diff options
Diffstat (limited to 'kernel')
61 files changed, 2463 insertions, 1592 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index f70396e5a24b..2d9de86b7e76 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -23,6 +23,7 @@ CFLAGS_REMOVE_irq_work.o = -pg endif obj-y += sched/ +obj-y += power/ obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.o @@ -52,8 +53,6 @@ obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_KALLSYMS) += kallsyms.o -obj-$(CONFIG_PM) += power/ -obj-$(CONFIG_FREEZER) += power/ obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o diff --git a/kernel/acct.c b/kernel/acct.c index 203dfead2e06..02e6167a53b0 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -84,11 +84,10 @@ static void do_acct_process(struct bsd_acct_struct *acct, * the cache line to have the data after getting the lock. */ struct bsd_acct_struct { - volatile int active; - volatile int needcheck; + int active; + unsigned long needcheck; struct file *file; struct pid_namespace *ns; - struct timer_list timer; struct list_head list; }; @@ -96,15 +95,6 @@ static DEFINE_SPINLOCK(acct_lock); static LIST_HEAD(acct_list); /* - * Called whenever the timer says to check the free space. - */ -static void acct_timeout(unsigned long x) -{ - struct bsd_acct_struct *acct = (struct bsd_acct_struct *)x; - acct->needcheck = 1; -} - -/* * Check the amount of free space and suspend/resume accordingly. */ static int check_free_space(struct bsd_acct_struct *acct, struct file *file) @@ -112,12 +102,12 @@ static int check_free_space(struct bsd_acct_struct *acct, struct file *file) struct kstatfs sbuf; int res; int act; - sector_t resume; - sector_t suspend; + u64 resume; + u64 suspend; spin_lock(&acct_lock); res = acct->active; - if (!file || !acct->needcheck) + if (!file || time_is_before_jiffies(acct->needcheck)) goto out; spin_unlock(&acct_lock); @@ -127,8 +117,8 @@ static int check_free_space(struct bsd_acct_struct *acct, struct file *file) suspend = sbuf.f_blocks * SUSPEND; resume = sbuf.f_blocks * RESUME; - sector_div(suspend, 100); - sector_div(resume, 100); + do_div(suspend, 100); + do_div(resume, 100); if (sbuf.f_bavail <= suspend) act = -1; @@ -160,10 +150,7 @@ static int check_free_space(struct bsd_acct_struct *acct, struct file *file) } } - del_timer(&acct->timer); - acct->needcheck = 0; - acct->timer.expires = jiffies + ACCT_TIMEOUT*HZ; - add_timer(&acct->timer); + acct->needcheck = jiffies + ACCT_TIMEOUT*HZ; res = acct->active; out: spin_unlock(&acct_lock); @@ -185,9 +172,7 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file, if (acct->file) { old_acct = acct->file; old_ns = acct->ns; - del_timer(&acct->timer); acct->active = 0; - acct->needcheck = 0; acct->file = NULL; acct->ns = NULL; list_del(&acct->list); @@ -195,13 +180,9 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file, if (file) { acct->file = file; acct->ns = ns; - acct->needcheck = 0; + acct->needcheck = jiffies + ACCT_TIMEOUT*HZ; acct->active = 1; list_add(&acct->list, &acct_list); - /* It's been deleted if it was used before so this is safe */ - setup_timer(&acct->timer, acct_timeout, (unsigned long)acct); - acct->timer.expires = jiffies + ACCT_TIMEOUT*HZ; - add_timer(&acct->timer); } if (old_acct) { mnt_unpin(old_acct->f_path.mnt); @@ -334,7 +315,7 @@ void acct_auto_close(struct super_block *sb) spin_lock(&acct_lock); restart: list_for_each_entry(acct, &acct_list, list) - if (acct->file && acct->file->f_path.mnt->mnt_sb == sb) { + if (acct->file && acct->file->f_path.dentry->d_sb == sb) { acct_file_reopen(acct, NULL, NULL); goto restart; } @@ -348,7 +329,6 @@ void acct_exit_ns(struct pid_namespace *ns) if (acct == NULL) return; - del_timer_sync(&acct->timer); spin_lock(&acct_lock); if (acct->file != NULL) acct_file_reopen(acct, NULL, NULL); @@ -498,7 +478,7 @@ static void do_acct_process(struct bsd_acct_struct *acct, * Fill the accounting struct with the needed info as recorded * by the different kernel functions. */ - memset((caddr_t)&ac, 0, sizeof(acct_t)); + memset(&ac, 0, sizeof(acct_t)); ac.ac_version = ACCT_VERSION | ACCT_BYTEORDER; strlcpy(ac.ac_comm, current->comm, sizeof(ac.ac_comm)); diff --git a/kernel/async.c b/kernel/async.c index 80b74b88fefe..bd0c168a3bbe 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -78,8 +78,6 @@ static DECLARE_WAIT_QUEUE_HEAD(async_done); static atomic_t entry_count; -extern int initcall_debug; - /* * MUST be called with the lock held! diff --git a/kernel/audit.c b/kernel/audit.c index 09fae2677a45..bb0eb5bb9a0a 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -601,13 +601,13 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) case AUDIT_TTY_SET: case AUDIT_TRIM: case AUDIT_MAKE_EQUIV: - if (security_netlink_recv(skb, CAP_AUDIT_CONTROL)) + if (!capable(CAP_AUDIT_CONTROL)) err = -EPERM; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: - if (security_netlink_recv(skb, CAP_AUDIT_WRITE)) + if (!capable(CAP_AUDIT_WRITE)) err = -EPERM; break; default: /* bad msg */ @@ -631,7 +631,7 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type, } *ab = audit_log_start(NULL, GFP_KERNEL, msg_type); - audit_log_format(*ab, "user pid=%d uid=%u auid=%u ses=%u", + audit_log_format(*ab, "pid=%d uid=%u auid=%u ses=%u", pid, uid, auid, ses); if (sid) { rc = security_secid_to_secctx(sid, &ctx, &len); @@ -1260,12 +1260,13 @@ static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, avail = audit_expand(ab, max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail)); if (!avail) - goto out; + goto out_va_end; len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2); } - va_end(args2); if (len > 0) skb_put(skb, len); +out_va_end: + va_end(args2); out: return; } @@ -1422,7 +1423,7 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix, char *p, *pathname; if (prefix) - audit_log_format(ab, " %s", prefix); + audit_log_format(ab, "%s", prefix); /* We will allow 11 spaces for ' (deleted)' to be appended */ pathname = kmalloc(PATH_MAX+11, ab->gfp_mask); diff --git a/kernel/audit.h b/kernel/audit.h index 91e7071c4d2c..816766803371 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -36,12 +36,8 @@ enum audit_state { AUDIT_DISABLED, /* Do not create per-task audit_context. * No syscall-specific audit records can * be generated. */ - AUDIT_SETUP_CONTEXT, /* Create the per-task audit_context, - * but don't necessarily fill it in at - * syscall entry time (i.e., filter - * instead). */ AUDIT_BUILD_CONTEXT, /* Create the per-task audit_context, - * and always fill it in at syscall + * and fill it in at syscall * entry time. This makes a full * syscall record available if some * other part of the kernel decides it diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index f8277c80d678..a6c3f1abd206 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -235,13 +235,15 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule *rule) switch(listnr) { default: goto exit_err; - case AUDIT_FILTER_USER: - case AUDIT_FILTER_TYPE: #ifdef CONFIG_AUDITSYSCALL case AUDIT_FILTER_ENTRY: + if (rule->action == AUDIT_ALWAYS) + goto exit_err; case AUDIT_FILTER_EXIT: case AUDIT_FILTER_TASK: #endif + case AUDIT_FILTER_USER: + case AUDIT_FILTER_TYPE: ; } if (unlikely(rule->action == AUDIT_POSSIBLE)) { @@ -385,7 +387,7 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule) goto exit_free; break; case AUDIT_FILETYPE: - if ((f->val & ~S_IFMT) > S_IFMT) + if (f->val & ~S_IFMT) goto exit_free; break; case AUDIT_INODE: @@ -459,6 +461,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_ARG1: case AUDIT_ARG2: case AUDIT_ARG3: + case AUDIT_OBJ_UID: + case AUDIT_OBJ_GID: break; case AUDIT_ARCH: entry->rule.arch_f = f; @@ -522,7 +526,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, goto exit_free; break; case AUDIT_FILTERKEY: - err = -EINVAL; if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN) goto exit_free; str = audit_unpack_string(&bufp, &remain, f->val); @@ -536,7 +539,11 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, goto exit_free; break; case