_to_timespec64(remaining); + } } /* Get the time remaining on a POSIX.1b interval timer. */ -SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct itimerspec __user *, setting) +static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting) { - struct itimerspec64 cur_setting64; - struct itimerspec cur_setting; struct k_itimer *timr; - struct k_clock *kc; + const struct k_clock *kc; unsigned long flags; int ret = 0; @@ -789,20 +724,45 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, if (!timr) return -EINVAL; - kc = clockid_to_kclock(timr->it_clock); + memset(setting, 0, sizeof(*setting)); + kc = timr->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_get)) ret = -EINVAL; else - kc->timer_get(timr, &cur_setting64); + kc->timer_get(timr, setting); unlock_timer(timr, flags); + return ret; +} - cur_setting = itimerspec64_to_itimerspec(&cur_setting64); - if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting))) - return -EFAULT; +/* Get the time remaining on a POSIX.1b interval timer. */ +SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, + struct itimerspec __user *, setting) +{ + struct itimerspec64 cur_setting; + + int ret = do_timer_gettime(timer_id, &cur_setting); + if (!ret) { + if (put_itimerspec64(&cur_setting, setting)) + ret = -EFAULT; + } + return ret; +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, + struct compat_itimerspec __user *, setting) +{ + struct itimerspec64 cur_setting; + int ret = do_timer_gettime(timer_id, &cur_setting); + if (!ret) { + if (put_compat_itimerspec64(&cur_setting, setting)) + ret = -EFAULT; + } return ret; } +#endif /* * Get the number of overruns of a POSIX.1b interval timer. This is to @@ -810,7 +770,7 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, * accumulating overruns on the next timer. The overrun is frozen when * the signal is delivered, either at the notify time (if the info block * is not queued) or at the actual delivery time (as we are informed by - * the call back to do_schedule_next_timer(). So all we need to do is + * the call back to posixtimer_rearm(). So all we need to do is * to pick up the frozen overrun. */ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) @@ -829,117 +789,175 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) return overrun; } -/* Set a POSIX.1b interval timer. */ -/* timr->it_lock is taken. */ -static int -common_timer_set(struct k_itimer *timr, int flags, - struct itimerspec64 *new_setting, struct itimerspec64 *old_setting) +static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, + bool absolute, bool sigev_none) { struct hrtimer *timer = &timr->it.real.timer; enum hrtimer_mode mode; + mode = absolute ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL; + /* + * Posix magic: Relative CLOCK_REALTIME timers are not affected by + * clock modifications, so they become CLOCK_MONOTONIC based under the + * hood. See hrtimer_init(). Update timr->kclock, so the generic + * functions which use timr->kclock->clock_get() work. + * + * Note: it_clock stays unmodified, because the next timer_set() might + * use ABSTIME, so it needs to switch back. + */ + if (timr->it_clock == CLOCK_REALTIME) + timr->kclock = absolute ? &clock_realtime : &clock_monotonic; + + hrtimer_init(&timr->it.real.timer, timr->it_clock, mode); + timr->it.real.timer.function = posix_timer_fn; + + if (!absolute) + expires = ktime_add_safe(expires, timer->base->get_time()); + hrtimer_set_expires(timer, expires); + + if (!sigev_none) + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); +} + +static int common_hrtimer_try_to_cancel(struct k_itimer *timr) +{ + return hrtimer_try_to_cancel(&timr->it.real.timer); +} + +/* Set a POSIX.1b interval timer. */ +int common_timer_set(struct k_itimer *timr, int flags, + struct itimerspec64 *new_setting, + struct itimerspec64 *old_setting) +{ + const struct k_clock *kc = timr->kclock; + bool sigev_none; + ktime_t expires; + if (old_setting) common_timer_get(timr, old_setting); - /* disable the timer */ - timr->it.real.interval = 0; + /* Prevent rearming by clearing the interval */ + timr->it_interval = 0; /* - * careful here. If smp we could be in the "fire" routine which will - * be spinning as we hold the lock. But this is ONLY an SMP issue. + * Careful here. On SMP systems the timer expiry function could be + * active and spinning on timr->it_lock. */ - if (hrtimer_try_to_cancel(timer) < 0) + if (kc->timer_try_to_cancel(timr) < 0) return TIMER_RETRY; - timr->it_requeue_pending = (timr->it_requeue_pending + 2) & + timr->it_active = 0; + timr->it_requeue_pending = (timr->it_requeue_pending + 2) & ~REQUEUE_PENDING; timr->it_overrun_last = 0; - /* switch off the timer when it_value is zero */ + /* Switch off the timer when it_value is zero */ if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) return 0; - mode = flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL; - hrtimer_init(&timr->it.real.timer, timr->it_clock, mode); - timr->it.real.timer.function = posix_timer_fn; - - hrtimer_set_expires(timer, timespec64_to_ktime(new_setting->it_value)); - - /* Convert interval */ - timr->it.real.interval = timespec64_to_ktime(new_setting->it_interval); - - /* SIGEV_NONE timers are not queued ! See common_timer_get */ - if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) { - /* Setup correct expiry time for relative timers */ - if (mode == HRTIMER_MODE_REL) { - hrtimer_add_expires(timer, timer->base->get_time()); - } - return 0; - } + timr->it_interval = timespec64_to_ktime(new_setting->it_interval); + expires = timespec64_to_ktime(new_setting->it_value); + sigev_none = (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE; - hrtimer_start_expires(timer, mode); + kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none); + timr->it_active = !sigev_none; return 0; } -/* Set a POSIX.1b interval timer */ -SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - const struct itimerspec __user *, new_setting, - struct itimerspec __user *, old_setting) +static int do_timer_settime(timer_t timer_id, int flags, + struct itimerspec64 *new_spec64, + struct itimerspec64 *old_spec64) { - struct itimerspec64 new_spec64, old_spec64; - struct itimerspec64 *rtn = old_setting ? &old_spec64 : NULL; - struct itimerspec new_spec, old_spec; + const struct k_clock *kc; struct k_itimer *timr; unsigned long flag; - struct k_clock *kc; int error = 0; - if (!new_setting) + if (!timespec64_valid(&new_spec64->it_interval) || + !timespec64_valid(&new_spec64->it_value)) return -EINVAL; - if (copy_from_user(&new_spec, new_setting, sizeof (new_spec))) - return -EFAULT; - new_spec64 = itimerspec_to_itimerspec64(&new_spec); - - if (!timespec64_valid(&new_spec64.it_interval) || - !timespec64_valid(&new_spec64.it_value)) - return -EINVAL; + if (old_spec64) + memset(old_spec64, 0, sizeof(*old_spec64)); retry: timr = lock_timer(timer_id, &flag); if (!timr) return -EINVAL; - kc = clockid_to_kclock(timr->it_clock); + kc = timr->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; else - error = kc->timer_set(timr, flags, &new_spec64, rtn); + error = kc->timer_set(timr, flags, new_spec64, old_spec64); unlock_timer(timr, flag); if (error == TIMER_RETRY) { - rtn = NULL; // We already got the old time... + old_spec64 = NULL; // We already got the old time... goto retry; } - old_spec = itimerspec64_to_itimerspec(&old_spec64); - if (old_setting && !error && - copy_to_user(old_setting, &old_spec, sizeof (old_spec))) - error = -EFAULT; + return error; +} + +/* Set a POSIX.1b interval timer */ +SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, + const struct itimerspec __user *, new_setting, + struct itimerspec __user *, old_setting) +{ + struct itimerspec64 new_spec, old_spec; + struct itimerspec64 *rtn = old_setting ? &old_spec : NULL; + int error = 0; + + if (!new_setting) + return -EINVAL; + if (get_itimerspec64(&new_spec, new_setting)) + return -EFAULT; + + error = do_timer_settime(timer_id, flags, &new_spec, rtn); + if (!error && old_setting) { + if (put_itimerspec64(&old_spec, old_setting)) + error = -EFAULT; + } + return error; +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, + struct compat_itimerspec __user *, new, + struct compat_itimerspec __user *, old) +{ + struct itimerspec64 new_spec, old_spec; + struct itimerspec64 *rtn = old ? &old_spec : NULL; + int error = 0; + + if (!new) + return -EINVAL; + if (get_compat_itimerspec64(&new_spec, new)) + return -EFAULT; + + error = do_timer_settime(timer_id, flags, &new_spec, rtn); + if (!error && old) { + if (put_compat_itimerspec64(&old_spec, old)) + error = -EFAULT; + } return error; } +#endif -static int common_timer_del(struct k_itimer *timer) +int common_timer_del(struct k_itimer *timer) { - timer->it.real.interval = 0; + const struct k_clock *kc = timer->kclock; - if (hrtimer_try_to_cancel(&timer->it.real.timer) < 0) + timer->it_interval = 0; + if (kc->timer_try_to_cancel(timer) < 0) return TIMER_RETRY; + timer->it_active = 0; return 0; } static inline int timer_delete_hook(struct k_itimer *timer) { - struct k_clock *kc = clockid_to_kclock(timer->it_clock); + const struct k_clock *kc = timer->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_del)) return -EINVAL; @@ -1018,35 +1036,31 @@ void exit_itimers(struct signal_struct *sig) SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, const struct timespec __user *, tp) { - struct k_clock *kc = clockid_to_kclock(which_clock); - struct timespec64 new_tp64; - struct timespec new_tp; + const struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec64 new_tp; if (!kc || !kc->clock_set) return -EINVAL; - if (copy_from_user(&new_tp, tp, sizeof (*tp))) + if (get_timespec64(&new_tp, tp)) return -EFAULT; - new_tp64 = timespec_to_timespec64(new_tp); - return kc->clock_set(which_clock, &new_tp64); + return kc->clock_set(which_clock, &new_tp); } SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, struct timespec __user *,tp) { - struct k_clock *kc = clockid_to_kclock(which_clock); - struct timespec64 kernel_tp64; - struct timespec kernel_tp; + const struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec64 kernel_tp; int error; if (!kc) return -EINVAL; - error = kc->clock_get(which_clock, &kernel_tp64); - kernel_tp = timespec64_to_timespec(kernel_tp64); + error = kc->clock_get(which_clock, &kernel_tp); - if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp))) + if (!error && put_timespec64(&kernel_tp, tp)) error = -EFAULT; return error; @@ -1055,7 +1069,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, struct timex __user *, utx) { - struct k_clock *kc = clockid_to_kclock(which_clock); + const struct k_clock *kc = clockid_to_kclock(which_clock); struct timex ktx; int err; @@ -1078,30 +1092,106 @@ SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct timespec __user *, tp) { - struct k_clock *kc = clockid_to_kclock(which_clock); - struct timespec64 rtn_tp64; - struct timespec rtn_tp; + const struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec64 rtn_tp; int error; if (!kc) return -EINVAL; - error = kc->clock_getres(which_clock, &rtn_tp64); - rtn_tp = timespec64_to_timespec(rtn_tp64); + error = kc->clock_getres(which_clock, &rtn_tp); - if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp))) + if (!error && tp && put_timespec64(&rtn_tp, tp)) error = -EFAULT; return error; } +#ifdef CONFIG_COMPAT + +COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, + struct compat_timespec __user *, tp) +{ + const struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec64 ts; + + if (!kc || !kc->clock_set) + return -EINVAL; + + if (compat_get_timespec64(&ts, tp)) + return -EFAULT; + + return kc->clock_set(which_clock, &ts); +} + +COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, + struct compat_timespec __user *, tp) +{ + const struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec64 ts; + int err; + + if (!kc) + return -EINVAL; + + err = kc->clock_get(which_clock, &ts); + + if (!err && compat_put_timespec64(&ts, tp)) + err = -EFAULT; + + return err; +} + +COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, + struct compat_timex __user *, utp) +{ + const struct k_clock *kc = clockid_to_kclock(which_clock); + struct timex ktx; + int err; + + if (!kc) + return -EINVAL; + if (!kc->clock_adj) + return -EOPNOTSUPP; + + err = compat_get_timex(&ktx, utp); + if (err) + return err; + + err = kc->clock_adj(which_clock, &ktx); + + if (err >= 0) + err = compat_put_timex(utp, &ktx); + + return