diff options
Diffstat (limited to 'kernel')
73 files changed, 3111 insertions, 2083 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 8d528f9930da..a8a91bd2b2a9 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -932,7 +932,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (!audit_enabled && msg_type != AUDIT_USER_AVC) return 0; - err = audit_filter_user(msg_type); + err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ err = 0; if (msg_type == AUDIT_USER_TTY) { @@ -1379,7 +1379,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, if (audit_initialized != AUDIT_INITIALIZED) return NULL; - if (unlikely(audit_filter_type(type))) + if (unlikely(!audit_filter(type, AUDIT_FILTER_TYPE))) return NULL; if (gfp_mask & __GFP_DIRECT_RECLAIM) { diff --git a/kernel/audit.h b/kernel/audit.h index a492f4c4e710..431444c3708b 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -331,6 +331,8 @@ extern pid_t audit_sig_pid; extern kuid_t audit_sig_uid; extern u32 audit_sig_sid; +extern int audit_filter(int msgtype, unsigned int listtype); + #ifdef CONFIG_AUDITSYSCALL extern int __audit_signal_info(int sig, struct task_struct *t); static inline int audit_signal_info(int sig, struct task_struct *t) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 94ca7b1e5e7e..85d9cac497e4 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1290,113 +1290,72 @@ int audit_compare_dname_path(const char *dname, const char *path, int parentlen) return strncmp(p, dname, dlen); } -static int audit_filter_user_rules(struct audit_krule *rule, int type, - enum audit_state *state) +int audit_filter(int msgtype, unsigned int listtype) { - int i; - - for (i = 0; i < rule->field_count; i++) { - struct audit_field *f = &rule->fields[i]; - pid_t pid; - int result = 0; - u32 sid; - - switch (f->type) { - case AUDIT_PID: - pid = task_pid_nr(current); - result = audit_comparator(pid, f->op, f->val); - break; - case AUDIT_UID: - result = audit_uid_comparator(current_uid(), f->op, f->uid); - break; - case AUDIT_GID: - result = audit_gid_comparator(current_gid(), f->op, f->gid); - break; - case AUDIT_LOGINUID: - result = audit_uid_comparator(audit_get_loginuid(current), - f->op, f->uid); - break; - case AUDIT_LOGINUID_SET: - result = audit_comparator(audit_loginuid_set(current), - f->op, f->val); - break; - case AUDIT_MSGTYPE: - result = audit_comparator(type, f->op, f->val); - break; - case AUDIT_SUBJ_USER: - case AUDIT_SUBJ_ROLE: - case AUDIT_SUBJ_TYPE: - case AUDIT_SUBJ_SEN: - case AUDIT_SUBJ_CLR: - if (f->lsm_rule) { - security_task_getsecid(current, &sid); - result = security_audit_rule_match(sid, - f->type, - f->op, - f->lsm_rule, - NULL); - } - break; - } - - if (!result) - return 0; - } - switch (rule->action) { - case AUDIT_NEVER: *state = AUDIT_DISABLED; break; - case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break; - } - return 1; -} - -int audit_filter_user(int type) -{ - enum audit_state state = AUDIT_DISABLED; struct audit_entry *e; - int rc, ret; - - ret = 1; /* Audit by default */ - - rcu_read_lock(); - list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_USER], list) { - rc = audit_filter_user_rules(&e->rule, type, &state); - if (rc) { - if (rc > 0 && state == AUDIT_DISABLED) - ret = 0; - break; - } - } - rcu_read_unlock(); - - return ret; -} - -int audit_filter_type(int type) -{ - struct audit_entry *e; - int result = 0; + int ret = 1; /* Audit by default */ rcu_read_lock(); - if (list_empty(&audit_filter_list[AUDIT_FILTER_TYPE])) + if (list_empty(&audit_filter_list[listtype])) goto unlock_and_return; + list_for_each_entry_rcu(e, &audit_filter_list[listtype], list) { + int i, result = 0; - list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TYPE], - list) { - int i; for (i = 0; i < e->rule.field_count; i++) { struct audit_field *f = &e->rule.fields[i]; - if (f->type == AUDIT_MSGTYPE) { - result = audit_comparator(type, f->op, f->val); - if (!result) - break; + pid_t pid; + u32 sid; + + switch (f->type) { + case AUDIT_PID: + pid = task_pid_nr(current); + result = audit_comparator(pid, f->op, f->val); + break; + case AUDIT_UID: + result = audit_uid_comparator(current_uid(), f->op, f->uid); + break; + case AUDIT_GID: + result = audit_gid_comparator(current_gid(), f->op, f->gid); + break; + case AUDIT_LOGINUID: + result = audit_uid_comparator(audit_get_loginuid(current), + f->op, f->uid); + break; + case AUDIT_LOGINUID_SET: + result = audit_comparator(audit_loginuid_set(current), + f->op, f->val); + break; + case AUDIT_MSGTYPE: + result = audit_comparator(msgtype, f->op, f->val); + break; + case AUDIT_SUBJ_USER: + case AUDIT_SUBJ_ROLE: + case AUDIT_SUBJ_TYPE: + case AUDIT_SUBJ_SEN: + case AUDIT_SUBJ_CLR: + if (f->lsm_rule) { + security_task_getsecid(current, &sid); + result = security_audit_rule_match(sid, + f->type, f->op, f->lsm_rule, NULL); + } + break; + default: + goto unlock_and_return; } + if (result < 0) /* error */ + goto unlock_and_return; + if (!result) + break; + } + if (result > 0) { + if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_TYPE) + ret = 0; + break; } - if (result) - goto unlock_and_return; } unlock_and_return: rcu_read_unlock(); - return result; + return ret; } static int update_lsm_rule(struct audit_krule *r) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 2672d105cffc..5abf1dc1f91c 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -72,6 +72,7 @@ #include <linux/compat.h> #include <linux/ctype.h> #include <linux/string.h> +#include <linux/uaccess.h> #include <uapi/linux/limits.h> #include "audit.h" @@ -81,7 +82,8 @@ #define AUDITSC_SUCCESS 1 #define AUDITSC_FAILURE 2 -/* no execve audit message should be longer than this (userspace limits) */ +/* no execve audit message should be longer than this (userspace limits), + * see the note near the top of audit_log_execve_info() about this value */ #define MAX_EXECVE_AUDIT_LEN 7500 /* max length to print of cmdline/proctitle value during audit */ @@ -694,8 +696,12 @@ static int audit_filter_rules(struct task_struct *tsk, ctx->prio = rule->prio; } switch (rule->action) { - case AUDIT_NEVER: *state = AUDIT_DISABLED; break; - case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break; + case AUDIT_NEVER: + *state = AUDIT_DISABLED; + break; + case AUDIT_ALWAYS: + *state = AUDIT_RECORD_CONTEXT; + break; } return 1; } @@ -987,184 +993,178 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid, return rc; } -/* - * to_send and len_sent accounting are very loose estimates. We aren't - * really worried about a hard cap to MAX_EXECVE_AUDIT_LEN so much as being - * within about 500 bytes (next page boundary) - * - * why snprintf? an int is up to 12 digits long. if we just assumed when - * logging that a[%d]= was going to be 16 characters long we would be wasting - * space in every audit message. In one 7500 byte message we can log up to - * about 1000 min size arguments. That comes down to about 50% waste of space - * if we didn't do the snprintf to find out how long arg_num_len was. - */ -static int audit_log_single_execve_arg(struct audit_context *context, - struct audit_buffer **ab, - int arg_num, - size_t *len_sent, - const char __user *p, - char *buf) +static void audit_log_execve_info(struct audit_context *context, + struct audit_buffer **ab) { - char arg_num_len_buf[12]; - const char __user *tmp_p = p; - /* how many digits are in arg_num? 5 is the length of ' a=""' */ - size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5; - size_t len, len_left, to_send; - size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN; - unsigned int i, has_cntl = 0, too_long = 0; - int ret; - - /* strnlen_user includes the null we don't want to send */ - len_left = len = strnlen_user(p, MAX_ARG_STRLEN) - 1; - - /* - * We just created this mm, if we can't find the strings - * we just copied into it something is _very_ wrong. Similar - * for strings that are too long, we should not have created - * any. - */ - if (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) { - send_sig(SIGKILL, current, 0); - return -1; + long len_max; + long len_rem; + long len_full; + long len_buf; + long len_abuf; + long len_tmp; + bool require_data; + bool encode; + unsigned int iter; + unsigned int arg; + char *buf_head; + char *buf; + const char __user *p = (const char __user *)current->mm->arg_start; + + /* NOTE: this buffer needs to be large enough to hold all the non-arg + * data we put in the audit record for this argument (see the + * code below) ... at this point in time 96 is plenty */ + char abuf[96]; + + /* NOTE: we set MAX_EXECVE_AUDIT_LEN to a rather arbitrary limit, the + * current value of 7500 is not as important as the fact that it + * is less than 8k, a setting of 7500 gives us plenty of wiggle + * room if we go over a little bit in the logging below */ + WARN_ON_ONCE(MAX_EXECVE_AUDIT_LEN > 7500); + len_max = MAX_EXECVE_AUDIT_LEN; + + /* scratch buffer to hold the userspace args */ + buf_head = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL); + if (!buf_head) { + audit_panic("out of memory for argv string"); + return; } + buf = buf_head; - /* walk the whole argument looking for non-ascii chars */ + audit_log_format(*ab, "argc=%d", context->execve.argc); + + len_rem = len_max; + len_buf = 0; + len_full = 0; + require_data = true; + encode = false; + iter = 0; + arg = 0; do { - if (len_left > MAX_EXECVE_AUDIT_LEN) - to_send = MAX_EXECVE_AUDIT_LEN; - else - to_send = len_left; - ret = copy_from_user(buf, tmp_p, to_send); - /* - * There is no reason for this copy to be short. We just - * copied them here, and the mm hasn't been exposed to user- - * space yet. - */ - if (ret) { - WARN_ON(1); - send_sig(SIGKILL, current, 0); - return -1; - } - buf[to_send] = '\0'; - has_cntl = audit_string_contains_control(buf, to_send); - if (has_cntl) { - /* - * hex messages get logged as 2 bytes, so we can only - * send half as much in each message - */ - max_execve_audit_len = MAX_EXECVE_AUDIT_LEN / 2; - break; - } - len_left -= to_send; - tmp_p += to_send; - } while (len_left > 0); - - len_left = len; - - if (len > max_execve_audit_len) - too_long = 1; - - /* rewalk the argument actually logging the message */ - for (i = 0; len_left > 0; i++) { - int room_left; - - if (len_left > max_execve_audit_len) - to_send = max_execve_audit_len; - else - to_send = len_left; - - /* do we have space left to send this argument in this ab? */ - room_left = MAX_EXECVE_AUDIT_LEN - arg_num_len - *len_sent; - if (has_cntl) - room_left -= (to_send * 2); - else - room_left -= to_send; - if (room_left < 0) { - *len_sent = 0; - audit_log_end(*ab); - *ab = audit_log_start(context, GFP_KERNEL, AUDIT_EXECVE); - if (!*ab) - return 0; - } + /* NOTE: we don't ever want to trust this value for anything + * serious, but the audit record format insists we + * provide an argument length for really long arguments, + * e.g. > MAX_EXECVE_AUDIT_LEN, so we have no choice but + * to use strncpy_from_user() to obtain this value for + * recording in the log, although we don't use it + * anywhere here to avoid a double-fetch problem */ + if (len_full == 0) + len_full = strnlen_user(p, MAX_ARG_STRLEN) - 1; + + /* read more data from userspace */ + if (require_data) { + /* can we make more room in the buffer? */ + if (buf != buf_head) { + memmove(buf_head, buf, len_buf); + buf = buf_head; + } + + /* fetch as much as we can of the argument */ + len_tmp = strncpy_from_user(&buf_head[len_buf], p, + len_max - len_buf); + if (len_tmp == -EFAULT) { + /* unable to copy from userspace */ + send_sig(SIGKILL, current, 0); + goto out; + } else if (len_tmp == (len_max - len_buf)) { + /* buffer is not large enough */ + require_data = true; + /* NOTE: if we are going to span multiple + * buffers force the encoding so we stand + * a chance at a sane len_full value and + * consistent record encoding */ + encode = true; + len_full = len_full * 2; + p += len_tmp; + } else { + require_data = false; + if (!encode) + encode = audit_string_contains_control( + buf, len_tmp); + /* try to use a trusted value for len_full */ + if (len_full < len_max) + len_full = (encode ? + len_tmp * 2 : len_tmp); + p += len_tmp + 1; + } + len_buf += len_tmp; + buf_head[len_buf] = '\0'; - /* - * first record needs to say how long the original string was - * so we can be sure nothing was lost. - */ - if ((i == 0) && (too_long)) - audit_log_format(*ab, " a%d_len=%zu", arg_num, - has_cntl ? 2*len : len); - - /* - * normally arguments are small enough to fit and we already - * filled buf above when we checked for control characters - * so don't bother with another copy_from_user - */ - if (len >= max_execve_audit_len) - ret = copy_from_user(buf, p, to_send); - else - ret = 0; - if (ret) { - WARN_ON(1); - send_sig(SIGKILL, current, 0); - return -1; + /* length of the buffer in the audit record? */ + len_abuf = (encode ? len_buf * 2 : len_buf + 2); } - buf[to_send] = '\0'; - - /* actually log it */ - audit_log_format(*ab, " a%d", arg_num); - if (too_long) - audit_log_format(*ab, "[%d]", i); - audit_log_format(*ab, "="); - if (has_cntl) - audit_log_n_hex(*ab, buf, to_send); - else - audit_log_string(*ab, buf); - - p += to_send; - len_left -= to_send; - *len_sent += arg_num_len; - if (has_cntl) - *len_sent += to_send * 2; - else - *len_sent += to_send; - } - /* include the null we didn't log */ - return len + 1; -} -static void audit_log_execve_info(struct audit_context *context, - struct audit_buffer **ab) -{ - int i, len; - size_t len_sent = 0; - const char __user *p; - char *buf; + /* write as much as we can to the audit log */ + if (len_buf > 0) { + /* NOTE: some magic numbers here - basically if we + * can't fit a reasonable amount of data into the + * existing audit buffer, flush it and start with + * a new buffer */ + if ((sizeof(abuf) + 8) > len_rem) { + len_rem = len_max; + audit_log_end(*ab); + *ab = audit_log_start(context, + GFP_KERNEL, AUDIT_EXECVE); + if (!*ab) + goto out; + } - p = (const char __user *)current->mm->arg_start; + /* create the non-arg portion of the arg record */ + len_tmp = 0; + if (require_data || (iter > 0) || + ((len_abuf + sizeof(abuf)) > len_rem)) { + if (iter == 0) { + len_tmp += snprintf(&abuf[len_tmp], + sizeof(abuf) - len_tmp, + " a%d_len=%lu", + arg, len_full); + } + len_tmp += snprintf(&abuf[len_tmp], + sizeof(abuf) - len_tmp, + " a%d[%d]=", arg, iter++); + } else + len_tmp += snprintf(&abuf[len_tmp], + sizeof(abuf) - len_tmp, + " a%d=", arg); + WARN_ON(len_tmp >= sizeof(abuf)); + abuf[sizeof(abuf) - 1] = '\0'; + + /* log the arg in the audit record */ + audit_log_format(*ab, "%s", abuf); + len_rem -= len_tmp; + len_tmp = len_buf; + if (encode) { + if (len_abuf > len_rem) + len_tmp = len_rem / 2; /* encoding */ + audit_log_n_hex(*ab, buf, len_tmp); + len_rem -= len_tmp * 2; + len_abuf -= len_tmp * 2; + } else { + if (len_abuf > len_rem) + len_tmp = len_rem - 2; /* quotes */ + audit_log_n_string(*ab, buf, len_tmp); + len_rem -= len_tmp + 2; + /* don't subtract the "2" because we still need + * to add quotes to the remaining string */ + len_abuf -= len_tmp; + } + len_buf -= len_tmp; + buf += len_tmp; + } - audit_log_format(*ab, "argc=%d", context->execve.argc); + /* ready to move to the next argument? */ + if ((len_buf == 0) && !require_data) { + arg++; + iter = 0; + len_full = 0; + require_data = true; + encode = false; + } + } while (arg < context->execve.argc); - /* - * we need some kernel buffer to hold the userspace args. Just - * allocate one big one rather than allocating one of the right size - * for every single argument inside audit_log_single_execve_arg() - * should be <8k allocation so should be pretty safe. - */ - buf = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL); - if (!buf) { - audit_panic("out of memory for argv string"); - return; - } + /* NOTE: the caller handles the final audit_log_end() call */ - for (i = 0; i < context->execve.argc; i++) { - len = audit_log_single_execve_arg(context, ab, i, - &len_sent, p, buf); - if (len <= 0) - break; - p += len; - } - kfree(buf); +out: + kfree(buf_head); } static void show_special(struct audit_context *context, int *call_panic) @@ -1425,7 +1425,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts if (context->pwd.dentry && context->pwd.mnt) { ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD); if (ab) { - audit_log_d_path(ab, " cwd=", &context->pwd); + audit_log_d_path(ab, "cwd=", &context->pwd); audit_log_end(ab); } } diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 76d5a794e426..633a650d7aeb 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -328,8 +328,8 @@ static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) } /* only called from syscall */ -static int fd_array_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, + void *key, void *value, u64 map_flags) { struct bpf_array *array = container_of(map, struct bpf_array, map); void *new_ptr, *old_ptr; @@ -342,7 +342,7 @@ static int fd_array_map_update_elem(struct bpf_map *map, void *key, return -E2BIG; ufd = *(u32 *)value; - new_ptr = map->ops->map_fd_get_ptr(map, ufd); + new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd); if (IS_ERR(new_ptr)) return PTR_ERR(new_ptr); @@ -371,10 +371,12 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key) } } -static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd) +static void *prog_fd_array_get_ptr(struct bpf_map *map, + struct file *map_file, int fd) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog = bpf_prog_get(fd); + if (IS_ERR(prog)) return prog; @@ -382,14 +384,13 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd) bpf_prog_put(prog); return ERR_PTR(-EINVAL); } + return prog; } static void prog_fd_array_put_ptr(void *ptr) { - struct bpf_prog *prog = ptr; - - bpf_prog_put_rcu(prog); + bpf_prog_put(ptr); } /* decrement refcnt of all bpf_progs that are stored in this map */ @@ -407,7 +408,6 @@ static const struct bpf_map_ops prog_array_ops = { .map_free = fd_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, - .map_update_elem = fd_array_map_update_elem, .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, @@ -425,59 +425,105 @@ static int __init register_prog_array_map(void) } late_initcall(register_prog_array_map); -static void perf_event_array_map_free(struct bpf_map *map) +static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, + struct file *map_file) { - bpf_fd_array_map_clear(map); - fd_array_map_free(map); + struct bpf_event_entry *ee; + + ee = kzalloc(sizeof(*ee), GFP_ATOMIC); + if (ee) { + ee->event = perf_file->private_data; + ee->perf_file = perf_file; + ee->map_file = map_file; + } + + return ee; } -static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) +static void __bpf_event_entry_free(struct rcu_head *rcu) { - struct perf_event *event; - const struct perf_event_attr *attr; - struct file *file; + struct bpf_event_entry *ee; - file = perf_event_get(fd); - if (IS_ERR(file)) - return file; + ee = container_of(rcu, struct bpf_event_entry, rcu); + fput(ee->perf_file); + kfree(ee); +} - event = file->private_data; +static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee) +{ + call_rcu(&ee->rcu, __bpf_event_entry_free); +} - attr = perf_event_attrs(event); - if (IS_ERR(attr)) - goto err; +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; - if (attr->inherit) - goto err; + perf_file = perf_event_get(fd); + if (IS_ERR(perf_file)) + return perf_file; - if (attr->type == PERF_TYPE_RAW) - return file; + event = perf_file->private_data; + ee = ERR_PTR(-EINVAL); - if (attr->type == PERF_TYPE_HARDWARE) - return file; + attr = perf_event_attrs(event); + if (IS_ERR(attr) || attr->inherit) + 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; + } - if (attr->type == PERF_TYPE_SOFTWARE && - attr->config == PERF_COUNT_SW_BPF_OUTPUT) - return file; -err: - fput(file); - return ERR_PTR(-EINVAL); +err_out: + fput(perf_file); + return ee; } static void perf_event_fd_array_put_ptr(void *ptr) { - fput((struct file *)ptr); + bpf_event_entry_free_rcu(ptr); +} + +static void perf_event_fd_array_release(struct bpf_map *map, + struct file *map_file) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct bpf_event_entry *ee; + int i; + + rcu_read_lock(); + for (i = 0; i < array->map.max_entries; i++) { + ee = READ_ONCE(array->ptrs[i]); + if (ee && ee->map_file == map_file) + fd_array_map_delete_elem(map, &i); + } + rcu_read_unlock(); } static const struct bpf_map_ops perf_event_array_ops = { .map_alloc = fd_array_map_alloc, - .map_free = perf_event_array_map_free, + .map_free = fd_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, - .map_update_elem = fd_array_map_update_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = perf_event_fd_array_get_ptr, .map_fd_put_ptr = perf_event_fd_array_put_ptr, + .map_release = perf_event_fd_array_release, }; static struct bpf_map_type_list perf_event_array_type __read_mostly = { @@ -491,3 +537,46 @@ static int __init register_perf_event_array_map(void) return 0; } late_initcall(register_perf_event_array_map); + +#ifdef CONFIG_SOCK_CGROUP_DATA +static void *cgroup_fd_array_get_ptr(struct bpf_map *map, + struct file *map_file /* not used */, + int fd) +{ + return cgroup_get_from_fd(fd); +} + +static void cgroup_fd_array_put_ptr(void *ptr) +{ + /* cgroup_put free cgrp after a rcu grace period */ + cgroup_put(ptr); +} + +static void cgroup_fd_array_free(struct bpf_map *map) +{ + bpf_fd_array_map_clear(map); + fd_array_map_free(map); +} + +static const struct bpf_map_ops cgroup_array_ops = { + .map_alloc = fd_array_map_alloc, + .map_free = cgroup_fd_array_free, + .map_get_next_key = array_map_get_next_key, + .map_lookup_elem = fd_array_map_lookup_elem, + .map_delete_elem = fd_array_map_delete_elem, + .map_fd_get_ptr = cgroup_fd_array_get_ptr, + .map_fd_put_ptr = cgroup_fd_array_put_ptr, +}; + +static struct bpf_map_type_list cgroup_array_type __read_mostly = { + .ops = &cgroup_array_ops, + .type = BPF_MAP_TYPE_CGROUP_ARRAY, +}; + +static int __init register_cgroup_array_map(void) +{ + bpf_register_map_type(&cgroup_array_type); + return 0; +} +late_initcall(register_cgroup_array_map); +#endif diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b94a36550591..03fd23d4d587 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -719,14 +719,13 @@ select_insn: if (unlikely(index >= array->map.max_entries)) goto out; - if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; prog = READ_ONCE(array->ptrs[index]); - if (unlikely(!prog)) + if (!prog) goto out; /* ARG1 at this point is guaranteed to point to CTX from @@ -1055,9 +1054,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) return NULL; } -const struct bpf_func_proto * __weak bpf_get_event_output_proto(void) +u64 __weak +bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, + void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { - return NULL; + return -ENOTSUPP; } /* Always built-in helper functions. */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index ad7a0573f71b..1ea3afba1a4f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -101,7 +101,7 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto = { static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { - return raw_smp_processor_id(); + return smp_processor_id(); } const struct bpf_func_proto bpf_get_smp_processor_id_proto = { diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 318858edb1cd..5967b870a895 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -11,7 +11,7 @@ * version 2 as published by the Free Software Foundation. */ -#include <linux/module.h> +#include <linux/init.h> #include <linux/magic.h> #include <linux/major.h> #include <linux/mount.h> @@ -367,8 +367,6 @@ static struct file_system_type bpf_fs_type = { .kill_sb = kill_litter_super, }; -MODULE_ALIAS_FS("bpf"); - static int __init bpf_init(void) { int ret; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 46ecce4b79ed..228f962447a5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -124,7 +124,12 @@ void bpf_map_put_with_uref(struct bpf_map *map) static int bpf_map_release(struct inode *inode, struct file *filp) { - bpf_map_put_with_uref(filp->private_data); + struct bpf_map *map = filp->private_data; + + if (map->ops->map_release) + map->ops->map_release(map, filp); + + bpf_map_put_with_uref(map); return 0; } @@ -387,6 +392,13 @@ static int map_update_elem(union bpf_attr *attr) err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || + map->map_type == BPF_MAP_TYPE_PROG_ARRAY || + map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY) { + rcu_read_lock(); + err = bpf_fd_array_map_update_elem(map, f.file, key, value, + attr->flags); + rcu_read_unlock(); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); @@ -612,7 +624,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) free_uid(user); } -static void __prog_put_common(struct rcu_head *rcu) +static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); @@ -621,17 +633,10 @@ static void __prog_put_common(struct rcu_head *rcu) bpf_prog_free(aux->prog); } -/* version of bpf_prog_put() that is called after a grace period */ -void bpf_prog_put_rcu(struct bpf_prog *prog) -{ - if (atomic_dec_and_test(&prog->aux->refcnt)) - call_rcu(&prog->aux->rcu, __prog_put_common); -} - void bpf_prog_put(struct bpf_prog *prog) { if (atomic_dec_and_test(&prog->aux->refcnt)) - __prog_put_common(&prog->aux->rcu); + call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } EXPORT_SYMBOL_GPL(bpf_prog_put); @@ -639,7 +644,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) { struct bpf_prog *prog = filp->private_data; - bpf_prog_put_rcu(prog); + bpf_prog_put(prog); return 0; } @@ -653,7 +658,7 @@ int bpf_prog_new_fd(struct bpf_prog *prog) O_RDWR | O_CLOEXEC); } -static struct bpf_prog *__bpf_prog_get(struct fd f) +static struct bpf_prog *____bpf_prog_get(struct fd f) { if (!f.file) return ERR_PTR(-EBADF); @@ -665,33 +670,50 @@ static struct bpf_prog *__bpf_prog_get(struct fd f) return f.file->private_data; } -struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) { - if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) { - atomic_dec(&prog->aux->refcnt); + if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) { + atomic_sub(i, &prog->aux->refcnt); return ERR_PTR(-EBUSY); } return prog; } +EXPORT_SYMBOL_GPL(bpf_prog_add); -/* called by sockets/tracing/seccomp before attaching program to an event - * pairs with bpf_prog_put() - */ -struct bpf_prog *bpf_prog_get(u32 ufd) +struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +{ + return bpf_prog_add(prog, 1); +} + +static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) { struct fd f = fdget(ufd); struct bpf_prog *prog; - prog = __bpf_prog_get(f); + prog = ____bpf_prog_get(f); if (IS_ERR(prog)) return prog; + if (type && prog->type != *type) { + prog = ERR_PTR(-EINVAL); + goto out; + } prog = bpf_prog_inc(prog); +out: fdput(f); - return prog; } -EXPORT_SYMBOL_GPL(bpf_prog_get); + +struct bpf_prog *bpf_prog_get(u32 ufd) +{ + return __bpf_prog_get(ufd, NULL); +} + +struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) +{ + return __bpf_prog_get(ufd, &type); +} +EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD kern_version diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eec9f90ba030..f72f23b8fdab 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -653,6 +653,16 @@ static int check_map_access(struct verifier_env *env, u32 regno, int off, #define MAX_PACKET_OFF 0xffff +static bool may_write_pkt_data(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_XDP: + return true; + default: + return false; + } +} + static int check_packet_access(struct verifier_env *env, u32 regno, int off, int size) { @@ -713,6 +723,7 @@ static int check_ptr_alignment(struct verifier_env *env, struct reg_state *reg, switch (env->prog->type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_XDP: break; default: verbose("verifier is misconfigured\n"); @@ -805,10 +816,15 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, err = check_stack_read(state, off, size, value_regno); } } else if (state->regs[regno].type == PTR_TO_PACKET) { - if (t == BPF_WRITE) { + if (t == BPF_WRITE && !may_write_pkt_data(env->prog->type)) { verbose("cannot write into packet\n"); return -EACCES; } + if (t == BPF_WRITE && value_regno >= 0 && + is_pointer_value(env, value_regno)) { + verbose("R%d leaks addr into packet\n", value_regno); + return -EACCES; + } err = check_packet_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown_value(state->regs, value_regno); @@ -1035,6 +1051,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (func_id != BPF_FUNC_get_stackid) goto error; break; + case BPF_MAP_TYPE_CGROUP_ARRAY: + if (func_id != BPF_FUNC_skb_in_cgroup) + goto error; + break; default: break; } @@ -1054,6 +1074,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; + case BPF_FUNC_skb_in_cgroup: + if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) + goto error; + break; default: break; } diff --git a/kernel/capability.c b/kernel/capability.c index 45432b54d5c6..00411c82dac5 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -361,6 +361,24 @@ bool has_capability_noaudit(struct task_struct *t, int cap) return has_ns_capability_noaudit(t, &init_user_ns, cap); } +static bool ns_capable_common(struct user_namespace *ns, int cap, bool audit) +{ + int capable; + + if (unlikely(!cap_valid(cap))) { + pr_crit("capable() called with invalid cap=%u\n", cap); + BUG(); + } + + capable = audit ? security_capable(current_cred(), ns, cap) : + security_capable_noaudit(current_cred(), ns, cap); + if (capable == 0) { + current->flags |= PF_SUPERPRIV; + return true; + } + return false; +} + /** * ns_capable - Determine if the current task has a superior capability in effect * @ns: The usernamespace we want the capability in @@ -374,19 +392,27 @@ bool has_capability_noaudit(struct task_struct *t, int cap) */ bool ns_capable(struct user_namespace *ns, int cap) { - if (unlikely(!cap_valid(cap))) { - pr_crit("capable() called with invalid cap=%u\n", cap); - BUG(); - } - - if (security_capable(current_cred(), ns, cap) == 0) { - current->flags |= PF_SUPERPRIV; - return true; - } - return false; + return ns_capable_common(ns, cap, true); } EXPORT_SYMBOL(ns_capable); +/** + * ns_capable_noaudit - Determine if the current task has a superior capability + * (unaudited) in effect + * @ns: The usernamespace we want the capability in + * @cap: The capability to be tested for + * + * Return true if the current task has the given superior capability currently + * available for use, false if not. + * + * This sets PF_SUPERPRIV on the task if the capability is available on the + * assumption that it's about to be used. + */ +bool ns_capable_noaudit(struct user_namespace *ns, int cap) +{ + return ns_capable_common(ns, cap, false); +} +EXPORT_SYMBOL(ns_capable_noaudit); /** * capable - Determine if the current task has a superior capability in effect diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 75c0ff00aca6..d1c51b7f5221 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -61,7 +61,7 @@ #include <linux/cpuset.h> #include <linux/proc_ns.h> #include <linux/nsproxy.h> -#include <linux/proc_ns.h> +#include <linux/file.h> #include <net/sock.h> /* @@ -1160,18 +1160,12 @@ static void cgroup_exit_root_id(struct cgroup_root *root) { lockdep_assert_held(&cgroup_mutex); - if (root->hierarchy_id) { - idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); - root->hierarchy_id = 0; - } + idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); } static void cgroup_free_root(struct cgroup_root *root) { if (root) { - /* hierarchy ID should already have been released */ - WARN_ON_ONCE(root->hierarchy_id); - idr_destroy(&root->cgroup_idr); kfree(root); } @@ -2215,12 +2209,8 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, goto out_unlock; } - /* - * We know this subsystem has not yet been bound. Users in a non-init - * user namespace may only mount hierarchies with no bound subsystems, - * i.e. 