AUDIT_FILETYPE: - if ((f->val & ~S_IFMT) > S_IFMT) + if (f->val & ~S_IFMT) + goto exit_free; + break; + case AUDIT_FIELD_COMPARE: + if (f->val > AUDIT_MAX_FIELD_COMPARE) goto exit_free; break; default: diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 47b7fc1ea893..caaea6e944f8 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -70,9 +70,15 @@ #include "audit.h" +/* flags stating the success for a syscall */ +#define AUDITSC_INVALID 0 +#define AUDITSC_SUCCESS 1 +#define AUDITSC_FAILURE 2 + /* AUDIT_NAMES is the number of slots we reserve in the audit_context - * for saving names from getname(). */ -#define AUDIT_NAMES 20 + * for saving names from getname(). If we get more names we will allocate + * a name dynamically and also add those to the list anchored by names_list. */ +#define AUDIT_NAMES 5 /* Indicates that audit should log the full pathname. */ #define AUDIT_NAME_FULL -1 @@ -101,9 +107,8 @@ struct audit_cap_data { * * Further, in fs/namei.c:path_lookup() we store the inode and device. */ struct audit_names { + struct list_head list; /* audit_context->names_list */ const char *name; - int name_len; /* number of name's characters to log */ - unsigned name_put; /* call __putname() for this name */ unsigned long ino; dev_t dev; umode_t mode; @@ -113,6 +118,14 @@ struct audit_names { u32 osid; struct audit_cap_data fcap; unsigned int fcap_ver; + int name_len; /* number of name's characters to log */ + bool name_put; /* call __putname() for this name */ + /* + * This was an allocated audit_names and not from the array of + * names allocated in the task audit context. Thus this name + * should be freed on syscall exit + */ + bool should_free; }; struct audit_aux_data { @@ -174,8 +187,17 @@ struct audit_context { long return_code;/* syscall return code */ u64 prio; int return_valid; /* return code is valid */ - int name_count; - struct audit_names names[AUDIT_NAMES]; + /* + * The names_list is the list of all audit_names collected during this + * syscall. The first AUDIT_NAMES entries in the names_list will + * actually be from the preallocated_names array for performance + * reasons. Except during allocation they should never be referenced + * through the preallocated_names array and should only be found/used + * by running the names_list. + */ + struct audit_names preallocated_names[AUDIT_NAMES]; + int name_count; /* total records in names_list */ + struct list_head names_list; /* anchor for struct audit_names->list */ char * filterkey; /* key for rule that triggered record */ struct path pwd; struct audit_context *previous; /* For nested syscalls */ @@ -210,12 +232,12 @@ struct audit_context { struct { uid_t uid; gid_t gid; - mode_t mode; + umode_t mode; u32 osid; int has_perm; uid_t perm_uid; gid_t perm_gid; - mode_t perm_mode; + umode_t perm_mode; unsigned long qbytes; } ipc; struct { @@ -234,7 +256,7 @@ struct audit_context { } mq_sendrecv; struct { int oflag; - mode_t mode; + umode_t mode; struct mq_attr attr; } mq_open; struct { @@ -305,21 +327,21 @@ static int audit_match_perm(struct audit_context *ctx, int mask) } } -static int audit_match_filetype(struct audit_context *ctx, int which) +static int audit_match_filetype(struct audit_context *ctx, int val) { - unsigned index = which & ~S_IFMT; - mode_t mode = which & S_IFMT; + struct audit_names *n; + umode_t mode = (umode_t)val; if (unlikely(!ctx)) return 0; - if (index >= ctx->name_count) - return 0; - if (ctx->names[index].ino == -1) - return 0; - if ((ctx->names[index].mode ^ mode) & S_IFMT) - return 0; - return 1; + list_for_each_entry(n, &ctx->names_list, list) { + if ((n->ino != -1) && + ((n->mode & S_IFMT) == mode)) + return 1; + } + + return 0; } /* @@ -441,6 +463,134 @@ static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree) return 0; } +static int audit_compare_id(uid_t uid1, + struct audit_names *name, + unsigned long name_offset, + struct audit_field *f, + struct audit_context *ctx) +{ + struct audit_names *n; + unsigned long addr; + uid_t uid2; + int rc; + + BUILD_BUG_ON(sizeof(uid_t) != sizeof(gid_t)); + + if (name) { + addr = (unsigned long)name; + addr += name_offset; + + uid2 = *(uid_t *)addr; + rc = audit_comparator(uid1, f->op, uid2); + if (rc) + return rc; + } + + if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + addr = (unsigned long)n; + addr += name_offset; + + uid2 = *(uid_t *)addr; + + rc = audit_comparator(uid1, f->op, uid2); + if (rc) + return rc; + } + } + return 0; +} + +static int audit_field_compare(struct task_struct *tsk, + const struct cred *cred, + struct audit_field *f, + struct audit_context *ctx, + struct audit_names *name) +{ + switch (f->val) { + /* process to file object comparisons */ + case AUDIT_COMPARE_UID_TO_OBJ_UID: + return audit_compare_id(cred->uid, + name, offsetof(struct audit_names, uid), + f, ctx); + case AUDIT_COMPARE_GID_TO_OBJ_GID: + return audit_compare_id(cred->gid, + name, offsetof(struct audit_names, gid), + f, ctx); + case AUDIT_COMPARE_EUID_TO_OBJ_UID: + return audit_compare_id(cred->euid, + name, offsetof(struct audit_names, uid), + f, ctx); + case AUDIT_COMPARE_EGID_TO_OBJ_GID: + return audit_compare_id(cred->egid, + name, offsetof(struct audit_names, gid), + f, ctx); + case AUDIT_COMPARE_AUID_TO_OBJ_UID: + return audit_compare_id(tsk->loginuid, + name, offsetof(struct audit_names, uid), + f, ctx); + case AUDIT_COMPARE_SUID_TO_OBJ_UID: + return audit_compare_id(cred->suid, + name, offsetof(struct audit_names, uid), + f, ctx); + case AUDIT_COMPARE_SGID_TO_OBJ_GID: + return audit_compare_id(cred->sgid, + name, offsetof(struct audit_names, gid), + f, ctx); + case AUDIT_COMPARE_FSUID_TO_OBJ_UID: + return audit_compare_id(cred->fsuid, + name, offsetof(struct audit_names, uid), + f, ctx); + case AUDIT_COMPARE_FSGID_TO_OBJ_GID: + return audit_compare_id(cred->fsgid, + name, offsetof(struct audit_names, gid), + f, ctx); + /* uid comparisons */ + case AUDIT_COMPARE_UID_TO_AUID: + return audit_comparator(cred->uid, f->op, tsk->loginuid); + case AUDIT_COMPARE_UID_TO_EUID: + return audit_comparator(cred->uid, f->op, cred->euid); + case AUDIT_COMPARE_UID_TO_SUID: + return audit_comparator(cred->uid, f->op, cred->suid); + case AUDIT_COMPARE_UID_TO_FSUID: + return audit_comparator(cred->uid, f->op, cred->fsuid); + /* auid comparisons */ + case AUDIT_COMPARE_AUID_TO_EUID: + return audit_comparator(tsk->loginuid, f->op, cred->euid); + case AUDIT_COMPARE_AUID_TO_SUID: + return audit_comparator(tsk->loginuid, f->op, cred->suid); + case AUDIT_COMPARE_AUID_TO_FSUID: + return audit_comparator(tsk->loginuid, f->op, cred->fsuid); + /* euid comparisons */ + case AUDIT_COMPARE_EUID_TO_SUID: + return audit_comparator(cred->euid, f->op, cred->suid); + case AUDIT_COMPARE_EUID_TO_FSUID: + return audit_comparator(cred->euid, f->op, cred->fsuid); + /* suid comparisons */ + case AUDIT_COMPARE_SUID_TO_FSUID: + return audit_comparator(cred->suid, f->op, cred->fsuid); + /* gid comparisons */ + case AUDIT_COMPARE_GID_TO_EGID: + return audit_comparator(cred->gid, f->op, cred->egid); + case AUDIT_COMPARE_GID_TO_SGID: + return audit_comparator(cred->gid, f->op, cred->sgid); + case AUDIT_COMPARE_GID_TO_FSGID: + return audit_comparator(cred->gid, f->op, cred->fsgid); + /* egid comparisons */ + case AUDIT_COMPARE_EGID_TO_SGID: + return audit_comparator(cred->egid, f->op, cred->sgid); + case AUDIT_COMPARE_EGID_TO_FSGID: + return audit_comparator(cred->egid, f->op, cred->fsgid); + /* sgid comparison */ + case AUDIT_COMPARE_SGID_TO_FSGID: + return audit_comparator(cred->sgid, f->op, cred->fsgid); + default: + WARN(1, "Missing AUDIT_COMPARE define. Report as a bug\n"); + return 0; + } + return 0; +} + /* Determine if any context name data matches a rule's watch data */ /* Compare a task_struct with an audit_rule. Return 1 on match, 0 * otherwise. @@ -457,13 +607,14 @@ static int audit_filter_rules(struct task_struct *tsk, bool task_creation) { const struct cred *cred; - int i, j, need_sid = 1; + int i, need_sid = 1; u32 sid; cred = rcu_dereference_check(tsk->cred, tsk == current || task_creation); for (i = 0; i < rule->field_count; i++) { struct audit_field *f = &rule->fields[i]; + struct audit_names *n; int result = 0; switch (f->type) { @@ -522,12 +673,14 @@ static int audit_filter_rules(struct task_struct *tsk, } break; case AUDIT_DEVMAJOR: - if (name) - result = audit_comparator(MAJOR(name->dev), - f->op, f->val); - else if (ctx) { - for (j = 0; j < ctx->name_count; j++) { - if (audit_comparator(MAJOR(ctx->names[j].dev), f->op, f->val)) { + if (name) { + if (audit_comparator(MAJOR(name->dev), f->op, f->val) || + audit_comparator(MAJOR(name->rdev), f->op, f->val)) + ++result; + } else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_comparator(MAJOR(n->dev), f->op, f->val) || + audit_comparator(MAJOR(n->rdev), f->op, f->val)) { ++result; break; } @@ -535,12 +688,14 @@ static int audit_filter_rules(struct task_struct *tsk, } break; case AUDIT_DEVMINOR: - if (name) - result = audit_comparator(MINOR(name->dev), - f->op, f->val); - else if (ctx) { - for (j = 0; j < ctx->name_count; j++) { - if (audit_comparator(MINOR(ctx->names[j].dev), f->op, f->val)) { + if (name) { + if (audit_comparator(MINOR(name->dev), f->op, f->val) || + audit_comparator(MINOR(name->rdev), f->op, f->val)) + ++result; + } else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_comparator(MINOR(n->dev), f->op, f->val) || + audit_comparator(MINOR(n->rdev), f->op, f->val)) { ++result; break; } @@ -551,8 +706,32 @@ static int audit_filter_rules(struct task_struct *tsk, if (name) result = (name->ino == f->val); else if (ctx) { - for (j = 0; j < ctx->name_count; j++) { - if (audit_comparator(ctx->names[j].ino, f->op, f->val)) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_comparator(n->ino, f->op, f->val)) { + ++result; + break; + } + } + } + break; + case AUDIT_OBJ_UID: + if (name) { + result = audit_comparator(name->uid, f->op, f->val); + } else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_comparator(n->uid, f->op, f->val)) { + ++result; + break; + } + } + } + break; + case AUDIT_OBJ_GID: + if (name) { + result = audit_comparator(name->gid, f->op, f->val); + } else if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_comparator(n->gid, f->op, f->val)) { ++result; break; } @@ -607,11 +786,10 @@ static int audit_filter_rules(struct task_struct *tsk, name->osid, f->type, f->op, f->lsm_rule, ctx); } else if (ctx) { - for (j = 0; j < ctx->name_count; j++) { - if (security_audit_rule_match( - ctx->names[j].osid, - f->type, f->op, - f->lsm_rule, ctx)) { + list_for_each_entry(n, &ctx->names_list, list) { + if (security_audit_rule_match(n->osid, f->type, + f->op, f->lsm_rule, + ctx)) { ++result; break; } @@ -643,8 +821,10 @@ static int audit_filter_rules(struct task_struct *tsk, case AUDIT_FILETYPE: result = audit_match_filetype(ctx, f->val); break; + case AUDIT_FIELD_COMPARE: + result = audit_field_compare(tsk, cred, f, ctx, name); + break; } - if (!result) return 0; } @@ -722,40 +902,53 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk, return AUDIT_BUILD_CONTEXT; } -/* At syscall exit time, this filter is called if any audit_names[] have been +/* + * Given an audit_name check the inode hash table to see if they match. + * Called holding the rcu read lock to protect the use of audit_inode_hash + */ +static int audit_filter_inode_name(struct task_struct *tsk, + struct audit_names *n, + struct audit_context *ctx) { + int word, bit; + int h = audit_hash_ino((u32)n->ino); + struct list_head *list = &audit_inode_hash[h]; + struct audit_entry *e; + enum audit_state state; + + word = AUDIT_WORD(ctx->major); + bit = AUDIT_BIT(ctx->major); + + if (list_empty(list)) + return 0; + + list_for_each_entry_rcu(e, list, list) { + if ((e->rule.mask[word] & bit) == bit && + audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) { + ctx->current_state = state; + return 1; + } + } + + return 0; +} + +/* At syscall exit time, this filter is called if any audit_names have been * collected during syscall processing. We only check rules in sublists at hash - * buckets applicable to the inode numbers in audit_names[]. + * buckets applicable to the inode numbers in audit_names. * Regarding audit_state, same rules apply as for audit_filter_syscall(). */ void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx) { - int i; - struct audit_entry *e; - enum audit_state state; + struct audit_names *n; if (audit_pid && tsk->tgid == audit_pid) return; rcu_read_lock(); - for (i = 0; i < ctx->name_count; i++) { - int word = AUDIT_WORD(ctx->major); - int bit = AUDIT_BIT(ctx->major); - struct audit_names *n = &ctx->names[i]; - int h = audit_hash_ino((u32)n->ino); - struct list_head *list = &audit_inode_hash[h]; - - if (list_empty(list)) - continue; - list_for_each_entry_rcu(e, list, list) { - if ((e->rule.mask[word] & bit) == bit && - audit_filter_rules(tsk, &e->rule, ctx, n, - &state, false)) { - rcu_read_unlock(); - ctx->current_state = state; - return; - } - } + list_for_each_entry(n, &ctx->names_list, list) { + if (audit_filter_inode_name(tsk, n, ctx)) + break; } rcu_read_unlock(); } @@ -766,7 +959,7 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk, { struct audit_context *context = tsk->audit_context; - if (likely(!context)) + if (!context) return NULL; context->return_valid = return_valid; @@ -799,7 +992,7 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk, static inline void audit_free_names(struct audit_context *context) { - int i; + struct audit_names *n, *next; #if AUDIT_DEBUG == 2 if (context->put_count + context->ino_count != context->name_count) { @@ -810,10 +1003,9 @@ static inline void audit_free_names(struct audit_context *context) context->serial, context->major, context->in_syscall, context->name_count, context->put_count, context->ino_count); - for (i = 0; i < context->name_count; i++) { + list_for_each_entry(n, &context->names_list, list) { printk(KERN_ERR "names[%d] = %p = %s\n", i, - context->names[i].name, - context->names[i].name ?: "(null)"); + n->name, n->name ?: "(null)"); } dump_stack(); return; @@ -824,9 +1016,12 @@ static inline void audit_free_names(struct audit_context *context) context->ino_count = 0; #endif - for (i = 0; i < context->name_count; i++) { - if (context->names[i].name && context->names[i].name_put) - __putname(context->names[i].name); + list_for_each_entry_safe(n, next, &context->names_list, list) { + list_del(&n->list); + if (n->name && n->name_put) + __putname(n->name); + if (n->should_free) + kfree(n); } context->name_count = 0; path_put(&context->pwd); @@ -864,6 +1059,7 @@ static inline struct audit_context *audit_alloc_context(enum audit_state state) return NULL; audit_zero_context(context, state); INIT_LIST_HEAD(&context->killed_trees); + INIT_LIST_HEAD(&context->names_list); return context; } @@ -886,7 +1082,7 @@ int audit_alloc(struct task_struct *tsk) return 0; /* Return if not auditing. */ state = audit_filter_task(tsk, &key); - if (likely(state == AUDIT_DISABLED)) + if (state == AUDIT_DISABLED) return 0; if (!