err; +} + +COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, + struct compat_timespec __user *, tp) +{ + const struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec64 ts; + int err; + + if (!kc) + return -EINVAL; + + err = kc->clock_getres(which_clock, &ts); + if (!err && tp && compat_put_timespec64(&ts, tp)) + return -EFAULT; + + return err; +} + +#endif + /* * nanosleep for monotonic and realtime clocks */ static int common_nsleep(const clockid_t which_clock, int flags, - struct timespec64 *tsave, struct timespec __user *rmtp) + const struct timespec64 *rqtp) { - return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ? + return hrtimer_nanosleep(rqtp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } @@ -1110,36 +1200,152 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, const struct timespec __user *, rqtp, struct timespec __user *, rmtp) { - struct k_clock *kc = clockid_to_kclock(which_clock); - struct timespec64 t64; - struct timespec t; + const struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec64 t; if (!kc) return -EINVAL; if (!kc->nsleep) return -ENANOSLEEP_NOTSUP; - if (copy_from_user(&t, rqtp, sizeof (struct timespec))) + if (get_timespec64(&t, rqtp)) return -EFAULT; - t64 = timespec_to_timespec64(t); - if (!timespec64_valid(&t64)) + if (!timespec64_valid(&t)) return -EINVAL; + if (flags & TIMER_ABSTIME) + rmtp = NULL; + current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; + current->restart_block.nanosleep.rmtp = rmtp; - return kc->nsleep(which_clock, flags, &t64, rmtp); + return kc->nsleep(which_clock, flags, &t); } -/* - * This will restart clock_nanosleep. This is required only by - * compat_clock_nanosleep_restart for now. - */ -long clock_nanosleep_restart(struct restart_block *restart_block) +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, + struct compat_timespec __user *, rqtp, + struct compat_timespec __user *, rmtp) { - clockid_t which_clock = restart_block->nanosleep.clockid; - struct k_clock *kc = clockid_to_kclock(which_clock); + const struct k_clock *kc = clockid_to_kclock(which_clock); + struct timespec64 t; + + if (!kc) + return -EINVAL; + if (!kc->nsleep) + return -ENANOSLEEP_NOTSUP; - if (WARN_ON_ONCE(!kc || !kc->nsleep_restart)) + if (compat_get_timespec64(&t, rqtp)) + return -EFAULT; + + if (!timespec64_valid(&t)) return -EINVAL; + if (flags & TIMER_ABSTIME) + rmtp = NULL; + current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; + current->restart_block.nanosleep.compat_rmtp = rmtp; + + return kc->nsleep(which_clock, flags, &t); +} +#endif - return kc->nsleep_restart(restart_block); +static const struct k_clock clock_realtime = { + .clock_getres = posix_get_hrtimer_res, + .clock_get = posix_clock_realtime_get, + .clock_set = posix_clock_realtime_set, + .clock_adj = posix_clock_realtime_adj, + .nsleep = common_nsleep, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + .timer_rearm = common_hrtimer_rearm, + .timer_forward = common_hrtimer_forward, + .timer_remaining = common_hrtimer_remaining, + .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_arm = common_hrtimer_arm, +}; + +static const struct k_clock clock_monotonic = { + .clock_getres = posix_get_hrtimer_res, + .clock_get = posix_ktime_get_ts, + .nsleep = common_nsleep, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + .timer_rearm = common_hrtimer_rearm, + .timer_forward = common_hrtimer_forward, + .timer_remaining = common_hrtimer_remaining, + .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_arm = common_hrtimer_arm, +}; + +static const struct k_clock clock_monotonic_raw = { + .clock_getres = posix_get_hrtimer_res, + .clock_get = posix_get_monotonic_raw, +}; + +static const struct k_clock clock_realtime_coarse = { + .clock_getres = posix_get_coarse_res, + .clock_get = posix_get_realtime_coarse, +}; + +static const struct k_clock clock_monotonic_coarse = { + .clock_getres = posix_get_coarse_res, + .clock_get = posix_get_monotonic_coarse, +}; + +static const struct k_clock clock_tai = { + .clock_getres = posix_get_hrtimer_res, + .clock_get = posix_get_tai, + .nsleep = common_nsleep, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + .timer_rearm = common_hrtimer_rearm, + .timer_forward = common_hrtimer_forward, + .timer_remaining = common_hrtimer_remaining, + .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_arm = common_hrtimer_arm, +}; + +static const struct k_clock clock_boottime = { + .clock_getres = posix_get_hrtimer_res, + .clock_get = posix_get_boottime, + .nsleep = common_nsleep, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + .timer_rearm = common_hrtimer_rearm, + .timer_forward = common_hrtimer_forward, + .timer_remaining = common_hrtimer_remaining, + .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_arm = common_hrtimer_arm, +}; + +static const struct k_clock * const posix_clocks[] = { + [CLOCK_REALTIME] = &clock_realtime, + [CLOCK_MONOTONIC] = &clock_monotonic, + [CLOCK_PROCESS_CPUTIME_ID] = &clock_process, + [CLOCK_THREAD_CPUTIME_ID] = &clock_thread, + [CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw, + [CLOCK_REALTIME_COARSE] = &clock_realtime_coarse, + [CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse, + [CLOCK_BOOTTIME] = &clock_boottime, + [CLOCK_REALTIME_ALARM] = &alarm_clock, + [CLOCK_BOOTTIME_ALARM] = &alarm_clock, + [CLOCK_TAI] = &clock_tai, +}; + +static const struct k_clock *clockid_to_kclock(const clockid_t id) +{ + if (id < 0) + return (id & CLOCKFD_MASK) == CLOCKFD ? + &clock_posix_dynamic : &clock_posix_cpu; + + if (id >= ARRAY_SIZE(posix_clocks) || !posix_clocks[id]) + return NULL; + return posix_clocks[id]; } diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h new file mode 100644 index 000000000000..fb303c3be4d3 --- /dev/null +++ b/kernel/time/posix-timers.h @@ -0,0 +1,40 @@ +#define TIMER_RETRY 1 + +struct k_clock { + int (*clock_getres)(const clockid_t which_clock, + struct timespec64 *tp); + int (*clock_set)(const clockid_t which_clock, + const struct timespec64 *tp); + int (*clock_get)(const clockid_t which_clock, + struct timespec64 *tp); + int (*clock_adj)(const clockid_t which_clock, struct timex *tx); + int (*timer_create)(struct k_itimer *timer); + int (*nsleep)(const