'none,name=user1' - */ - if (!opts.none && !capable(CAP_SYS_ADMIN)) { + /* Hierarchies may only be created in the initial cgroup namespace. */ + if (ns != &init_cgroup_ns) { ret = -EPERM; goto out_unlock; } @@ -2962,6 +2952,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) int retval = 0; mutex_lock(&cgroup_mutex); + percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; @@ -2976,6 +2967,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) if (retval) break; } + percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return retval; @@ -4343,6 +4335,8 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) mutex_lock(&cgroup_mutex); + percpu_down_write(&cgroup_threadgroup_rwsem); + /* all tasks in @from are being moved, all csets are source */ spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) @@ -4371,6 +4365,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) } while (task && !ret); out_err: cgroup_migrate_finish(&preloaded_csets); + percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return ret; } @@ -5146,6 +5141,8 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, lockdep_assert_held(&cgroup_mutex); css = ss->css_alloc(parent_css); + if (!css) + css = ERR_PTR(-ENOMEM); if (IS_ERR(css)) return css; @@ -6172,7 +6169,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) { WARN_ON_ONCE(!rcu_read_lock_held()); - return id > 0 ? idr_find(&ss->css_idr, id) : NULL; + return idr_find(&ss->css_idr, id); } /** @@ -6209,6 +6206,40 @@ struct cgroup *cgroup_get_from_path(const char *path) } EXPORT_SYMBOL_GPL(cgroup_get_from_path); +/** + * cgroup_get_from_fd - get a cgroup pointer from a fd + * @fd: fd obtained by open(cgroup2_dir) + * + * Find the cgroup from a fd which should be obtained + * by opening a cgroup directory. Returns a pointer to the + * cgroup on success. ERR_PTR is returned if the cgroup + * cannot be found. + */ +struct cgroup *cgroup_get_from_fd(int fd) +{ + struct cgroup_subsys_state *css; + struct cgroup *cgrp; + struct file *f; + + f = fget_raw(fd); + if (!f) + return ERR_PTR(-EBADF); + + css = css_tryget_online_from_dir(f->f_path.dentry, NULL); + fput(f); + if (IS_ERR(css)) + return ERR_CAST(css); + + cgrp = css->cgroup; + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + + return cgrp; +} +EXPORT_SYMBOL_GPL(cgroup_get_from_fd); + /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. @@ -6309,14 +6340,11 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - mutex_lock(&cgroup_mutex); + /* It is not safe to take cgroup_mutex here */ spin_lock_irq(&css_set_lock); - cset = task_css_set(current); get_css_set(cset); - spin_unlock_irq(&css_set_lock); - mutex_unlock(&cgroup_mutex); new_ns = alloc_cgroup_ns(); if (IS_ERR(new_ns)) { diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c index 303097b37429..2bd673783f1a 100644 --- a/kernel/cgroup_pids.c +++ b/kernel/cgroup_pids.c @@ -49,6 +49,12 @@ struct pids_cgroup { */ atomic64_t counter; int64_t limit; + + /* Handle for "pids.events" */ + struct cgroup_file events_file; + + /* Number of times fork failed because limit was hit. */ + atomic64_t events_limit; }; static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css) @@ -72,6 +78,7 @@ pids_css_alloc(struct cgroup_subsys_state *parent) pids->limit = PIDS_MAX; atomic64_set(&pids->counter, 0); + atomic64_set(&pids->events_limit, 0); return &pids->css; } @@ -213,10 +220,21 @@ static int pids_can_fork(struct task_struct *task) { struct cgroup_subsys_state *css; struct pids_cgroup *pids; + int err; css = task_css_check(current, pids_cgrp_id, true); pids = css_pids(css); - return pids_try_charge(pids, 1); + err = pids_try_charge(pids, 1); + if (err) { + /* Only log the first time events_limit is incremented. */ + if (atomic64_inc_return(&pids->events_limit) == 1) { + pr_info("cgroup: fork rejected by pids controller in "); + pr_cont_cgroup_path(task_cgroup(current, pids_cgrp_id)); + pr_cont("\n"); + } + cgroup_file_notify(&pids->events_file); + } + return err; } static void pids_cancel_fork(struct task_struct *task) @@ -288,6 +306,14 @@ static s64 pids_current_read(struct cgroup_subsys_state *css, return atomic64_read(&pids->counter); } +static int pids_events_show(struct seq_file *sf, void *v) +{ + struct pids_cgroup *pids = css_pids(seq_css(sf)); + + seq_printf(sf, "max %lld\n", (s64)atomic64_read(&pids->events_limit)); + return 0; +} + static struct cftype pids_files[] = { { .name = "max", @@ -300,6 +326,12 @@ static struct cftype pids_files[] = { .read_s64 = pids_current_read, .flags = CFTYPE_NOT_ON_ROOT, }, + { + .name = "events", + .seq_show = pids_events_show, + .file_offset = offsetof(struct pids_cgroup, events_file), + .flags = CFTYPE_NOT_ON_ROOT, + }, { } /* terminate */ }; diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config new file mode 100644 index 000000000000..9f748ed7bea8 --- /dev/null +++ b/kernel/configs/android-base.config @@ -0,0 +1,152 @@ +# KEEP ALPHABETICALLY SORTED +# CONFIG_DEVKMEM is not set +# CONFIG_DEVMEM is not set +# CONFIG_INET_LRO is not set +# CONFIG_MODULES is not set +# CONFIG_OABI_COMPAT is not set +# CONFIG_SYSVIPC is not set +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_ARMV8_DEPRECATED=y +CONFIG_ASHMEM=y +CONFIG_AUDIT=y +CONFIG_BLK_DEV_DM=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_CGROUPS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_SCHED=y +CONFIG_CP15_BARRIER_EMULATION=y +CONFIG_DM_CRYPT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_EMBEDDED=y +CONFIG_FB=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_INET=y +CONFIG_INET_DIAG_DESTROY=y +CONFIG_INET_ESP=y +CONFIG_INET_XFRM_MODE_TUNNEL=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IPV6=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_IPV6_PRIVACY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +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_NET=y +CONFIG_NETDEVICES=y +CONFIG_NETFILTER=y +CONFIG_NETFILTER_TPROXY=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NET_CLS_ACT=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_KEY=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_NAT=y +CONFIG_NO_HZ=y +CONFIG_PACKET=y +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +CONFIG_PREEMPT=y +CONFIG_QUOTA=y +CONFIG_RTC_CLASS=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SETEND_EMULATION=y +CONFIG_STAGING=y +CONFIG_SWP_EMULATION=y +CONFIG_SYNC=y +CONFIG_TUN=y +CONFIG_UNIX=y +CONFIG_USB_GADGET=y +CONFIG_USB_CONFIGFS=y +CONFIG_USB_CONFIGFS_F_FS=y +CONFIG_USB_CONFIGFS_F_MIDI=y +CONFIG_USB_OTG_WAKELOCK=y +CONFIG_XFRM_USER=y diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config new file mode 100644 index 000000000000..e3b953e966d2 --- /dev/null +++ b/kernel/configs/android-recommended.config @@ -0,0 +1,121 @@ +# KEEP ALPHABETICALLY SORTED +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_NF_CONNTRACK_SIP is not set +# CONFIG_PM_WAKELOCKS_GC is not set +# CONFIG_VT is not set +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_COMPACTION=y +CONFIG_DEBUG_RODATA=y +CONFIG_DM_UEVENT=y +CONFIG_DRAGONRISE_FF=y +CONFIG_ENABLE_DEFAULT_TRACERS=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_FUSE_FS=y +CONFIG_GREENASIA_FF=y +CONFIG_HIDRAW=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_EZKEY=y +CONFIG_HID_GREENASIA=y +CONFIG_HID_GYRATION=y +CONFIG_HID_HOLTEK=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_NTRIG=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_ROCCAT=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_HID_SONY=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_UCLOGIC=y +CONFIG_HID_WACOM=y +CONFIG_HID_WALTOP=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +CONFIG_INPUT_EVDEV=y +CONFIG_INPUT_GPIO=y +CONFIG_INPUT_JOYSTICK=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_TABLET=y +CONFIG_INPUT_UINPUT=y +CONFIG_ION=y +CONFIG_JOYSTICK_XPAD=y +CONFIG_JOYSTICK_XPAD_FF=y +CONFIG_JOYSTICK_XPAD_LEDS=y +CONFIG_KALLSYMS_ALL=y +CONFIG_KSM=y +CONFIG_LOGIG940_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGITECH_FF=y +CONFIG_MD=y +CONFIG_MEDIA_SUPPORT=y +CONFIG_MSDOS_FS=y +CONFIG_PANIC_TIMEOUT=5 +CONFIG_PANTHERLORD_FF=y +CONFIG_PERF_EVENTS=y +CONFIG_PM_DEBUG=y +CONFIG_PM_RUNTIME=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +CONFIG_POWER_SUPPLY=y +CONFIG_PSTORE=y +CONFIG_PSTORE_CONSOLE=y +CONFIG_PSTORE_RAM=y +CONFIG_SCHEDSTATS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_SND=y +CONFIG_SOUND=y +CONFIG_SUSPEND_TIME=y +CONFIG_TABLET_USB_ACECAD=y +CONFIG_TABLET_USB_AIPTEK=y +CONFIG_TABLET_USB_GTCO=y +CONFIG_TABLET_USB_HANWANG=y +CONFIG_TABLET_USB_KBTAB=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_TASK_XACCT=y +CONFIG_TIMER_STATS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_UHID=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_HIDDEV=y +CONFIG_USB_USBNET=y +CONFIG_VFAT_FS=y diff --git a/kernel/cpu.c b/kernel/cpu.c index 7b61887f7ccd..341bf80f80bd 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -517,6 +517,13 @@ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, if (!cpu_online(cpu)) return 0; + /* + * If we are up and running, use the hotplug thread. For early calls + * we invoke the thread function directly. + */ + if (!st->thread) + return cpuhp_invoke_callback(cpu, state, cb); + st->cb_state = state; st->cb = cb; /* @@ -1173,6 +1180,31 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown = NULL, .cant_stop = true, }, + [CPUHP_PERF_PREPARE] = { + .name = "perf prepare", + .startup = perf_event_init_cpu, + .teardown = perf_event_exit_cpu, + }, + [CPUHP_WORKQUEUE_PREP] = { + .name = "workqueue prepare", + .startup = workqueue_prepare_cpu, + .teardown = NULL, + }, + [CPUHP_HRTIMERS_PREPARE] = { + .name = "hrtimers prepare", + .startup = hrtimers_prepare_cpu, + .teardown = hrtimers_dead_cpu, + }, + [CPUHP_SMPCFD_PREPARE] = { + .name = "SMPCFD prepare", + .startup = smpcfd_prepare_cpu, + .teardown = smpcfd_dead_cpu, + }, + [CPUHP_RCUTREE_PREP] = { + .name = "RCU-tree prepare", + .startup = rcutree_prepare_cpu, + .teardown = rcutree_dead_cpu, + }, /* * Preparatory and dead notifiers. Will be replaced once the notifiers * are converted to states. @@ -1184,6 +1216,16 @@ static struct cpuhp_step cpuhp_bp_states[] = { .skip_onerr = true, .cant_stop = true, }, + /* + * On the tear-down path, timers_dead_cpu() must be invoked + * before blk_mq_queue_reinit_notify() from notify_dead(), + * otherwise a RCU stall occurs. + */ + [CPUHP_TIMERS_DEAD] = { + .name = "timers dead", + .startup = NULL, + .teardown = timers_dead_cpu, + }, /* Kicks the plugged cpu into life */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", @@ -1191,6 +1233,10 @@ static struct cpuhp_step cpuhp_bp_states[] = { .teardown = NULL, .cant_stop = true, }, + [CPUHP_AP_SMPCFD_DYING] = { + .startup = NULL, + .teardown = smpcfd_dying_cpu, + }, /* * Handled on controll processor until the plugged processor manages * this itself. @@ -1227,6 +1273,10 @@ static struct cpuhp_step cpuhp_ap_states[] = { .startup = sched_cpu_starting, .teardown = sched_cpu_dying, }, + [CPUHP_AP_RCUTREE_DYING] = { + .startup = NULL, + .teardown = rcutree_dying_cpu, + }, /* * Low level startup/teardown notifiers. Run with interrupts * disabled. Will be removed once the notifiers are converted to @@ -1250,6 +1300,22 @@ static struct cpuhp_step cpuhp_ap_states[] = { .startup = smpboot_unpark_threads, .teardown = NULL, }, + [CPUHP_AP_PERF_ONLINE] = { + .name = "perf online", + .startup = perf_event_init_cpu, + .teardown = perf_event_exit_cpu, + }, + [CPUHP_AP_WORKQUEUE_ONLINE] = { + .name = "workqueue online", + .startup = workqueue_online_cpu, + .teardown = workqueue_offline_cpu, + }, + [CPUHP_AP_RCUTREE_ONLINE] = { + .name = "RCU-tree online", + .startup = rcutree_online_cpu, + .teardown = rcutree_offline_cpu, + }, + /* * Online/down_prepare notifiers. Will be removed once the notifiers * are converted to states. diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 73e93e53884d..c7fd2778ed50 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1034,15 +1034,6 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, { bool need_loop; - /* - * Allow tasks that have access to memory reserves because they have - * been OOM killed to get memory anywhere. - */ - if (unlikely(test_thread_flag(TIF_MEMDIE))) - return; - if (current->flags & PF_EXITING) /* Let dying task have memory */ - return; - task_lock(tsk); /* * Determine if a loop is necessary if another thread is doing diff --git a/kernel/cred.c b/kernel/cred.c index 0c0cd8a62285..5f264fb5737d 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -689,6 +689,8 @@ EXPORT_SYMBOL(set_security_override_from_ctx); */ int set_create_files_as(struct cred *new, struct inode *inode) { + if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) + return -EINVAL; new->fsuid = inode->i_uid; new->fsgid = inode->i_gid; return security_kernel_create_files_as(new, inode); diff --git a/kernel/events/core.c b/kernel/events/core.c index 79dae188a987..a19550d80ab1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -448,7 +448,7 @@ static u64 __report_allowed; static void perf_duration_warn(struct irq_work *w) { - printk_ratelimited(KERN_WARNING + printk_ratelimited(KERN_INFO "perf: interrupt took too long (%lld > %lld), lowering " "kernel.perf_event_max_sample_rate to %d\n", __report_avg, __report_allowed, @@ -5617,16 +5617,26 @@ void perf_output_sample(struct perf_output_handle *handle, } if (sample_type & PERF_SAMPLE_RAW) { - if (data->raw) { - u32 raw_size = data->raw->size; - u32 real_size = round_up(raw_size + sizeof(u32), - sizeof(u64)) - sizeof(u32); - u64 zero = 0; - - perf_output_put(handle, real_size); - __output_copy(handle, data->raw->data, raw_size); - if (real_size - raw_size) - __output_copy(handle, &zero, real_size - raw_size); + struct perf_raw_record *raw = data->raw; + + if (raw) { + struct perf_raw_frag *frag = &raw->frag; + + perf_output_put(handle, raw->size); + do { + if (frag->copy) { + __output_custom(handle, frag->copy, + frag->data, frag->size); + } else { + __output_copy(handle, frag->data, + frag->size); + } + if (perf_raw_frag_last(frag)) + break; + frag = frag->next; + } while (1); + if (frag->pad) + __output_skip(handle, NULL, frag->pad); } else { struct { u32 size; @@ -5751,14 +5761,28 @@ void perf_prepare_sample(struct perf_event_header *header, } if (sample_type & PERF_SAMPLE_RAW) { - int size = sizeof(u32); - - if (data->raw) - size += data->raw->size; - else - size += sizeof(u32); + struct perf_raw_record *raw = data->raw; + int size; + + if (raw) { + struct perf_raw_frag *frag = &raw->frag; + u32 sum = 0; + + do { + sum += frag->size; + if (perf_raw_frag_last(frag)) + break; + frag = frag->next; + } while (1); + + size = round_up(sum + sizeof(u32), sizeof(u64)); + raw->size = size - sizeof(u32); + frag->pad = raw->size - sum; + } else { + size = sizeof(u64); + } - header->size += round_up(size, sizeof(u64)); + header->size += size; } if (sample_type & PERF_SAMPLE_BRANCH_STACK) { @@ -7398,7 +7422,7 @@ static struct pmu perf_swevent = { static int perf_tp_filter_match(struct perf_event *event, struct perf_sample_data *data) { - void *record = data->raw->data; + void *record = data->raw->frag.data; /* only top level events have filters set */ if (event->parent) @@ -7454,8 +7478,10 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct perf_event *event; struct perf_raw_record raw = { - .size = entry_size, - .data = record, + .frag = { + .size = entry_size, + .data = record, + }, }; perf_sample_data_init(&data, 0, 0); @@ -7596,7 +7622,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event) prog = event->tp_event->prog; if (prog) { event->tp_event->prog = NULL; - bpf_prog_put_rcu(prog); + bpf_prog_put(prog); } } @@ -10331,7 +10357,7 @@ static void __init perf_event_init_all_cpus(void) } } -static void perf_event_init_cpu(int cpu) +int perf_event_init_cpu(unsigned int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); @@ -10344,6 +10370,7 @@ static void perf_event_init_cpu(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 @@ -10375,14 +10402,17 @@ static void perf_event_exit_cpu_context(int cpu) } srcu_read_unlock(&pmus_srcu, idx); } +#else -static void perf_event_exit_cpu(int cpu) +static void perf_event_exit_cpu_context(int cpu) { } + +#endif + +int perf_event_exit_cpu(unsigned int cpu) { perf_event_exit_cpu_context(cpu); + return 0; } -#else -static inline void perf_event_exit_cpu(int cpu) { } -#endif static int perf_reboot(struct notifier_block *notifier, unsigned long val, void *v) @@ -10404,46 +10434,6 @@ static struct notifier_block perf_reboot_notifier = { .priority = INT_MIN, }; -static int -perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) -{ - unsigned int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { - - case CPU_UP_PREPARE: - /* - * This must be done before the CPU comes alive, because the - * moment we can run tasks we can encounter (software) events. - * - * Specifically, someone can have inherited events on kthreadd - * or a pre-existing worker thread that gets re-bound. - */ - perf_event_init_cpu(cpu); - break; - - case CPU_DOWN_PREPARE: - /* - * This must be done before the CPU dies because after that an - * active event might want to IPI the CPU and that'll not work - * so great for dead CPUs. - * - * XXX smp_call_function_single() return -ENXIO without a warn - * so we could possibly deal with this. - * - * This is safe against new events arriving because - * sys_perf_event_open() serializes against hotplug using - * get_online_cpus(). - */ - perf_event_exit_cpu(cpu); - break; - default: - break; - } - - return NOTIFY_OK; -} - void __init perf_event_init(void) { int ret; @@ -10456,7 +10446,7 @@ void __init perf_event_init(void) perf_pmu_register(&perf_cpu_clock, NULL, -1); perf_pmu_register(&perf_task_clock, NULL, -1); perf_tp_register(); - perf_cpu_notifier(perf_cpu_notify); + perf_event_init_cpu(smp_processor_id()); register_reboot_notifier(&perf_reboot_notifier); ret = init_hw_breakpoint(); diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 05f9f6d626df..486fd78eb8d5 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -123,21 +123,19 @@ static inline unsigned long perf_aux_size(struct ring_buffer *rb) return rb->aux_nr_pages << PAGE_SHIFT; } -#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ -static inline unsigned long \ -func_name(struct perf_output_handle *handle, \ - const void *buf, unsigned long len) \ +#define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...) \ { \ unsigned long size, written; \ \ do { \ size = min(handle->size, len); \ - written = memcpy_func(handle->addr, buf, size); \ + written = memcpy_func(__VA_ARGS__); \ written = size - written; \ \ len -= written; \ handle->addr += written; \ - buf += written; \ + if (advance_buf) \ + buf += written; \ handle->size -= written; \ if (!handle->size) { \ struct ring_buffer *rb = handle->rb; \ @@ -152,6 +150,21 @@ func_name(struct perf_output_handle *handle, \ return len; \ } +#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ +static inline unsigned long \ +func_name(struct perf_output_handle *handle, \ + const void *buf, unsigned long len) \ +__DEFINE_OUTPUT_COPY_BODY(true, memcpy_func, handle->addr, buf, size) + +static inline unsigned long +__output_custom(struct perf_output_handle *handle, perf_copy_f copy_func, + const void *buf, unsigned long len) +{ + unsigned long orig_len = len; + __DEFINE_OUTPUT_COPY_BODY(false, copy_func, handle->addr, buf, + orig_len - len, size) +} + static inline unsigned long memcpy_common(void *dst, const void *src, unsigned long n) { diff --git a/kernel/exit.c b/kernel/exit.c index 84ae830234f8..2f974ae042a6 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -715,7 +715,7 @@ static void check_stack_usage(void) spin_lock(&low_water_lock); if (free < lowest_to_date) { - pr_warn("%s (%d) used greatest stack depth: %lu bytes left\n", + pr_info("%s (%d) used greatest stack depth: %lu bytes left\n", current->comm, task_pid_nr(current), free); lowest_to_date = free; } diff --git a/kernel/fork.c b/kernel/fork.c index 4a7ec0c6c88c..52e725d4a866 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -162,23 +162,15 @@ void __weak arch_release_thread_stack(unsigned long *stack) static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { - struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, - THREAD_SIZE_ORDER); - - if (page) - memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, - 1 << THREAD_SIZE_ORDER); + struct page *page = alloc_pages_node(node, THREADINFO_GFP, + THREAD_SIZE_ORDER); return page ? page_address(page) : NULL; } static inline void free_thread_stack(unsigned long *stack) { - struct page *page = virt_to_page(stack); - - memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, - -(1 << THREAD_SIZE_ORDER)); - __free_kmem_pages(page, THREAD_SIZE_ORDER); + __free_pages(virt_to_page(stack), THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_stack_cache; @@ -223,9 +215,15 @@ static struct kmem_cache *mm_cachep; static void account_kernel_stack(unsigned long *stack, int account) { - struct zone *zone = page_zone(virt_to_page(stack)); + /* All stack pages are in the same zone and belong to the same memcg. */ + struct page *first_page = virt_to_page(stack); + + mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB, + THREAD_SIZE / 1024 * account); - mod_zone_page_state(zone, NR_KERNEL_STACK, account); + memcg_kmem_update_page_stat( + first_page, MEMCG_KERNEL_STACK_KB, + account * (THREAD_SIZE / 1024)); } void free_task(struct task_struct *tsk) diff --git a/kernel/freezer.c b/kernel/freezer.c index a8900a3bc27a..6f56a9e219fa 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -42,7 +42,7 @@ bool freezing_slow_path(struct task_struct *p) if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) return false; - if (test_thread_flag(TIF_MEMDIE)) + if (test_tsk_thread_flag(p, TIF_MEMDIE)) return false; if (pm_nosig_freezing || cgroup_freezing(p)) diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 0dbea887d625..93ad6c1fb9b6 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -14,6 +14,7 @@ #include <linux/err.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> +#include <linux/bug.h> #ifdef HAVE_JUMP_LABEL @@ -56,6 +57,49 @@ jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) static void jump_label_update(struct static_key *key); +/* + * There are similar definitions for the !HAVE_JUMP_LABEL case in jump_label.h. + * The use of 'atomic_read()' requires atomic.h and its problematic for some + * kernel headers such as kernel.h and others. Since static_key_count() is not + * used in the branch statements as it is for the !HAVE_JUMP_LABEL case its ok + * to have it be a function here. Similarly, for 'static_key_enable()' and + * 'static_key_disable()', which require bug.h. This should allow jump_label.h + * to be included from most/all places for HAVE_JUMP_LABEL. + */ +int static_key_count(struct static_key *key) +{ + /* + * -1 means the first static_key_slow_inc() is in progress. + * static_key_enabled() must return true, so return 1 here. + */ + int n = atomic_read(&key->enabled); + + return n >= 0 ? n : 1; +} +EXPORT_SYMBOL_GPL(static_key_count); + +void static_key_enable(struct static_key *key) +{ + int count = static_key_count(key); + + WARN_ON_ONCE(count < 0 || count > 1); + + if (!count) + static_key_slow_inc(key); +} +EXPORT_SYMBOL_GPL(static_key_enable); + +void static_key_disable(struct static_key *key) +{ + int count = static_key_count(key); + + WARN_ON_ONCE(count < 0 || count > 1); + + if (count) + static_key_slow_dec(key); +} +EXPORT_SYMBOL_GPL(static_key_disable); + void static_key_slow_inc(struct static_key *key) { int v, v1; @@ -235,6 +279,18 @@ void __init jump_label_init(void) struct static_key *key = NULL; struct jump_entry *iter; + /* + * Since we are initializing the static_key.enabled field with + * with the 'raw' int values (to avoid pulling in atomic.h) in + * jump_label.h, let's make sure that is safe. There are only two + * cases to check since we initialize to 0 or 1. + */ + BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0); + BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1); + + if (static_key_initialized) + return; + jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); @@ -284,11 +340,14 @@ static int __jump_label_mod_text_reserved(void *start, void *end) { struct module *mod; + preempt_disable(); mod = __module_text_address((unsigned long)start); + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + preempt_enable(); + if (!mod) return 0; - WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); return __jump_label_text_reserved(mod->jump_entries, mod->jump_entries + mod->num_jump_entries, diff --git a/kernel/kexec.c b/kernel/kexec.c index 4384672d3245..980936a90ee6 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -48,7 +48,8 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, if (kexec_on_panic) { /* Verify we have a valid entry point */ - if ((entry < crashk_res.start) || (entry > crashk_res.end)) + if ((entry < phys_to_boot_phys(crashk_res.start)) || + (entry > phys_to_boot_phys(crashk_res.end))) return -EADDRNOTAVAIL; } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 56b3ed0927b0..561675589511 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -95,6 +95,12 @@ int kexec_should_crash(struct task_struct *p) return 0; } +int kexec_crash_loaded(void) +{ + return !!kexec_crash_image; +} +EXPORT_SYMBOL_GPL(kexec_crash_loaded); + /* * When kexec transitions to the new kernel there is a one-to-one * mapping between physical and virtual addresses. On processors @@ -140,6 +146,7 @@ int kexec_should_crash(struct task_struct *p) * allocating pages whose destination address we do not care about. */ #define KIMAGE_NO_DEST (-1UL) +#define PAGE_COUNT(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT) static struct page *kimage_alloc_page(struct kimage *image, gfp_t gfp_mask, @@ -147,8 +154,9 @@ static struct page *kimage_alloc_page(struct kimage *image, int sanity_check_segment_list(struct kimage *image) { - int result, i; + int i; unsigned long nr_segments = image->nr_segments; + unsigned long total_pages = 0; /* * Verify we have good destination addresses. The caller is @@ -163,16 +171,17 @@ int sanity_check_segment_list(struct kimage *image) * simply because addresses are changed to page size * granularity. */ - result = -EADDRNOTAVAIL; for (i = 0; i < nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz; + if (mstart > mend) + return -EADDRNOTAVAIL; if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK)) - return result; + return -EADDRNOTAVAIL; if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT) - return result; + return -EADDRNOTAVAIL; } /* Verify our destination addresses do not overlap. @@ -180,7 +189,6 @@ int sanity_check_segment_list(struct kimage *image) * through very weird things can happen with no * easy explanation as one segment stops on another. */ - result = -EINVAL; for (i = 0; i < nr_segments; i++) { unsigned long mstart, mend; unsigned long j; @@ -194,7 +202,7 @@ int sanity_check_segment_list(struct kimage *image) pend = pstart + image->segment[j].memsz; /* Do the segments overlap ? */ if ((mend > pstart) && (mstart < pend)) - return result; + return -EINVAL; } } @@ -203,12 +211,26 @@ int sanity_check_segment_list(struct kimage *image) * and it is easier to check up front than to be surprised * later on. */ - result = -EINVAL; for (i = 0; i < nr_segments; i++) { if (image->segment[i].bufsz > image->segment[i].memsz) - return result; + return -EINVAL; + } + + /* + * Verify that no more than half of memory will be consumed. If the + * request from userspace is too large, a large amount of time will be + * wasted allocating pages, which can cause a soft lockup. + */ + for (i = 0; i < nr_segments; i++) { + if (PAGE_COUNT(image->segment[i].memsz) > totalram_pages / 2) + return -EINVAL; + + total_pages += PAGE_COUNT(image->segment[i].memsz); } + if (total_pages > totalram_pages / 2) + return -EINVAL; + /* * Verify we have good destination addresses. Normally * the caller is responsible for making certain we don't @@ -220,16 +242,15 @@ int sanity_check_segment_list(struct kimage *image) */ if (image->type == KEXEC_TYPE_CRASH) { - result = -EADDRNOTAVAIL; for (i = 0; i < nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz - 1; /* Ensure we are within the crash kernel limits */ - if ((mstart < crashk_res.start) || - (mend > crashk_res.end)) - return result; + if ((mstart < phys_to_boot_phys(crashk_res.start)) || + (mend > phys_to_boot_phys(crashk_res.end))) + return -EADDRNOTAVAIL; } } @@ -352,7 +373,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image, pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order); if (!pages) break; - pfn = page_to_pfn(pages); + pfn = page_to_boot_pfn(pages); epfn = pfn + count; addr = pfn << PAGE_SHIFT; eaddr = epfn << PAGE_SHIFT; @@ -478,7 +499,7 @@ static int kimage_add_entry(struct kimage *image, kimage_entry_t entry) return -ENOMEM; ind_page = page_address(page); - *image->entry = virt_to_phys(ind_page) | IND_INDIRECTION; + *image->entry = virt_to_boot_phys(ind_page) | IND_INDIRECTION; image->entry = ind_page; image->last_entry = ind_page + ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1); @@ -533,13 +554,13 @@ void kimage_terminate(struct kimage *image) #define for_each_kimage_entry(image, ptr, entry) \ for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \ ptr = (entry & IND_INDIRECTION) ? \ - phys_to_virt((entry & PAGE_MASK)) : ptr + 1) + boot_phys_to_virt((entry & PAGE_MASK)) : ptr + 1) static void kimage_free_entry(kimage_entry_t entry) { struct page *page; - page = pfn_to_page(entry >> PAGE_SHIFT); + page = boot_pfn_to_page(entry >> PAGE_SHIFT); kimage_free_pages(page); } @@ -633,7 +654,7 @@ static struct page *kimage_alloc_page(struct kimage *image, * have a match. */ list_for_each_entry(page, &image->dest_pages, lru) { - addr = page_to_pfn(page) << PAGE_SHIFT; + addr = page_to_boot_pfn(page) << PAGE_SHIFT; if (addr == destination) { list_del(&page->lru); return page; @@ -648,12 +669,12 @@ static struct page *kimage_alloc_page(struct kimage *image, if (!page) return NULL; /* If the page cannot be used file it away */ - if (page_to_pfn(page) > + if (page_to_boot_pfn(page) > (KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) { list_add(&page->lru, &image->unusable_pages); continue; } - addr = page_to_pfn(page) << PAGE_SHIFT; + addr = page_to_boot_pfn(page) << PAGE_SHIFT; /* If it is the destination page we want use it */ if (addr == destination) @@ -676,7 +697,7 @@ static struct page *kimage_alloc_page(struct kimage *image, struct page *old_page; old_addr = *old & PAGE_MASK; - old_page = pfn_to_page(old_addr >> PAGE_SHIFT); + old_page = boot_pfn_to_page(old_addr >> PAGE_SHIFT); copy_highpage(page, old_page); *old = addr | (*old & ~PAGE_MASK); @@ -732,7 +753,7 @@ static int kimage_load_normal_segment(struct kimage *image, result = -ENOMEM; goto out; } - result = kimage_add_page(image, page_to_pfn(page) + result = kimage_add_page(image, page_to_boot_pfn(page) << PAGE_SHIFT); if (result < 0) goto out; @@ -793,7 +814,7 @@ static int kimage_load_crash_segment(struct kimage *image, char *ptr; size_t uchunk, mchunk; - page = pfn_to_page(maddr >> PAGE_SHIFT); + page = boot_pfn_to_page(maddr >> PAGE_SHIFT); if (!page) { result = -ENOMEM; goto out; @@ -921,7 +942,7 @@ void __weak crash_free_reserved_phys_range(unsigned long begin, unsigned long addr; for (addr = begin; addr < end; addr += PAGE_SIZE) - free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT)); + free_reserved_page(boot_pfn_to_page(addr >> PAGE_SHIFT)); } int crash_shrink_memory(unsigned long new_size) @@ -1374,7 +1395,7 @@ void vmcoreinfo_append_str(const char *fmt, ...) void __weak arch_crash_save_vmcoreinfo(void) {} -unsigned long __weak paddr_vmcoreinfo_note(void) +phys_addr_t __weak paddr_vmcoreinfo_note(void) { return __pa((unsigned long)(char *)&vmcoreinfo_note); } diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 152da4a48867..ee1bc1bb8feb 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -101,7 +101,7 @@ KERNEL_ATTR_RO(kexec_loaded); static ssize_t kexec_crash_loaded_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", !!kexec_crash_image); + return sprintf(buf, "%d\n", kexec_crash_loaded()); } KERNEL_ATTR_RO(kexec_crash_loaded); @@ -128,8 +128,8 @@ KERNEL_ATTR_RW(kexec_crash_size); static ssize_t vmcoreinfo_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%lx %x\n", - paddr_vmcoreinfo_note(), + phys_addr_t vmcore_base = paddr_vmcoreinfo_note(); + return sprintf(buf, "%pa %x\n", &vmcore_base, (unsigned int)sizeof(vmcoreinfo_note)); } KERNEL_ATTR_RO(vmcoreinfo); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 5c2bc1052691..8bbe50704621 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -309,7 +309,7 @@ static int klp_write_object_relocations(struct module *pmod, break; } - module_enable_ro(pmod); + module_enable_ro(pmod, true); return ret; } diff --git a/kernel/memremap.c b/kernel/memremap.c index 017532193fb1..251d16b4cb41 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -169,12 +169,6 @@ void devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(devm_memunmap); -pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags) -{ - return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); -} -EXPORT_SYMBOL(phys_to_pfn_t); - #ifdef CONFIG_ZONE_DEVICE static DEFINE_MUTEX(pgmap_lock); static RADIX_TREE(pgmap_radix, GFP_KERNEL); @@ -308,12 +302,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (is_ram == REGION_INTERSECTS) return __va(res->start); - if (altmap && !IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) { - dev_err(dev, "%s: altmap requires CONFIG_SPARSEMEM_VMEMMAP=y\n", - __func__); - return ERR_PTR(-ENXIO); - } - if (!ref) return ERR_PTR(-EINVAL); @@ -401,7 +389,6 @@ void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) altmap->alloc -= nr_pfns; } -#ifdef CONFIG_SPARSEMEM_VMEMMAP struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) { /* @@ -427,5 +414,4 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) return pgmap ? pgmap->altmap : NULL; } -#endif /* CONFIG_SPARSEMEM_VMEMMAP */ #endif /* CONFIG_ZONE_DEVICE */ diff --git a/kernel/module.c b/kernel/module.c index 5f71aa63ed2a..529efae9f481 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -60,6 +60,7 @@ #include <linux/jump_label.h> #include <linux/pfn.h> #include <linux/bsearch.h> +#include <linux/dynamic_debug.h> #include <uapi/linux/module.h> #include "module-internal.h" @@ -264,7 +265,7 @@ static void module_assert_mutex_or_preempt(void) if (unlikely(!debug_locks)) return; - WARN_ON(!rcu_read_lock_sched_held() && + WARN_ON_ONCE(!rcu_read_lock_sched_held() && !lockdep_is_held(&module_mutex)); #endif } @@ -336,7 +337,7 @@ static inline void add_taint_module(struct module *mod, unsigned flag, * A thread that wants to hold a reference to a module only while it * is running can call this to safely exit. nfsd and lockd use this. */ -void __module_put_and_exit(struct module *mod, long code) +void __noreturn __module_put_and_exit(struct module *mod, long code) { module_put(mod); do_exit(code); @@ -1693,8 +1694,7 @@ static int module_add_modinfo_attrs(struct module *mod) temp_attr = mod->modinfo_attrs; for (i = 0; (attr = modinfo_attrs[i]) && !error; i++) { - if (!attr->test || - (attr->test && attr->test(mod))) { + if (!attr->test || attr->test(mod)) { memcpy(temp_attr, attr, sizeof(*temp_attr)); sysfs_attr_init(&temp_attr->attr); error = sysfs_create_file(&mod->mkobj.kobj, @@ -1858,10 +1858,11 @@ static void mod_sysfs_teardown(struct module *mod) * from modification and any data from execution. * * General layout of module is: - * [text] [read-only-data] [writable data] - * text_size -----^ ^ ^ - * ro_size ------------------------| | - * size -------------------------------------------| + * [text] [read-only-data] [ro-after-init] [writable data] + * text_size -----^ ^ ^ ^ + * ro_size ------------------------| | | + * ro_after_init_size -----------------------------| | + * size -----------------------------------------------------------| * * These values are always page-aligned (as is base) */ @@ -1884,14 +1885,24 @@ static void frob_rodata(const struct module_layout *layout, (layout->ro_size - layout->text_size) >> PAGE_SHIFT); } +static void frob_ro_after_init(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) +{ + BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->ro_after_init_size & (PAGE_SIZE-1)); + set_memory((unsigned long)layout->base + layout->ro_size, + (layout->ro_after_init_size - layout->ro_size) >> PAGE_SHIFT); +} + static void frob_writable_data(const struct module_layout *layout, int (*set_memory)(unsigned long start, int num_pages)) { BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); - BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->ro_after_init_size & (PAGE_SIZE-1)); BUG_ON((unsigned long)layout->size & (PAGE_SIZE-1)); - set_memory((unsigned long)layout->base + layout->ro_size, - (layout->size - layout->ro_size) >> PAGE_SHIFT); + set_memory((unsigned long)layout->base + layout->ro_after_init_size, + (layout->size - layout->ro_after_init_size) >> PAGE_SHIFT); } /* livepatching wants to disable read-only so it can frob module. */ @@ -1899,21 +1910,26 @@ void module_disable_ro(const struct module *mod) { frob_text(&mod->core_layout, set_memory_rw); frob_rodata(&mod->core_layout, set_memory_rw); + frob_ro_after_init(&mod->core_layout, set_memory_rw); frob_text(&mod->init_layout, set_memory_rw); frob_rodata(&mod->init_layout, set_memory_rw); } -void module_enable_ro(const struct module *mod) +void module_enable_ro(const struct module *mod, bool after_init) { frob_text(&mod->core_layout, set_memory_ro); frob_rodata(&mod->core_layout, set_memory_ro); frob_text(&mod->init_layout, set_memory_ro); frob_rodata(&mod->init_layout, set_memory_ro); + + if (after_init) + frob_ro_after_init(&mod->core_layout, set_memory_ro); } static void module_enable_nx(const struct module *mod) { frob_rodata(&mod->core_layout, set_memory_nx); + frob_ro_after_init(&mod->core_layout, set_memory_nx); frob_writable_data(&mod->core_layout, set_memory_nx); frob_rodata(&mod->init_layout, set_memory_nx); frob_writable_data(&mod->init_layout, set_memory_nx); @@ -1922,6 +1938,7 @@ static void module_enable_nx(const struct module *mod) static void module_disable_nx(const struct module *mod) { frob_rodata(&mod->core_layout, set_memory_x); + frob_ro_after_init(&mod->core_layout, set_memory_x); frob_writable_data(&mod->core_layout, set_memory_x); frob_rodata(&mod->init_layout, set_memory_x); frob_writable_data(&mod->init_layout, set_memory_x); @@ -1964,6 +1981,8 @@ static void disable_ro_nx(const struct module_layout *layout) frob_text(layout, set_memory_rw); frob_rodata(layout, set_memory_rw); frob_rodata(layout, set_memory_x); + frob_ro_after_init(layout, set_memory_rw); + frob_ro_after_init(layout, set_memory_x); frob_writable_data(layout, set_memory_x); } @@ -2306,6 +2325,7 @@ static void layout_sections(struct module *mod, struct load_info *info) * finder in the two loops below */ { SHF_EXECINSTR | SHF_ALLOC, ARCH_SHF_SMALL }, { SHF_ALLOC, SHF_WRITE | ARCH_SHF_SMALL }, + { SHF_RO_AFTER_INIT | SHF_ALLOC, ARCH_SHF_SMALL }, { SHF_WRITE | SHF_ALLOC, ARCH_SHF_SMALL }, { ARCH_SHF_SMALL | SHF_ALLOC, 0 } }; @@ -2337,7 +2357,11 @@ static void layout_sections(struct module *mod, struct load_info *info) mod->core_layout.size = debug_align(mod->core_layout.size); mod->core_layout.ro_size = mod->core_layout.size; break; - case 3: /* whole core */ + case 2: /* RO after init */ + mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.ro_after_init_size = mod->core_layout.size; + break; + case 4: /* whole core */ mod->core_layout.size = debug_align(mod->core_layout.size); break; } @@ -2367,7 +2391,14 @@ static void layout_sections(struct module *mod, struct load_info *info) mod->init_layout.size = debug_align(mod->init_layout.size); mod->init_layout.ro_size = mod->init_layout.size; break; - case 3: /* whole init */ + case 2: + /* + * RO after init doesn't apply to init_layout (only + * core_layout), so it just takes the value of ro_size. + */ + mod->init_layout.ro_after_init_size = mod->init_layout.ro_size; + break; + case 4: /* whole init */ mod->init_layout.size = debug_align(mod->init_layout.size); break; } @@ -2687,13 +2718,18 @@ static inline void kmemleak_load_module(const struct module *mod, #endif #ifdef CONFIG_MODULE_SIG -static int module_sig_check(struct load_info *info) +static int module_sig_check(struct load_info *info, int flags) { int err = -ENOKEY; const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; const void *mod = info->hdr; - if (info->len > markerlen && + /* + * Require flags == 0, as a module with version information + * removed is no longer the module that was signed + */ + if (flags == 0 && + info->len > markerlen && memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { /* We truncate the module to discard the signature */ info->len -= markerlen; @@ -2712,7 +2748,7 @@ static int module_sig_check(struct load_info *info) return err; } #else /* !CONFIG_MODULE_SIG */ -static int module_sig_check(struct load_info *info) +static int module_sig_check(struct load_info *info, int flags) { return 0; } @@ -2920,8 +2956,12 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) return -ENOEXEC; } - if (!get_modinfo(info, "intree")) + if (!get_modinfo(info, "intree")) { + if (!test_taint(TAINT_OOT_MODULE)) + pr_warn("%s: loading out-of-tree module taints kernel.\n", + mod->name); add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK); + } if (get_modinfo(info, "staging")) { add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK); @@ -3090,6 +3130,8 @@ static int move_module(struct module *mod, struct load_info *info) static int check_module_license_and_versions(struct module *mod) { + int prev_taint = test_taint(TAINT_PROPRIETARY_MODULE); + /* * ndiswrapper is under GPL by itself, but loads proprietary modules. * Don't use add_taint_module(), as it would prevent ndiswrapper from @@ -3108,6 +3150,9 @@ static int check_module_license_and_versions(struct module *mod) add_taint_module(mod, TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); + if (!prev_taint && test_taint(TAINT_PROPRIETARY_MODULE)) + pr_warn("%s: module license taints kernel.\n", mod->name); + #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || (mod->num_gpl_syms && !mod->gpl_crcs) @@ -3155,16 +3200,41 @@ int __weak module_frob_arch_sections(Elf_Ehdr *hdr, return 0; } +/* module_blacklist is a comma-separated list of module names */ +static char *module_blacklist; +static bool blacklisted(char *module_name) +{ + const char *p; + size_t len; + + if (!module_blacklist) + return false; + + for (p = module_blacklist; *p; p += len) { + len = strcspn(p, ","); + if (strlen(module_name) == len && !memcmp(module_name, p, len)) + return true; + if (p[len] == ',') + len++; + } + return false; +} +core_param(module_blacklist, module_blacklist, charp, 0400); + static struct module *layout_and_allocate(struct load_info *info, int flags) { /* Module within temporary copy. */ struct module *mod; + unsigned int ndx; int err; mod = setup_load_info(info, flags); if (IS_ERR(mod)) return mod; + if (blacklisted(mod->name)) + return ERR_PTR(-EPERM); + err = check_modinfo(mod, info, flags); if (err) return ERR_PTR(err); @@ -3178,6 +3248,15 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) /* We will do a special allocation for per-cpu sections later. */ info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC; + /* + * Mark ro_after_init section with SHF_RO_AFTER_INIT so that + * layout_sections() can put it in the right place. + * Note: ro_after_init sections also have SHF_{WRITE,ALLOC} set. + */ + ndx = find_sec(info, ".data..ro_after_init"); + if (ndx) + info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT; + /* Determine total sizes, and put offsets in sh_entsize. For now this is done generically; there doesn't appear to be any special cases for the architectures. */ @@ -3344,12 +3423,14 @@ static noinline int do_init_module(struct module *mod) /* Switch to core kallsyms now init is done: kallsyms may be walking! */ rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms); #endif + module_enable_ro(mod, true); mod_tree_remove_init(mod); disable_ro_nx(&mod->init_layout); module_arch_freeing_init(mod); mod->init_layout.base = NULL; mod->init_layout.size = 0; mod->init_layout.ro_size = 0; + mod->init_layout.ro_after_init_size = 0; mod->init_layout.text_size = 0; /* * We want to free module_init, but be aware that kallsyms may be @@ -3441,8 +3522,7 @@ static int complete_formation(struct module *mod, struct load_info *info) /* This relies on module_mutex for list integrity. */ module_bug_finalize(info->hdr, info->sechdrs, mod); - /* Set RO and NX regions */ - module_enable_ro(mod); + module_enable_ro(mod, false); module_enable_nx(mod); /* Mark state as coming so strong_try_module_get() ignores us, @@ -3498,7 +3578,7 @@ static int load_module(struct load_info *info, const char __user *uargs, long err; char *after_dashes; - err = module_sig_check(info); + err = module_sig_check(info, flags); if (err) goto free_copy; diff --git a/kernel/panic.c b/kernel/panic.c index 8aa74497cc5a..ca8cea1ef673 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -108,6 +108,7 @@ void panic(const char *fmt, ...) long i, i_next = 0; int state = 0; int old_cpu, this_cpu; + bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; /* * Disable local interrupts. This will prevent panic_smp_self_stop @@ -160,7 +161,7 @@ void panic(const char *fmt, ...) * * Bypass the panic_cpu check and call __crash_kexec directly. */ - if (!crash_kexec_post_notifiers) { + if (!_crash_kexec_post_notifiers) { printk_nmi_flush_on_panic(); __crash_kexec(NULL); } @@ -191,7 +192,7 @@ void panic(const char *fmt, ...) * * Bypass the panic_cpu check and call __crash_kexec directly. */ - if (crash_kexec_post_notifiers) + if (_crash_kexec_post_notifiers) __crash_kexec(NULL); bust_spinlocks(0); @@ -571,13 +572,7 @@ EXPORT_SYMBOL(__stack_chk_fail); core_param(panic, panic_timeout, int, 0644); core_param(pause_on_oops, pause_on_oops, int, 0644); core_param(panic_on_warn, panic_on_warn, int, 0644); - -static int __init setup_crash_kexec_post_notifiers(char *s) -{ - crash_kexec_post_notifiers = true; - return 0; -} -early_param("crash_kexec_post_notifiers", setup_crash_kexec_post_notifiers); +core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644); static int __init oops_setup(char *s) { diff --git a/kernel/power/Makefile b/kernel/power/Makefile index cb880a14cc39..eb4f717705ba 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -1,6 +1,8 @@ ccflags-$(CONFIG_PM_DEBUG) := -DDEBUG +KASAN_SANITIZE_snapshot.o := n + obj-y += qos.o obj-$(CONFIG_PM) += main.o obj-$(CONFIG_VT_CONSOLE_SLEEP) += console.o diff --git a/kernel/power/console.c b/kernel/power/console.c index aba9c545a0e3..0e781798b0b3 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -126,17 +126,17 @@ out: return ret; } -int pm_prepare_console(void) +void pm_prepare_console(void) { if (!pm_vt_switch()) - return 0; + return; orig_fgconsole = vt_move_to_console(SUSPEND_CONSOLE, 1); if (orig_fgconsole < 0) - return 1; + return; orig_kmsg = vt_kmsg_redirect(SUSPEND_CONSOLE); - return 0; + return; } void pm_restore_console(void) diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 9021387c6ff4..a881c6a7ba74 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -52,6 +52,7 @@ enum { #ifdef CONFIG_SUSPEND HIBERNATION_SUSPEND, #endif + HIBERNATION_TEST_RESUME, /* keep last */ __HIBERNATION_AFTER_LAST }; @@ -409,6 +410,11 @@ int hibernation_snapshot(int platform_mode) goto Close; } +int __weak hibernate_resume_nonboot_cpu_disable(void) +{ + return disable_nonboot_cpus(); +} + /** * resume_target_kernel - Restore system state from a hibernation image. * @platform_mode: Whether or not to use the platform driver. @@ -433,7 +439,7 @@ static int resume_target_kernel(bool platform_mode) if (error) goto Cleanup; - error = disable_nonboot_cpus(); + error = hibernate_resume_nonboot_cpu_disable(); if (error) goto Enable_cpus; @@ -642,12 +648,39 @@ static void power_down(void) cpu_relax(); } +static int load_image_and_restore(void) +{ + int error; + unsigned int flags; + + pr_debug("PM: Loading hibernation image.\n"); + + lock_device_hotplug(); + error = create_basic_memory_bitmaps(); + if (error) + goto Unlock; + + error = swsusp_read(&flags); + swsusp_close(FMODE_READ); + if (!error) + hibernation_restore(flags & SF_PLATFORM_MODE); + + printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n"); + swsusp_free(); + free_basic_memory_bitmaps(); + Unlock: + unlock_device_hotplug(); + + return error; +} + /** * hibernate - Carry out system hibernation, including saving the image. */ int hibernate(void) { - int error; + int error, nr_calls = 0; + bool snapshot_test = false; if (!hibernation_available()) { pr_debug("PM: Hibernation not available.\n"); @@ -662,9 +695,11 @@ int hibernate(void) } pm_prepare_console(); - error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); - if (error) + error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; goto Exit; + } printk(KERN_INFO "PM: Syncing filesystems ... "); sys_sync(); @@ -697,8 +732,12 @@ int hibernate(void) pr_debug("PM: writing image.\n"); error = swsusp_write(flags); swsusp_free(); - if (!error) - power_down(); + if (!error) { + if (hibernation_mode == HIBERNATION_TEST_RESUME) + snapshot_test = true; + else + power_down(); + } in_suspend = 0; pm_restore_gfp_mask(); } else { @@ -709,12 +748,18 @@ int hibernate(void) free_basic_memory_bitmaps(); Thaw: unlock_device_hotplug(); + if (snapshot_test) { + pr_debug("PM: Checking hibernation image\n"); + error = swsusp_check(); + if (!error) + error = load_image_and_restore(); + } thaw_processes(); /* Don't bother checking whether freezer_test_done is true */ freezer_test_done = false; Exit: - pm_notifier_call_chain(PM_POST_HIBERNATION); + __pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL); pm_restore_console(); atomic_inc(&snapshot_device_available); Unlock: @@ -740,8 +785,7 @@ int hibernate(void) */ static int software_resume(void) { - int error; - unsigned int flags; + int error, nr_calls = 0; /* * If the user said "noresume".. bail out early. @@ -827,35 +871,20 @@ static int software_resume(void) } pm_prepare_console(); - error = pm_notifier_call_chain(PM_RESTORE_PREPARE); - if (error) + error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; goto Close_Finish; + } pr_debug("PM: Preparing processes for restore.\n"); error = freeze_processes(); if (error) goto Close_Finish; - - pr_debug("PM: Loading hibernation image.\n"); - - lock_device_hotplug(); - error = create_basic_memory_bitmaps(); - if (error) - goto Thaw; - - error = swsusp_read(&flags); - swsusp_close(FMODE_READ); - if (!error) - hibernation_restore(flags & SF_PLATFORM_MODE); - - printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n"); - swsusp_free(); - free_basic_memory_bitmaps(); - Thaw: - unlock_device_hotplug(); + error = load_image_and_restore(); thaw_processes(); Finish: - pm_notifier_call_chain(PM_POST_RESTORE); + __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL); pm_restore_console(); atomic_inc(&snapshot_device_available); /* For success case, the suspend path will release the lock */ @@ -878,6 +907,7 @@ static const char * const hibernation_modes[] = { #ifdef CONFIG_SUSPEND [HIBERNATION_SUSPEND] = "suspend", #endif + [HIBERNATION_TEST_RESUME] = "test_resume", }; /* @@ -924,6 +954,7 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, #ifdef CONFIG_SUSPEND case HIBERNATION_SUSPEND: #endif + case HIBERNATION_TEST_RESUME: break; case HIBERNATION_PLATFORM: if (hibernation_ops) @@ -970,6 +1001,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, #ifdef CONFIG_SUSPEND case HIBERNATION_SUSPEND: #endif + case HIBERNATION_TEST_RESUME: hibernation_mode = mode; break; case HIBERNATION_PLATFORM: @@ -1115,13 +1147,16 @@ static int __init resume_offset_setup(char *str) static int __init hibernate_setup(char *str) { - if (!strncmp(str, "noresume", 8)) + if (!strncmp(str, "noresume", 8)) { noresume = 1; - else if (!strncmp(str, "nocompress", 10)) + } else if (!strncmp(str, "nocompress", 10)) { nocompress = 1; - else if (!strncmp(str, "no", 2)) { + } else if (!strncmp(str, "no", 2)) { noresume = 1; nohibernate = 1; + } else if (IS_ENABLED(CONFIG_DEBUG_RODATA) + && !strncmp(str, "protect_image", 13)) { + enable_restore_image_protection(); } return 1; } diff --git a/kernel/power/main.c b/kernel/power/main.c index 27946975eff0..5ea50b1b7595 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -38,12 +38,19 @@ int unregister_pm_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_pm_notifier); -int pm_notifier_call_chain(unsigned long val) +int __pm_notifier_call_chain(unsigned long val, int nr_to_call, int *nr_calls) { - int ret = blocking_notifier_call_chain(&pm_chain_head, val, NULL); + int ret; + + ret = __blocking_notifier_call_chain(&pm_chain_head, val, NULL, + nr_to_call, nr_calls); return notifier_to_errno(ret); } +int pm_notifier_call_chain(unsigned long val) +{ + return __pm_notifier_call_chain(val, -1, NULL); +} /* If set, devices may be suspended and resumed asynchronously. */ int pm_async_enabled = 1; diff --git a/kernel/power/power.h b/kernel/power/power.h index efe1b3b17c88..242d8b827dd5 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -38,6 +38,8 @@ static inline char *check_image_kernel(struct swsusp_info *info) } #endif /* CONFIG_ARCH_HIBERNATION_HEADER */ +extern int hibernate_resume_nonboot_cpu_disable(void); + /* * Keep some memory free so that I/O operations can succeed without paging * [Might this be more than 4 MB?] @@ -59,6 +61,13 @@ extern int hibernation_snapshot(int platform_mode); extern int hibernation_restore(int platform_mode); extern int hibernation_platform_enter(void); +#ifdef CONFIG_DEBUG_RODATA +/* kernel/power/snapshot.c */ +extern void enable_restore_image_protection(void); +#else +static inline void enable_restore_image_protection(void) {} +#endif /* CONFIG_DEBUG_RODATA */ + #else /* !CONFIG_HIBERNATION */ static inline void hibernate_reserved_size_init(void) {} @@ -200,6 +209,8 @@ static inline void suspend_test_finish(const char *label) {} #ifdef CONFIG_PM_SLEEP /* kernel/power/main.c */ +extern int __pm_notifier_call_chain(unsigned long val, int nr_to_call, + int *nr_calls); extern int pm_notifier_call_chain(unsigned long val); #endif diff --git a/kernel/power/process.c b/kernel/power/process.c index 0c2ee9761d57..8f27d5a8adf6 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -89,6 +89,9 @@ static int try_to_freeze_tasks(bool user_only) elapsed_msecs / 1000, elapsed_msecs % 1000, todo - wq_busy, wq_busy); + if (wq_busy) + show_workqueue_state(); + if (!wakeup) { read_lock(&tasklist_lock); for_each_process_thread(g, p) { diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3a970604308f..9a0178c2ac1d 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -38,6 +38,43 @@ #include "power.h" +#ifdef CONFIG_DEBUG_RODATA +static bool hibernate_restore_protection; +static bool hibernate_restore_protection_active; + +void enable_restore_image_protection(void) +{ + hibernate_restore_protection = true; +} + +static inline void hibernate_restore_protection_begin(void) +{ + hibernate_restore_protection_active = hibernate_restore_protection; +} + +static inline void hibernate_restore_protection_end(void) +{ + hibernate_restore_protection_active = false; +} + +static inline void hibernate_restore_protect_page(void *page_address) +{ + if (hibernate_restore_protection_active) + set_memory_ro((unsigned long)page_address, 1); +} + +static inline void hibernate_restore_unprotect_page(void *page_address) +{ + if (hibernate_restore_protection_active) + set_memory_rw((unsigned long)page_address, 1); +} +#else +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_DEBUG_RODATA */ + static int swsusp_page_is_free(struct page *); static void swsusp_set_page_forbidden(struct page *); static void swsusp_unset_page_forbidden(struct page *); @@ -67,25 +104,32 @@ void __init hibernate_image_size_init(void) image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE; } -/* List of PBEs needed for restoring the pages that were allocated before +/* + * List of PBEs needed for restoring the pages that were allocated before * the suspend and included in the suspend image, but have also been * allocated by the "resume" kernel, so their contents cannot be written * directly to their "original" page frames. */ struct pbe *restore_pblist; -/* Pointer to an auxiliary buffer (1 page) */ -static void *buffer; +/* struct linked_page is used to build chains of pages */ -/** - * @safe_needed - on resume, for storing the PBE list and the image, - * we can only use memory pages that do not conflict with the pages - * used before suspend. The unsafe pages have PageNosaveFree set - * and we count them using unsafe_pages. - * - * Each allocated image page is marked as PageNosave and PageNosaveFree - * so that swsusp_free() can release it. +#define LINKED_PAGE_DATA_SIZE (PAGE_SIZE - sizeof(void *)) + +struct linked_page { + struct linked_page *next; + char data[LINKED_PAGE_DATA_SIZE]; +} __packed; + +/* + * List of "safe" pages (ie. pages that were not used by the image kernel + * before hibernation) that may be used as temporary storage for image kernel + * memory contents. */ +static struct linked_page *safe_pages_list; + +/* Pointer to an auxiliary buffer (1 page) */ +static void *buffer; #define PG_ANY 0 #define PG_SAFE 1 @@ -94,6 +138,19 @@ static void *buffer; static unsigned int allocated_unsafe_pages; +/** + * get_image_page - Allocate a page for a hibernation image. + * @gfp_mask: GFP mask for the allocation. + * @safe_needed: Get pages that were not used before hibernation (restore only) + * + * During image restoration, for storing the PBE list and the image data, we can + * only use memory pages that do not conflict with the pages used before + * hibernation. The "unsafe" pages have PageNosaveFree set and we count them + * using allocated_unsafe_pages. + * + * Each allocated image page is marked as PageNosave and PageNosaveFree so that + * swsusp_free() can release it. + */ static void *get_image_page(gfp_t gfp_mask, int safe_needed) { void *res; @@ -113,9 +170,21 @@ static void *get_image_page(gfp_t gfp_mask, int safe_needed) return res; } +static void *__get_safe_page(gfp_t gfp_mask) +{ + if (safe_pages_list) { + void *ret = safe_pages_list; + + safe_pages_list = safe_pages_list->next; + memset(ret, 0, PAGE_SIZE); + return ret; + } + return get_image_page(gfp_mask, PG_SAFE); +} + unsigned long get_safe_page(gfp_t gfp_mask) { - return (unsigned long)get_image_page(gfp_mask, PG_SAFE); + return (unsigned long)__get_safe_page(gfp_mask); } static struct page *alloc_image_page(gfp_t gfp_mask) @@ -130,11 +199,22 @@ static struct page *alloc_image_page(gfp_t gfp_mask) return page; } +static void recycle_safe_page(void *page_address) +{ + struct linked_page *lp = page_address; + + lp->next = safe_pages_list; + safe_pages_list = lp; +} + /** - * free_image_page - free page represented by @addr, allocated with - * get_image_page (page flags set by it must be cleared) + * free_image_page - Free a page allocated for hibernation image. + * @addr: Address of the page to free. + * @clear_nosave_free: If set, clear the PageNosaveFree bit for the page. + * + * The page to free should have been allocated by get_image_page() (page flags + * set by it are affected). */ - static inline void free_image_page(void *addr, int clear_nosave_free) { struct page *page; @@ -150,17 +230,8 @@ static inline void free_image_page(void *addr, int clear_nosave_free) __free_page(page); } -/* struct linked_page is used to build chains of pages */ - -#define LINKED_PAGE_DATA_SIZE (PAGE_SIZE - sizeof(void *)) - -struct linked_page { - struct linked_page *next; - char data[LINKED_PAGE_DATA_SIZE]; -} __packed; - -static inline void -free_list_of_pages(struct linked_page *list, int clear_page_nosave) +static inline void free_list_of_pages(struct linked_page *list, + int clear_page_nosave) { while (list) { struct linked_page *lp = list->next; @@ -170,30 +241,28 @@ free_list_of_pages(struct linked_page *list, int clear_page_nosave) } } -/** - * struct chain_allocator is used for allocating small objects out of - * a linked list of pages called 'the chain'. - * - * The chain grows each time when there is no room for a new object in - * the current page. The allocated objects cannot be freed individually. - * It is only possible to free them all at once, by freeing the entire - * chain. - * - * NOTE: The chain allocator may be inefficient if the allocated objects - * are not much smaller than PAGE_SIZE. - */ - +/* + * struct chain_allocator is used for allocating small objects out of + * a linked list of pages called 'the chain'. + * + * The chain grows each time when there is no room for a new object in + * the current page. The allocated objects cannot be freed individually. + * It is only possible to free them all at once, by freeing the entire + * chain. + * + * NOTE: The chain allocator may be inefficient if the allocated objects + * are not much smaller than PAGE_SIZE. + */ struct chain_allocator { struct linked_page *chain; /* the chain */ unsigned int used_space; /* total size of objects allocated out - * of the current page - */ + of the current page */ gfp_t gfp_mask; /* mask for allocating pages */ int safe_needed; /* if set, only "safe" pages are allocated */ }; -static void -chain_init(struct chain_allocator *ca, gfp_t gfp_mask, int safe_needed) +static void chain_init(struct chain_allocator *ca, gfp_t gfp_mask, + int safe_needed) { ca->chain = NULL; ca->used_space = LINKED_PAGE_DATA_SIZE; @@ -208,7 +277,8 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size) if (LINKED_PAGE_DATA_SIZE - ca->used_space < size) { struct linked_page *lp; - lp = get_image_page(ca->gfp_mask, ca->safe_needed); + lp = ca->safe_needed ? __get_safe_page(ca->gfp_mask) : + get_image_page(ca->gfp_mask, PG_ANY); if (!lp) return NULL; @@ -222,44 +292,44 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size) } /** - * Data types related to memory bitmaps. + * Data types related to memory bitmaps. * - * Memory bitmap is a structure consiting of many linked lists of - * objects. The main list's elements are of type struct zone_bitmap - * and each of them corresonds to one zone. For each zone bitmap - * object there is a list of objects of type struct bm_block that - * represent each blocks of bitmap in which information is stored. + * Memory bitmap is a structure consiting of many linked lists of + * objects. The main list's elements are of type struct zone_bitmap + * and each of them corresonds to one zone. For each zone bitmap + * object there is a list of objects of type struct bm_block that + * represent each blocks of bitmap in which information is stored. * - * struct memory_bitmap contains a pointer to the main list of zone - * bitmap objects, a struct bm_position used for browsing the bitmap, - * and a pointer to the list of pages used for allocating all of the - * zone bitmap