(context = audit_alloc_context(state))) { @@ -975,7 +1171,7 @@ static void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk while (vma) { if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file) { - audit_log_d_path(ab, "exe=", + audit_log_d_path(ab, " exe=", &vma->vm_file->f_path); break; } @@ -1166,8 +1362,8 @@ static void audit_log_execve_info(struct audit_context *context, struct audit_buffer **ab, struct audit_aux_data_execve *axi) { - int i; - size_t len, len_sent = 0; + int i, len; + size_t len_sent = 0; const char __user *p; char *buf; @@ -1249,7 +1445,7 @@ static void show_special(struct audit_context *context, int *call_panic) case AUDIT_IPC: { u32 osid = context->ipc.osid; - audit_log_format(ab, "ouid=%u ogid=%u mode=%#o", + audit_log_format(ab, "ouid=%u ogid=%u mode=%#ho", context->ipc.uid, context->ipc.gid, context->ipc.mode); if (osid) { char *ctx = NULL; @@ -1267,7 +1463,7 @@ static void show_special(struct audit_context *context, int *call_panic) ab = audit_log_start(context, GFP_KERNEL, AUDIT_IPC_SET_PERM); audit_log_format(ab, - "qbytes=%lx ouid=%u ogid=%u mode=%#o", + "qbytes=%lx ouid=%u ogid=%u mode=%#ho", context->ipc.qbytes, context->ipc.perm_uid, context->ipc.perm_gid, @@ -1278,7 +1474,7 @@ static void show_special(struct audit_context *context, int *call_panic) break; } case AUDIT_MQ_OPEN: { audit_log_format(ab, - "oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld " + "oflag=0x%x mode=%#ho mq_flags=0x%lx mq_maxmsg=%ld " "mq_msgsize=%ld mq_curmsgs=%ld", context->mq_open.oflag, context->mq_open.mode, context->mq_open.attr.mq_flags, @@ -1324,6 +1520,68 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_end(ab); } +static void audit_log_name(struct audit_context *context, struct audit_names *n, + int record_num, int *call_panic) +{ + struct audit_buffer *ab; + ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH); + if (!ab) + return; /* audit_panic has been called */ + + audit_log_format(ab, "item=%d", record_num); + + if (n->name) { + switch (n->name_len) { + case AUDIT_NAME_FULL: + /* log the full path */ + audit_log_format(ab, " name="); + audit_log_untrustedstring(ab, n->name); + break; + case 0: + /* name was specified as a relative path and the + * directory component is the cwd */ + audit_log_d_path(ab, " name=", &context->pwd); + break; + default: + /* log the name's directory component */ + audit_log_format(ab, " name="); + audit_log_n_untrustedstring(ab, n->name, + n->name_len); + } + } else + audit_log_format(ab, " name=(null)"); + + if (n->ino != (unsigned long)-1) { + audit_log_format(ab, " inode=%lu" + " dev=%02x:%02x mode=%#ho" + " ouid=%u ogid=%u rdev=%02x:%02x", + n->ino, + MAJOR(n->dev), + MINOR(n->dev), + n->mode, + n->uid, + n->gid, + MAJOR(n->rdev), + MINOR(n->rdev)); + } + if (n->osid != 0) { + char *ctx = NULL; + u32 len; + if (security_secid_to_secctx( + n->osid, &ctx, &len)) { + audit_log_format(ab, " osid=%u", n->osid); + *call_panic = 2; + } else { + audit_log_format(ab, " obj=%s", ctx); + security_release_secctx(ctx, len); + } + } + + audit_log_fcaps(ab, n); + + audit_log_end(ab); +} + static void audit_log_exit(struct audit_context *context, struct task_struct *tsk) { const struct cred *cred; @@ -1331,6 +1589,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts struct audit_buffer *ab; struct audit_aux_data *aux; const char *tty; + struct audit_names *n; /* tsk == current */ context->pid = tsk->pid; @@ -1466,70 +1725,14 @@ 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); } } - for (i = 0; i < context->name_count; i++) { - struct audit_names *n = &context->names[i]; - ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH); - if (!ab) - continue; /* audit_panic has been called */ - - audit_log_format(ab, "item=%d", i); - - if (n->name) { - switch(n->name_len) { - case AUDIT_NAME_FULL: - /* log the full path */ - audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, n->name); - break; - case 0: - /* name was specified as a relative path and the - * directory component is the cwd */ - audit_log_d_path(ab, "name=", &context->pwd); - break; - default: - /* log the name's directory component */ - audit_log_format(ab, " name="); - audit_log_n_untrustedstring(ab, n->name, - n->name_len); - } - } else - audit_log_format(ab, " name=(null)"); - - if (n->ino != (unsigned long)-1) { - audit_log_format(ab, " inode=%lu" - " dev=%02x:%02x mode=%#o" - " ouid=%u ogid=%u rdev=%02x:%02x", - n->ino, - MAJOR(n->dev), - MINOR(n->dev), - n->mode, - n->uid, - n->gid, - MAJOR(n->rdev), - MINOR(n->rdev)); - } - if (n->osid != 0) { - char *ctx = NULL; - u32 len; - if (security_secid_to_secctx( - n->osid, &ctx, &len)) { - audit_log_format(ab, " osid=%u", n->osid); - call_panic = 2; - } else { - audit_log_format(ab, " obj=%s", ctx); - security_release_secctx(ctx, len); - } - } - - audit_log_fcaps(ab, n); - - audit_log_end(ab); - } + i = 0; + list_for_each_entry(n, &context->names_list, list) + audit_log_name(context, n, i++, &call_panic); /* Send end of event record to help user space know we are finished */ ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE); @@ -1545,12 +1748,12 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts * * Called from copy_process and do_exit */ -void audit_free(struct task_struct *tsk) +void __audit_free(struct task_struct *tsk) { struct audit_context *context; context = audit_get_context(tsk, 0, 0); - if (likely(!context)) + if (!context) return; /* Check for system calls that do not go through the exit @@ -1583,7 +1786,7 @@ void audit_free(struct task_struct *tsk) * will only be written if another part of the kernel requests that it * be written). */ -void audit_syscall_entry(int arch, int major, +void __audit_syscall_entry(int arch, int major, unsigned long a1, unsigned long a2, unsigned long a3, unsigned long a4) { @@ -1591,7 +1794,7 @@ void audit_syscall_entry(int arch, int major, struct audit_context *context = tsk->audit_context; enum audit_state state; - if (unlikely(!context)) + if (!context) return; /* @@ -1648,7 +1851,7 @@ void audit_syscall_entry(int arch, int major, context->prio = 0; state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]); } - if (likely(state == AUDIT_DISABLED)) + if (state == AUDIT_DISABLED) return; context->serial = 0; @@ -1658,30 +1861,9 @@ void audit_syscall_entry(int arch, int major, context->ppid = 0; } -void audit_finish_fork(struct task_struct *child) -{ - struct audit_context *ctx = current->audit_context; - struct audit_context *p = child->audit_context; - if (!p || !ctx) - return; - if (!ctx->in_syscall || ctx->current_state != AUDIT_RECORD_CONTEXT) - return; - p->arch = ctx->arch; - p->major = ctx->major; - memcpy(p->argv, ctx->argv, sizeof(ctx->argv)); - p->ctime = ctx->ctime; - p->dummy = ctx->dummy; - p->in_syscall = ctx->in_syscall; - p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL); - p->ppid = current->pid; - p->prio = ctx->prio; - p->current_state = ctx->current_state; -} - /** * audit_syscall_exit - deallocate audit context after a system call - * @valid: success/failure flag - * @return_code: syscall return value + * @pt_regs: syscall registers * * Tear down after system call. If the audit context has been marked as * auditable (either because of the AUDIT_RECORD_CONTEXT state from @@ -1689,14 +1871,18 @@ void audit_finish_fork(struct task_struct *child) * message), then write out the syscall information. In call cases, * free the names stored from getname(). */ -void audit_syscall_exit(int valid, long return_code) +void __audit_syscall_exit(int success, long return_code) { struct task_struct *tsk = current; struct audit_context *context; - context = audit_get_context(tsk, valid, return_code); + if (success) + success = AUDITSC_SUCCESS; + else + success = AUDITSC_FAILURE; - if (likely(!context)) + context = audit_get_context(tsk, success, return_code); + if (!context) return; if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT) @@ -1821,6 +2007,30 @@ retry: #endif } +static struct audit_names *audit_alloc_name(struct audit_context *context) +{ + struct audit_names *aname; + + if (context->name_count < AUDIT_NAMES) { + aname = &context->preallocated_names[context->name_count]; + memset(aname, 0, sizeof(*aname)); + } else { + aname = kzalloc(sizeof(*aname), GFP_NOFS); + if (!aname) + return NULL; + aname->should_free = true; + } + + aname->ino = (unsigned long)-1; + list_add_tail(&aname->list, &context->names_list); + + context->name_count++; +#if AUDIT_DEBUG + context->ino_count++; +#endif + return aname; +} + /** * audit_getname - add a name to the list * @name: name to add @@ -1831,9 +2041,7 @@ retry: void __audit_getname(const char *name) { struct audit_context *context = current->audit_context; - - if (IS_ERR(name) || !name) - return; + struct audit_names *n; if (!context->in_syscall) { #if AUDIT_DEBUG == 2 @@ -1843,13 +2051,15 @@ void __audit_getname(const char *name) #endif return; } - BUG_ON(context->name_count >= AUDIT_NAMES); - context->names[context->name_count].name = name; - context->names[context->name_count].name_len = AUDIT_NAME_FULL; - context->names[context->name_count].name_put = 1; - context->names[context->name_count].ino = (unsigned long)-1; - context->names[context->name_count].osid = 0; - ++context->name_count; + + n = audit_alloc_name(context); + if (!n) + return; + + n->name = name; + n->name_len = AUDIT_NAME_FULL; + n->name_put = true; + if (!context->pwd.dentry) get_fs_pwd(current->fs, &context->pwd); } @@ -1871,12 +2081,13 @@ void audit_putname(const char *name) printk(KERN_ERR "%s:%d(:%d): __putname(%p)\n", __FILE__, __LINE__, context->serial, name); if (context->name_count) { + struct audit_names *n; int i; - for (i = 0; i < context->name_count; i++) + + list_for_each_entry(n, &context->names_list, list) printk(KERN_ERR "name[%d] = %p = %s\n", i, - context->names[i].name, - context->names[i].name ?: "(null)"); - } + n->name, n->name ?: "(null)"); + } #endif __putname(name); } @@ -1897,39 +2108,11 @@ void audit_putname(const char *name) #endif } -static int audit_inc_name_count(struct audit_context *context, - const struct inode *inode) -{ - if (context->name_count >= AUDIT_NAMES) { - if (inode) - printk(KERN_DEBUG "audit: name_count maxed, losing inode data: " - "dev=%02x:%02x, inode=%lu\n", - MAJOR(inode->i_sb->s_dev), - MINOR(inode->i_sb->s_dev), - inode->i_ino); - - else - printk(KERN_DEBUG "name_count maxed, losing inode data\n"); - return 1; - } - context->name_count++; -#if AUDIT_DEBUG - context->ino_count++; -#endif - return 0; -} - - static inline int audit_copy_fcaps(struct audit_names *name, const struct dentry *dentry) { struct cpu_vfs_cap_data caps; int rc; - memset(&name->fcap.permitted, 0, sizeof(kernel_cap_t)); - memset(&name->fcap.inheritable, 0, sizeof(kernel_cap_t)); - name->fcap.fE = 0; - name->fcap_ver = 0; - if (!dentry) return 0; @@ -1969,30 +2152,25 @@ static void audit_copy_inode(struct audit_names *name, const struct dentry *dent */ void __audit_inode(const char *name, const struct dentry *dentry) { - int idx; struct audit_context *context = current->audit_context; const struct inode *inode = dentry->d_inode; + struct audit_names *n; if (!context->in_syscall) return; - if (context->name_count - && context->names[context->name_count-1].name - && context->names[context->name_count-1].name == name) - idx = context->name_count - 1; - else if (context->name_count > 1 - && context->names[context->name_count-2].name - && context->names[context->name_count-2].name == name) - idx = context->name_count - 2; - else { - /* FIXME: how much do we care about inodes that have no - * associated name? */ - if (audit_inc_name_count(context, inode)) - return; - idx = context->name_count - 1; - context->names[idx].name = NULL; + + list_for_each_entry_reverse(n, &context->names_list, list) { + if (n->name && (n->name == name)) + goto out; } + + /* unable to find the name from a previous getname() */ + n = audit_alloc_name(context); + if (!n) + return; +out: handle_path(dentry); - audit_copy_inode(&context->names[idx], dentry, inode); + audit_copy_inode(n, dentry, inode); } /** @@ -2011,11 +2189,11 @@ void __audit_inode(const char *name, const struct dentry *dentry) void __audit_inode_child(const struct dentry *dentry, const struct inode *parent) { - int idx; struct audit_context *context = current->audit_context; const char *found_parent = NULL, *found_child = NULL; const struct inode *inode = dentry->d_inode; const char *dname = dentry->d_name.name; + struct audit_names *n; int dirlen = 0; if (!context->in_syscall) @@ -2025,9 +2203,7 @@ void __audit_inode_child(const struct dentry *dentry, handle_one(inode); /* parent is more likely, look for it first */ - for (idx = 0; idx < context->name_count; idx++) { - struct audit_names *n = &context->names[idx]; - + list_for_each_entry(n, &context->names_list, list) { if (!n->name) continue; @@ -2040,9 +2216,7 @@ void __audit_inode_child(const struct dentry *dentry, } /* no matching parent, look for matching child */ - for (idx = 0; idx < context->name_count; idx++) { - struct audit_names *n = &context->names[idx]; - + list_for_each_entry(n, &context->names_list, list) { if (!n->name) continue; @@ -2060,34 +2234,29 @@ void __audit_inode_child(const struct dentry *dentry, add_names: if (!found_parent) { - if (audit_inc_name_count(context, parent)) + n = audit_alloc_name(context); + if (!n) return; - idx = context->name_count - 1; - context->names[idx].name = NULL; - audit_copy_inode(&context->names[idx], NULL, parent); + audit_copy_inode(n, NULL, parent); } if (!found_child) { - if (audit_inc_name_count(context, inode)) + n = audit_alloc_name(context); + if (!n) return; - idx = context->name_count - 1; /* Re-use the name belonging to the slot for a matching parent * directory. All names for this context are relinquished in * audit_free_names() */ if (found_parent) { - context->names[idx].name = found_parent; - context->names[idx].name_len = AUDIT_NAME_FULL; + n->name = found_parent; + n->name_len = AUDIT_NAME_FULL; /* don't call __putname() */ - context->names[idx].name_put = 0; - } else { - context->names[idx].name = NULL; + n->name_put = false; } if (inode) - audit_copy_inode(&context->names[idx], NULL, inode); - else - context->names[idx].ino = (unsigned long)-1; + audit_copy_inode(n, NULL, inode); } } EXPORT_SYMBOL_GPL(__audit_inode_child); @@ -2121,19 +2290,28 @@ int auditsc_get_stamp(struct audit_context *ctx, static atomic_t session_id = ATOMIC_INIT(0); /** - * audit_set_loginuid - set a task's audit_context loginuid - * @task: task whose audit context is being modified + * audit_set_loginuid - set current task's audit_context loginuid * @loginuid: loginuid value * * Returns 0. * * Called (set) from fs/proc/base.c::proc_loginuid_write(). */ -int audit_set_loginuid(struct task_struct *task, uid_t loginuid) +int audit_set_loginuid(uid_t loginuid) { - unsigned int sessionid = atomic_inc_return(&session_id); + struct task_struct *task = current; struct audit_context *context = task->audit_context; + unsigned int sessionid; + +#ifdef CONFIG_AUDIT_LOGINUID_IMMUTABLE + if (task->loginuid != -1) + return -EPERM; +#else /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */ + if (!capable(CAP_AUDIT_CONTROL)) + return -EPERM; +#endif /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */ + sessionid = atomic_inc_return(&session_id); if (context && context->in_syscall) { struct audit_buffer *ab; @@ -2160,7 +2338,7 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid) * @attr: queue attributes * */ -void __audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr) +void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { struct audit_context *context = current->audit_context; @@ -2260,7 +2438,7 @@ void __audit_ipc_obj(struct kern_ipc_perm *ipcp) * * Called only after audit_ipc_obj(). */ -void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode) +void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { struct audit_context *context = current->audit_context; @@ -2271,14 +2449,11 @@ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mod context->ipc.has_perm = 1; } -int audit_bprm(struct linux_binprm *bprm) +int __audit_bprm(struct linux_binprm *bprm) { struct audit_aux_data_execve *ax; struct audit_context *context = current->audit_context; - if (likely(!audit_enabled || !context || context->dummy)) - return 0; - ax = kmalloc(sizeof(*ax), GFP_KERNEL); if (!ax) return -ENOMEM; @@ -2299,13 +2474,10 @@ int audit_bprm(struct linux_binprm *bprm) * @args: args array * */ -void audit_socketcall(int nargs, unsigned long *args) +void __audit_socketcall(int nargs, unsigned long *args) { struct audit_context *context = current->audit_context; - if (likely(!context || context->dummy)) - return; - context->type = AUDIT_SOCKETCALL; context->socketcall.nargs = nargs; memcpy(context->socketcall.args, args, nargs * sizeof(unsigned long)); @@ -2331,13 +2503,10 @@ void __audit_fd_pair(int fd1, int fd2) * * Returns 0 for success or NULL context or < 0 on error. */ -int audit_sockaddr(int len, void *a) +int __audit_sockaddr(int len, void *a) { struct audit_context *context = current->audit_context; - if (likely(!context || context->dummy)) - return 0; - if (!context->sockaddr) { void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL); if (!p) @@ -2499,6 +2668,25 @@ void __audit_mmap_fd(int fd, int flags) context->type = AUDIT_MMAP; } +static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr) +{ + uid_t auid, uid; + gid_t gid; + unsigned int sessionid; + + auid = audit_get_loginuid(current); + sessionid = audit_get_sessionid(current); + current_uid_gid(&uid, &gid); + + audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u", + auid, uid, gid, sessionid); + audit_log_task_context(ab); + audit_log_format(ab, " pid=%d comm=", current->pid); + audit_log_untrustedstring(ab, current->comm); + audit_log_format(ab, " reason="); + audit_log_string(ab, reason); + audit_log_format(ab, " sig=%ld", signr); +} /** * audit_core_dumps - record information about processes that end abnormally * @signr: signal value @@ -2509,10 +2697,6 @@ void __audit_mmap_fd(int fd, int flags) void audit_core_dumps(long signr) { struct audit_buffer *ab; - u32 sid; - uid_t auid = audit_get_loginuid(current), uid; - gid_t gid; - unsigned int sessionid = audit_get_sessionid(current); if (!audit_enabled) return; @@ -2521,24 +2705,17 @@ void audit_core_dumps(long signr) return; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); - current_uid_gid(&uid, &gid); - audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u", - auid, uid, gid, sessionid); - security_task_getsecid(current, &sid); - if (sid) { - char *ctx = NULL; - u32 len; + audit_log_abend(ab, "memory violation", signr); + audit_log_end(ab); +} - if (security_secid_to_secctx(sid, &ctx, &len)) - audit_log_format(ab, " ssid=%u", sid); - else { - audit_log_format(ab, " subj=%s", ctx); - security_release_secctx(ctx, len); - } - } - audit_log_format(ab, " pid=%d comm=", current->pid); - audit_log_untrustedstring(ab, current->comm); - audit_log_format(ab, " sig=%ld", signr); +void __audit_seccomp(unsigned long syscall) +{ + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); + audit_log_abend(ab, "seccomp", SIGKILL); + audit_log_format(ab, " syscall=%ld", syscall); audit_log_end(ab); } diff --git a/kernel/capability.c b/kernel/capability.c index b463871a4e69..3f1adb6c6470 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -287,74 +287,84 @@ error: } /** - * has_capability - Does a task have a capability in init_user_ns + * has_ns_capability - Does a task have a capability in a specific user ns * @t: The task in question + * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability - * currently in effect to the initial user namespace, false if not. + * currently in effect to the specified user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ -bool has_capability(struct task_struct *t, int cap) +bool has_ns_capability(struct task_struct *t, + struct user_namespace *ns, int cap) { - int ret = security_real_capable(t, &init_user_ns, cap); + int ret; + + rcu_read_lock(); + ret = security_capable(__task_cred(t), ns, cap); + rcu_read_unlock(); return (ret == 0); } /** - * has_capability - Does a task have a capability in a specific user ns + * has_capability - Does a task have a capability in init_user_ns * @t: The task in question - * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability - * currently in effect to the specified user namespace, false if not. + * currently in effect to the initial user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ -bool has_ns_capability(struct task_struct *t, - struct user_namespace *ns, int cap) +bool has_capability(struct task_struct *t, int cap) { - int ret = security_real_capable(t, ns, cap); - - return (ret == 0); + return has_ns_capability(t, &init_user_ns, cap); } /** - * has_capability_noaudit - Does a task have a capability (unaudited) + * has_ns_capability_noaudit - Does a task have a capability (unaudited) + * in a specific user ns. * @t: The task in question + * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability - * currently in effect to init_user_ns, false if not. Don't write an - * audit message for the check. + * currently in effect to the specified user namespace, false if not. + * Do not write an audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ -bool has_capability_noaudit(struct task_struct *t, int cap) +bool has_ns_capability_noaudit(struct task_struct *t, + struct user_namespace *ns, int cap) { - int ret = security_real_capable_noaudit(t, &init_user_ns, cap); + int ret; + + rcu_read_lock(); + ret = security_capable_noaudit(__task_cred(t), ns, cap); + rcu_read_unlock(); return (ret == 0); } /** - * capable - Determine if the current task has a superior capability in effect + * has_capability_noaudit - Does a task have a capability (unaudited) in the + * initial user ns + * @t: The task in question * @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. + * Return true if the specified task has the given superior capability + * currently in effect to init_user_ns, false if not. Don't write an + * audit message for the check. * - * This sets PF_SUPERPRIV on the task if the capability is available on the - * assumption that it's about to be used. + * Note that this does not set PF_SUPERPRIV on the task. */ -bool capable(int cap) +bool has_capability_noaudit(struct task_struct *t, int cap) { - return ns_capable(&init_user_ns, cap); + return has_ns_capability_noaudit(t, &init_user_ns, cap); } -EXPORT_SYMBOL(capable); /** * ns_capable - Determine if the current task has a superior capability in effect @@ -374,7 +384,7 @@ bool ns_capable(struct user_namespace *ns, int cap) BUG(); } - if (security_capable(ns, current_cred(), cap) == 0) { + if (security_capable(current_cred(), ns, cap) == 0) { current->flags |= PF_SUPERPRIV; return true; } @@ -383,18 +393,20 @@ bool ns_capable(struct user_namespace *ns, int cap) EXPORT_SYMBOL(ns_capable); /** - * task_ns_capable - Determine whether current task has a superior - * capability targeted at a specific task's user namespace. - * @t: The task whose user namespace is targeted. - * @cap: The capability in question. + * capable - Determine if the current task has a superior capability in effect + * @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. * - * Return true if it does, false otherwise. + * This sets PF_SUPERPRIV on the task if the capability is available on the + * assumption that it's about to be used. */ -bool task_ns_capable(struct task_struct *t, int cap) +bool capable(int cap) { - return ns_capable(task_cred_xxx(t, user)->user_ns, cap); + return ns_capable(&init_user_ns, cap); } -EXPORT_SYMBOL(task_ns_capable); +EXPORT_SYMBOL(capable); /** * nsown_capable - Check superior capability to one's own user_ns diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a184470cf9b5..a5d3b5325f77 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -63,7 +63,24 @@ #include <linux/atomic.h> +/* + * cgroup_mutex is the master lock. Any modification to cgroup or its + * hierarchy must be performed while holding it. + * + * cgroup_root_mutex nests inside cgroup_mutex and should be held to modify + * cgroupfs_root of any cgroup hierarchy - subsys list, flags, + * release_agent_path and so on. Modifying requires both cgroup_mutex and + * cgroup_root_mutex. Readers can acquire either of the two. This is to + * break the following locking order cycle. + * + * A. cgroup_mutex -> cred_guard_mutex -> s_type->i_mutex_key -> namespace_sem + * B. namespace_sem -> cgroup_mutex + * + * B happens only through cgroup_show_options() and using cgroup_root_mutex + * breaks it. + */ static DEFINE_MUTEX(cgroup_mutex); +static DEFINE_MUTEX(cgroup_root_mutex); /* * Generate an array of cgroup subsystem pointers. At boot time, this is @@ -760,7 +777,7 @@ EXPORT_SYMBOL_GPL(cgroup_unlock); * -> cgroup_mkdir. */ -static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode); +static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); static