clockid_t which_clock, int flags, + const struct timespec64 *); + int (*timer_set)(struct k_itimer *timr, int flags, + struct itimerspec64 *new_setting, + struct itimerspec64 *old_setting); + int (*timer_del)(struct k_itimer *timr); + void (*timer_get)(struct k_itimer *timr, + struct itimerspec64 *cur_setting); + void (*timer_rearm)(struct k_itimer *timr); + int (*timer_forward)(struct k_itimer *timr, ktime_t now); + ktime_t (*timer_remaining)(struct k_itimer *timr, ktime_t now); + int (*timer_try_to_cancel)(struct k_itimer *timr); + void (*timer_arm)(struct k_itimer *timr, ktime_t expires, + bool absolute, bool sigev_none); +}; + +extern const struct k_clock clock_posix_cpu; +extern const struct k_clock clock_posix_dynamic; +extern const struct k_clock clock_process; +extern const struct k_clock clock_thread; +extern const struct k_clock alarm_clock; + +int posix_timer_event(struct k_itimer *timr, int si_private); + +void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting); +int common_timer_set(struct k_itimer *timr, int flags, + struct itimerspec64 *new_setting, + struct itimerspec64 *old_setting); +int common_timer_del(struct k_itimer *timer); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 987e496bb51a..b398c2ea69b2 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -37,9 +37,11 @@ static int tick_broadcast_forced; static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); #ifdef CONFIG_TICK_ONESHOT +static void tick_broadcast_setup_oneshot(struct clock_event_device *bc); static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); #else +static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } static inline void tick_broadcast_clear_oneshot(int cpu) { } static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } #endif @@ -867,7 +869,7 @@ static void tick_broadcast_init_next_event(struct cpumask *mask, /** * tick_broadcast_setup_oneshot - setup the broadcast device */ -void tick_broadcast_setup_oneshot(struct clock_event_device *bc) +static void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { int cpu = smp_processor_id(); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index f738251000fe..be0ac01f2e12 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -126,7 +126,6 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } /* Functions related to oneshot broadcasting */ #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) -extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc); extern void tick_broadcast_switch_to_oneshot(void); extern void tick_shutdown_broadcast_oneshot(unsigned int cpu); extern int tick_broadcast_oneshot_active(void); @@ -134,7 +133,6 @@ extern void tick_check_oneshot_broadcast_this_cpu(void); bool tick_broadcast_oneshot_available(void); extern struct cpumask *tick_get_broadcast_oneshot_mask(void); #else /* !(BROADCAST && ONESHOT): */ -static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } static inline void tick_broadcast_switch_to_oneshot(void) { } static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 64c97fc130c4..c7a899c5ce64 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -150,6 +150,12 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) touch_softlockup_watchdog_sched(); if (is_idle_task(current)) ts->idle_jiffies++; + /* + * In case the current tick fired too early past its expected + * expiration, make sure we don't bypass the next clock reprogramming + * to the same deadline. + */ + ts->next_tick = 0; } #endif update_process_times(user_mode(regs)); @@ -554,7 +560,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) update_ts_time_stats(smp_processor_id(), ts, now, NULL); ts->idle_active = 0; - sched_clock_idle_wakeup_event(0); + sched_clock_idle_wakeup_event(); } static ktime_t tick_nohz_start_idle(struct tick_sched *ts) @@ -660,6 +666,12 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); else tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); + + /* + * Reset to make sure next tick stop doesn't get fooled by past + * cached clock deadline. + */ + ts->next_tick = 0; } static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, @@ -701,8 +713,6 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, */ delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { - tick = 0; - /* * Tell the timer code that the base is not idle, i.e. undo * the effect of get_next_timer_interrupt(): @@ -712,23 +722,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. */ - if (!ts->tick_stopped) - goto out; - - /* - * If, OTOH, we did stop it, but there's a pending (expired) - * timer reprogram the timer hardware to fire now. - * - * We will not restart the tick proper, just prod the timer - * hardware into firing an interrupt to process the pending - * timers. Just like tick_irq_exit() will not restart the tick - * for 'normal' interrupts. - * - * Only once we exit the idle loop will we re-enable the tick, - * see tick_nohz_idle_exit(). - */ - if (delta == 0) { - tick_nohz_restart(ts, now); + if (!ts->tick_stopped) { + tick = 0; goto out; } } @@ -771,8 +766,16 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, tick = expires; /* Skip reprogram of event if its not changed */ - if (ts->tick_stopped && (expires == dev->next_event)) - goto out; + if (ts->tick_stopped && (expires == ts->next_tick)) { + /* Sanity check: make sure clockevent is actually programmed */ + if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) + goto out; + + WARN_ON_ONCE(1); + printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n", + basemono, ts->next_tick, dev->next_event, + hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer)); + } /* * nohz_stop_sched_tick can be called several times before @@ -782,8 +785,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, * the scheduler tick in nohz_restart_sched_tick. */ if (!ts->tick_stopped) { - nohz_balance_enter_idle(cpu); - calc_load_enter_idle(); + calc_load_nohz_start(); cpu_load_update_nohz_start(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); @@ -791,6 +793,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, trace_tick_stop(1, TICK_DEP_MASK_NONE); } + ts->next_tick = tick; + /* * If the expiration time == KTIME_MAX, then we simply stop * the tick timer. @@ -801,12 +805,17 