objects and bitmap block objects. + * struct memory_bitmap contains a pointer to the main list of zone + * bitmap objects, a struct bm_position used for browsing the bitmap, + * and a pointer to the list of pages used for allocating all of the + * zone bitmap objects and bitmap block objects. * - * NOTE: It has to be possible to lay out the bitmap in memory - * using only allocations of order 0. Additionally, the bitmap is - * designed to work with arbitrary number of zones (this is over the - * top for now, but let's avoid making unnecessary assumptions ;-). + * NOTE: It has to be possible to lay out the bitmap in memory + * using only allocations of order 0. Additionally, the bitmap is + * designed to work with arbitrary number of zones (this is over the + * top for now, but let's avoid making unnecessary assumptions ;-). * - * struct zone_bitmap contains a pointer to a list of bitmap block - * objects and a pointer to the bitmap block object that has been - * most recently used for setting bits. Additionally, it contains the - * pfns that correspond to the start and end of the represented zone. + * struct zone_bitmap contains a pointer to a list of bitmap block + * objects and a pointer to the bitmap block object that has been + * most recently used for setting bits. Additionally, it contains the + * PFNs that correspond to the start and end of the represented zone. * - * struct bm_block contains a pointer to the memory page in which - * information is stored (in the form of a block of bitmap) - * It also contains the pfns that correspond to the start and end of - * the represented memory area. + * struct bm_block contains a pointer to the memory page in which + * information is stored (in the form of a block of bitmap) + * It also contains the pfns that correspond to the start and end of + * the represented memory area. * - * The memory bitmap is organized as a radix tree to guarantee fast random - * access to the bits. There is one radix tree for each zone (as returned - * from create_mem_extents). + * The memory bitmap is organized as a radix tree to guarantee fast random + * access to the bits. There is one radix tree for each zone (as returned + * from create_mem_extents). * - * One radix tree is represented by one struct mem_zone_bm_rtree. There are - * two linked lists for the nodes of the tree, one for the inner nodes and - * one for the leave nodes. The linked leave nodes are used for fast linear - * access of the memory bitmap. + * One radix tree is represented by one struct mem_zone_bm_rtree. There are + * two linked lists for the nodes of the tree, one for the inner nodes and + * one for the leave nodes. The linked leave nodes are used for fast linear + * access of the memory bitmap. * - * The struct rtree_node represents one node of the radix tree. + * The struct rtree_node represents one node of the radix tree. */ #define BM_END_OF_MAP (~0UL) @@ -305,9 +375,8 @@ struct bm_position { struct memory_bitmap { struct list_head zones; struct linked_page *p_list; /* list of pages used to store zone - * bitmap objects and bitmap block - * objects - */ + bitmap objects and bitmap block + objects */ struct bm_position cur; /* most recently used bit position */ }; @@ -321,12 +390,12 @@ struct memory_bitmap { #endif #define BM_RTREE_LEVEL_MASK ((1UL << BM_RTREE_LEVEL_SHIFT) - 1) -/* - * alloc_rtree_node - Allocate a new node and add it to the radix tree. +/** + * alloc_rtree_node - Allocate a new node and add it to the radix tree. * - * This function is used to allocate inner nodes as well as the - * leave nodes of the radix tree. It also adds the node to the - * corresponding linked list passed in by the *list parameter. + * This function is used to allocate inner nodes as well as the + * leave nodes of the radix tree. It also adds the node to the + * corresponding linked list passed in by the *list parameter. */ static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca, @@ -347,12 +416,12 @@ static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed, return node; } -/* - * add_rtree_block - Add a new leave node to the radix tree +/** + * add_rtree_block - Add a new leave node to the radix tree. * - * The leave nodes need to be allocated in order to keep the leaves - * linked list in order. This is guaranteed by the zone->blocks - * counter. + * The leave nodes need to be allocated in order to keep the leaves + * linked list in order. This is guaranteed by the zone->blocks + * counter. */ static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca) @@ -417,17 +486,18 @@ static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask, static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free); -/* - * create_zone_bm_rtree - create a radix tree for one zone +/** + * create_zone_bm_rtree - Create a radix tree for one zone. * - * Allocated the mem_zone_bm_rtree structure and initializes it. - * This function also allocated and builds the radix tree for the - * zone. + * Allocated the mem_zone_bm_rtree structure and initializes it. + * This function also allocated and builds the radix tree for the + * zone. */ -static struct mem_zone_bm_rtree * -create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed, - struct chain_allocator *ca, - unsigned long start, unsigned long end) +static struct mem_zone_bm_rtree *create_zone_bm_rtree(gfp_t gfp_mask, + int safe_needed, + struct chain_allocator *ca, + unsigned long start, + unsigned long end) { struct mem_zone_bm_rtree *zone; unsigned int i, nr_blocks; @@ -454,12 +524,12 @@ create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed, return zone; } -/* - * free_zone_bm_rtree - Free the memory of the radix tree +/** + * free_zone_bm_rtree - Free the memory of the radix tree. * - * Free all node pages of the radix tree. The mem_zone_bm_rtree - * structure itself is not freed here nor are the rtree_node - * structs. + * Free all node pages of the radix tree. The mem_zone_bm_rtree + * structure itself is not freed here nor are the rtree_node + * structs. */ static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free) @@ -492,8 +562,8 @@ struct mem_extent { }; /** - * free_mem_extents - free a list of memory extents - * @list - list of extents to empty + * free_mem_extents - Free a list of memory extents. + * @list: List of extents to free. */ static void free_mem_extents(struct list_head *list) { @@ -506,10 +576,11 @@ static void free_mem_extents(struct list_head *list) } /** - * create_mem_extents - create a list of memory extents representing - * contiguous ranges of PFNs - * @list - list to put the extents into - * @gfp_mask - mask to use for memory allocations + * create_mem_extents - Create a list of memory extents. + * @list: List to put the extents into. + * @gfp_mask: Mask to use for memory allocations. + * + * The extents represent contiguous ranges of PFNs. */ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask) { @@ -565,10 +636,10 @@ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask) } /** - * memory_bm_create - allocate memory for a memory bitmap - */ -static int -memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) + * memory_bm_create - Allocate memory for a memory bitmap. + */ +static int memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, + int safe_needed) { struct chain_allocator ca; struct list_head mem_extents; @@ -607,8 +678,9 @@ memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) } /** - * memory_bm_free - free memory occupied by the memory bitmap @bm - */ + * memory_bm_free - Free memory occupied by the memory bitmap. + * @bm: Memory bitmap. + */ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) { struct mem_zone_bm_rtree *zone; @@ -622,14 +694,13 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) } /** - * memory_bm_find_bit - Find the bit for pfn in the memory - * bitmap + * memory_bm_find_bit - Find the bit for a given PFN in a memory bitmap. * - * Find the bit in the bitmap @bm that corresponds to given pfn. - * The cur.zone, cur.block and cur.node_pfn member of @bm are - * updated. - * It walks the radix tree to find the page which contains the bit for - * pfn and returns the bit position in **addr and *bit_nr. + * Find the bit in memory bitmap @bm that corresponds to the given PFN. + * The cur.zone, cur.block and cur.node_pfn members of @bm are updated. + * + * Walk the radix tree to find the page containing the bit that represents @pfn + * and return the position of the bit in @addr and @bit_nr. */ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, void **addr, unsigned int *bit_nr) @@ -658,10 +729,9 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, zone_found: /* - * We have a zone. Now walk the radix tree to find the leave - * node for our pfn. + * We have found the zone. Now walk the radix tree to find the leaf node + * for our PFN. */ - node = bm->cur.node; if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) goto node_found; @@ -754,14 +824,14 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) } /* - * rtree_next_node - Jumps to the next leave node + * rtree_next_node - Jump to the next leaf node. * - * Sets the position to the beginning of the next node in the - * memory bitmap. This is either the next node in the current - * zone's radix tree or the first node in the radix tree of the - * next zone. + * Set the position to the beginning of the next node in the + * memory bitmap. This is either the next node in the current + * zone's radix tree or the first node in the radix tree of the + * next zone. * - * Returns true if there is a next node, false otherwise. + * Return true if there is a next node, false otherwise. */ static bool rtree_next_node(struct memory_bitmap *bm) { @@ -790,14 +860,15 @@ static bool rtree_next_node(struct memory_bitmap *bm) } /** - * memory_bm_rtree_next_pfn - Find the next set bit in the bitmap @bm + * memory_bm_rtree_next_pfn - Find the next set bit in a memory bitmap. + * @bm: Memory bitmap. * - * Starting from the last returned position this function searches - * for the next set bit in the memory bitmap and returns its - * number. If no more bit is set BM_END_OF_MAP is returned. + * Starting from the last returned position this function searches for the next + * set bit in @bm and returns the PFN represented by it. If no more bits are + * set, BM_END_OF_MAP is returned. * - * It is required to run memory_bm_position_reset() before the - * first call to this function. + * It is required to run memory_bm_position_reset() before the first call to + * this function for the given memory bitmap. */ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) { @@ -819,11 +890,10 @@ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) return BM_END_OF_MAP; } -/** - * This structure represents a range of page frames the contents of which - * should not be saved during the suspend. +/* + * This structure represents a range of page frames the contents of which + * should not be saved during hibernation. */ - struct nosave_region { struct list_head list; unsigned long start_pfn; @@ -832,15 +902,42 @@ struct nosave_region { static LIST_HEAD(nosave_regions); +static void recycle_zone_bm_rtree(struct mem_zone_bm_rtree *zone) +{ + struct rtree_node *node; + + list_for_each_entry(node, &zone->nodes, list) + recycle_safe_page(node->data); + + list_for_each_entry(node, &zone->leaves, list) + recycle_safe_page(node->data); +} + +static void memory_bm_recycle(struct memory_bitmap *bm) +{ + struct mem_zone_bm_rtree *zone; + struct linked_page *p_list; + + list_for_each_entry(zone, &bm->zones, list) + recycle_zone_bm_rtree(zone); + + p_list = bm->p_list; + while (p_list) { + struct linked_page *lp = p_list; + + p_list = lp->next; + recycle_safe_page(lp); + } +} + /** - * register_nosave_region - register a range of page frames the contents - * of which should not be saved during the suspend (to be used in the early - * initialization code) + * register_nosave_region - Register a region of unsaveable memory. + * + * Register a range of page frames the contents of which should not be saved + * during hibernation (to be used in the early initialization code). */ - -void __init -__register_nosave_region(unsigned long start_pfn, unsigned long end_pfn, - int use_kmalloc) +void __init __register_nosave_region(unsigned long start_pfn, + unsigned long end_pfn, int use_kmalloc) { struct nosave_region *region; @@ -857,12 +954,13 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn, } } if (use_kmalloc) { - /* during init, this shouldn't fail */ + /* During init, this shouldn't fail */ region = kmalloc(sizeof(struct nosave_region), GFP_KERNEL); BUG_ON(!region); - } else + } else { /* This allocation cannot fail */ region = memblock_virt_alloc(sizeof(struct nosave_region), 0); + } region->start_pfn = start_pfn; region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); @@ -923,10 +1021,12 @@ static void swsusp_unset_page_forbidden(struct page *page) } /** - * mark_nosave_pages - set bits corresponding to the page frames the - * contents of which should not be saved in a given bitmap. + * mark_nosave_pages - Mark pages that should not be saved. + * @bm: Memory bitmap. + * + * Set the bits in @bm that correspond to the page frames the contents of which + * should not be saved. */ - static void mark_nosave_pages(struct memory_bitmap *bm) { struct nosave_region *region; @@ -956,13 +1056,13 @@ static void mark_nosave_pages(struct memory_bitmap *bm) } /** - * create_basic_memory_bitmaps - create bitmaps needed for marking page - * frames that should not be saved and free page frames. The pointers - * forbidden_pages_map and free_pages_map are only modified if everything - * goes well, because we don't want the bits to be used before both bitmaps - * are set up. + * create_basic_memory_bitmaps - Create bitmaps to hold basic page information. + * + * Create bitmaps needed for marking page frames that should not be saved and + * free page frames. The forbidden_pages_map and free_pages_map pointers are + * only modified if everything goes well, because we don't want the bits to be + * touched before both bitmaps are set up. */ - int create_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; @@ -1007,12 +1107,12 @@ int create_basic_memory_bitmaps(void) } /** - * free_basic_memory_bitmaps - free memory bitmaps allocated by - * create_basic_memory_bitmaps(). The auxiliary pointers are necessary - * so that the bitmaps themselves are not referred to while they are being - * freed. + * free_basic_memory_bitmaps - Free memory bitmaps holding basic information. + * + * Free memory bitmaps allocated by create_basic_memory_bitmaps(). The + * auxiliary pointers are necessary so that the bitmaps themselves are not + * referred to while they are being freed. */ - void free_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; @@ -1033,11 +1133,13 @@ void free_basic_memory_bitmaps(void) } /** - * snapshot_additional_pages - estimate the number of additional pages - * be needed for setting up the suspend image data structures for given - * zone (usually the returned value is greater than the exact number) + * snapshot_additional_pages - Estimate the number of extra pages needed. + * @zone: Memory zone to carry out the computation for. + * + * Estimate the number of additional pages needed for setting up a hibernation + * image data structures for @zone (usually, the returned value is greater than + * the exact number). */ - unsigned int snapshot_additional_pages(struct zone *zone) { unsigned int rtree, nodes; @@ -1055,10 +1157,10 @@ unsigned int snapshot_additional_pages(struct zone *zone) #ifdef CONFIG_HIGHMEM /** - * count_free_highmem_pages - compute the total number of free highmem - * pages, system-wide. + * count_free_highmem_pages - Compute the total number of free highmem pages. + * + * The returned number is system-wide. */ - static unsigned int count_free_highmem_pages(void) { struct zone *zone; @@ -1072,11 +1174,12 @@ static unsigned int count_free_highmem_pages(void) } /** - * saveable_highmem_page - Determine whether a highmem page should be - * included in the suspend image. + * saveable_highmem_page - Check if a highmem page is saveable. * - * We should save the page if it isn't Nosave or NosaveFree, or Reserved, - * and it isn't a part of a free chunk of pages. + * Determine whether a highmem page should be included in a hibernation image. + * + * We should save the page if it isn't Nosave or NosaveFree, or Reserved, + * and it isn't part of a free chunk of pages. */ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) { @@ -1102,10 +1205,8 @@ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) } /** - * count_highmem_pages - compute the total number of saveable highmem - * pages. + * count_highmem_pages - Compute the total number of saveable highmem pages. */ - static unsigned int count_highmem_pages(void) { struct zone *zone; @@ -1133,12 +1234,14 @@ static inline void *saveable_highmem_page(struct zone *z, unsigned long p) #endif /* CONFIG_HIGHMEM */ /** - * saveable_page - Determine whether a non-highmem page should be included - * in the suspend image. + * saveable_page - Check if the given page is saveable. * - * We should save the page if it isn't Nosave, and is not in the range - * of pages statically defined as 'unsaveable', and it isn't a part of - * a free chunk of pages. + * Determine whether a non-highmem page should be included in a hibernation + * image. + * + * We should save the page if it isn't Nosave, and is not in the range + * of pages statically defined as 'unsaveable', and it isn't part of + * a free chunk of pages. */ static struct page *saveable_page(struct zone *zone, unsigned long pfn) { @@ -1167,10 +1270,8 @@ static struct page *saveable_page(struct zone *zone, unsigned long pfn) } /** - * count_data_pages - compute the total number of saveable non-highmem - * pages. + * count_data_pages - Compute the total number of saveable non-highmem pages. */ - static unsigned int count_data_pages(void) { struct zone *zone; @@ -1190,7 +1291,8 @@ static unsigned int count_data_pages(void) return n; } -/* This is needed, because copy_page and memcpy are not usable for copying +/* + * This is needed, because copy_page and memcpy are not usable for copying * task structs. */ static inline void do_copy_page(long *dst, long *src) @@ -1201,12 +1303,12 @@ static inline void do_copy_page(long *dst, long *src) *dst++ = *src++; } - /** - * safe_copy_page - check if the page we are going to copy is marked as - * present in the kernel page tables (this always is the case if - * CONFIG_DEBUG_PAGEALLOC is not set and in that case - * kernel_page_present() always returns 'true'). + * safe_copy_page - Copy a page in a safe way. + * + * Check if the page we are going to copy is marked as present in the kernel + * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set + * and in that case kernel_page_present() always returns 'true'). */ static void safe_copy_page(void *dst, struct page *s_page) { @@ -1219,10 +1321,8 @@ static void safe_copy_page(void *dst, struct page *s_page) } } - #ifdef CONFIG_HIGHMEM -static inline struct page * -page_is_saveable(struct zone *zone, unsigned long pfn) +static inline struct page *page_is_saveable(struct zone *zone, unsigned long pfn) { return is_highmem(zone) ? saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn); @@ -1243,7 +1343,8 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) kunmap_atomic(src); } else { if (PageHighMem(d_page)) { - /* Page pointed to by src may contain some kernel + /* + * The page pointed to by src may contain some kernel * data modified by kmap_atomic() */ safe_copy_page(buffer, s_page); @@ -1265,8 +1366,8 @@ static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) } #endif /* CONFIG_HIGHMEM */ -static void -copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm) +static void copy_data_pages(struct memory_bitmap *copy_bm, + struct memory_bitmap *orig_bm) { struct zone *zone; unsigned long pfn; @@ -1315,12 +1416,11 @@ static struct memory_bitmap orig_bm; static struct memory_bitmap copy_bm; /** - * swsusp_free - free pages allocated for the suspend. + * swsusp_free - Free pages allocated for hibernation image. * - * Suspend pages are alocated before the atomic copy is made, so we - * need to release them after the resume. + * Image pages are alocated before snapshot creation, so they need to be + * released after resume. */ - void swsusp_free(void) { unsigned long fb_pfn, fr_pfn; @@ -1351,6 +1451,7 @@ loop: memory_bm_clear_current(forbidden_pages_map); memory_bm_clear_current(free_pages_map); + hibernate_restore_unprotect_page(page_address(page)); __free_page(page); goto loop; } @@ -1362,6 +1463,7 @@ out: buffer = NULL; alloc_normal = 0; alloc_highmem = 0; + hibernate_restore_protection_end(); } /* Helper functions used for the shrinking of memory. */ @@ -1369,7 +1471,7 @@ out: #define GFP_IMAGE (GFP_KERNEL | __GFP_NOWARN) /** - * preallocate_image_pages - Allocate a number of pages for hibernation image + * preallocate_image_pages - Allocate a number of pages for hibernation image. * @nr_pages: Number of page frames to allocate. * @mask: GFP flags to use for the allocation. * @@ -1419,7 +1521,7 @@ static unsigned long preallocate_image_highmem(unsigned long nr_pages) } /** - * __fraction - Compute (an approximation of) x * (multiplier / base) + * __fraction - Compute (an approximation of) x * (multiplier / base). */ static unsigned long __fraction(u64 x, u64 multiplier, u64 base) { @@ -1429,8 +1531,8 @@ static unsigned long __fraction(u64 x, u64 multiplier, u64 base) } static unsigned long preallocate_highmem_fraction(unsigned long nr_pages, - unsigned long highmem, - unsigned long total) + unsigned long highmem, + unsigned long total) { unsigned long alloc = __fraction(nr_pages, highmem, total); @@ -1443,15 +1545,15 @@ static inline unsigned long preallocate_image_highmem(unsigned long nr_pages) } static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages, - unsigned long highmem, - unsigned long total) + unsigned long highmem, + unsigned long total) { return 0; } #endif /* CONFIG_HIGHMEM */ /** - * free_unnecessary_pages - Release preallocated pages not needed for the image + * free_unnecessary_pages - Release preallocated pages not needed for the image. */ static unsigned long free_unnecessary_pages(void) { @@ -1505,7 +1607,7 @@ static unsigned long free_unnecessary_pages(void) } /** - * minimum_image_size - Estimate the minimum acceptable size of an image + * minimum_image_size - Estimate the minimum acceptable size of an image. * @saveable: Number of saveable pages in the system. * * We want to avoid attempting to free too much memory too hard, so estimate the @@ -1525,17 +1627,17 @@ static unsigned long minimum_image_size(unsigned long saveable) unsigned long size; size = global_page_state(NR_SLAB_RECLAIMABLE) - + global_page_state(NR_ACTIVE_ANON) - + global_page_state(NR_INACTIVE_ANON) - + global_page_state(NR_ACTIVE_FILE) - + global_page_state(NR_INACTIVE_FILE) - - global_page_state(NR_FILE_MAPPED); + + global_node_page_state(NR_ACTIVE_ANON) + + global_node_page_state(NR_INACTIVE_ANON) + + global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE) + - global_node_page_state(NR_FILE_MAPPED); return saveable <= size ? 0 : saveable - size; } /** - * hibernate_preallocate_memory - Preallocate memory for hibernation image + * hibernate_preallocate_memory - Preallocate memory for hibernation image. * * To create a hibernation image it is necessary to make a copy of every page * frame in use. We also need a number of page frames to be free during @@ -1708,10 +1810,11 @@ int hibernate_preallocate_memory(void) #ifdef CONFIG_HIGHMEM /** - * count_pages_for_highmem - compute the number of non-highmem pages - * that will be necessary for creating copies of highmem pages. - */ - + * count_pages_for_highmem - Count non-highmem pages needed for copying highmem. + * + * Compute the number of non-highmem pages that will be necessary for creating + * copies of highmem pages. + */ static unsigned int count_pages_for_highmem(unsigned int nr_highmem) { unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem; @@ -1724,15 +1827,12 @@ static unsigned int count_pages_for_highmem(unsigned int nr_highmem) return nr_highmem; } #else -static unsigned int -count_pages_for_highmem(unsigned int nr_highmem) { return 0; } +static unsigned int count_pages_for_highmem(unsigned int nr_highmem) { return 0; } #endif /* CONFIG_HIGHMEM */ /** - * enough_free_mem - Make sure we have enough free memory for the - * snapshot image. + * enough_free_mem - Check if there is enough free memory for the image. */ - static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem) { struct zone *zone; @@ -1751,10 +1851,11 @@ static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem) #ifdef CONFIG_HIGHMEM /** - * get_highmem_buffer - if there are some highmem pages in the suspend - * image, we may need the buffer to copy them and/or load their data. + * get_highmem_buffer - Allocate a buffer for highmem pages. + * + * If there are some highmem pages in the hibernation image, we may need a + * buffer to copy them and/or load their data. */ - static inline int get_highmem_buffer(int safe_needed) { buffer = get_image_page(GFP_ATOMIC | __GFP_COLD, safe_needed); @@ -1762,13 +1863,13 @@ static inline int get_highmem_buffer(int safe_needed) } /** - * alloc_highmem_image_pages - allocate some highmem pages for the image. - * Try to allocate as many pages as needed, but if the number of free - * highmem pages is lesser than that, allocate them all. + * alloc_highmem_image_pages - Allocate some highmem pages for the image. + * + * Try to allocate as many pages as needed, but if the number of free highmem + * pages is less than that, allocate them all. */ - -static inline unsigned int -alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem) +static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm, + unsigned int nr_highmem) { unsigned int to_alloc = count_free_highmem_pages(); @@ -1787,25 +1888,24 @@ alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem) #else static inline int get_highmem_buffer(int safe_needed) { return 0; } -static inline unsigned int -alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; } +static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm, + unsigned int n) { return 0; } #endif /* CONFIG_HIGHMEM */ /** - * swsusp_alloc - allocate memory for the suspend image + * swsusp_alloc - Allocate memory for hibernation image. * - * We first try to allocate as many highmem pages as there are - * saveable highmem pages in the system. If that fails, we allocate - * non-highmem pages for the copies of the remaining highmem ones. + * We first try to allocate as many highmem pages as there are + * saveable highmem pages in the system. If that fails, we allocate + * non-highmem pages for the copies of the remaining highmem ones. * - * In this approach it is likely that the copies of highmem pages will - * also be located in the high memory, because of the way in which - * copy_data_pages() works. + * In this approach it is likely that the copies of highmem pages will + * 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, - unsigned int nr_pages, unsigned int nr_highmem) +static int swsusp_alloc(struct memory_bitmap *orig_bm, + struct memory_bitmap *copy_bm, + unsigned int nr_pages, unsigned int nr_highmem) { if (nr_highmem > 0) { if (get_highmem_buffer(PG_ANY)) @@ -1855,7 +1955,8 @@ asmlinkage __visible int swsusp_save(void) return -ENOMEM; } - /* During allocating of suspend pagedir, new cold pages may appear. + /* + * During allocating of suspend pagedir, new cold pages may appear. * Kill them. */ drain_local_pages(NULL); @@ -1918,12 +2019,14 @@ static int init_header(struct swsusp_info *info) } /** - * pack_pfns - pfns corresponding to the set bits found in the bitmap @bm - * are stored in the array @buf[] (1 page at a time) + * pack_pfns - Prepare PFNs for saving. + * @bm: Memory bitmap. + * @buf: Memory buffer to store the PFNs in. + * + * PFNs corresponding to set bits in @bm are stored in the area of memory + * pointed to by @buf (1 page at a time). */ - -static inline void -pack_pfns(unsigned long *buf, struct memory_bitmap *bm) +static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm) { int j; @@ -1937,22 +2040,21 @@ pack_pfns(unsigned long *buf, struct memory_bitmap *bm) } /** - * snapshot_read_next - used for reading the system memory snapshot. + * snapshot_read_next - Get the address to read the next image page from. + * @handle: Snapshot handle to be used for the reading. * - * On the first call to it @handle should point to a zeroed - * snapshot_handle structure. The structure gets updated and a pointer - * to it should be passed to this function every next time. + * On the first call, @handle should point to a zeroed snapshot_handle + * structure. The structure gets populated then and a pointer to it should be + * passed to this function every next time. * - * On success the function returns a positive number. Then, the caller - * is allowed to read up to the returned number of bytes from the memory - * location computed by the data_of() macro. + * On success, the function returns a positive number. Then, the caller + * is allowed to read up to the returned number of bytes from the memory + * location computed by the data_of() macro. * - * The function returns 0 to indicate the end of data stream condition, - * and a negative number is returned on error. In such cases the - * structure pointed to by @handle is not updated and should not be used - * any more. + * The function returns 0 to indicate the end of the data stream condition, + * and negative numbers are returned on errors. If that happens, the structure + * pointed to by @handle is not updated and should not be used any more. */ - int snapshot_read_next(struct snapshot_handle *handle) { if (handle->cur > nr_meta_pages + nr_copy_pages) @@ -1981,7 +2083,8 @@ int snapshot_read_next(struct snapshot_handle *handle) page = pfn_to_page(memory_bm_next_pfn(©_bm)); if (PageHighMem(page)) { - /* Highmem pages are copied to the buffer, + /* + * Highmem pages are copied to the buffer, * because we can't return with a kmapped * highmem page (we may not be called again). */ @@ -1999,53 +2102,41 @@ int snapshot_read_next(struct snapshot_handle *handle) return PAGE_SIZE; } -/** - * mark_unsafe_pages - mark the pages that cannot be used for storing - * the image during resume, because they conflict with the pages that - * had been used before suspend - */ - -static int mark_unsafe_pages(struct memory_bitmap *bm) +static void duplicate_memory_bitmap(struct memory_bitmap *dst, + struct memory_bitmap *src) { - struct zone *zone; - unsigned long pfn, max_zone_pfn; + unsigned long pfn; - /* Clear page flags */ - for_each_populated_zone(zone) { - max_zone_pfn = zone_end_pfn(zone); - for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) - if (pfn_valid(pfn)) - swsusp_unset_page_free(pfn_to_page(pfn)); + memory_bm_position_reset(src); + pfn = memory_bm_next_pfn(src); + while (pfn != BM_END_OF_MAP) { + memory_bm_set_bit(dst, pfn); + pfn = memory_bm_next_pfn(src); } - - /* Mark pages that correspond to the "original" pfns as "unsafe" */ - memory_bm_position_reset(bm); - do { - pfn = memory_bm_next_pfn(bm); - if (likely(pfn != BM_END_OF_MAP)) { - if (likely(pfn_valid(pfn))) - swsusp_set_page_free(pfn_to_page(pfn)); - else - return -EFAULT; - } - } while (pfn != BM_END_OF_MAP); - - allocated_unsafe_pages = 0; - - return 0; } -static void -duplicate_memory_bitmap(struct memory_bitmap *dst, struct memory_bitmap *src) +/** + * mark_unsafe_pages - Mark pages that were used