struct dentry *cgroup_lookup(struct inode *, struct dentry *, struct nameidata *); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp); @@ -775,7 +792,7 @@ static struct backing_dev_info cgroup_backing_dev_info = { static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent, struct cgroup *child); -static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) +static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb) { struct inode *inode = new_inode(sb); @@ -921,7 +938,7 @@ static void cgroup_d_remove_dir(struct dentry *dentry) * * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex; */ -DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq); +static DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq); static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp) { @@ -953,6 +970,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, int i; BUG_ON(!mutex_is_locked(&cgroup_mutex)); + BUG_ON(!mutex_is_locked(&cgroup_root_mutex)); removed_bits = root->actual_subsys_bits & ~final_bits; added_bits = final_bits & ~root->actual_subsys_bits; @@ -1038,12 +1056,12 @@ static int rebind_subsystems(struct cgroupfs_root *root, return 0; } -static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs) +static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry) { - struct cgroupfs_root *root = vfs->mnt_sb->s_fs_info; + struct cgroupfs_root *root = dentry->d_sb->s_fs_info; struct cgroup_subsys *ss; - mutex_lock(&cgroup_mutex); + mutex_lock(&cgroup_root_mutex); for_each_subsys(root, ss) seq_printf(seq, ",%s", ss->name); if (test_bit(ROOT_NOPREFIX, &root->flags)) @@ -1054,7 +1072,7 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_printf(seq, ",name=%s", root->name); - mutex_unlock(&cgroup_mutex); + mutex_unlock(&cgroup_root_mutex); return 0; } @@ -1175,10 +1193,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) /* * If the 'all' option was specified select all the subsystems, - * otherwise 'all, 'none' and a subsystem name options were not - * specified, let's default to 'all' + * otherwise if 'none', 'name=' and a subsystem name options + * were not specified, let's default to 'all' */ - if (all_ss || (!all_ss && !one_ss && !opts->none)) { + if (all_ss || (!one_ss && !opts->none && !opts->name)) { for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (ss == NULL) @@ -1269,6 +1287,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) mutex_lock(&cgrp->dentry->d_inode->i_mutex); mutex_lock(&cgroup_mutex); + mutex_lock(&cgroup_root_mutex); /* See what subsystems are wanted */ ret = parse_cgroupfs_options(data, &opts); @@ -1297,6 +1316,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) out_unlock: kfree(opts.release_agent); kfree(opts.name); + mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); mutex_unlock(&cgrp->dentry->d_inode->i_mutex); return ret; @@ -1481,6 +1501,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, int ret = 0; struct super_block *sb; struct cgroupfs_root *new_root; + struct inode *inode; /* First find the desired set of subsystems */ mutex_lock(&cgroup_mutex); @@ -1514,7 +1535,6 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, /* We used the new root structure, so this is a new hierarchy */ struct list_head tmp_cg_links; struct cgroup *root_cgrp = &root->top_cgroup; - struct inode *inode; struct cgroupfs_root *existing_root; const struct cred *cred; int i; @@ -1528,18 +1548,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, mutex_lock(&inode->i_mutex); mutex_lock(&cgroup_mutex); + mutex_lock(&cgroup_root_mutex); - if (strlen(root->name)) { - /* Check for name clashes with existing mounts */ - for_each_active_root(existing_root) { - if (!strcmp(existing_root->name, root->name)) { - ret = -EBUSY; - mutex_unlock(&cgroup_mutex); - mutex_unlock(&inode->i_mutex); - goto drop_new_super; - } - } - } + /* Check for name clashes with existing mounts */ + ret = -EBUSY; + if (strlen(root->name)) + for_each_active_root(existing_root) + if (!strcmp(existing_root->name, root->name)) + goto unlock_drop; /* * We're accessing css_set_count without locking @@ -1549,18 +1565,13 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, * have some link structures left over */ ret = allocate_cg_links(css_set_count, &tmp_cg_links); - if (ret) { - mutex_unlock(&cgroup_mutex); - mutex_unlock(&inode->i_mutex); - goto drop_new_super; - } + if (ret) + goto unlock_drop; ret = rebind_subsystems(root, root->subsys_bits); if (ret == -EBUSY) { - mutex_unlock(&cgroup_mutex); - mutex_unlock(&inode->i_mutex); free_cg_links(&tmp_cg_links); - goto drop_new_super; + goto unlock_drop; } /* * There must be no failure case after here, since rebinding @@ -1599,6 +1610,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, cred = override_creds(&init_cred); cgroup_populate_dir(root_cgrp); revert_creds(cred); + mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); mutex_unlock(&inode->i_mutex); } else { @@ -1615,6 +1627,10 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, kfree(opts.name); return dget(sb->s_root); + unlock_drop: + mutex_unlock(&cgroup_root_mutex); + mutex_unlock(&cgroup_mutex); + mutex_unlock(&inode->i_mutex); drop_new_super: deactivate_locked_super(sb); drop_modules: @@ -1639,6 +1655,7 @@ static void cgroup_kill_sb(struct super_block *sb) { BUG_ON(!list_empty(&cgrp->sibling)); mutex_lock(&cgroup_mutex); + mutex_lock(&cgroup_root_mutex); /* Rebind all subsystems back to the default hierarchy */ ret = rebind_subsystems(root, 0); @@ -1664,6 +1681,7 @@ static void cgroup_kill_sb(struct super_block *sb) { root_count--; } + mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); kill_litter_super(sb); @@ -1740,11 +1758,90 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) EXPORT_SYMBOL_GPL(cgroup_path); /* + * Control Group taskset + */ +struct task_and_cgroup { + struct task_struct *task; + struct cgroup *cgrp; +}; + +struct cgroup_taskset { + struct task_and_cgroup single; + struct flex_array *tc_array; + int tc_array_len; + int idx; + struct cgroup *cur_cgrp; +}; + +/** + * cgroup_taskset_first - reset taskset and return the first task + * @tset: taskset of interest + * + * @tset iteration is initialized and the first task is returned. + */ +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset) +{ + if (tset->tc_array) { + tset->idx = 0; + return cgroup_taskset_next(tset); + } else { + tset->cur_cgrp = tset->single.cgrp; + return tset->single.task; + } +} +EXPORT_SYMBOL_GPL(cgroup_taskset_first); + +/** + * cgroup_taskset_next - iterate to the next task in taskset + * @tset: taskset of interest + * + * Return the next task in @tset. Iteration must have been initialized + * with cgroup_taskset_first(). + */ +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) +{ + struct task_and_cgroup *tc; + + if (!tset->tc_array || tset->idx >= tset->tc_array_len) + return NULL; + + tc = flex_array_get(tset->tc_array, tset->idx++); + tset->cur_cgrp = tc->cgrp; + return tc->task; +} +EXPORT_SYMBOL_GPL(cgroup_taskset_next); + +/** + * cgroup_taskset_cur_cgroup - return the matching cgroup for the current task + * @tset: taskset of interest + * + * Return the cgroup for the current (last returned) task of @tset. This + * function must be preceded by either cgroup_taskset_first() or + * cgroup_taskset_next(). + */ +struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset) +{ + return tset->cur_cgrp; +} +EXPORT_SYMBOL_GPL(cgroup_taskset_cur_cgroup); + +/** + * cgroup_taskset_size - return the number of tasks in taskset + * @tset: taskset of interest + */ +int cgroup_taskset_size(struct cgroup_taskset *tset) +{ + return tset->tc_array ? tset->tc_array_len : 1; +} +EXPORT_SYMBOL_GPL(cgroup_taskset_size); + + +/* * cgroup_task_migrate - move a task from one cgroup to another. * * 'guarantee' is set if the caller promises that a new css_set for the task * will already exist. If not set, this function might sleep, and can fail with - * -ENOMEM. Otherwise, it can only fail