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, goto out; } + hrtimer_set_expires(&ts->sched_timer, tick); + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) - hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED); + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); else tick_program_event(tick, 1); out: - /* Update the estimated sleep length */ + /* + * Update the estimated sleep length until the next timer + * (not only the tick). + */ ts->sleep_length = ktime_sub(dev->next_event, now); return tick; } @@ -823,7 +832,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) */ timer_clear_idle(); - calc_load_exit_idle(); + calc_load_nohz_stop(); touch_softlockup_watchdog_sched(); /* * Cancel the scheduled timer and restore the tick @@ -864,6 +873,11 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (unlikely(!cpu_online(cpu))) { if (cpu == tick_do_timer_cpu) tick_do_timer_cpu = TICK_DO_TIMER_NONE; + /* + * Make sure the CPU doesn't get fooled by obsolete tick + * deadline if it comes back online later. + */ + ts->next_tick = 0; return false; } @@ -923,8 +937,10 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts) ts->idle_expires = expires; } - if (!was_stopped && ts->tick_stopped) + if (!was_stopped && ts->tick_stopped) { ts->idle_jiffies = ts->last_jiffies; + nohz_balance_enter_idle(cpu); + } } } @@ -1172,6 +1188,8 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) */ if (regs) tick_sched_handle(ts, regs); + else + ts->next_tick = 0; /* No need to reprogram if we are in idle or full dynticks mode */ if (unlikely(ts->tick_stopped)) diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index bf38226e5c17..075444e3d48e 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -27,6 +27,7 @@ enum tick_nohz_mode { * timer is modified for nohz sleeps. This is necessary * to resume the tick timer operation in the timeline * when the CPU returns from nohz sleep. + * @next_tick: Next tick to be fired when in dynticks mode. * @tick_stopped: Indicator that the idle tick has been stopped * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_calls: Total number of idle calls @@ -44,6 +45,7 @@ struct tick_sched { unsigned long check_clocks; enum tick_nohz_mode nohz_mode; ktime_t last_tick; + ktime_t next_tick; int inidle; int tick_stopped; unsigned long idle_jiffies; diff --git a/kernel/time/time.c b/kernel/time/time.c index 49c73c6ed648..44a8c1402133 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -39,6 +39,7 @@ #include <linux/ptrace.h> #include <linux/uaccess.h> +#include <linux/compat.h> #include <asm/unistd.h> #include <generated/timeconst.h> @@ -99,6 +100,47 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr) #endif /* __ARCH_WANT_SYS_TIME */ +#ifdef CONFIG_COMPAT +#ifdef __ARCH_WANT_COMPAT_SYS_TIME + +/* compat_time_t is a 32 bit "long" and needs to get converted. */ +COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) +{ + struct timeval tv; + compat_time_t i; + + do_gettimeofday(&tv); + i = tv.tv_sec; + + if (tloc) { + if (put_user(i,tloc)) + return -EFAULT; + } + force_successful_syscall_return(); + return i; +} + +COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr) +{ + struct timespec tv; + int err; + + if (get_user(tv.tv_sec, tptr)) + return -EFAULT; + + tv.tv_nsec = 0; + + err = security_settime(&tv, NULL); + if (err) + return err; + + do_settimeofday(&tv); + return 0; +} + +#endif /* __ARCH_WANT_COMPAT_SYS_TIME */ +#endif + SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv, struct timezone __user *, tz) { @@ -215,6 +257,47 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv, return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv, + struct timezone __user *, tz) +{ + if (tv) { + struct timeval ktv; + + do_gettimeofday(&ktv); + if (compat_put_timeval(&ktv, tv)) + return -EFAULT; + } + if (tz) { + if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) + return -EFAULT; + } + + return 0; +} + +COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv, + struct timezone __user *, tz) +{ + struct timespec64 new_ts; + struct timeval user_tv; + struct timezone new_tz; + + if (tv) { + if (compat_get_timeval(&user_tv, tv)) + return -EFAULT; + new_ts.tv_sec = user_tv.tv_sec; + new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC; + } + if (tz) { + if (copy_from_user(&new_tz, tz, sizeof(*tz))) + return -EFAULT; + } + + return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); +} +#endif + SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p) { struct timex txc; /* Local copy of parameter */ @@ -224,12 +307,33 @@ SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p) * structure. But bear in mind that the structures * may change */ - if(copy_from_user(&txc, txc_p, sizeof(struct timex))) + if (copy_from_user(&txc, txc_p, sizeof(struct timex))) return -EFAULT; ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret; } +#ifdef CONFIG_COMPAT + +COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp) +{ + struct timex txc; + int err, ret; + + err = compat_get_timex(&txc, utp); + if (err) + return err; + + ret = do_adjtimex(&txc); + + err = compat_put_timex(utp, &txc); + if (err) + return err; + + return ret; +} +#endif + /* * Convert jiffies to milliseconds and back. * @@ -786,3 +890,61 @@ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, return res; } + +int get_timespec64(struct timespec64 *ts, + const struct timespec __user *uts) +{ + struct timespec kts; + int ret; + + ret = copy_from_user(&kts, uts, sizeof(kts)); + if (ret) + return -EFAULT; + + ts->tv_sec = kts.tv_sec; + ts->tv_nsec = kts.tv_nsec; + + return 0; +} +EXPORT_SYMBOL_GPL(get_timespec64); + +int put_timespec64(const struct timespec64 *ts, + struct timespec __user *uts) +{ + struct timespec kts = { + .tv_sec = ts->tv_sec, + .tv_nsec = ts->tv_nsec + }; + return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0; +} +EXPORT_SYMBOL_GPL(put_timespec64); + +int get_itimerspec64(struct itimerspec64 *it, + const struct itimerspec __user *uit) +{ + int ret; + + ret = get_timespec64(&it->it_interval, &uit->it_interval); + if (ret) + return ret; + + ret = get_timespec64(&it->it_value, &uit->it_value); + + return ret; +} +EXPORT_SYMBOL_GPL(get_itimerspec64); + +int put_itimerspec64(const