before hibernation. + * + * Mark the pages that cannot be used for storing the image during restoration, + * because they conflict with the pages that had been used before hibernation. + */ +static void mark_unsafe_pages(struct memory_bitmap *bm) { unsigned long pfn; - memory_bm_position_reset(src); - pfn = memory_bm_next_pfn(src); + /* Clear the "free"/"unsafe" bit for all PFNs */ + memory_bm_position_reset(free_pages_map); + pfn = memory_bm_next_pfn(free_pages_map); while (pfn != BM_END_OF_MAP) { - memory_bm_set_bit(dst, pfn); - pfn = memory_bm_next_pfn(src); + memory_bm_clear_current(free_pages_map); + pfn = memory_bm_next_pfn(free_pages_map); } + + /* Mark pages that correspond to the "original" PFNs as "unsafe" */ + duplicate_memory_bitmap(free_pages_map, bm); + + allocated_unsafe_pages = 0; } static int check_header(struct swsusp_info *info) @@ -2063,11 +2154,9 @@ static int check_header(struct swsusp_info *info) } /** - * load header - check the image header and copy data from it + * load header - Check the image header and copy the data from it. */ - -static int -load_header(struct swsusp_info *info) +static int load_header(struct swsusp_info *info) { int error; @@ -2081,8 +2170,12 @@ load_header(struct swsusp_info *info) } /** - * unpack_orig_pfns - for each element of @buf[] (1 page at a time) set - * the corresponding bit in the memory bitmap @bm + * unpack_orig_pfns - Set bits corresponding to given PFNs in a memory bitmap. + * @bm: Memory bitmap. + * @buf: Area of memory containing the PFNs. + * + * For each element of the array pointed to by @buf (1 page at a time), set the + * corresponding bit in @bm. */ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) { @@ -2095,7 +2188,7 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) /* Extract and buffer page key for data page (s390 only). */ page_key_memorize(buf + j); - if (memory_bm_pfn_present(bm, buf[j])) + if (pfn_valid(buf[j]) && memory_bm_pfn_present(bm, buf[j])) memory_bm_set_bit(bm, buf[j]); else return -EFAULT; @@ -2104,13 +2197,9 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) return 0; } -/* List of "safe" pages that may be used to store data loaded from the suspend - * image - */ -static struct linked_page *safe_pages_list; - #ifdef CONFIG_HIGHMEM -/* struct highmem_pbe is used for creating the list of highmem pages that +/* + * struct highmem_pbe is used for creating the list of highmem pages that * should be restored atomically during the resume from disk, because the page * frames they have occupied before the suspend are in use. */ @@ -2120,7 +2209,8 @@ struct highmem_pbe { struct highmem_pbe *next; }; -/* List of highmem PBEs needed for restoring the highmem pages that were +/* + * List of highmem PBEs needed for restoring the highmem pages that were * allocated before the suspend and included in the suspend image, but have * also been allocated by the "resume" kernel, so their contents cannot be * written directly to their "original" page frames. @@ -2128,11 +2218,11 @@ struct highmem_pbe { static struct highmem_pbe *highmem_pblist; /** - * count_highmem_image_pages - compute the number of highmem pages in the - * suspend image. The bits in the memory bitmap @bm that correspond to the - * image pages are assumed to be set. + * count_highmem_image_pages - Compute the number of highmem pages in the image. + * @bm: Memory bitmap. + * + * The bits in @bm that correspond to image pages are assumed to be set. */ - static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { unsigned long pfn; @@ -2149,24 +2239,25 @@ static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) return cnt; } -/** - * prepare_highmem_image - try to allocate as many highmem pages as - * there are highmem image pages (@nr_highmem_p points to the variable - * containing the number of highmem image pages). The pages that are - * "safe" (ie. will not be overwritten when the suspend image is - * restored) have the corresponding bits set in @bm (it must be - * unitialized). - * - * NOTE: This function should not be called if there are no highmem - * image pages. - */ - static unsigned int safe_highmem_pages; static struct memory_bitmap *safe_highmem_bm; -static int -prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) +/** + * prepare_highmem_image - Allocate memory for loading highmem data from image. + * @bm: Pointer to an uninitialized memory bitmap structure. + * @nr_highmem_p: Pointer to the number of highmem image pages. + * + * Try to allocate as many highmem pages as there are highmem image pages + * (@nr_highmem_p points to the variable containing the number of highmem image + * pages). The pages that are "safe" (ie. will not be overwritten when the + * hibernation image is restored entirely) have the corresponding bits set in + * @bm (it must be unitialized). + * + * NOTE: This function should not be called if there are no highmem image pages. + */ +static int prepare_highmem_image(struct memory_bitmap *bm, + unsigned int *nr_highmem_p) { unsigned int to_alloc; @@ -2201,39 +2292,42 @@ prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) return 0; } +static struct page *last_highmem_page; + /** - * get_highmem_page_buffer - for given highmem image page find the buffer - * that suspend_write_next() should set for its caller to write to. + * get_highmem_page_buffer - Prepare a buffer to store a highmem image page. * - * If the page is to be saved to its "original" page frame or a copy of - * the page is to be made in the highmem, @buffer is returned. Otherwise, - * the copy of the page is to be made in normal memory, so the address of - * the copy is returned. + * For a given highmem image page get a buffer that suspend_write_next() should + * return to its caller to write to. * - * If @buffer is returned, the caller of suspend_write_next() will write - * the page's contents to @buffer, so they will have to be copied to the - * right location on the next call to suspend_write_next() and it is done - * with the help of copy_last_highmem_page(). For this purpose, if - * @buffer is returned, @last_highmem page is set to the page to which - * the data will have to be copied from @buffer. + * If the page is to be saved to its "original" page frame or a copy of + * the page is to be made in the highmem, @buffer is returned. Otherwise, + * the copy of the page is to be made in normal memory, so the address of + * the copy is returned. + * + * If @buffer is returned, the caller of suspend_write_next() will write + * the page's contents to @buffer, so they will have to be copied to the + * right location on the next call to suspend_write_next() and it is done + * with the help of copy_last_highmem_page(). For this purpose, if + * @buffer is returned, @last_highmem_page is set to the page to which + * the data will have to be copied from @buffer. */ - -static struct page *last_highmem_page; - -static void * -get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) +static void *get_highmem_page_buffer(struct page *page, + struct chain_allocator *ca) { struct highmem_pbe *pbe; void *kaddr; if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) { - /* We have allocated the "original" page frame and we can + /* + * We have allocated the "original" page frame and we can * use it directly to store the loaded page. */ last_highmem_page = page; return buffer; } - /* The "original" page frame has not been allocated and we have to + /* + * The "original" page frame has not been allocated and we have to * use a "safe" page frame to store the loaded page. */ pbe = chain_alloc(ca, sizeof(struct highmem_pbe)); @@ -2263,11 +2357,12 @@ get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) } /** - * copy_last_highmem_page - copy the contents of a highmem image from - * @buffer, where the caller of snapshot_write_next() has place them, - * to the right location represented by @last_highmem_page . + * copy_last_highmem_page - Copy most the most recent highmem image page. + * + * Copy the contents of a highmem image from @buffer, where the caller of + * snapshot_write_next() has stored them, to the right location represented by + * @last_highmem_page . */ - static void copy_last_highmem_page(void) { if (last_highmem_page) { @@ -2294,17 +2389,13 @@ static inline void free_highmem_data(void) free_image_page(buffer, PG_UNSAFE_CLEAR); } #else -static unsigned int -count_highmem_image_pages(struct memory_bitmap *bm) { return 0; } +static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { return 0; } -static inline int -prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) -{ - return 0; -} +static inline int prepare_highmem_image(struct memory_bitmap *bm, + unsigned int *nr_highmem_p) { return 0; } -static inline void * -get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) +static inline void *get_highmem_page_buffer(struct page *page, + struct chain_allocator *ca) { return ERR_PTR(-EINVAL); } @@ -2314,27 +2405,27 @@ static inline int last_highmem_page_copied(void) { return 1; } static inline void free_highmem_data(void) {} #endif /* CONFIG_HIGHMEM */ +#define PBES_PER_LINKED_PAGE (LINKED_PAGE_DATA_SIZE / sizeof(struct pbe)) + /** - * prepare_image - use the memory bitmap @bm to mark the pages that will - * be overwritten in the process of restoring the system memory state - * from the suspend image ("unsafe" pages) and allocate memory for the - * image. + * prepare_image - Make room for loading hibernation image. + * @new_bm: Unitialized memory bitmap structure. + * @bm: Memory bitmap with unsafe pages marked. + * + * Use @bm to mark the pages that will be overwritten in the process of + * restoring the system memory state from the suspend image ("unsafe" pages) + * and allocate memory for the image. * - * The idea is to allocate a new memory bitmap first and then allocate - * as many pages as needed for the image data, but not to assign these - * pages to specific tasks initially. Instead, we just mark them as - * allocated and create a lists of "safe" pages that will be used - * later. On systems with high memory a list of "safe" highmem pages is - * also created. + * The idea is to allocate a new memory bitmap first and then allocate + * as many pages as needed for image data, but without specifying what those + * pages will be used for just yet. Instead, we mark them all as allocated and + * create a lists of "safe" pages to be used later. On systems with high + * memory a list of "safe" highmem pages is created too. */ - -#define PBES_PER_LINKED_PAGE (LINKED_PAGE_DATA_SIZE / sizeof(struct pbe)) - -static int -prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) +static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) { unsigned int nr_pages, nr_highmem; - struct linked_page *sp_list, *lp; + struct linked_page *lp; int error; /* If there is no highmem, the buffer will not be necessary */ @@ -2342,9 +2433,7 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) buffer = NULL; nr_highmem = count_highmem_image_pages(bm); - error = mark_unsafe_pages(bm); - if (error) - goto Free; + mark_unsafe_pages(bm); error = memory_bm_create(new_bm, GFP_ATOMIC, PG_SAFE); if (error) @@ -2357,14 +2446,15 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) if (error) goto Free; } - /* Reserve some safe pages for potential later use. + /* + * Reserve some safe pages for potential later use. * * NOTE: This way we make sure there will be enough safe pages for the * chain_alloc() in get_buffer(). It is a bit wasteful, but * nr_copy_pages cannot be greater than 50% of the memory anyway. + * + * nr_copy_pages cannot be less than allocated_unsafe_pages too. */ - sp_list = NULL; - /* nr_copy_pages cannot be lesser than allocated_unsafe_pages */ nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages; nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE); while (nr_pages > 0) { @@ -2373,12 +2463,11 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) error = -ENOMEM; goto Free; } - lp->next = sp_list; - sp_list = lp; + lp->next = safe_pages_list; + safe_pages_list = lp; nr_pages--; } /* Preallocate memory for the image */ - safe_pages_list = NULL; nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages; while (nr_pages > 0) { lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC); @@ -2396,12 +2485,6 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) swsusp_set_page_free(virt_to_page(lp)); nr_pages--; } - /* Free the reserved safe pages so that chain_alloc() can use them */ - while (sp_list) { - lp = sp_list->next; - free_image_page(sp_list, PG_UNSAFE_CLEAR); - sp_list = lp; - } return 0; Free: @@ -2410,10 +2493,11 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) } /** - * get_buffer - compute the address that snapshot_write_next() should - * set for its caller to write to. + * get_buffer - Get the address to store the next image data page. + * + * Get the address that snapshot_write_next() should return to its caller to + * write to. */ - static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) { struct pbe *pbe; @@ -2428,12 +2512,14 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) return get_highmem_page_buffer(page, ca); if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) - /* We have allocated the "original" page frame and we can + /* + * We have allocated the "original" page frame and we can * use it directly to store the loaded page. */ return page_address(page); - /* The "original" page frame has not been allocated and we have to + /* + * The "original" page frame has not been allocated and we have to * use a "safe" page frame to store the loaded page. */ pbe = chain_alloc(ca, sizeof(struct pbe)); @@ -2450,22 +2536,21 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) } /** - * snapshot_write_next - used for writing the system memory snapshot. + * snapshot_write_next - Get the address to store the next image page. + * @handle: Snapshot handle structure to guide the writing. * - * On the first call to it @handle should point to a zeroed - * snapshot_handle structure. The structure gets updated and a pointer - * to it should be passed to this function every next time. + * On the first call, @handle should point to a zeroed snapshot_handle + * structure. The structure gets populated then and a pointer to it should be + * passed to this function every next time. * - * On success the function returns a positive number. Then, the caller - * is allowed to write up to the returned number of bytes to the memory - * location computed by the data_of() macro. + * On success, the function returns a positive number. Then, the caller + * is allowed to write up to the returned number of bytes to the memory + * location computed by the data_of() macro. * - * The function returns 0 to indicate the "end of file" condition, - * and a negative number is returned on error. In such cases the - * structure pointed to by @handle is not updated and should not be used - * any more. + * The function returns 0 to indicate the "end of file" condition. Negative + * numbers are returned on errors, in which cases the structure pointed to by + * @handle is not updated and should not be used any more. */ - int snapshot_write_next(struct snapshot_handle *handle) { static struct chain_allocator ca; @@ -2491,6 +2576,8 @@ int snapshot_write_next(struct snapshot_handle *handle) if (error) return error; + safe_pages_list = NULL; + error = memory_bm_create(©_bm, GFP_ATOMIC, PG_ANY); if (error) return error; @@ -2500,6 +2587,7 @@ int snapshot_write_next(struct snapshot_handle *handle) if (error) return error; + hibernate_restore_protection_begin(); } else if (handle->cur <= nr_meta_pages + 1) { error = unpack_orig_pfns(buffer, ©_bm); if (error) @@ -2522,6 +2610,7 @@ int snapshot_write_next(struct snapshot_handle *handle) copy_last_highmem_page(); /* Restore page key for data page (s390 only). */ page_key_write(handle->buffer); + hibernate_restore_protect_page(handle->buffer); handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); @@ -2533,22 +2622,23 @@ int snapshot_write_next(struct snapshot_handle *handle) } /** - * snapshot_write_finalize - must be called after the last call to - * snapshot_write_next() in case the last page in the image happens - * to be a highmem page and its contents should be stored in the - * highmem. Additionally, it releases the memory that will not be - * used any more. + * snapshot_write_finalize - Complete the loading of a hibernation image. + * + * Must be called after the last call to snapshot_write_next() in case the last + * page in the image happens to be a highmem page and its contents should be + * stored in highmem. Additionally, it recycles bitmap memory that's not + * necessary any more. */ - void snapshot_write_finalize(struct snapshot_handle *handle) { copy_last_highmem_page(); /* Restore page key for data page (s390 only). */ page_key_write(handle->buffer); page_key_free(); - /* Free only if we have loaded the image entirely */ + hibernate_restore_protect_page(handle->buffer); + /* Do that only if we have loaded the image entirely */ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) { - memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR); + memory_bm_recycle(&orig_bm); free_highmem_data(); } } @@ -2561,8 +2651,8 @@ int snapshot_image_loaded(struct snapshot_handle *handle) #ifdef CONFIG_HIGHMEM /* Assumes that @buf is ready and points to a "safe" page */ -static inline void -swap_two_pages_data(struct page *p1, struct page *p2, void *buf) +static inline void swap_two_pages_data(struct page *p1, struct page *p2, + void *buf) { void *kaddr1, *kaddr2; @@ -2576,15 +2666,15 @@ swap_two_pages_data(struct page *p1, struct page *p2, void *buf) } /** - * restore_highmem - for each highmem page that was allocated before - * the suspend and included in the suspend image, and also has been - * allocated by the "resume" kernel swap its current (ie. "before - * resume") contents with the previous (ie. "before suspend") one. + * restore_highmem - Put highmem image pages into their original locations. + * + * For each highmem page that was in use before hibernation and is included in + * the image, and also has been allocated by the "restore" kernel, swap its + * current contents with the previous (ie. "before hibernation") ones. * - * If the resume eventually fails, we can call this function once - * again and restore the "before resume" highmem state. + * If the restore eventually fails, we can call this function once again and + * restore the highmem state as seen by the restore kernel. */ - int restore_highmem(void) { struct highmem_pbe *pbe = highmem_pblist; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 5b70d64b871e..0acab9d7f96f 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -266,16 +266,18 @@ static int suspend_test(int level) */ static int suspend_prepare(suspend_state_t state) { - int error; + int error, nr_calls = 0; if (!sleep_state_supported(state)) return -EPERM; pm_prepare_console(); - error = pm_notifier_call_chain(PM_SUSPEND_PREPARE); - if (error) + error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls); + if (error) { + nr_calls--; goto Finish; + } trace_suspend_resume(TPS("freeze_processes"), 0, true); error = suspend_freeze_processes(); @@ -286,7 +288,7 @@ static int suspend_prepare(suspend_state_t state) suspend_stats.failed_freeze++; dpm_save_failed_step(SUSPEND_FREEZE); Finish: - pm_notifier_call_chain(PM_POST_SUSPEND); + __pm_notifier_call_chain(PM_POST_SUSPEND, nr_calls, NULL); pm_restore_console(); return error; } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 160e1006640d..a3b1e617bcdc 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -261,7 +261,7 @@ static void hib_end_io(struct bio *bio) bio_put(bio); } -static int hib_submit_io(int rw, pgoff_t page_off, void *addr, +static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr, struct hib_bio_batch *hb) { struct page *page = virt_to_page(addr); @@ -271,6 +271,7 @@ static int hib_submit_io(int rw, pgoff_t page_off, void *addr, bio = bio_alloc(__GFP_RECLAIM | __GFP_HIGH, 1); bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9); bio->bi_bdev = hib_resume_bdev; + bio_set_op_attrs(bio, op, op_flags); if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { printk(KERN_ERR "PM: Adding page to bio failed at %llu\n", @@ -283,9 +284,9 @@ static int hib_submit_io(int rw, pgoff_t page_off, void *addr, bio->bi_end_io = hib_end_io; bio->bi_private = hb; atomic_inc(&hb->count); - submit_bio(rw, bio); + submit_bio(bio); } else { - error = submit_bio_wait(rw, bio); + error = submit_bio_wait(bio); bio_put(bio); } @@ -306,7 +307,8 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) { int error; - hib_submit_io(READ_SYNC, swsusp_resume_block, swsusp_header, NULL); + hib_submit_io(REQ_OP_READ, READ_SYNC, swsusp_resume_block, + swsusp_header, NULL); if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) || !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) { memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10); @@ -315,8 +317,8 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) swsusp_header->flags = flags; if (flags & SF_CRC32_MODE) swsusp_header->crc32 = handle->crc32; - error = hib_submit_io(WRITE_SYNC, swsusp_resume_block, - swsusp_header, NULL); + error = hib_submit_io(REQ_OP_WRITE, WRITE_SYNC, + swsusp_resume_block, swsusp_header, NULL); } else { printk(KERN_ERR "PM: Swap header not found!\n"); error = -ENODEV; @@ -348,6 +350,12 @@ static int swsusp_swap_check(void) if (res < 0) blkdev_put(hib_resume_bdev, FMODE_WRITE); + /* + * Update the resume device to the one actually used, + * so the test_resume mode can use it in case it is + * invoked from hibernate() to test the snapshot. + */ + swsusp_resume_device = hib_resume_bdev->bd_dev; return res; } @@ -389,7 +397,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb) } else { src = buf; } - return hib_submit_io(WRITE_SYNC, offset, src, hb); + return hib_submit_io(REQ_OP_WRITE, WRITE_SYNC, offset, src, hb); } static void release_swap_writer(struct swap_map_handle *handle) @@ -992,7 +1000,8 @@ static int get_swap_reader(struct swap_map_handle *handle, return -ENOMEM; } - error = hib_submit_io(READ_SYNC, offset, tmp->map, NULL); + error = hib_submit_io(REQ_OP_READ, READ_SYNC, offset, + tmp->map, NULL); if (error) { release_swap_reader(handle); return error; @@ -1016,7 +1025,7 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf, offset = handle->cur->entries[handle->k]; if (!offset) return -EFAULT; - error = hib_submit_io(READ_SYNC, offset, buf, hb); + error = hib_submit_io(REQ_OP_READ, READ_SYNC, offset, buf, hb); if (error) return error; if (++handle->k >= MAP_PAGE_ENTRIES) { @@ -1525,7 +1534,8 @@ int swsusp_check(void) if (!IS_ERR(hib_resume_bdev)) { set_blocksize(hib_resume_bdev, PAGE_SIZE); clear_page(swsusp_header); - error = hib_submit_io(READ_SYNC, swsusp_resume_block, + error = hib_submit_io(REQ_OP_READ, READ_SYNC, + swsusp_resume_block, swsusp_header, NULL); if (error) goto put; @@ -1533,7 +1543,8 @@ int swsusp_check(void) if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) { memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10); /* Reset swap signature now */ - error = hib_submit_io(WRITE_SYNC, swsusp_resume_block, + error = hib_submit_io(REQ_OP_WRITE, WRITE_SYNC, + swsusp_resume_block, swsusp_header, NULL); } else { error = -EINVAL; @@ -1577,10 +1588,12 @@ int swsusp_unmark(void) { int error; - hib_submit_io(READ_SYNC, swsusp_resume_block, swsusp_header, NULL); + hib_submit_io(REQ_OP_READ, READ_SYNC, swsusp_resume_block, + swsusp_header, NULL); if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) { memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10); - error = hib_submit_io(WRITE_SYNC, swsusp_resume_block, + error = hib_submit_io(REQ_OP_WRITE, WRITE_SYNC, + swsusp_resume_block, swsusp_header, NULL); } else { printk(KERN_ERR "PM: Cannot find swsusp signature!\n"); diff --git a/kernel/power/user.c b/kernel/power/user.c index 526e8911460a..35310b627388 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -47,7 +47,7 @@ atomic_t snapshot_device_available = ATOMIC_INIT(1); static int snapshot_open(struct inode *inode, struct file *filp) { struct snapshot_data *data; - int error; + int error, nr_calls = 0; if (!hibernation_available()) return -EPERM; @@ -74,9 +74,9 @@ static int snapshot_open(struct inode *inode, struct file *filp) swap_type_of(swsusp_resume_device, 0, NULL) : -1; data->mode = O_RDONLY; data->free_bitmaps = false; - error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); + error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls); if (error) - pm_notifier_call_chain(PM_POST_HIBERNATION); + __pm_notifier_call_chain(PM_POST_HIBERNATION, --nr_calls, NULL); } else { /* * Resuming. We may need to wait for the image device to @@ -86,13 +86,15 @@ static int snapshot_open(struct inode *inode, struct file *filp) data->swap = -1; data->mode = O_WRONLY; - error = pm_notifier_call_chain(PM_RESTORE_PREPARE); + error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls); if (!error) { error = create_basic_memory_bitmaps(); data->free_bitmaps = !error; - } + } else + nr_calls--; + if (error) - pm_notifier_call_chain(PM_POST_RESTORE); + __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL); } if (error) atomic_inc(&snapshot_device_available); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 60cdf6386763..eea6dbc2d8cf 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -26,7 +26,6 @@ #include <linux/nmi.h> #include <linux/module.h> #include <linux/moduleparam.h> -#include <linux/interrupt.h> /* For in_interrupt() */ #include <linux/delay.h> #include <linux/smp.h> #include <linux/security.h> @@ -48,7 +47,7 @@ #include <linux/uio.h> #include <asm/uaccess.h> -#include <asm-generic/sections.h> +#include <asm/sections.h> #define CREATE_TRACE_POINTS #include <trace/events/printk.h> @@ -86,6 +85,111 @@ static struct lockdep_map console_lock_dep_map = { }; #endif +enum devkmsg_log_bits { + __DEVKMSG_LOG_BIT_ON = 0, + __DEVKMSG_LOG_BIT_OFF, + __DEVKMSG_LOG_BIT_LOCK, +}; + +enum devkmsg_log_masks { + DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON), + DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF), + DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK), +}; + +/* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */ +#define DEVKMSG_LOG_MASK_DEFAULT 0 + +static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; + +static int __control_devkmsg(char *str) +{ + if (!str) + return -EINVAL; + + if (!strncmp(str, "on", 2)) { + devkmsg_log = DEVKMSG_LOG_MASK_ON; + return 2; + } else if (!strncmp(str, "off", 3)) { + devkmsg_log = DEVKMSG_LOG_MASK_OFF; + return 3; + } else if (!strncmp(str, "ratelimit", 9)) { + devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; + return 9; + } + return -EINVAL; +} + +static int __init control_devkmsg(char *str) +{ + if (__control_devkmsg(str) < 0) + return 1; + + /* + * Set sysctl string accordingly: + */ + if (devkmsg_log == DEVKMSG_LOG_MASK_ON) { + memset(devkmsg_log_str, 0, DEVKMSG_STR_MAX_SIZE); + strncpy(devkmsg_log_str, "on", 2); + } else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) { + memset(devkmsg_log_str, 0, DEVKMSG_STR_MAX_SIZE); + strncpy(devkmsg_log_str, "off", 3); + } + /* else "ratelimit" which is set by default. */ + + /* + * Sysctl cannot change it anymore. The kernel command line setting of + * this parameter is to force the setting to be permanent throughout the + * runtime of the system. This is a precation measure against userspace + * trying to be a smarta** and attempting to change it up on us. + */ + devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; + + return 0; +} +__setup("printk.devkmsg=", control_devkmsg); + +char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; + +int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + char old_str[DEVKMSG_STR_MAX_SIZE]; + unsigned int old; + int err; + + if (write) { + if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK) + return -EINVAL; + + old = devkmsg_log; + strncpy(old_str, devkmsg_log_str, DEVKMSG_STR_MAX_SIZE); + } + + err = proc_dostring(table, write, buffer, lenp, ppos); + if (err) + return err; + + if (write) { + err = __control_devkmsg(devkmsg_log_str); + + /* + * Do not accept an unknown string OR a known string with + * trailing crap... + */ + if (err < 0 || (err + 1 != *lenp)) { + + /* ... and restore old setting. */ + devkmsg_log = old; + strncpy(devkmsg_log_str, old_str, DEVKMSG_STR_MAX_SIZE); + + return -EINVAL; + } + } + + return 0; +} + /* * Number of registered extended console drivers. * @@ -614,6 +718,7 @@ struct devkmsg_user { u64 seq; u32 idx; enum log_flags prev; + struct ratelimit_state rs; struct mutex lock; char buf[CONSOLE_EXT_LOG_MAX]; }; @@ -623,11 +728,24 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) char *buf, *line; int level = default_message_loglevel; int facility = 1; /* LOG_USER */ + struct file *file = iocb->ki_filp; + struct devkmsg_user *user = file->private_data; size_t len = iov_iter_count(from); ssize_t ret = len; - if (len > LOG_LINE_MAX) + if (!user || len > LOG_LINE_MAX) return -EINVAL; + + /* Ignore when user logging is disabled. */ + if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) + return len; + + /* Ratelimit when not explicitly enabled. */ + if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) { + if (!