struct itimerspec64 *it, + struct itimerspec __user *uit) +{ + int ret; + + ret = put_timespec64(&it->it_interval, &uit->it_interval); + if (ret) + return ret; + + ret = put_timespec64(&it->it_value, &uit->it_value); + + return ret; +} +EXPORT_SYMBOL_GPL(put_itimerspec64); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 9652bc57fd09..cedafa008de5 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -72,6 +72,10 @@ static inline void tk_normalize_xtime(struct timekeeper *tk) tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } + while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { + tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; + tk->raw_sec++; + } } static inline struct timespec64 tk_xtime(struct timekeeper *tk) @@ -118,6 +122,26 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) tk->offs_boot = ktime_add(tk->offs_boot, delta); } +/* + * tk_clock_read - atomic clocksource read() helper + * + * This helper is necessary to use in the read paths because, while the + * seqlock ensures we don't return a bad value while structures are updated, + * it doesn't protect from potential crashes. There is the possibility that + * the tkr's clocksource may change between the read reference, and the + * clock reference passed to the read function. This can cause crashes if + * the wrong clocksource is passed to the wrong read function. + * This isn't necessary to use when holding the timekeeper_lock or doing + * a read of the fast-timekeeper tkrs (which is protected by its own locking + * and update logic). + */ +static inline u64 tk_clock_read(struct tk_read_base *tkr) +{ + struct clocksource *clock = READ_ONCE(tkr->clock); + + return clock->read(clock); +} + #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ @@ -175,7 +199,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) */ do { seq = read_seqcount_begin(&tk_core.seq); - now = tkr->read(tkr->clock); + now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; @@ -209,7 +233,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) u64 cycle_now, delta; /* read clocksource */ - cycle_now = tkr->read(tkr->clock); + cycle_now = tk_clock_read(tkr); /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); @@ -238,12 +262,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; - tk->tkr_mono.read = clock->read; tk->tkr_mono.mask = clock->mask; - tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); + tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; - tk->tkr_raw.read = clock->read; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; @@ -262,17 +284,19 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; - tk->raw_interval = (interval * clock->mult) >> clock->shift; + tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; - if (shift_change < 0) + if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; - else + tk->tkr_raw.xtime_nsec >>= -shift_change; + } else { tk->tkr_mono.xtime_nsec <<= shift_change; + tk->tkr_raw.xtime_nsec <<= shift_change; + } } - tk->tkr_raw.xtime_nsec = 0; tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; @@ -404,7 +428,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) now += timekeeping_delta_to_ns(tkr, clocksource_delta( - tkr->read(tkr->clock), + tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_retry(&tkf->seq, seq)); @@ -461,6 +485,10 @@ static u64 dummy_clock_read(struct clocksource *cs) return cycles_at_suspend; } +static struct clocksource dummy_clock = { + .read = dummy_clock_read, +}; + /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. @@ -477,17 +505,18 @@ static void halt_fast_timekeeper(struct timekeeper *tk) struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - cycles_at_suspend = tkr->read(tkr->clock); - tkr_dummy.read = dummy_clock_read; + cycles_at_suspend = tk_clock_read(tkr); + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - tkr_dummy.read = dummy_clock_read; + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } #ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD +#warning Please contact your maintainers, as GENERIC_TIME_VSYSCALL_OLD compatibity will disappear soon. static inline void update_vsyscall(struct timekeeper *tk) { @@ -597,9 +626,6 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); - /* Update the monotonic raw base */ - tk->tkr_raw.base = timespec64_to_ktime(tk->raw_time); - /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take @@ -609,6 +635,11 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; + + /* Update the monotonic raw base */ + seconds = tk->raw_sec; + nsec = (u32)(tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift); + tk->tkr_raw.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); } /* must hold timekeeper_lock */ @@ -649,11 +680,9 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - struct clocksource *clock = tk->tkr_mono.clock; u64 cycle_now, delta; - u64 nsec; - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -663,10 +692,13 @@ static void timekeeping_forward_now(struct timekeeper *tk) /* If arch requires, add in get_arch_timeoffset() */ tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift; - tk_normalize_xtime(tk); - nsec = clocksource_cyc2ns(delta, tk->tkr_raw.mult, tk->tkr_raw.shift); - timespec64_add_ns(&tk->raw_time, nsec); + tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult; + + /* If arch requires, add in get_arch_timeoffset() */ + tk->tkr_raw.