___ratelimit(&user->rs, current->comm)) + return ret; + } + buf = kmalloc(len+1, GFP_KERNEL); if (buf == NULL) return -ENOMEM; @@ -800,19 +918,24 @@ static int devkmsg_open(struct inode *inode, struct file *file) struct devkmsg_user *user; int err; - /* write-only does not need any file context */ - if ((file->f_flags & O_ACCMODE) == O_WRONLY) - return 0; + if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) + return -EPERM; - err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, - SYSLOG_FROM_READER); - if (err) - return err; + /* write-only does not need any file context */ + if ((file->f_flags & O_ACCMODE) != O_WRONLY) { + err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, + SYSLOG_FROM_READER); + if (err) + return err; + } user = kmalloc(sizeof(struct devkmsg_user), GFP_KERNEL); if (!user) return -ENOMEM; + ratelimit_default_init(&user->rs); + ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE); + mutex_init(&user->lock); raw_spin_lock_irq(&logbuf_lock); @@ -831,6 +954,8 @@ static int devkmsg_release(struct inode *inode, struct file *file) if (!user) return 0; + ratelimit_state_exit(&user->rs); + mutex_destroy(&user->lock); kfree(user); return 0; @@ -986,6 +1111,11 @@ module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting (prints all kernel messages to the console)"); +static bool suppress_message_printing(int level) +{ + return (level >= console_loglevel && !ignore_loglevel); +} + #ifdef CONFIG_BOOT_PRINTK_DELAY static int boot_delay; /* msecs delay after each printk during bootup */ @@ -1015,7 +1145,7 @@ static void boot_delay_msec(int level) unsigned long timeout; if ((boot_delay == 0 || system_state != SYSTEM_BOOTING) - || (level >= console_loglevel && !ignore_loglevel)) { + || suppress_message_printing(level)) { return; } @@ -1439,8 +1569,6 @@ static void call_console_drivers(int level, trace_console(text, len); - if (level >= console_loglevel && !ignore_loglevel) - return; if (!console_drivers) return; @@ -1888,6 +2016,7 @@ static void call_console_drivers(int level, static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev, bool syslog, char *buf, size_t size) { return 0; } static size_t cont_print_text(char *text, size_t size) { return 0; } +static bool suppress_message_printing(int level) { return false; } /* Still needs to be defined for users */ DEFINE_PER_CPU(printk_func_t, printk_func); @@ -2167,6 +2296,13 @@ static void console_cont_flush(char *text, size_t size) if (!cont.len) goto out; + if (suppress_message_printing(cont.level)) { + cont.cons = cont.len; + if (cont.flushed) + cont.len = 0; + goto out; + } + /* * We still queue earlier records, likely because the console was * busy. The earlier ones need to be printed before this one, we @@ -2270,10 +2406,13 @@ skip: break; msg = log_from_idx(console_idx); - if (msg->flags & LOG_NOCONS) { + level = msg->level; + if ((msg->flags & LOG_NOCONS) || + suppress_message_printing(level)) { /* * Skip record we have buffered and already printed - * directly to the console when we received it. + * directly to the console when we received it, and + * record that has level above the console loglevel. */ console_idx = log_next(console_idx); console_seq++; @@ -2287,7 +2426,6 @@ skip: goto skip; } - level = msg->level; len += msg_print_text(msg, console_prev, false, text + len, sizeof(text) - len); if (nr_ext_console_drivers) { @@ -3177,9 +3315,8 @@ void show_regs_print_info(const char *log_lvl) { dump_stack_print_info(log_lvl); - printk("%stask: %p ti: %p task.ti: %p\n", - log_lvl, current, current_thread_info(), - task_thread_info(current)); + printk("%stask: %p task.stack: %p\n", + log_lvl, current, task_stack_page(current)); } #endif diff --git a/kernel/profile.c b/kernel/profile.c index c2199e9901c9..2dbccf2d806c 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -328,68 +328,57 @@ out: put_cpu(); } -static int profile_cpu_callback(struct notifier_block *info, - unsigned long action, void *__cpu) +static int profile_dead_cpu(unsigned int cpu) { - int node, cpu = (unsigned long)__cpu; struct page *page; + int i; - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - node = cpu_to_mem(cpu); - per_cpu(cpu_profile_flip, cpu) = 0; - if (!per_cpu(cpu_profile_hits, cpu)[1]) { - page = __alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO, - 0); - if (!page) - return notifier_from_errno(-ENOMEM); - per_cpu(cpu_profile_hits, cpu)[1] = page_address(page); - } - if (!per_cpu(cpu_profile_hits, cpu)[0]) { - page = __alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO, - 0); - if (!page) - goto out_free; - per_cpu(cpu_profile_hits, cpu)[0] = page_address(page); - } - break; -out_free: - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]); - per_cpu(cpu_profile_hits, cpu)[1] = NULL; - __free_page(page); - return notifier_from_errno(-ENOMEM); - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - if (prof_cpu_mask != NULL) - cpumask_set_cpu(cpu, prof_cpu_mask); - break; - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - if (prof_cpu_mask != NULL) - cpumask_clear_cpu(cpu, prof_cpu_mask); - if (per_cpu(cpu_profile_hits, cpu)[0]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]); - per_cpu(cpu_profile_hits, cpu)[0] = NULL; + if (prof_cpu_mask != NULL) + cpumask_clear_cpu(cpu, prof_cpu_mask); + + for (i = 0; i < 2; i++) { + if (per_cpu(cpu_profile_hits, cpu)[i]) { + page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]); + per_cpu(cpu_profile_hits, cpu)[i] = NULL; __free_page(page); } - if (per_cpu(cpu_profile_hits, cpu)[1]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]); - per_cpu(cpu_profile_hits, cpu)[1] = NULL; - __free_page(page); + } + return 0; +} + +static int profile_prepare_cpu(unsigned int cpu) +{ + int i, node = cpu_to_mem(cpu); + struct page *page; + + per_cpu(cpu_profile_flip, cpu) = 0; + + for (i = 0; i < 2; i++) { + if (per_cpu(cpu_profile_hits, cpu)[i]) + continue; + + page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!page) { + profile_dead_cpu(cpu); + return -ENOMEM; } - break; + per_cpu(cpu_profile_hits, cpu)[i] = page_address(page); + } - return NOTIFY_OK; + return 0; +} + +static int profile_online_cpu(unsigned int cpu) +{ + if (prof_cpu_mask != NULL) + cpumask_set_cpu(cpu, prof_cpu_mask); + + return 0; } + #else /* !CONFIG_SMP */ #define profile_flip_buffers() do { } while (0) #define profile_discard_flip_buffers() do { } while (0) -#define profile_cpu_callback NULL static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { @@ -531,83 +520,43 @@ static const struct file_operations proc_profile_operations = { .llseek = default_llseek, }; -#ifdef CONFIG_SMP -static void profile_nop(void *unused) -{ -} - -static int create_hash_tables(void) +int __ref create_proc_profile(void) { - int cpu; - - for_each_online_cpu(cpu) { - int node = cpu_to_mem(cpu); - struct page *page; - - page = __alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - 0); - if (!page) - goto out_cleanup; - per_cpu(cpu_profile_hits, cpu)[1] - = (struct profile_hit *)page_address(page); - page = __alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - 0); - if (!page) - goto out_cleanup; - per_cpu(cpu_profile_hits, cpu)[0] - = (struct profile_hit *)page_address(page); - } - return 0; -out_cleanup: - prof_on = 0; - smp_mb(); - on_each_cpu(profile_nop, NULL, 1); - for_each_online_cpu(cpu) { - struct page *page; - - if (per_cpu(cpu_profile_hits, cpu)[0]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]); - per_cpu(cpu_profile_hits, cpu)[0] = NULL; - __free_page(page); - } - if (per_cpu(cpu_profile_hits, cpu)[1]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]); - per_cpu(cpu_profile_hits, cpu)[1] = NULL; - __free_page(page); - } - } - return -1; -} -#else -#define create_hash_tables() ({ 0; }) + struct proc_dir_entry *entry; +#ifdef CONFIG_SMP + enum cpuhp_state online_state; #endif -int __ref create_proc_profile(void) /* false positive from hotcpu_notifier */ -{ - struct proc_dir_entry *entry; int err = 0; if (!prof_on) return 0; - - cpu_notifier_register_begin(); - - if (create_hash_tables()) { - err = -ENOMEM; - goto out; - } - +#ifdef CONFIG_SMP + err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE", + profile_prepare_cpu, profile_dead_cpu); + if (err) + return err; + + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PROFILE_ONLINE", + profile_online_cpu, NULL); + if (err < 0) + goto err_state_prep; + online_state = err; + err = 0; +#endif entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &proc_profile_operations); if (!entry) - goto out; + goto err_state_onl; proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); - __hotcpu_notifier(profile_cpu_callback, 0); -out: - cpu_notifier_register_done(); + return err; +err_state_onl: +#ifdef CONFIG_SMP + cpuhp_remove_state(online_state); +err_state_prep: + cpuhp_remove_state(CPUHP_PROFILE_PREPARE); +#endif return err; } subsys_initcall(create_proc_profile); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index d49bfa1e53e6..1d3b7665d0be 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -585,8 +585,8 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data) return -EINVAL; if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { - if (!config_enabled(CONFIG_CHECKPOINT_RESTORE) || - !config_enabled(CONFIG_SECCOMP)) + if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || + !IS_ENABLED(CONFIG_SECCOMP)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index f433959e9322..5d80925e7fc8 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1073,11 +1073,11 @@ EXPORT_SYMBOL_GPL(rcu_is_watching); * offline to continue to use RCU for one jiffy after marking itself * offline in the cpu_online_mask. This leniency is necessary given the * non-atomic nature of the online and offline processing, for example, - * the fact that a CPU enters the scheduler after completing the CPU_DYING - * notifiers. + * the fact that a CPU enters the scheduler after completing the teardown + * of the CPU. * - * This is also why RCU internally marks CPUs online during the - * CPU_UP_PREPARE phase and offline during the CPU_DEAD phase. + * This is also why RCU internally marks CPUs online during in the + * preparation phase and offline after the CPU has been taken down. * * Disable checking if in an NMI handler because we cannot safely report * errors from NMI handlers anyway. @@ -3806,12 +3806,58 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } -static void rcu_prepare_cpu(int cpu) +int rcutree_prepare_cpu(unsigned int cpu) { struct rcu_state *rsp; for_each_rcu_flavor(rsp) rcu_init_percpu_data(cpu, rsp); + + rcu_prepare_kthreads(cpu); + rcu_spawn_all_nocb_kthreads(cpu); + + return 0; +} + +static void rcutree_affinity_setting(unsigned int cpu, int outgoing) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); + + rcu_boost_kthread_setaffinity(rdp->mynode, outgoing); +} + +int rcutree_online_cpu(unsigned int cpu) +{ + sync_sched_exp_online_cleanup(cpu); + rcutree_affinity_setting(cpu, -1); + return 0; +} + +int rcutree_offline_cpu(unsigned int cpu) +{ + rcutree_affinity_setting(cpu, cpu); + return 0; +} + + +int rcutree_dying_cpu(unsigned int cpu) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_cpu(rsp); + return 0; +} + +int rcutree_dead_cpu(unsigned int cpu) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + rcu_cleanup_dead_cpu(cpu, rsp); + do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu)); + } + return 0; } #ifdef CONFIG_HOTPLUG_CPU @@ -3851,52 +3897,6 @@ void rcu_report_dead(unsigned int cpu) } #endif -/* - * Handle CPU online/offline notification events. - */ -int rcu_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - long cpu = (long)hcpu; - struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); - struct rcu_node *rnp = rdp->mynode; - struct rcu_state *rsp; - - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - rcu_prepare_cpu(cpu); - rcu_prepare_kthreads(cpu); - rcu_spawn_all_nocb_kthreads(cpu); - break; - case CPU_ONLINE: - case CPU_DOWN_FAILED: - sync_sched_exp_online_cleanup(cpu); - rcu_boost_kthread_setaffinity(rnp, -1); - break; - case CPU_DOWN_PREPARE: - rcu_boost_kthread_setaffinity(rnp, cpu); - break; - case CPU_DYING: - case CPU_DYING_FROZEN: - for_each_rcu_flavor(rsp) - rcu_cleanup_dying_cpu(rsp); - break; - case CPU_DEAD: - case CPU_DEAD_FROZEN: - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - for_each_rcu_flavor(rsp) { - rcu_cleanup_dead_cpu(cpu, rsp); - do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu)); - } - break; - default: - break; - } - return NOTIFY_OK; -} - static int rcu_pm_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -4208,10 +4208,9 @@ void __init rcu_init(void) * this is called early in boot, before either interrupts * or the scheduler are operational. */ - cpu_notifier(rcu_cpu_notify, 0); pm_notifier(rcu_pm_notify, 0); for_each_online_cpu(cpu) - rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu); + rcutree_prepare_cpu(cpu); } #include "tree_exp.h" diff --git a/kernel/relay.c b/kernel/relay.c index 04d7cf3ef8cf..d797502140b9 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -451,6 +451,13 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) if (!dentry) goto free_buf; relay_set_buf_dentry(buf, dentry); + } else { + /* Only retrieve global info, nothing more, nothing less */ + dentry = chan->cb->create_buf_file(NULL, NULL, + S_IRUSR, buf, + &chan->is_global); + if (WARN_ON(dentry)) + goto free_buf; } buf->cpu = cpu; @@ -562,6 +569,10 @@ static int relay_hotcpu_callback(struct notifier_block *nb, * attributes specified. The created channel buffer files * will be named base_filename0...base_filenameN-1. File * permissions will be %S_IRUSR. + * + * If opening a buffer (@parent = NULL) that you later wish to register + * in a filesystem, call relay_late_setup_files() once the @parent dentry + * is available. */ struct rchan *relay_open(const char *base_filename, struct dentry *parent, @@ -640,8 +651,12 @@ static void __relay_set_buf_dentry(void *info) * * Returns 0 if successful, non-zero otherwise. * - * Use to setup files for a previously buffer-only channel. - * Useful to do early tracing in kernel, before VFS is up, for example. + * Use to setup files for a previously buffer-only channel created + * by relay_open() with a NULL parent dentry. + * + * For example, this is useful for perfomring early tracing in kernel, + * before VFS is up and then exposing the early results once the dentry + * is available. */ int relay_late_setup_files(struct rchan *chan, const char *base_filename, @@ -666,6 +681,20 @@ int relay_late_setup_files(struct rchan *chan, } chan->has_base_filename = 1; chan->parent = parent; + + if (chan->is_global) { + err = -EINVAL; + if (!WARN_ON_ONCE(!chan->buf[0])) { + dentry = relay_create_buf_file(chan, chan->buf[0], 0); + if (dentry && !WARN_ON_ONCE(!chan->is_global)) { + relay_set_buf_dentry(chan->buf[0], dentry); + err = 0; + } + } + mutex_unlock(&relay_channels_mutex); + return err; + } + curr_cpu = get_cpu(); /* * The CPU hotplug notifier ran before us and created buffers with @@ -706,6 +735,7 @@ int relay_late_setup_files(struct rchan *chan, return err; } +EXPORT_SYMBOL_GPL(relay_late_setup_files); /** * relay_switch_subbuf - switch to a new sub-buffer diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 14c4aa25cc45..a84641b222c1 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -47,6 +47,8 @@ struct sugov_cpu { struct update_util_data update_util; struct sugov_policy *sg_policy; + unsigned int cached_raw_freq; + /* The fields below are only needed when sharing a policy. */ unsigned long util; unsigned long max; @@ -106,7 +108,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, /** * get_next_freq - Compute a new frequency for a given cpufreq policy. - * @policy: cpufreq policy object to compute the new frequency for. + * @sg_cpu: schedutil cpu object to compute the new frequency for. * @util: Current CPU utilization. * @max: CPU capacity. * @@ -121,14 +123,25 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, * next_freq = C * curr_freq * util_raw / max * * Take C = 1.25 for the frequency tipping point at (util / max) = 0.8. + * + * The lowest driver-supported frequency which is equal or greater than the raw + * next_freq (as calculated above) is returned, subject to policy min/max and + * cpufreq driver limitations. */ -static unsigned int get_next_freq(struct cpufreq_policy *policy, - unsigned long util, unsigned long max) +static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util, + unsigned long max) { + struct sugov_policy *sg_policy = sg_cpu->sg_policy; + struct cpufreq_policy *policy = sg_policy->policy; unsigned int freq = arch_scale_freq_invariant() ? policy->cpuinfo.max_freq : policy->cur; - return (freq + (freq >> 2)) * util / max; + freq = (freq + (freq >> 2)) * util / max; + + if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX) + return sg_policy->next_freq; + sg_cpu->cached_raw_freq = freq; + return cpufreq_driver_resolve_freq(policy, freq); } static void sugov_update_single(struct update_util_data *hook, u64 time, @@ -143,13 +156,14 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, return; next_f = util == ULONG_MAX ? policy->cpuinfo.max_freq : - get_next_freq(policy, util, max); + get_next_freq(sg_cpu, util, max); sugov_update_commit(sg_policy, time, next_f); } -static unsigned int sugov_next_freq_shared(struct sugov_policy *sg_policy, +static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, unsigned long util, unsigned long max) { + struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; unsigned int max_f = policy->cpuinfo.max_freq; u64 last_freq_update_time = sg_policy->last_freq_update_time; @@ -189,7 +203,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_policy *sg_policy, } } - return get_next_freq(policy, util, max); + return get_next_freq(sg_cpu, util, max); } static void sugov_update_shared(struct update_util_data *hook, u64 time, @@ -206,7 +220,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, sg_cpu->last_update = time; if (sugov_should_update_freq(sg_policy, time)) { - next_f = sugov_next_freq_shared(sg_policy, util, max); + next_f = sugov_next_freq_shared(sg_cpu, util, max); sugov_update_commit(sg_policy, time, next_f); } @@ -394,7 +408,7 @@ static int sugov_init(struct cpufreq_policy *policy) return ret; } -static int sugov_exit(struct cpufreq_policy *policy) +static void sugov_exit(struct cpufreq_policy *policy) { struct sugov_policy *sg_policy = policy->governor_data; struct sugov_tunables *tunables = sg_policy->tunables; @@ -412,7 +426,6 @@ static int sugov_exit(struct cpufreq_policy *policy) mutex_unlock(&global_tunables_lock); sugov_policy_free(sg_policy); - return 0; } static int sugov_start(struct cpufreq_policy *policy) @@ -434,6 +447,7 @@ static int sugov_start(struct cpufreq_policy *policy) sg_cpu->util = ULONG_MAX; sg_cpu->max = 0; sg_cpu->last_update = 0; + sg_cpu->cached_raw_freq = 0; cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, sugov_update_shared); } else { @@ -444,7 +458,7 @@ static int sugov_start(struct cpufreq_policy *policy) return 0; } -static int sugov_stop(struct cpufreq_policy *policy) +static void sugov_stop(struct cpufreq_policy *policy) { struct sugov_policy *sg_policy = policy->governor_data; unsigned int cpu; @@ -456,53 +470,29 @@ static int sugov_stop(struct cpufreq_policy *policy) irq_work_sync(&sg_policy->irq_work); cancel_work_sync(&sg_policy->work); - return 0; } -static int sugov_limits(struct cpufreq_policy *policy) +static void sugov_limits(struct cpufreq_policy *policy) { struct sugov_policy *sg_policy = policy->governor_data; if (!policy->fast_switch_enabled) { mutex_lock(&sg_policy->work_lock); - - if (policy->max < policy->cur) - __cpufreq_driver_target(policy, policy->max, - CPUFREQ_RELATION_H); - else if (policy->min > policy->cur) - __cpufreq_driver_target(policy, policy->min, - CPUFREQ_RELATION_L); - + cpufreq_policy_apply_limits(policy); mutex_unlock(&sg_policy->work_lock); } sg_policy->need_freq_update = true; - return 0; -} - -int sugov_governor(struct cpufreq_policy *policy, unsigned int event) -{ - if (event == CPUFREQ_GOV_POLICY_INIT) { - return sugov_init(policy); - } else if (policy->governor_data) { - switch (event) { - case CPUFREQ_GOV_POLICY_EXIT: - return sugov_exit(policy); - case CPUFREQ_GOV_START: - return sugov_start(policy); - case CPUFREQ_GOV_STOP: - return sugov_stop(policy); - case CPUFREQ_GOV_LIMITS: - return sugov_limits(policy); - } - } - return -EINVAL; } static struct cpufreq_governor schedutil_gov = { .name = "schedutil", - .governor = sugov_governor, .owner = THIS_MODULE, + .init = sugov_init, + .exit = sugov_exit, + .start = sugov_start, + .stop = sugov_stop, + .limits = sugov_limits, }; static int __init sugov_module_init(void) diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index ea0f6f31a244..1934f658c036 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -503,16 +503,6 @@ void account_process_tick(struct task_struct *p, int user_tick) } /* - * Account multiple ticks of steal time. - * @p: the process from which the cpu time has been stolen - * @ticks: number of stolen ticks - */ -void account_steal_ticks(unsigned long ticks) -{ - account_steal_time(jiffies_to_cputime(ticks)); -} - -/* * Account multiple ticks of idle time. * @ticks: number of stolen ticks */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 7002796f14a4..ef6c6c3f9d8a 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -173,7 +173,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) * * Returns valid seccomp BPF response codes. */ -static u32 seccomp_run_filters(struct seccomp_data *sd) +static u32 seccomp_run_filters(const struct seccomp_data *sd) { struct seccomp_data sd_local; u32 ret = SECCOMP_RET_ALLOW; @@ -347,7 +347,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) { struct seccomp_filter *sfilter; int ret; - const bool save_orig = config_enabled(CONFIG_CHECKPOINT_RESTORE); + const bool save_orig = IS_ENABLED(CONFIG_CHECKPOINT_RESTORE); if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) return ERR_PTR(-EINVAL); @@ -542,7 +542,7 @@ void secure_computing_strict(int this_syscall) { int mode = current->seccomp.mode; - if (config_enabled(CONFIG_CHECKPOINT_RESTORE) && + if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) && unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) return; @@ -554,20 +554,10 @@ void secure_computing_strict(int this_syscall) BUG(); } #else -int __secure_computing(void) -{ - u32 phase1_result = seccomp_phase1(NULL); - - if (likely(phase1_result == SECCOMP_PHASE1_OK)) - return 0; - else if (likely(phase1_result == SECCOMP_PHASE1_SKIP)) - return -1; - else - return seccomp_phase2(phase1_result); -} #ifdef CONFIG_SECCOMP_FILTER -static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd) +static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, + const bool recheck_after_trace) { u32 filter_ret, action; int data; @@ -599,10 +589,46 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd) goto skip; case SECCOMP_RET_TRACE: - return filter_ret; /* Save the rest for phase 2. */ + /* We've been put in this state by the ptracer already. */ + if (recheck_after_trace) + return 0; + + /* ENOSYS these calls if there is no tracer attached. */ + if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { + syscall_set_return_value(current, + task_pt_regs(current), + -ENOSYS, 0); + goto skip; + } + + /* Allow the BPF to provide the event message */ + ptrace_event(PTRACE_EVENT_SECCOMP, data); + /* + * The delivery of a fatal signal during event + * notification may silently skip tracer notification. + * Terminating the task now avoids executing a system + * call that may not be intended. + */ + if (fatal_signal_pending(current)) + do_exit(SIGSYS); + /* Check if the tracer forced the syscall to be skipped. */ + this_syscall = syscall_get_nr(current, task_pt_regs(current)); + if (this_syscall < 0) + goto skip; + + /* + * Recheck the syscall, since it may have changed. This + * intentionally uses a NULL struct seccomp_data to force + * a reload of all registers. This does not goto skip since + * a skip would have already been reported. + */ + if (__seccomp_filter(this_syscall, NULL, true)) + return -1; + + return 0; case SECCOMP_RET_ALLOW: - return SECCOMP_PHASE1_OK; + return 0; case SECCOMP_RET_KILL: default: @@ -614,96 +640,38 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd) skip: audit_seccomp(this_syscall, 0, action); - return SECCOMP_PHASE1_SKIP; + return -1; +} +#else +static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, + const bool recheck_after_trace) +{ + BUG(); } #endif -/** - * seccomp_phase1() - run fast path seccomp checks on the current syscall - * @arg sd: The seccomp_data or NULL - * - * This only reads pt_regs via the syscall_xyz helpers. The only change - * it will make to pt_regs is via syscall_set_return_value, and it will - * only do that if it returns SECCOMP_PHASE1_SKIP. - * - * If sd is provided, it will not read pt_regs at all. - * - * It may also call do_exit or force a signal; these actions must be - * safe. - * - * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should - * be processed normally. - * - * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be - * invoked. In this case, seccomp_phase1 will have set the return value - * using syscall_set_return_value. - * - * If it returns anything else, then the return value should be passed - * to seccomp_phase2 from a context in which ptrace hooks are safe. - */ -u32 seccomp_phase1(struct seccomp_data *sd) +int __secure_computing(const struct seccomp_data *sd) { int mode = current->seccomp.mode; - int this_syscall = sd ? sd->nr : - syscall_get_nr(current, task_pt_regs(current)); + int this_syscall; - if (config_enabled(CONFIG_CHECKPOINT_RESTORE) && + if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) && unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) - return SECCOMP_PHASE1_OK; + return 0; + + this_syscall = sd ? sd->nr : + syscall_get_nr(current, task_pt_regs(current)); switch (mode) { case SECCOMP_MODE_STRICT: __secure_computing_strict(this_syscall); /* may call do_exit */ - return SECCOMP_PHASE1_OK; -#ifdef CONFIG_SECCOMP_FILTER + return 0; case SECCOMP_MODE_FILTER: - return __seccomp_phase1_filter(this_syscall, sd); -#endif + return __seccomp_filter(this_syscall, sd, false); default: BUG(); } } - -/** - * seccomp_phase2() - finish slow path seccomp work for the current syscall - * @phase1_result: The return value from seccomp_phase1() - * - * This must be called from a context in which ptrace hooks can be used. - * - * Returns 0 if the syscall should be processed or -1 to skip the syscall. - */ -int seccomp_phase2(u32 phase1_result) -{ - struct pt_regs *regs = task_pt_regs(current); - u32 action = phase1_result & SECCOMP_RET_ACTION; - int data = phase1_result & SECCOMP_RET_DATA; - - BUG_ON(action != SECCOMP_RET_TRACE); - - audit_seccomp(syscall_get_nr(current, regs), 0, action); - - /* Skip these calls if there is no tracer. */ - if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { - syscall_set_return_value(current, regs, - -ENOSYS, 0); - return -1; - } - - /* Allow the BPF to provide the event message */ - ptrace_event(PTRACE_EVENT_SECCOMP, data); - /* - * The delivery of a fatal signal during event - * notification may silently skip tracer notification. - * Terminating the task now avoids executing a system - * call that may not be intended. - */ - if (fatal_signal_pending(current)) - do_exit(SIGSYS); - if (syscall_get_nr(current, regs) < 0) - return -1; /* Explicit request to skip. */ - - return 0; -} #endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */ long prctl_get_seccomp(void) diff --git a/kernel/smp.c b/kernel/smp.c index 36552beed397..3aa642d39c03 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -33,69 +33,54 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static void flush_smp_call_function_queue(bool warn_cpu_offline); -static int -hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) +int smpcfd_prepare_cpu(unsigned int cpu) { - long cpu = (long)hcpu; struct call_function_data *cfd = &per_cpu(cfd_data, cpu); - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, - cpu_to_node(cpu))) - return notifier_from_errno(-ENOMEM); - cfd->csd = alloc_percpu(struct call_single_data); - if (!cfd->csd) { - free_cpumask_var(cfd->cpumask); - return notifier_from_errno(-ENOMEM); - } - break; - -#ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - /* Fall-through to the CPU_DEAD[_FROZEN] case. */ - - case CPU_DEAD: - case CPU_DEAD_FROZEN: + if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, + cpu_to_node(cpu))) + return -ENOMEM; + cfd->csd = alloc_percpu(struct call_single_data); + if (!cfd->csd) { free_cpumask_var(cfd->cpumask); - free_percpu(cfd->csd); - break; + return -ENOMEM; + } - case CPU_DYING: - case CPU_DYING_FROZEN: - /* - * The IPIs for the smp-call-function callbacks queued by other - * CPUs might arrive late, either due to hardware latencies or - * because this CPU disabled interrupts (inside stop-machine) - * before the IPIs were sent. So flush out any pending callbacks - * explicitly (without waiting for the IPIs to arrive), to - * ensure that the outgoing CPU doesn't go offline with work - * still pending. - */ - flush_smp_call_function_queue(false); - break; -#endif - }; + return 0; +} + +int smpcfd_dead_cpu(unsigned int cpu) +{ + struct call_function_data *cfd = &per_cpu(cfd_data, cpu); - return NOTIFY_OK; + free_cpumask_var(cfd->cpumask); + free_percpu(cfd->csd); + return 0; } -static struct notifier_block hotplug_cfd_notifier = { - .notifier_call = hotplug_cfd, -}; +int smpcfd_dying_cpu(unsigned int cpu) +{ + /* + * The IPIs for the smp-call-function callbacks queued by other + * CPUs might arrive late, either due to hardware latencies or + * because this CPU disabled interrupts (inside stop-machine) + * before the IPIs were sent. So flush out any pending callbacks + * explicitly (without waiting for the IPIs to arrive), to + * ensure that the outgoing CPU doesn't go offline with work + * still pending. + */ + flush_smp_call_function_queue(false); + return 0; +} void __init call_function_init(void) { - void *cpu = (void *)(long)smp_processor_id(); int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); - hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu); - register_cpu_notifier(&hotplug_cfd_notifier); + smpcfd_prepare_cpu(smp_processor_id()); } /* diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index a467e6c28a3b..4a1ca5f6da7e 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -21,6 +21,7 @@ #include <linux/smpboot.h> #include <linux/atomic.h> #include <linux/lglock.h> +#include <linux/nmi.h> /* * Structure to determine completion condition and record errors. May @@ -209,6 +210,13 @@ static int multi_cpu_stop(void *data) break; } ack_state(msdata); + } else if (curstate > MULTI_STOP_PREPARE) { + /* + * At this stage all other CPUs we depend on must spin + * in the same loop. Any reason for hard-lockup should + * be detected and reported on their side. + */ + touch_nmi_watchdog(); } } while (curstate != MULTI_STOP_EXIT); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 35f0dcb1cb4f..b43d0b27c1fe 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -814,6 +814,13 @@ static struct ctl_table kern_table[] = { .extra2 = &ten_thousand, }, { + .procname = "printk_devkmsg", + .data = devkmsg_log_str, + .maxlen = DEVKMSG_STR_MAX_SIZE, + .mode = 0644, + .proc_handler = devkmsg_sysctl_set_loglvl, + }, + { .procname = "dmesg_restrict", .data = &dmesg_restrict, .maxlen = sizeof(int), @@ -1508,8 +1515,8 @@ static struct ctl_table vm_table[] = { #ifdef CONFIG_NUMA { .procname = "zone_reclaim_mode", - .data = &zone_reclaim_mode, - .maxlen = sizeof(zone_reclaim_mode), + .data = &node_reclaim_mode, + .maxlen = sizeof(node_reclaim_mode), .mode = 0644, .proc_handler = proc_dointvec, .extra1 = &zero, diff --git a/kernel/task_work.c b/kernel/task_work.c index 6ab4842b00e8..d513051fcca2 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -29,7 +29,7 @@ task_work_add(struct task_struct *task, struct callback_head *work, bool notify) struct callback_head *head; do { - head = ACCESS_ONCE(task->task_works); + head = READ_ONCE(task->task_works); if (unlikely(head == &work_exited)) return -ESRCH; work->next = head; @@ -57,6 +57,9 @@ task_work_cancel(struct task_struct *task, task_work_func_t func) struct callback_head **pprev = &task->task_works; struct callback_head *work; unsigned long flags; + + if (likely(!task->task_works)) + return NULL; /* * If cmpxchg() fails we continue without updating pprev. * Either we raced with task_work_add() which added the @@ -64,8 +67,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func) * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); - while ((work = ACCESS_ONCE(*pprev))) { - smp_read_barrier_depends(); + while ((work = lockless_dereference(*pprev))) { if (work->func != func) pprev = &work->next; else if (cmpxchg(pprev, work, work->next) == work) @@ -95,7 +97,7 @@ void task_work_run(void) * work_exited unless the list is empty. */ do { - work = ACCESS_ONCE(task->task_works); + work = READ_ONCE(task->task_works); head = !work && (task->flags & PF_EXITING) ? &work_exited : NULL; } while (cmpxchg(&task->task_works, work, head) != work); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index d13c9aebf7a3..9ba7c820fc23 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1590,7 +1590,7 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, /* * Functions related to boot-time initialization: */ -static void init_hrtimers_cpu(int cpu) +int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; @@ -1602,6 +1602,7 @@ static void init_hrtimers_cpu(int cpu) cpu_base->cpu = cpu; hrtimer_init_hres(cpu_base); + return 0; } #ifdef CONFIG_HOTPLUG_CPU @@ -1636,7 +1637,7 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, } } -static void migrate_hrtimers(int scpu) +int hrtimers_dead_cpu(unsigned int scpu) { struct hrtimer_cpu_base *old_base, *new_base; int i; @@ -1665,45 +1666,14 @@ static void