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_raw.shift; + + tk_normalize_xtime(tk); } /** @@ -929,8 +961,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) do { seq = read_seqcount_begin(&tk_core.seq); - - now = tk->tkr_mono.read(tk->tkr_mono.clock); + now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, @@ -1108,7 +1139,7 @@ int get_device_system_crosststamp(int (*get_time_fn) * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ - now = tk->tkr_mono.read(tk->tkr_mono.clock); + now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!cycle_between(interval_start, cycles, now)) { clock_was_set_seq = tk->clock_was_set_seq; @@ -1353,19 +1384,18 @@ int timekeeping_notify(struct clocksource *clock) void getrawmonotonic64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - struct timespec64 ts64; unsigned long seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); + ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); - ts64 = tk->raw_time; } while (read_seqcount_retry(&tk_core.seq, seq)); - timespec64_add_ns(&ts64, nsecs); - *ts = ts64; + ts->tv_nsec = 0; + timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(getrawmonotonic64); @@ -1489,8 +1519,7 @@ void __init timekeeping_init(void) tk_setup_internals(tk, clock); tk_set_xtime(tk, &now); - tk->raw_time.tv_sec = 0; - tk->raw_time.tv_nsec = 0; + tk->raw_sec = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) boot = tk_xtime(tk); @@ -1629,7 +1658,7 @@ void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && cycle_now > tk->tkr_mono.cycle_last) { u64 nsec, cyc_delta; @@ -1976,7 +2005,7 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; - u64 raw_nsecs; + u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) @@ -1991,14 +2020,12 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ - raw_nsecs = (u64)tk->raw_interval << shift; - raw_nsecs += tk->raw_time.tv_nsec; - if (raw_nsecs >= NSEC_PER_SEC) { - u64 raw_secs = raw_nsecs; - raw_nsecs = do_div(raw_secs, NSEC_PER_SEC); - tk->raw_time.tv_sec += raw_secs; + tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; + snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; + while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { + tk->tkr_raw.xtime_nsec -= snsec_per_sec; + tk->raw_sec++; } - tk->raw_time.tv_nsec = raw_nsecs; /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; @@ -2030,7 +2057,7 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock), + offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); #endif diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 152a706ef8b8..71ce3f4eead3 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -195,7 +195,7 @@ EXPORT_SYMBOL(jiffies_64); #endif struct timer_base { - spinlock_t lock; + raw_spinlock_t lock; struct timer_list *running_timer; unsigned long clk; unsigned long next_expiry; @@ -913,10 +913,10 @@ static struct timer_base *lock_timer_base(struct timer_list *timer, if (!(tf & TIMER_MIGRATING)) { base = get_timer_base(tf); - spin_lock_irqsave(&base->lock, *flags); + raw_spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; - spin_unlock_irqrestore(&base->lock, *flags); + raw_spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); } @@ -986,9 +986,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) /* See the comment in lock_timer_base() */ timer->flags |= TIMER_MIGRATING; - spin_unlock(&base->lock); + raw_spin_unlock(&base->lock); base = new_base; - spin_lock(&base->lock); + raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); } @@ -1013,7 +1013,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) } out_unlock: - spin_unlock_irqrestore(&base->lock, flags); + raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } @@ -1106,16 +1106,16 @@ void add_timer_on(struct timer_list *timer, int cpu) if (base != new_base) { timer->flags |= TIMER_MIGRATING; - spin_unlock(&base->lock); + raw_spin_unlock(&base->lock); base = new_base; - spin_lock(&base->lock); + raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } debug_activate(timer, timer->expires); internal_add_timer(base, timer); - spin_unlock_irqrestore(&base->lock, flags); + raw_spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); @@ -1141,7 +1141,7 @@ int del_timer(struct timer_list *timer) if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); - spin_unlock_irqrestore(&base->lock, flags); + raw_spin_unlock_irqrestore(&base->lock, flags); } return ret; @@ -1150,7 +1150,7 @@ EXPORT_SYMBOL(del_timer); /** * try_to_del_timer_sync - Try to deactivate a timer - * @timer: timer do del + * @timer: timer to delete * * This function tries to deactivate a timer. Upon successful (ret >= 0) * exit the timer is not queued and the handler is not running on any CPU. @@ -1168,7 +1168,7 @@ int try_to_del_timer_sync(struct timer_list *timer) if (base->running_timer != timer) ret = detach_if_pending(timer, base, true); - spin_unlock_irqrestore(&base->lock, flags); + raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } @@ -1299,13 +1299,13 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) data = timer->data; if (timer->flags & TIMER_IRQSAFE) { - spin_unlock(&base->lock); + raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, data); - spin_lock(&base->lock); + raw_spin_lock(&base->lock); } else { - spin_unlock_irq(&base->lock); + raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, data); - spin_lock_irq(&base->lock); + raw_spin_lock_irq(&base->lock); } } } @@ -1474,7 +1474,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) if (cpu_is_offline(smp_processor_id())) return expires; - spin_lock(&base->lock); + raw_spin_lock(&base->lock); nextevt = __next_timer_interrupt(base); is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA); base->next_expiry = nextevt; @@ -1502,7 +1502,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) if ((expires - basem) > TICK_NSEC) base->is_idle = true; } - spin_unlock(&base->lock); + raw_spin_unlock(&base->lock); return cmp_next_hrtimer_event(basem, expires); } @@ -1590,7 +1590,7 @@ static inline void __run_timers(struct timer_base *base) if (!time_after_eq(jiffies, base->clk)) return; - spin_lock_irq(&base->lock); + raw_spin_lock_irq(&base->lock); while (time_after_eq(jiffies, base->clk)) { @@ -1601,7 +1601,7 @@ static inline void __run_timers(struct timer_base *base) expire_timers(base, heads + levels); } base->running_timer = NULL; - spin_unlock_irq(&base->lock); + raw_spin_unlock_irq(&base->lock); } /* @@ -1786,16 +1786,16 @@ int timers_dead_cpu(unsigned int cpu) * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ - spin_lock_irq(&new_base->lock); - spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + raw_spin_lock_irq(&new_base->lock); + raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); BUG_ON(old_base->running_timer); for (i = 0; i < WHEEL_SIZE; i++) migrate_timer_list(new_base, old_base->vectors + i); - spin_unlock(&old_base->lock); - spin_unlock_irq(&new_base->lock); + raw_spin_unlock(&old_base->lock); + raw_spin_unlock_irq(&new_base->lock); put_cpu_ptr(&timer_bases); } return 0; @@ -1811,7 +1811,7 @@ static void __init init_timer_cpu(int cpu) for (i = 0; i < NR_BASES; i++) { base = per_cpu_ptr(&timer_bases[i], cpu); base->cpu = cpu; - spin_lock_init(&base->lock); + raw_spin_lock_init(&base->lock); base->clk = jiffies; } } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 193c5f5e3f79..bc364f86100a 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -867,7 +867,7 @@ static void blk_add_trace_split(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, - BLK_TA_SPLIT, bio->bi_error, sizeof(rpdu), + BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), &rpdu); } } @@ -900,7 +900,7 @@ static void blk_add_trace_bio_remap(void *ignore, r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_error, + bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, sizeof(r), &r); } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 460a031c77e5..37385193a608 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -122,8 +122,8 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) } /* - * limited trace_printk() - * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed + * Only limited trace_printk() conversion specifiers allowed: + * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s */ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) @@ -198,7 +198,8 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, i++; } - if (fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') + if (fmt[i] != 'i' && fmt[i] != 'd' && + fmt[i] != 'u' && fmt[i] != 'x') return -EINVAL; fmt_cnt++; } @@ -234,7 +235,8 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; - struct perf_event *event; + u64 value = 0; + int err; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; @@ -247,21 +249,14 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) if (!ee) return -ENOENT; - event = ee->event; - if (unlikely(event->attr.type != PERF_TYPE_HARDWARE && - event->attr.type != PERF_TYPE_RAW)) - return -EINVAL; - - /* make sure event is local and doesn't have pmu::count */ - if (unlikely(event->oncpu != cpu || event->pmu->count)) - return -EINVAL; - + err = perf_event_read_local(ee->event, &value); /* - * we don't know if the function is run successfully by the - * return value. It can be judged in other places, such as - * eBPF programs. + * this api is ugly since we miss [-22..-2] range of valid + * counter values, but that's uapi */ - return perf_event_read_local(event); + if (err) + return err; + return value; } static const struct bpf_func_proto bpf_perf_event_read_proto = { @@ -272,14 +267,16 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; +static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd); + static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, u64 flags, struct perf_raw_record *raw) { struct bpf_array *array = container_of(map, struct bpf_array, map); + struct perf_sample_data *sd = this_cpu_ptr(&bpf_sd); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; - struct perf_sample_data sample_data; struct bpf_event_entry *ee; struct perf_event *event; @@ -300,9 +297,9 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; - perf_sample_data_init(&sample_data, 0, 0); - sample_data.raw = raw; - perf_event_output(event, &sample_data, regs); + perf_sample_data_init(sd, 0, 0); + sd->raw = raw; + perf_event_output(event, sd, regs); return 0; } @@ -483,7 +480,7 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func /* bpf+kprobe programs can access fields of 'struct pt_regs' */ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct pt_regs)) return false; @@ -566,7 +563,7 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) } static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) return false; @@ -585,40 +582,47 @@ const struct bpf_verifier_ops tracepoint_prog_ops = { }; static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type) + struct bpf_insn_access_aux *info) { + const int size_sp = FIELD_SIZEOF(struct bpf_perf_event_data, + sample_period); + if (off < 0 || off >= sizeof(struct bpf_perf_event_data)) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; - if (off == offsetof(struct bpf_perf_event_data, sample_period)) { - if (size != sizeof(u64)) + + switch (off) { + case bpf_ctx_range(struct bpf_perf_event_data, sample_period): + bpf_ctx_record_field_size(info, size_sp); + if (!bpf_ctx_narrow_access_ok(off, size, size_sp)) return false; - } else { + break; + default: if (size != sizeof(long)) return false; } + return true; } static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, - struct bpf_prog *prog) + struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_perf_event_data, sample_period): - BUILD_BUG_ON(FIELD_SIZEOF(struct perf_sample_data, period) != sizeof(u64)); - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, data), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, - offsetof(struct perf_sample_data, period)); + bpf_target_off(struct perf_sample_data, period, 8, + target_size)); break; default: *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c129fca6ec99..b53c8d369163 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -707,20 +707,16 @@ static int create_trace_kprobe(int argc, char **argv) pr_info("Probe point is not specified.\n"); return -EINVAL; } - if (isdigit(argv[1][0])) { - /* an address specified */ - ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); - if (ret) { - pr_info("Failed to parse address.\n"); - return ret; - } - } else { + + /* try to parse an address. if that fails, try to read the + * input as a symbol. */ + if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) { /* a symbol specified */ symbol = argv[1]; /* TODO: support .init module functions */ ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret) { - pr_info("Failed to parse symbol.\n"); + pr_info("Failed to parse either an address or a symbol.\n"); return ret; } if (offset && is_return && diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c74bf39ef764..a86688fabc55 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2864,11 +2864,11 @@ bool flush_work(struct work_struct *work) EXPORT_SYMBOL_GPL(flush_work); struct cwt_wait { - wait_queue_t wait; + wait_queue_entry_t wait; struct work_struct *work; }; -static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); |