migrate_hrtimers(int scpu) /* Check, if we got expired work to do */ __hrtimer_peek_ahead_timers(); local_irq_enable(); + return 0; } #endif /* CONFIG_HOTPLUG_CPU */ -static int hrtimer_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - int scpu = (long)hcpu; - - switch (action) { - - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - init_hrtimers_cpu(scpu); - break; - -#ifdef CONFIG_HOTPLUG_CPU - case CPU_DEAD: - case CPU_DEAD_FROZEN: - migrate_hrtimers(scpu); - break; -#endif - - default: - break; - } - - return NOTIFY_OK; -} - -static struct notifier_block hrtimers_nb = { - .notifier_call = hrtimer_cpu_notify, -}; - void __init hrtimers_init(void) { - hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, - (void *)(long)smp_processor_id()); - register_cpu_notifier(&hrtimers_nb); + hrtimers_prepare_cpu(smp_processor_id()); } /** diff --git a/kernel/time/timer.c b/kernel/time/timer.c index cb9ab401e2d9..555670a5143c 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1804,7 +1804,7 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h } } -static void migrate_timers(int cpu) +int timers_dead_cpu(unsigned int cpu) { struct timer_base *old_base; struct timer_base *new_base; @@ -1831,29 +1831,9 @@ static void migrate_timers(int cpu) spin_unlock_irq(&new_base->lock); put_cpu_ptr(&timer_bases); } + return 0; } -static int timer_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - switch (action) { - case CPU_DEAD: - case CPU_DEAD_FROZEN: - migrate_timers((long)hcpu); - break; - default: - break; - } - - return NOTIFY_OK; -} - -static inline void timer_register_cpu_notifier(void) -{ - cpu_notifier(timer_cpu_notify, 0); -} -#else -static inline void timer_register_cpu_notifier(void) { } #endif /* CONFIG_HOTPLUG_CPU */ static void __init init_timer_cpu(int cpu) @@ -1881,7 +1861,6 @@ void __init init_timers(void) { init_timer_cpus(); init_timer_stats(); - timer_register_cpu_notifier(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index fafeaf803bd0..f4b86e8ca1e7 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -542,6 +542,7 @@ config HIST_TRIGGERS bool "Histogram triggers" depends on ARCH_HAVE_NMI_SAFE_CMPXCHG select TRACING_MAP + select TRACING default n help Hist triggers allow one or more arbitrary trace event fields diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 979e7bfbde7a..d0a1617b52b4 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -1,4 +1,8 @@ +# We are fully aware of the dangers of __builtin_return_address() +FRAME_CFLAGS := $(call cc-disable-warning,frame-address) +KBUILD_CFLAGS += $(FRAME_CFLAGS) + # Do not instrument the tracer itself: ifdef CONFIG_FUNCTION_TRACER diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 9aef8654e90d..7598e6ca817a 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -127,12 +127,13 @@ static void trace_note_tsk(struct task_struct *tsk) static void trace_note_time(struct blk_trace *bt) { - struct timespec now; + struct timespec64 now; unsigned long flags; u32 words[2]; - getnstimeofday(&now); - words[0] = now.tv_sec; + /* need to check user space to see if this breaks in y2038 or y2106 */ + ktime_get_real_ts64(&now); + words[0] = (u32)now.tv_sec; words[1] = now.tv_nsec; local_irq_save(flags); @@ -189,6 +190,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) }; #define BLK_TC_RAHEAD BLK_TC_AHEAD +#define BLK_TC_PREFLUSH BLK_TC_FLUSH /* The ilog2() calls fall out because they're constant */ #define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \ @@ -199,7 +201,8 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), * blk_io_trace structure and places it in a per-cpu subbuffer. */ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, - int rw, u32 what, int error, int pdu_len, void *pdu_data) + int op, int op_flags, u32 what, int error, int pdu_len, + void *pdu_data) { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; @@ -214,13 +217,16 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; - what |= ddir_act[rw & WRITE]; - what |= MASK_TC_BIT(rw, SYNC); - what |= MASK_TC_BIT(rw, RAHEAD); - what |= MASK_TC_BIT(rw, META); - what |= MASK_TC_BIT(rw, DISCARD); - what |= MASK_TC_BIT(rw, FLUSH); - what |= MASK_TC_BIT(rw, FUA); + what |= ddir_act[op_is_write(op) ? WRITE : READ]; + what |= MASK_TC_BIT(op_flags, SYNC); + what |= MASK_TC_BIT(op_flags, RAHEAD); + what |= MASK_TC_BIT(op_flags, META); + what |= MASK_TC_BIT(op_flags, PREFLUSH); + what |= MASK_TC_BIT(op_flags, FUA); + if (op == REQ_OP_DISCARD) + what |= BLK_TC_ACT(BLK_TC_DISCARD); + if (op == REQ_OP_FLUSH) + what |= BLK_TC_ACT(BLK_TC_FLUSH); pid = tsk->pid; if (act_log_check(bt, what, sector, pid)) @@ -708,11 +714,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { what |= BLK_TC_ACT(BLK_TC_PC); - __blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags, + __blk_add_trace(bt, 0, nr_bytes, req_op(rq), rq->cmd_flags, what, rq->errors, rq->cmd_len, rq->cmd); } else { what |= BLK_TC_ACT(BLK_TC_FS); - __blk_add_trace(bt, blk_rq_pos(rq), nr_bytes, + __blk_add_trace(bt, blk_rq_pos(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, rq->errors, 0, NULL); } } @@ -770,7 +776,7 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, return; __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio->bi_rw, what, error, 0, NULL); + bio_op(bio), bio->bi_opf, what, error, 0, NULL); } static void blk_add_trace_bio_bounce(void *ignore, @@ -818,7 +824,8 @@ static void blk_add_trace_getrq(void *ignore, struct blk_trace *bt = q->blk_trace; if (bt) - __blk_add_trace(bt, 0, 0, rw, BLK_TA_GETRQ, 0, 0, NULL); + __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, + NULL); } } @@ -833,7 +840,7 @@ static void blk_add_trace_sleeprq(void *ignore, struct blk_trace *bt = q->blk_trace; if (bt) - __blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ, + __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, 0, 0, NULL); } } @@ -843,7 +850,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q) struct blk_trace *bt = q->blk_trace; if (bt) - __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL); + __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, @@ -860,7 +867,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, else what = BLK_TA_UNPLUG_TIMER; - __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu); + __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu); } } @@ -874,8 +881,9 @@ static void blk_add_trace_split(void *ignore, __be64 rpdu = cpu_to_be64(pdu); __blk_add_trace(bt, bio->bi_iter.bi_sector, - bio->bi_iter.bi_size, bio->bi_rw, BLK_TA_SPLIT, - bio->bi_error, sizeof(rpdu), &rpdu); + bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, + BLK_TA_SPLIT, bio->bi_error, sizeof(rpdu), + &rpdu); } } @@ -907,7 +915,7 @@ 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->bi_rw, BLK_TA_REMAP, bio->bi_error, + bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_error, sizeof(r), &r); } @@ -940,7 +948,7 @@ static void blk_add_trace_rq_remap(void *ignore, r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), - rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors, + rq_data_dir(rq), 0, BLK_TA_REMAP, !!rq->errors, sizeof(r), &r); } @@ -965,10 +973,10 @@ void blk_add_driver_data(struct request_queue *q, return; if (rq->cmd_type == REQ_TYPE_BLOCK_PC) - __blk_add_trace(bt, 0, blk_rq_bytes(rq), 0, + __blk_add_trace(bt, 0, blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, rq->errors, len, data); else - __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0, + __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, rq->errors, len, data); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1769,21 +1777,34 @@ void blk_dump_cmd(char *buf, struct request *rq) } } -void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) +void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes) { int i = 0; - if (rw & REQ_FLUSH) + if (rw & REQ_PREFLUSH) rwbs[i++] = 'F'; - if (rw & WRITE) + switch (op) { + case REQ_OP_WRITE: + case REQ_OP_WRITE_SAME: rwbs[i++] = 'W'; - else if (rw & REQ_DISCARD) + break; + case REQ_OP_DISCARD: + rwbs[i++] = 'D'; + break; + case REQ_OP_SECURE_ERASE: rwbs[i++] = 'D'; - else if (bytes) + rwbs[i++] = 'E'; + break; + case REQ_OP_FLUSH: + rwbs[i++] = 'F'; + break; + case REQ_OP_READ: rwbs[i++] = 'R'; - else + break; + default: rwbs[i++] = 'N'; + } if (rw & REQ_FUA) rwbs[i++] = 'F'; @@ -1793,8 +1814,6 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) rwbs[i++] = 'S'; if (rw & REQ_META) rwbs[i++] = 'M'; - if (rw & REQ_SECURE) - rwbs[i++] = 'E'; rwbs[i] = '\0'; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 26f603da7e26..b20438fdb029 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -81,6 +81,49 @@ static const struct bpf_func_proto bpf_probe_read_proto = { .arg3_type = ARG_ANYTHING, }; +static u64 bpf_probe_write_user(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + void *unsafe_ptr = (void *) (long) r1; + void *src = (void *) (long) r2; + int size = (int) r3; + + /* + * Ensure we're in user context which is safe for the helper to + * run. This helper has no business in a kthread. + * + * access_ok() should prevent writing to non-user memory, but in + * some situations (nommu, temporary switch, etc) access_ok() does + * not provide enough validation, hence the check on KERNEL_DS. + */ + + if (unlikely(in_interrupt() || + current->flags & (PF_KTHREAD | PF_EXITING))) + return -EPERM; + if (unlikely(segment_eq(get_fs(), KERNEL_DS))) + return -EPERM; + if (!access_ok(VERIFY_WRITE, unsafe_ptr, size)) + return -EPERM; + + return probe_kernel_write(unsafe_ptr, src, size); +} + +static const struct bpf_func_proto bpf_probe_write_user_proto = { + .func = bpf_probe_write_user, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, +}; + +static const struct bpf_func_proto *bpf_get_probe_write_proto(void) +{ + pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!", + current->comm, task_pid_nr(current)); + + return &bpf_probe_write_user_proto; +} + /* * limited trace_printk() * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed @@ -188,31 +231,35 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) +static u64 bpf_perf_event_read(u64 r1, u64 flags, u64 r3, u64 r4, u64 r5) { struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; struct bpf_array *array = container_of(map, struct bpf_array, map); + unsigned int cpu = smp_processor_id(); + u64 index = flags & BPF_F_INDEX_MASK; + struct bpf_event_entry *ee; struct perf_event *event; - struct file *file; + if (unlikely(flags & ~(BPF_F_INDEX_MASK))) + return -EINVAL; + if (index == BPF_F_CURRENT_CPU) + index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; - file = READ_ONCE(array->ptrs[index]); - if (unlikely(!file)) + ee = READ_ONCE(array->ptrs[index]); + if (!ee) return -ENOENT; - event = file->private_data; - - /* make sure event is local and doesn't have pmu::count */ - if (event->oncpu != smp_processor_id() || - event->pmu->count) - return -EINVAL; - + 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; + /* * we don't know if the function is run successfully by the * return value. It can be judged in other places, such as @@ -229,47 +276,58 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; -static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size) +static __always_inline u64 +__bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, + u64 flags, struct perf_raw_record *raw) { - struct pt_regs *regs = (struct pt_regs *) (long) r1; - struct bpf_map *map = (struct bpf_map *) (long) r2; struct bpf_array *array = container_of(map, struct bpf_array, map); + unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; - void *data = (void *) (long) r4; struct perf_sample_data sample_data; + struct bpf_event_entry *ee; struct perf_event *event; - struct file *file; - struct perf_raw_record raw = { - .size = size, - .data = data, - }; - if (unlikely(flags & ~(BPF_F_INDEX_MASK))) - return -EINVAL; if (index == BPF_F_CURRENT_CPU) - index = raw_smp_processor_id(); + index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; - file = READ_ONCE(array->ptrs[index]); - if (unlikely(!file)) + ee = READ_ONCE(array->ptrs[index]); + if (!ee) return -ENOENT; - event = file->private_data; - + event = ee->event; if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) return -EINVAL; - if (unlikely(event->oncpu != smp_processor_id())) + if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; perf_sample_data_init(&sample_data, 0, 0); - sample_data.raw = &raw; + sample_data.raw = raw; perf_event_output(event, &sample_data, regs); return 0; } +static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size) +{ + struct pt_regs *regs = (struct pt_regs *)(long) r1; + struct bpf_map *map = (struct bpf_map *)(long) r2; + void *data = (void *)(long) r4; + struct perf_raw_record raw = { + .frag = { + .size = size, + .data = data, + }, + }; + + if (unlikely(flags & ~(BPF_F_INDEX_MASK))) + return -EINVAL; + + return __bpf_perf_event_output(regs, map, flags, &raw); +} + static const struct bpf_func_proto bpf_perf_event_output_proto = { .func = bpf_perf_event_output, .gpl_only = true, @@ -283,31 +341,41 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = { static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs); -static u64 bpf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size) +u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, + void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs); + struct perf_raw_frag frag = { + .copy = ctx_copy, + .size = ctx_size, + .data = ctx, + }; + struct perf_raw_record raw = { + .frag = { + { + .next = ctx_size ? &frag : NULL, + }, + .size = meta_size, + .data = meta, + }, + }; perf_fetch_caller_regs(regs); - return bpf_perf_event_output((long)regs, r2, flags, r4, size); + return __bpf_perf_event_output(regs, map, flags, &raw); +} + +static u64 bpf_get_current_task(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return (long) current; } -static const struct bpf_func_proto bpf_event_output_proto = { - .func = bpf_event_output, +static const struct bpf_func_proto bpf_get_current_task_proto = { + .func = bpf_get_current_task, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_STACK, - .arg5_type = ARG_CONST_STACK_SIZE, }; -const struct bpf_func_proto *bpf_get_event_output_proto(void) -{ - return &bpf_event_output_proto; -} - static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -325,6 +393,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; + case BPF_FUNC_get_current_task: + return &bpf_get_current_task_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_comm: @@ -335,6 +405,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) return &bpf_get_smp_processor_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; + case BPF_FUNC_probe_write_user: + return bpf_get_probe_write_proto(); default: return NULL; } @@ -356,18 +428,12 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, enum bpf_reg_type *reg_type) { - /* check bounds */ if (off < 0 || off >= sizeof(struct pt_regs)) return false; - - /* only read is allowed */ if (type != BPF_READ) return false; - - /* disallow misaligned access */ if (off % size != 0) return false; - return true; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 900dbb1efff2..84752c8e28b5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -89,16 +89,16 @@ struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; /* What to set function_trace_op to */ static struct ftrace_ops *set_function_trace_op; -/* List for set_ftrace_pid's pids. */ -LIST_HEAD(ftrace_pids); -struct ftrace_pid { - struct list_head list; - struct pid *pid; -}; - -static bool ftrace_pids_enabled(void) +static bool ftrace_pids_enabled(struct ftrace_ops *ops) { - return !list_empty(&ftrace_pids); + struct trace_array *tr; + + if (!(ops->flags & FTRACE_OPS_FL_PID) || !ops->private) + return false; + + tr = ops->private; + + return tr->function_pids != NULL; } static void ftrace_update_trampoline(struct ftrace_ops *ops); @@ -179,7 +179,9 @@ int ftrace_nr_registered_ops(void) static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs) { - if (!test_tsk_trace_trace(current)) + struct trace_array *tr = op->private; + + if (tr && this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid)) return; op->saved_func(ip, parent_ip, op, regs); @@ -417,7 +419,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops) /* Always save the function, and reset at unregistering */ ops->saved_func = ops->func; - if (ops->flags & FTRACE_OPS_FL_PID && ftrace_pids_enabled()) + if (ftrace_pids_enabled(ops)) ops->func = ftrace_pid_func; ftrace_update_trampoline(ops); @@ -450,7 +452,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) static void ftrace_update_pid_func(void) { - bool enabled = ftrace_pids_enabled(); struct ftrace_ops *op; /* Only do something if we are tracing something */ @@ -459,8 +460,8 @@ static void ftrace_update_pid_func(void) do_for_each_ftrace_op(op, ftrace_ops_list) { if (op->flags & FTRACE_OPS_FL_PID) { - op->func = enabled ? ftrace_pid_func : - op->saved_func; + op->func = ftrace_pids_enabled(op) ? + ftrace_pid_func : op->saved_func; ftrace_update_trampoline(op); } } while_for_each_ftrace_op(op); @@ -5324,179 +5325,99 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) return ops->func; } -static void clear_ftrace_swapper(void) +static void +ftrace_filter_pid_sched_switch_probe(void *data, bool preempt, + struct task_struct *prev, struct task_struct *next) { - struct task_struct *p; - int cpu; + struct trace_array *tr = data; + struct trace_pid_list *pid_list; - get_online_cpus(); - for_each_online_cpu(cpu) { - p = idle_task(cpu); - clear_tsk_trace_trace(p); - } - put_online_cpus(); -} - -static void set_ftrace_swapper(void) -{ - struct task_struct *p; - int cpu; + pid_list = rcu_dereference_sched(tr->function_pids); - get_online_cpus(); - for_each_online_cpu(cpu) { - p = idle_task(cpu); - set_tsk_trace_trace(p); - } - put_online_cpus(); + this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid, + trace_ignore_this_task(pid_list, next)); } -static void clear_ftrace_pid(struct pid *pid) +static void clear_ftrace_pids(struct trace_array *tr) { - struct task_struct *p; + struct trace_pid_list *pid_list; + int cpu; - rcu_read_lock(); - do_each_pid_task(pid, PIDTYPE_PID, p) { - clear_tsk_trace_trace(p); - } while_each_pid_task(pid, PIDTYPE_PID, p); - rcu_read_unlock(); + pid_list = rcu_dereference_protected(tr->function_pids, + lockdep_is_held(&ftrace_lock)); + if (!pid_list) + return; - put_pid(pid); -} + unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr); -static void set_ftrace_pid(struct pid *pid) -{ - struct task_struct *p; + for_each_possible_cpu(cpu) + per_cpu_ptr(tr->trace_buffer.data, cpu)->ftrace_ignore_pid = false; - rcu_read_lock(); - do_each_pid_task(pid, PIDTYPE_PID, p) { - set_tsk_trace_trace(p); - } while_each_pid_task(pid, PIDTYPE_PID, p); - rcu_read_unlock(); -} + rcu_assign_pointer(tr->function_pids, NULL); -static void clear_ftrace_pid_task(struct pid *pid) -{ - if (pid == ftrace_swapper_pid) - clear_ftrace_swapper(); - else - clear_ftrace_pid(pid); -} + /* Wait till all users are no longer using pid filtering */ + synchronize_sched(); -static void set_ftrace_pid_task(struct pid *pid) -{ - if (pid == ftrace_swapper_pid) - set_ftrace_swapper(); - else - set_ftrace_pid(pid); + trace_free_pid_list(pid_list); } -static int ftrace_pid_add(int p) +static void ftrace_pid_reset(struct trace_array *tr) { - struct pid *pid; - struct ftrace_pid *fpid; - int ret = -EINVAL; - mutex_lock(&ftrace_lock); - - if (!p) - pid = ftrace_swapper_pid; - else - pid = find_get_pid(p); - - if (!pid) - goto out; - - ret = 0; - - list_for_each_entry(fpid, &ftrace_pids, list) - if (fpid->pid == pid) - goto out_put; - - ret = -ENOMEM; - - fpid = kmalloc(sizeof(*fpid), GFP_KERNEL); - if (!fpid) - goto out_put; - - list_add(&fpid->list, &ftrace_pids); - fpid->pid = pid; - - set_ftrace_pid_task(pid); + clear_ftrace_pids(tr); ftrace_update_pid_func(); - ftrace_startup_all(0); mutex_unlock(&ftrace_lock); - return 0; - -out_put: - if (pid != ftrace_swapper_pid) - put_pid(pid); - -out: - mutex_unlock(&ftrace_lock); - return ret; } -static void ftrace_pid_reset(void) -{ - struct ftrace_pid *fpid, *safe; - - mutex_lock(&ftrace_lock); - list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) { - struct pid *pid = fpid->pid; - - clear_ftrace_pid_task(pid); - - list_del(&fpid->list); - kfree(fpid); - } - - ftrace_update_pid_func(); - ftrace_startup_all(0); - - mutex_unlock(&ftrace_lock); -} +/* Greater than any max PID */ +#define FTRACE_NO_PIDS (void *)(PID_MAX_LIMIT + 1) static void *fpid_start(struct seq_file *m, loff_t *pos) + __acquires(RCU) { + struct trace_pid_list *pid_list; + struct trace_array *tr = m->private; + mutex_lock(&ftrace_lock); + rcu_read_lock_sched(); - if (!ftrace_pids_enabled() && (!*pos)) - return (void *) 1; + pid_list = rcu_dereference_sched(tr->function_pids); - return seq_list_start(&ftrace_pids, *pos); + if (!pid_list) + return !(*pos) ? FTRACE_NO_PIDS : NULL; + + return trace_pid_start(pid_list, pos); } static void *fpid_next(struct seq_file *m, void *v, loff_t *pos) { - if (v == (void *)1) + struct trace_array *tr = m->private; + struct trace_pid_list *pid_list = rcu_dereference_sched(tr->function_pids); + + if (v == FTRACE_NO_PIDS) return NULL; - return seq_list_next(v, &ftrace_pids, pos); + return trace_pid_next(pid_list, v, pos); } static void fpid_stop(struct seq_file *m, void *p) + __releases(RCU) { + rcu_read_unlock_sched(); mutex_unlock(&ftrace_lock); } static int fpid_show(struct seq_file *m, void *v) { - const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list); - - if (v == (void *)1) { + if (v == FTRACE_NO_PIDS) { seq_puts(m, "no pid\n"); return 0; } - if (fpid->pid == ftrace_swapper_pid) - seq_puts(m, "swapper tasks\n"); - else - seq_printf(m, "%u\n", pid_vnr(fpid->pid)); - - return 0; + return trace_pid_show(m, v); } static const struct seq_operations ftrace_pid_sops = { @@ -5509,58 +5430,103 @@ static const struct seq_operations ftrace_pid_sops = { static int ftrace_pid_open(struct inode *inode, struct file *file) { + struct trace_array *tr = inode->i_private; + struct seq_file *m; int ret = 0; + if (trace_array_get(tr) < 0) + return -ENODEV; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - ftrace_pid_reset(); + ftrace_pid_reset(tr); - if (file->f_mode & FMODE_READ) - ret = seq_open(file, &ftrace_pid_sops); + ret = seq_open(file, &ftrace_pid_sops); + if (ret < 0) { + trace_array_put(tr); + } else { + m = file->private_data; + /* copy tr over to seq ops */ + m->private = tr; + } return ret; } +static void ignore_task_cpu(void *data) +{ + struct trace_array *tr = data; + struct trace_pid_list *pid_list; + + /* + * This function is called by on_each_cpu() while the + * event_mutex is held. + */ + pid_list = rcu_dereference_protected(tr->function_pids, + mutex_is_locked(&ftrace_lock)); + + this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid, + trace_ignore_this_task(pid_list, current)); +} + static ssize_t ftrace_pid_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - char buf[64], *tmp; - long val; - int ret; + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; + struct trace_pid_list *filtered_pids = NULL; + struct trace_pid_list *pid_list; + ssize_t ret; - if (cnt >= sizeof(buf)) - return -EINVAL; + if (!cnt) + return 0; + + mutex_lock(&ftrace_lock); + + filtered_pids = rcu_dereference_protected(tr->function_pids, + lockdep_is_held(&ftrace_lock)); + + ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); + if (ret < 0) + goto out; - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; + rcu_assign_pointer(tr->function_pids, pid_list); - buf[cnt] = 0; + if (filtered_pids) { + synchronize_sched(); + trace_free_pid_list(filtered_pids); + } else if (pid_list) { + /* Register a probe to set whether to ignore the tracing of a task */ + register_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr); + } /* - * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid" - * to clean the filter quietly. + * Ignoring of pids is done at task switch. But we have to + * check for those tasks that are currently running. + * Always do this in case a pid was appended or removed. */ - tmp = strstrip(buf); - if (strlen(tmp) == 0) - return 1; + on_each_cpu(ignore_task_cpu, tr, 1); - ret = kstrtol(tmp, 10, &val); - if (ret < 0) - return ret; + ftrace_update_pid_func(); + ftrace_startup_all(0); + out: + mutex_unlock(&ftrace_lock); - ret = ftrace_pid_add(val); + if (ret > 0) + *ppos += ret; - return ret ? ret : cnt; + return ret; } static int ftrace_pid_release(struct inode *inode, struct file *file) { - if (file->f_mode & FMODE_READ) - seq_release(inode, file); + struct trace_array *tr = inode->i_private; - return 0; + trace_array_put(tr); + + return seq_release(inode, file); } static const struct file_operations ftrace_pid_fops = { @@ -5571,24 +5537,21 @@ static const struct file_operations ftrace_pid_fops = { .release = ftrace_pid_release, }; -static __init int ftrace_init_tracefs(void) +void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer) { - struct dentry *d_tracer; + trace_create_file("set_ftrace_pid", 0644, d_tracer, + tr, &ftrace_pid_fops); +} - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) - return 0; +void __init ftrace_init_tracefs_toplevel(struct trace_array *tr, + struct dentry *d_tracer) +{ + /* Only the top level directory has the dyn_tracefs and profile */ + WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL)); ftrace_init_dyn_tracefs(d_tracer); - - trace_create_file("set_ftrace_pid", 0644, d_tracer, - NULL, &ftrace_pid_fops); - ftrace_profile_tracefs(d_tracer); - - return 0; } -fs_initcall(ftrace_init_tracefs); /** * ftrace_kill - kill ftrace diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8a4bd6b68a0b..dade4c9559cc 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -25,7 +25,7 @@ #include <linux/hardirq.h> #include <linux/linkage.h> #include <linux/uaccess.h> -#include <linux/kprobes.h> +#include <linux/vmalloc.h> #include <linux/ftrace.h> #include <linux/module.h> #include <linux/percpu.h> @@ -319,6 +319,258 @@ int call_filter_check_discard(struct trace_event_call *call, void *rec, return 0; } +void trace_free_pid_list(struct trace_pid_list *pid_list) +{ + vfree(pid_list->pids); + kfree(pid_list); +} + +/** + * trace_find_filtered_pid - check if a pid exists in a filtered_pid list + * @filtered_pids: The list of pids to check + * @search_pid: The PID to find in @filtered_pids + * + * Returns true if @search_pid is fonud in @filtered_pids, and false otherwis. + */ +bool +trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) +{ + /* + * If pid_max changed after filtered_pids was created, we + * by default ignore all pids greater than the previous pid_max. + */ + if (search_pid >= filtered_pids->pid_max) + return false; + + return test_bit(search_pid, filtered_pids->pids); +} + +/** + * trace_ignore_this_task - should a task be ignored for tracing + * @filtered_pids: The list of pids to check + * @task: The task that should be ignored if not filtered + * + * Checks if @task should be traced or not from @filtered_pids. + * Returns true if @task should *NOT* be traced. + * Returns false if @task should be traced. + */ +bool +trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task) +{ + /* + * Return false, because if filtered_pids does not exist, + * all pids are good to trace. + */ + if (!filtered_pids) + return false; + + return !trace_find_filtered_pid(filtered_pids, task->pid); +} + +/** + * trace_pid_filter_add_remove - Add or remove a task from a pid_list + * @pid_list: The list to modify + * @self: The current task for fork or NULL for exit + * @task: The task to add or remove + * + * If adding a task, if @self is defined, the task is only added if @self + * is also included in @pid_list. This happens on fork and tasks should + * only be added when the parent is listed. If @self is NULL, then the + * @task pid will be removed from the list, which would happen on exit + * of a task. + */ +void trace_filter_add_remove_task(struct trace_pid_list *pid_list, + struct task_struct *self, + struct task_struct *task) +{ + if (!pid_list) + return; + + /* For forks, we only add if the forking task is listed */ + if (self) { + if (!trace_find_filtered_pid(pid_list, self->pid)) + return; + } + + /* Sorry, but we don't support pid_max changing after setting */ + if (task->pid >= pid_list->pid_max) + return; + + /* "self" is set for forks, and NULL for exits */ + if (self) + set_bit(task->pid, pid_list->pids); + else + clear_bit(task->pid, pid_list->pids); +} + +/** + * trace_pid_next - Used for seq_file to get to the next pid of a pid_list + * @pid_list: The pid list to show + * @v: The last pid that was shown (+1 the actual pid to let zero be displayed) + * @pos: The position of the file + * + * This is used by the seq_file "next" operation to iterate the pids + * listed in a trace_pid_list structure. + * + * Returns the pid+1 as we want to display pid of zero, but NULL would + * stop the iteration. + */ +void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos) +{ + unsigned long pid = (unsigned long)v; + + (*pos)++; + + /* pid already is +1 of the actual prevous bit */ + pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid); + + /* Return pid + 1 to allow zero to be represented */ + if (pid < pid_list->pid_max) + return (void *)(pid + 1); + + return NULL; +} + +/** + * trace_pid_start - Used for seq_file to start reading pid lists + * @pid_list: The pid list to show + * @pos: The position of the file + * + * This is used by seq_file "start" operation to start the iteration + * of listing pids. + * + * Returns the pid+1 as we want to display pid of zero, but NULL would + * stop the iteration. + */ +void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos) +{ + unsigned long pid; + loff_t l = 0; + + pid = find_first_bit(pid_list->pids, pid_list->pid_max); + if (pid >= pid_list->pid_max) + return NULL; + + /* Return pid + 1 so that zero can be the exit value */ + for (pid++; pid && l < *pos; + pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l)) + ; + return (void *)pid; +} + +/** + * trace_pid_show - show the current pid in seq_file processing + * @m: The seq_file structure to write into + * @v: A void pointer of the pid (+1) value to display + * + * Can be directly used by seq_file operations to display the current + * pid value. + */ +int trace_pid_show(struct seq_file *m, void *v) +{ + unsigned long pid = (unsigned long)v - 1; + + seq_printf(m, "%lu\n", pid); + return 0; +} + +/* 128 should be much more than enough */ +#define PID_BUF_SIZE 127 + +int trace_pid_write(struct trace_pid_list *filtered_pids, + struct trace_pid_list **new_pid_list, + const char __user *ubuf, size_t cnt) +{ + struct trace_pid_list *pid_list; + struct trace_parser parser; + unsigned long val; + int nr_pids = 0; + ssize_t read = 0; + ssize_t ret = 0; + loff_t pos; + pid_t pid; + + if (trace_parser_get_init(&parser, PID_BUF_SIZE + 1)) + return -ENOMEM; + + /* + * Always recreate a new array. The write is an all or nothing + * operation. Always create a new array when adding new pids by + * the user. If the operation fails, then the current list is + * not modified. + */ + pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL); + if (!pid_list) + return -ENOMEM; + + pid_list->pid_max = READ_ONCE(pid_max); + + /* Only truncating will shrink pid_max */ + if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max) + pid_list->pid_max = filtered_pids->pid_max; + + pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3); + if (!pid_list->pids) { + kfree(pid_list); + return -ENOMEM; + } + + if (filtered_pids) { + /* copy the current bits to the new max */ + for_each_set_bit(pid, filtered_pids->pids, + filtered_pids->pid_max) { + set_bit(pid, pid_list->pids); + nr_pids++; + } + } + + while (cnt > 0) { + + pos = 0; + + ret = trace_get_user(&parser, ubuf, cnt, &pos); + if (ret < 0 || !trace_parser_loaded(&parser)) + break; + + read += ret; + ubuf += ret; + cnt -= ret; + + parser.buffer[parser.idx] = 0; + + ret = -EINVAL; + if (kstrtoul(parser.buffer, 0, &val)) + break; + if (val >= pid_list->pid_max) + break; + + pid = (pid_t)val; + + set_bit(pid, pid_list->pids); + nr_pids++; + + trace_parser_clear(&parser); + ret = 0; + } + trace_parser_put(&parser); + + if (ret < 0) { + trace_free_pid_list(pid_list); + return ret; + } + + if (!nr_pids) { + /* Cleared the list of pids */ + trace_free_pid_list(pid_list); + read = ret; + pid_list = NULL; + } + + *new_pid_list = pid_list; + + return read; +} + static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu) { u64 ts; @@ -1862,7 +2114,17 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, { __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, flags, 0, pc, regs); + /* + * If regs is not set, then skip the following callers: + * trace_buffer_unlock_commit_regs + * event_trigger_unlock_commit + * trace_event_buffer_commit + * trace_event_raw_event_sched_switch + * Note, we can still get here via blktrace, wakeup tracer + * and mmiotrace, but that's ok if they lose a function or + * two. They are that meaningful. + */ + ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } @@ -1913,6 +2175,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, trace.skip = skip; /* + * Add two, for this function and the call to save_stack_trace() + * If regs is set, then these functions will not be in the way. + */ + if (!regs) + trace.skip += 2; + + /* * Since events can happen in NMIs there's no safe way to * use the per cpu ftrace_stacks. We reserve it and if an interrupt * or NMI comes in, it will just have to use the default @@ -2083,83 +2352,41 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags) /* created for use with alloc_percpu */ struct trace_buffer_struct { - char buffer[TRACE_BUF_SIZE]; + int nesting; + char buffer[4][TRACE_BUF_SIZE]; }; static struct trace_buffer_struct *trace_percpu_buffer; -static struct trace_buffer_struct *trace_percpu_sirq_buffer; -static struct trace_buffer_struct *trace_percpu_irq_buffer; -static struct trace_buffer_struct *trace_percpu_nmi_buffer; /* - * The buffer used is dependent on the context. There is a per cpu - * buffer for normal context, softirq contex, hard irq context and - * for NMI context. Thise allows for lockless recording. - * - * Note, if the buffers failed to be allocated, then this returns NULL + * Thise allows for lockless recording. If we're nested too deeply, then + * this returns NULL. */ static char *get_trace_buf(void) { - struct trace_buffer_struct *percpu_buffer; - - /* - * If we have allocated per cpu buffers, then we do not - * need to do any locking. - */ - if (in_nmi()) - percpu_buffer = trace_percpu_nmi_buffer; - else if (in_irq()) - percpu_buffer = trace_percpu_irq_buffer; - else if (in_softirq()) - percpu_buffer = trace_percpu_sirq_buffer; - else - percpu_buffer = trace_percpu_buffer; + struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer); - if (!percpu_buffer) + if (!buffer || buffer->nesting >= 4) return NULL; - return this_cpu_ptr(&percpu_buffer->buffer[0]); + return &buffer->buffer[buffer->nesting++][0]; +} + +static void put_trace_buf(void) +{ + this_cpu_dec(trace_percpu_buffer->nesting); } static int alloc_percpu_trace_buffer(void) { struct trace_buffer_struct *buffers; - struct trace_buffer_struct *sirq_buffers; - struct trace_buffer_struct *irq_buffers; - struct trace_buffer_struct *nmi_buffers; buffers = alloc_percpu(struct trace_buffer_struct); - if (!buffers) - goto err_warn; - - sirq_buffers = alloc_percpu(struct trace_buffer_struct); - if (!sirq_buffers) - goto err_sirq; - - irq_buffers = alloc_percpu(struct trace_buffer_struct); - if (!irq_buffers) - goto err_irq; - - nmi_buffers = alloc_percpu(struct trace_buffer_struct); - if (!nmi_buffers) - goto err_nmi; + if (WARN(!buffers, "Could not allocate percpu trace_printk buffer")) + return -ENOMEM; trace_percpu_buffer = buffers; - trace_percpu_sirq_buffer = sirq_buffers; - trace_percpu_irq_buffer = irq_buffers; - trace_percpu_nmi_buffer = nmi_buffers; - return 0; - - err_nmi: - free_percpu(irq_buffers); - err_irq: - free_percpu(sirq_buffers); - err_sirq: - free_percpu(buffers); - err_warn: - WARN(1, "Could not allocate percpu trace_printk buffer"); - return -ENOMEM; } static int buffers_allocated; @@ -2250,7 +2477,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; - goto out; + goto out_nobuffer; } len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); @@ -2276,6 +2503,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) } out: + put_trace_buf(); + +out_nobuffer: preempt_enable_notrace(); unpause_graph_tracing(); @@ -2307,7 +2537,7 @@ __trace_array_vprintk(struct ring_buffer *buffer, tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; - goto out; + goto out_nobuffer; } len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); @@ -2326,7 +2556,11 @@ __trace_array_vprintk(struct ring_buffer *buffer, __buffer_unlock_commit(buffer, event); ftrace_trace_stack(&global_trace, buffer, flags, 6, pc, NULL); } - out: + +out: + put_trace_buf(); + +out_nobuffer: preempt_enable_notrace(); unpause_graph_tracing(); @@ -6977,6 +7211,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) for_each_tracing_cpu(cpu) tracing_init_tracefs_percpu(tr, cpu); + ftrace_init_tracefs(tr, d_tracer); } static struct vfsmount *trace_automount(void *ingore) @@ -7130,6 +7365,7 @@ static __init int tracer_init_tracefs(void) return 0; init_tracer_tracefs(&global_trace, d_tracer); + ftrace_init_tracefs_toplevel(&global_trace, d_tracer); trace_create_file("tracing_thresh", 0644, d_tracer, &global_trace, &tracing_thresh_fops); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5167c366d6b7..f783df416726 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -80,6 +80,12 @@ enum trace_type { FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ filter) +#undef FTRACE_ENTRY_PACKED +#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print, \ + filter) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) __packed + #include "trace_entries.h" /* @@ -156,6 +162,9 @@ struct trace_array_cpu { char comm[TASK_COMM_LEN]; bool ignore_pid; +#ifdef CONFIG_FUNCTION_TRACER + bool ftrace_ignore_pid; +#endif }; struct tracer; @@ -247,6 +256,7 @@ struct trace_array { int ref; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops *ops; + struct trace_pid_list __rcu *function_pids; /* function tracing enabled */ int function_enabled; #endif @@ -628,6 +638,25 @@ extern unsigned long nsecs_to_usecs(unsigned long nsecs); extern unsigned long tracing_thresh; +/* PID filtering */ + +extern int pid_max; + +bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, + pid_t search_pid); +bool trace_ignore_this_task(struct trace_pid_list *filtered_pids, + struct task_struct *task); +void trace_filter_add_remove_task(struct trace_pid_list *pid_list, + struct task_struct *self, + struct task_struct *task); +void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos); +void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos); +int trace_pid_show(struct seq_file *m, void *v); +void trace_free_pid_list(struct trace_pid_list *pid_list); +int trace_pid_write(struct trace_pid_list *filtered_pids, + struct trace_pid_list **new_pid_list, + const char __user *ubuf, size_t cnt); + #ifdef CONFIG_TRACER_MAX_TRACE void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu); void update_max_tr_single(struct trace_array *tr, @@ -821,12 +850,9 @@ extern struct list_head ftrace_pids; #ifdef CONFIG_FUNCTION_TRACER extern bool ftrace_filter_param __initdata; -static inline int ftrace_trace_task(struct task_struct *task) +static inline int ftrace_trace_task(struct trace_array *tr) { - if (list_empty(&ftrace_pids)) - return 1; - - return test_tsk_trace_trace(task); + return !this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid); } extern int ftrace_is_dead(void); int ftrace_create_function_files(struct trace_array *tr, @@ -836,8 +862,11 @@ void ftrace_init_global_array_ops(struct trace_array *tr); void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func); void ftrace_reset_array_ops(struct trace_array *tr); int using_ftrace_ops_list_func(void); +void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); +void ftrace_init_tracefs_toplevel(struct trace_array *tr, + struct dentry *d_tracer); #else -static inline int ftrace_trace_task(struct task_struct *task) +static inline int ftrace_trace_task(struct trace_array *tr) { return 1; } @@ -852,6 +881,8 @@ static inline void ftrace_destroy_function_files(struct trace_array *tr) { } static inline __init void ftrace_init_global_array_ops(struct trace_array *tr) { } static inline void ftrace_reset_array_ops(struct trace_array *tr) { } +static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { } +static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { } /* ftace_func_t type is not defined, use macro instead of static inline */ #define ftrace_init_array_ops(tr, func) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER */ @@ -1600,6 +1631,11 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); #define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ filter) +#undef FTRACE_ENTRY_PACKED +#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) + #include "trace_entries.h" #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER) diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index ee7b94a4810a..5c30efcda5e6 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -72,7 +72,7 @@ FTRACE_ENTRY_REG(function, ftrace_entry, ); /* Function call entry */ -FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, +FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry, TRACE_GRAPH_ENT, @@ -88,7 +88,7 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, ); /* Function return entry */ -FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry, +FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, TRACE_GRAPH_RET, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 3d4155892a1e..03c0a48c3ac4 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -15,7 +15,6 @@ #include <linux/kthread.h> #include <linux/tracefs.h> #include <linux/uaccess.h> -#include <linux/vmalloc.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/sort.h> @@ -262,6 +261,14 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, local_save_flags(fbuffer->flags); fbuffer->pc = preempt_count(); + /* + * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables + * preemption (adding one to the preempt_count). Since we are + * interested in the preempt_count at the time the tracepoint was + * hit, we need to subtract one to offset the increment. + */ + if (IS_ENABLED(CONFIG_PREEMPT)) + fbuffer->pc--; fbuffer->trace_file = trace_file; fbuffer->event = @@ -499,60 +506,6 @@ static void ftrace_clear_events(struct trace_array *tr) mutex_unlock(&event_mutex); } -/* Shouldn't this be in a header? */ -extern int pid_max; - -/* Returns true if found in filter */ -static bool -find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) -{ - /* - * If pid_max changed after filtered_pids was created, we - * by default ignore all pids greater than the previous pid_max. - */ - if (search_pid >= filtered_pids->pid_max) - return false; - - return test_bit(search_pid, filtered_pids->pids); -} - -static bool -ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task) -{ - /* - * Return false, because if filtered_pids does not exist, - * all pids are good to trace. - */ - if (!filtered_pids) - return false; - - return !find_filtered_pid(filtered_pids, task->pid); -} - -static void filter_add_remove_task(struct trace_pid_list *pid_list, - struct task_struct *self, - struct task_struct *task) -{ - if (!pid_list) - return; - - /* For forks, we only add if the forking task is listed */ - if (self) { - if (!find_filtered_pid(pid_list, self->pid)) - return; - } - - /* Sorry, but we don't support pid_max changing after setting */ - if (task->pid >= pid_list->pid_max) - return; - - /* "self" is set for forks, and NULL for exits */ - if (self) - set_bit(task->pid, pid_list->pids); - else - clear_bit(task->pid, pid_list->pids); -} - static void event_filter_pid_sched_process_exit(void *data, struct task_struct *task) { @@ -560,7 +513,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task) struct trace_array *tr = data; pid_list = rcu_dereference_sched(tr->filtered_pids); - filter_add_remove_task(pid_list, NULL, task); + trace_filter_add_remove_task(pid_list, NULL, task); } static void @@ -572,7 +525,7 @@ event_filter_pid_sched_process_fork(void *data, struct trace_array *tr = data; pid_list = rcu_dereference_sched(tr->filtered_pids); - filter_add_remove_task(pid_list, self, task); + trace_filter_add_remove_task(pid_list, self, task); } void trace_event_follow_fork(struct trace_array *tr, bool enable) @@ -600,8 +553,8 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, pid_list = rcu_dereference_sched(tr->filtered_pids); this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, prev) && - ignore_this_task(pid_list, next)); + trace_ignore_this_task(pid_list, prev) && + trace_ignore_this_task(pid_list, next)); } static void @@ -614,7 +567,7 @@ event_filter_pid_sched_switch_probe_post(void *data, bool preempt, pid_list = rcu_dereference_sched(tr->filtered_pids); this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, next)); + trace_ignore_this_task(pid_list, next)); } static void @@ -630,7 +583,7 @@ event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task) pid_list = rcu_dereference_sched(tr->filtered_pids); this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, task)); + trace_ignore_this_task(pid_list, task)); } static void @@ -647,7 +600,7 @@ event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task) /* Set tracing if current is enabled */ this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, current)); + trace_ignore_this_task(pid_list, current)); } static void __ftrace_clear_event_pids(struct trace_array *tr) @@ -685,8 +638,7 @@ static void __ftrace_clear_event_pids(struct trace_array *tr) /* Wait till all users are no longer using pid filtering */ synchronize_sched(); - vfree(pid_list->pids); - kfree(pid_list); + trace_free_pid_list(pid_list); } static void ftrace_clear_event_pids(struct trace_array *tr) @@ -1034,18 +986,8 @@ p_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_array *tr = m->private; struct trace_pid_list *pid_list = rcu_dereference_sched(tr->filtered_pids); - unsigned long pid = (unsigned long)v; - - (*pos)++; - - /* pid already is +1 of the actual prevous bit */ - pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid); - /* Return pid + 1 to allow zero to be represented */ - if (pid < pid_list->pid_max) - return (void *)(pid + 1); - - return NULL; + return trace_pid_next(pid_list, v, pos); } static void *p_start(struct seq_file *m, loff_t *pos) @@ -1053,8 +995,6 @@ static void *p_start(struct seq_file *m, loff_t *pos) { struct trace_pid_list *pid_list; struct trace_array *tr = m->private; - unsigned long pid; - loff_t l = 0; /* * Grab the mutex, to keep calls to p_next() having the same @@ -1070,15 +1010,7 @@ static void *p_start(struct seq_file *m, loff_t *pos) if (!pid_list) return NULL; - pid = find_first_bit(pid_list->pids, pid_list->pid_max); - if (pid >= pid_list->pid_max) - return NULL; - - /* Return pid + 1 so that zero can be the exit value */ - for (pid++; pid && l < *pos; - pid = (unsigned long)p_next(m, (void *)pid, &l)) - ; - return (void *)pid; + return trace_pid_start(pid_list, pos); } static void p_stop(struct seq_file *m, void *p) @@ -1088,14 +1020,6 @@ static void p_stop(struct seq_file *m, void *p) mutex_unlock(&event_mutex); } -static int p_show(struct seq_file *m, void *v) -{ - unsigned long pid = (unsigned long)v - 1; - - seq_printf(m, "%lu\n", pid); - return 0; -} - static ssize_t event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -1654,7 +1578,7 @@ static void ignore_task_cpu(void *data) mutex_is_locked(&event_mutex)); this_cpu_write(tr->trace_buffer.data->ignore_pid, - ignore_this_task(pid_list, current)); + trace_ignore_this_task(pid_list, current)); } static ssize_t @@ -1666,13 +1590,7 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, struct trace_pid_list *filtered_pids = NULL; struct trace_pid_list *pid_list; struct trace_event_file *file; - struct trace_parser parser; - unsigned long val; - loff_t this_pos; - ssize_t read = 0; - ssize_t ret = 0; - pid_t pid; - int nr_pids = 0; + ssize_t ret; if (!cnt) return 0; @@ -1681,93 +1599,15 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, if (ret < 0) return ret; - if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1)) - return -ENOMEM; - mutex_lock(&event_mutex); + filtered_pids = rcu_dereference_protected(tr->filtered_pids, lockdep_is_held(&event_mutex)); - /* - * Always recreate a new array. The write is an all or nothing - * operation. Always create a new array when adding new pids by - * the user. If the operation fails, then the current list is - * not modified. - */ - pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL); - if (!pid_list) { - read = -ENOMEM; - goto out; - } - pid_list->pid_max = READ_ONCE(pid_max); - /* Only truncating will shrink pid_max */ - if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max) - pid_list->pid_max = filtered_pids->pid_max; - pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3); - if (!pid_list->pids) { - kfree(pid_list); - read = -ENOMEM; - goto out; - } - if (filtered_pids) { - /* copy the current bits to the new max */ - pid = find_first_bit(filtered_pids->pids, - filtered_pids->pid_max); - while (pid < filtered_pids->pid_max) { - set_bit(pid, pid_list->pids); - pid = find_next_bit(filtered_pids->pids, - filtered_pids->pid_max, - pid + 1); - nr_pids++; - } - } - - while (cnt > 0) { - - this_pos = 0; - - ret = trace_get_user(&parser, ubuf, cnt, &this_pos); - if (ret < 0 || !trace_parser_loaded(&parser)) - break; - - read += ret; - ubuf += ret; - cnt -= ret; - - parser.buffer[parser.idx] = 0; - - ret = -EINVAL; - if (kstrtoul(parser.buffer, 0, &val)) - break; - if (val >= pid_list->pid_max) - break; - - pid = (pid_t)val; - - set_bit(pid, pid_list->pids); - nr_pids++; - - trace_parser_clear(&parser); - ret = 0; - } - trace_parser_put(&parser); - - if (ret < 0) { - vfree(pid_list->pids); - kfree(pid_list); - read = ret; + ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); + if (ret < 0) goto out; - } - if (!nr_pids) { - /* Cleared the list of pids */ - vfree(pid_list->pids); - kfree(pid_list); - read = ret; - if (!filtered_pids) - goto out; - pid_list = NULL; - } rcu_assign_pointer(tr->filtered_pids, pid_list); list_for_each_entry(file, &tr->events, list) { @@ -1776,10 +1616,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, if (filtered_pids) { synchronize_sched(); - - vfree(filtered_pids->pids); - kfree(filtered_pids); - } else { + trace_free_pid_list(filtered_pids); + } else if (pid_list) { /* * Register a probe that is called before all other probes * to set ignore_pid if next or prev do not match. @@ -1817,9 +1655,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, out: mutex_unlock(&event_mutex); - ret = read; - if (read > 0) - *ppos += read; + if (ret > 0) + *ppos += ret; return ret; } @@ -1846,7 +1683,7 @@ static const struct seq_operations show_set_event_seq_ops = { static const struct seq_operations show_set_pid_seq_ops = { .start = p_start, .next = p_next, - .show = p_show, + .show = trace_pid_show, .stop = p_stop, }; diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0c05b8a99806..f3a960ed75a1 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1441,6 +1441,9 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops, goto out; } + if (hist_data->attrs->pause) + data->paused = true; + if (named_data) { destroy_hist_data(data->private_data); data->private_data = named_data->private_data; @@ -1448,9 +1451,6 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops, data->ops = &event_hist_trigger_named_ops; } - if (hist_data->attrs->pause) - data->paused = true; - if (data->ops->init) { ret = data->ops->init(data->ops, data); if (ret < 0) @@ -1500,9 +1500,9 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops, static void hist_unreg_all(struct trace_event_file *file) { - struct event_trigger_data *test; + struct event_trigger_data *test, *n; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry_safe(test, n, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { list_del_rcu(&test->list); trace_event_trigger_enable_disable(file, 0); @@ -1699,9 +1699,9 @@ hist_enable_get_trigger_ops(char *cmd, char *param) static void hist_enable_unreg_all(struct trace_event_file *file) { - struct event_trigger_data *test; + struct event_trigger_data *test, *n; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry_safe(test, n, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_HIST_ENABLE) { list_del_rcu(&test->list); update_cond_flag(file); diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 5a095c2e4b69..0efa00d80623 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -43,7 +43,7 @@ static int allocate_ftrace_ops(struct trace_array *tr) /* Currently only the non stack verision is supported */ ops->func = function_trace_call; - ops->flags = FTRACE_OPS_FL_RECURSION_SAFE; + ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID; tr->ops = ops; ops->private = tr; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 3a0244ff7ea8..7363ccf79512 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -319,7 +319,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) int cpu; int pc; - if (!ftrace_trace_task(current)) + if (!ftrace_trace_task(tr)) return 0; /* trace it when it is-nested-in or is a function enabled. */ @@ -338,6 +338,13 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) if (ftrace_graph_notrace_addr(trace->func)) return 1; + /* + * Stop here if tracing_threshold is set. We only write function return + * events to the ring buffer. + */ + if (tracing_thresh) + return 1; + local_irq_save(flags); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->trace_buffer.data, cpu); @@ -355,14 +362,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) return ret; } -static int trace_graph_thresh_entry(struct ftrace_graph_ent *trace) -{ - if (tracing_thresh) - return 1; - else - return trace_graph_entry(trace); -} - static void __trace_graph_function(struct trace_array *tr, unsigned long ip, unsigned long flags, int pc) @@ -457,7 +456,7 @@ static int graph_trace_init(struct trace_array *tr) set_graph_array(tr); if (tracing_thresh) ret = register_ftrace_graph(&trace_graph_thresh_return, - &trace_graph_thresh_entry); + &trace_graph_entry); else ret = register_ftrace_graph(&trace_graph_return, &trace_graph_entry); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5546eec0505f..9aedb0b06683 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -587,6 +587,7 @@ static int create_trace_kprobe(int argc, char **argv) * $retval : fetch return value * $stack : fetch stack address * $stackN : fetch Nth of stack (N:0-) + * $comm : fetch current task comm * @ADDR : fetch memory at ADDR (ADDR should be in kernel) * @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol) * %REG : fetch register REG diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 68f376ca6d3f..cd7480d0a201 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -68,19 +68,15 @@ static void mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev) trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x", dev->bus->number, dev->devfn, dev->vendor, dev->device, dev->irq); - /* - * XXX: is pci_resource_to_user() appropriate, since we are - * supposed to interpret the __ioremap() phys_addr argument based on - * these printed values? - */ for (i = 0; i < 7; i++) { - pci_resource_to_user(dev, i, &dev->resource[i], &start, &end); + start = dev->resource[i].start; trace_seq_printf(s, " %llx", (unsigned long long)(start | (dev->resource[i].flags & PCI_REGION_FLAG_MASK))); } for (i = 0; i < 7; i++) { - pci_resource_to_user(dev, i, &dev->resource[i], &start, &end); + start = dev->resource[i].start; + end = dev->resource[i].end; trace_seq_printf(s, " %llx", dev->resource[i].start < dev->resource[i].end ? (unsigned long long)(end - start) + 1 : 0); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 1d372fa6fefb..74e80a582c28 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -218,6 +218,28 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data) kfree(data); } +void FETCH_FUNC_NAME(comm, string)(struct pt_regs *regs, + void *data, void *dest) +{ + int maxlen = get_rloc_len(*(u32 *)dest); + u8 *dst = get_rloc_data(dest); + long ret; + + if (!maxlen) + return; + + ret = strlcpy(dst, current->comm, maxlen); + *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest)); +} +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string)); + +void FETCH_FUNC_NAME(comm, string_size)(struct pt_regs *regs, + void *data, void *dest) +{ + *(u32 *)dest = strlen(current->comm) + 1; +} +NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string_size)); + static const struct fetch_type *find_fetch_type(const char *type, const struct fetch_type *ftbl) { @@ -348,6 +370,11 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, } } else ret = -EINVAL; + } else if (strcmp(arg, "comm") == 0) { + if (strcmp(t->name, "string") != 0 && + strcmp(t->name, "string_size") != 0) + return -EINVAL; + f->fn = t->fetch[FETCH_MTD_comm]; } else ret = -EINVAL; @@ -522,6 +549,12 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, arg[t - parg->comm] = '\0'; t++; } + /* + * The default type of $comm should be "string", and it can't be + * dereferenced. + */ + if (!t && strcmp(arg, "$comm") == 0) + t = "string"; parg->type = find_fetch_type(t, ftbl); if (!parg->type) { pr_info("Unsupported type: %s\n", t); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index f6398db09114..45400ca5ded1 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -102,6 +102,7 @@ enum { FETCH_MTD_reg = 0, FETCH_MTD_stack, FETCH_MTD_retval, + FETCH_MTD_comm, FETCH_MTD_memory, FETCH_MTD_symbol, FETCH_MTD_deref, @@ -183,6 +184,14 @@ DECLARE_BASIC_FETCH_FUNCS(bitfield); #define fetch_bitfield_string NULL #define fetch_bitfield_string_size NULL +/* comm only makes sense as a string */ +#define fetch_comm_u8 NULL +#define fetch_comm_u16 NULL +#define fetch_comm_u32 NULL +#define fetch_comm_u64 NULL +DECLARE_FETCH_FUNC(comm, string); +DECLARE_FETCH_FUNC(comm, string_size); + /* * Define macro for basic types - we don't need to define s* types, because * we have to care only about bitwidth at recording time. @@ -213,6 +222,7 @@ DEFINE_FETCH_##method(u64) ASSIGN_FETCH_FUNC(reg, ftype), \ ASSIGN_FETCH_FUNC(stack, ftype), \ ASSIGN_FETCH_FUNC(retval, ftype), \ +ASSIGN_FETCH_FUNC(comm, ftype), \ ASSIGN_FETCH_FUNC(memory, ftype), \ ASSIGN_FETCH_FUNC(symbol, ftype), \ ASSIGN_FETCH_FUNC(deref, ftype), \ diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 9bafc211930c..68f594212759 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -938,6 +938,20 @@ bool userns_may_setgroups(const struct user_namespace *ns) return allowed; } +/* + * Returns true if @ns is the same namespace as or a descendant of + * @target_ns. + */ +bool current_in_userns(const struct user_namespace *target_ns) +{ + struct user_namespace *ns; + for (ns = current_user_ns(); ns; ns = ns->parent) { + if (ns == target_ns) + return true; + } + return false; +} + static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 97e7b793df35..ef071ca73fc3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4369,8 +4369,8 @@ static void show_pwq(struct pool_workqueue *pwq) /** * show_workqueue_state - dump workqueue state * - * Called from a sysrq handler and prints out all busy workqueues and - * pools. + * Called from a sysrq handler or try_to_freeze_tasks() and prints out + * all busy workqueues and pools. */ void show_workqueue_state(void) { @@ -4607,84 +4607,65 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } -/* - * Workqueues should be brought up before normal priority CPU notifiers. - * This will be registered high priority CPU notifier. - */ -static int workqueue_cpu_up_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) +int workqueue_prepare_cpu(unsigned int cpu) +{ + struct worker_pool *pool; + + for_each_cpu_worker_pool(pool, cpu) { + if (pool->nr_workers) + continue; + if (!create_worker(pool)) + return -ENOMEM; + } + return 0; +} + +int workqueue_online_cpu(unsigned int cpu) { - int cpu = (unsigned long)hcpu; struct worker_pool *pool; struct workqueue_struct *wq; int pi; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - for_each_cpu_worker_pool(pool, cpu) { - if (pool->nr_workers) - continue; - if (!create_worker(pool)) - return NOTIFY_BAD; - } - break; - - case CPU_DOWN_FAILED: - case CPU_ONLINE: - mutex_lock(&wq_pool_mutex); + mutex_lock(&wq_pool_mutex); - for_each_pool(pool, pi) { - mutex_lock(&pool->attach_mutex); + for_each_pool(pool, pi) { + mutex_lock(&pool->attach_mutex); - if (pool->cpu == cpu) - rebind_workers(pool); - else if (pool->cpu < 0) - restore_unbound_workers_cpumask(pool, cpu); + if (pool->cpu == cpu) + rebind_workers(pool); + else if (pool->cpu < 0) + restore_unbound_workers_cpumask(pool, cpu); - mutex_unlock(&pool->attach_mutex); - } + mutex_unlock(&pool->attach_mutex); + } - /* update NUMA affinity of unbound workqueues */ - list_for_each_entry(wq, &workqueues, list) - wq_update_unbound_numa(wq, cpu, true); + /* update NUMA affinity of unbound workqueues */ + list_for_each_entry(wq, &workqueues, list) + wq_update_unbound_numa(wq, cpu, true); - mutex_unlock(&wq_pool_mutex); - break; - } - return NOTIFY_OK; + mutex_unlock(&wq_pool_mutex); + return 0; } -/* - * Workqueues should be brought down after normal priority CPU notifiers. - * This will be registered as low priority CPU notifier. - */ -static int workqueue_cpu_down_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) +int workqueue_offline_cpu(unsigned int cpu) { - int cpu = (unsigned long)hcpu; struct work_struct unbind_work; struct workqueue_struct *wq; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DOWN_PREPARE: - /* unbinding per-cpu workers should happen on the local CPU */ - INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn); - queue_work_on(cpu, system_highpri_wq, &unbind_work); - - /* update NUMA affinity of unbound workqueues */ - mutex_lock(&wq_pool_mutex); - list_for_each_entry(wq, &workqueues, list) - wq_update_unbound_numa(wq, cpu, false); - mutex_unlock(&wq_pool_mutex); - - /* wait for per-cpu unbinding to finish */ - flush_work(&unbind_work); - destroy_work_on_stack(&unbind_work); - break; - } - return NOTIFY_OK; + /* unbinding per-cpu workers should happen on the local CPU */ + INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn); + queue_work_on(cpu, system_highpri_wq, &unbind_work); + + /* update NUMA affinity of unbound workqueues */ + mutex_lock(&wq_pool_mutex); + list_for_each_entry(wq, &workqueues, list) + wq_update_unbound_numa(wq, cpu, false); + mutex_unlock(&wq_pool_mutex); + + /* wait for per-cpu unbinding to finish */ + flush_work(&unbind_work); + destroy_work_on_stack(&unbind_work); + return 0; } #ifdef CONFIG_SMP @@ -5486,9 +5467,6 @@ static int __init init_workqueues(void) pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); - cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); - hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); - wq_numa_init(); /* initialize CPU pools */ |