with -ESRCH. + * -ENOMEM. Must be called with cgroup_mutex and threadgroup locked. */ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, struct task_struct *tsk, bool guarantee) @@ -1753,14 +1850,12 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, struct css_set *newcg; /* - * get old css_set. we need to take task_lock and refcount it, because - * an exiting task can change its css_set to init_css_set and drop its - * old one without taking cgroup_mutex. + * We are synchronized through threadgroup_lock() against PF_EXITING + * setting such that we can't race against cgroup_exit() changing the + * css_set to init_css_set and dropping the old one. */ - task_lock(tsk); + WARN_ON_ONCE(tsk->flags & PF_EXITING); oldcg = tsk->cgroups; - get_css_set(oldcg); - task_unlock(tsk); /* locate or allocate a new css_set for this task. */ if (guarantee) { @@ -1775,20 +1870,11 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, might_sleep(); /* find_css_set will give us newcg already referenced. */ newcg = find_css_set(oldcg, cgrp); - if (!newcg) { - put_css_set(oldcg); + if (!newcg) return -ENOMEM; - } } - put_css_set(oldcg); - /* if PF_EXITING is set, the tsk->cgroups pointer is no longer safe. */ task_lock(tsk); - if (tsk->flags & PF_EXITING) { - task_unlock(tsk); - put_css_set(newcg); - return -ESRCH; - } rcu_assign_pointer(tsk->cgroups, newcg); task_unlock(tsk); @@ -1814,8 +1900,8 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, * @cgrp: the cgroup the task is attaching to * @tsk: the task to be attached * - * Call holding cgroup_mutex. May take task_lock of - * the task 'tsk' during call. + * Call with cgroup_mutex and threadgroup locked. May take task_lock of + * @tsk during call. */ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { @@ -1823,15 +1909,23 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) struct cgroup_subsys *ss, *failed_ss = NULL; struct cgroup *oldcgrp; struct cgroupfs_root *root = cgrp->root; + struct cgroup_taskset tset = { }; + + /* @tsk either already exited or can't exit until the end */ + if (tsk->flags & PF_EXITING) + return -ESRCH; /* Nothing to do if the task is already in that cgroup */ oldcgrp = task_cgroup_from_root(tsk, root); if (cgrp == oldcgrp) return 0; + tset.single.task = tsk; + tset.single.cgrp = oldcgrp; + for_each_subsys(root, ss) { if (ss->can_attach) { - retval = ss->can_attach(ss, cgrp, tsk); + retval = ss->can_attach(ss, cgrp, &tset); if (retval) { /* * Remember on which subsystem the can_attach() @@ -1843,13 +1937,6 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) goto out; } } - if (ss->can_attach_task) { - retval = ss->can_attach_task(cgrp, tsk); - if (retval) { - failed_ss = ss; - goto out; - } - } } retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false); @@ -1857,12 +1944,8 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) goto out; for_each_subsys(root, ss) { - if (ss->pre_attach) - ss->pre_attach(cgrp); - if (ss->attach_task) - ss->attach_task(cgrp, tsk); if (ss->attach) - ss->attach(ss, cgrp, oldcgrp, tsk); + ss->attach(ss, cgrp, &tset); } synchronize_rcu(); @@ -1884,7 +1967,7 @@ out: */ break; if (ss->cancel_attach) - ss->cancel_attach(ss, cgrp, tsk); + ss->cancel_attach(ss, cgrp, &tset); } } return retval; @@ -1935,23 +2018,17 @@ static bool css_set_check_fetched(struct cgroup *cgrp, read_lock(&css_set_lock); newcg = find_existing_css_set(cg, cgrp, template); - if (newcg) - get_css_set(newcg); read_unlock(&css_set_lock); /* doesn't exist at all? */ if (!newcg) return false; /* see if it's already in the list */ - list_for_each_entry(cg_entry, newcg_list, links) { - if (cg_entry->cg == newcg) { - put_css_set(newcg); + list_for_each_entry(cg_entry, newcg_list, links) + if (cg_entry->cg == newcg) return true; - } - } /* not found */ - put_css_set(newcg); return false; } @@ -1985,21 +2062,21 @@ static int css_set_prefetch(struct cgroup *cgrp, struct css_set *cg, * @cgrp: the cgroup to attach to * @leader: the threadgroup leader task_struct of the group to be attached * - * Call holding cgroup_mutex and the threadgroup_fork_lock of the leader. Will - * take task_lock of each thread in leader's threadgroup individually in turn. + * Call holding cgroup_mutex and the group_rwsem of the leader. Will take + * task_lock of each thread in leader's threadgroup individually in turn. */ -int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) +static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) { int retval, i, group_size; struct cgroup_subsys *ss, *failed_ss = NULL; - bool cancel_failed_ss = false; /* guaranteed to be initialized later, but the compiler needs this */ - struct cgroup *oldcgrp = NULL; struct css_set *oldcg; struct cgroupfs_root *root = cgrp->root; /* threadgroup list cursor and array */ struct task_struct *tsk; + struct task_and_cgroup *tc; struct flex_array *group; + struct cgroup_taskset tset = { }; /* * we need to make sure we have css_sets for all the tasks we're * going to move -before- we actually start moving them, so that in @@ -2012,13 +2089,12 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) * step 0: in order to do expensive, possibly blocking operations for * every thread, we cannot iterate the thread group list, since it needs * rcu or tasklist locked. instead, build an array of all threads in the - * group - threadgroup_fork_lock prevents new threads from appearing, - * and if threads exit, this will just be an over-estimate. + * group - group_rwsem prevents new threads from appearing, and if + * threads exit, this will just be an over-estimate. */ group_size = get_nr_threads(leader); /* flex_array supports very large thread-groups better than kmalloc. */ - group = flex_array_alloc(sizeof(struct task_struct *), group_size, - GFP_KERNEL); + group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL); if (!group) return -ENOMEM; /* pre-allocate to guarantee space while iterating in rcu read-side. */ @@ -2040,49 +2116,53 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) retval = -EAGAIN; goto out_free_group_list; } - /* take a reference on each task in the group to go in the array. */ + tsk = leader; i = 0; do { + struct task_and_cgroup ent; + + /* @tsk either already exited or can't exit until the end */ + if (tsk->flags & PF_EXITING) + continue; + /* as per above, nr_threads may decrease, but not increase. */ BUG_ON(i >= group_size); - get_task_struct(tsk); /* * saying GFP_ATOMIC has no effect here because we did prealloc * earlier, but it's good form to communicate our expectations. */ - retval = flex_array_put_ptr(group, i, tsk, GFP_ATOMIC); + ent.task = tsk; + ent.cgrp = task_cgroup_from_root(tsk, root); + /* nothing to do if this task is already in the cgroup */ + if (ent.cgrp == cgrp) + continue; + retval = flex_array_put(group, i, &ent, GFP_ATOMIC); BUG_ON(retval != 0); i++; } while_each_thread(leader, tsk); /* remember the number of threads in the array for later. */ group_size = i; + tset.tc_array = group; + tset.tc_array_len = group_size; read_unlock(&tasklist_lock); + /* methods shouldn't be called if no task is actually migrating */ + retval = 0; + if (!group_size) + goto out_free_group_list; + /* * step 1: check that we can legitimately attach to the cgroup. */ for_each_subsys(root, ss) { if (ss->can_attach) { - retval = ss->can_attach(ss, cgrp, leader); + retval = ss->can_attach(ss, cgrp, &tset); if (retval) { failed_ss = ss; goto out_cancel_attach; } } - /* a callback to be run on every thread in the threadgroup. */ - if (ss->can_attach_task) { - /* run on each task in the threadgroup. */ - for (i = 0; i < group_size; i++) { - tsk = flex_array_get_ptr(group, i); - retval = ss->can_attach_task(cgrp, tsk); - if (retval) { - failed_ss = ss; - cancel_failed_ss = true; - goto out_cancel_attach; - } - } - } } /* @@ -2091,67 +2171,36 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) */ INIT_LIST_HEAD(&newcg_list); for (i = 0; i < group_size; i++) { - tsk = flex_array_get_ptr(group, i); - /* nothing to do if this task is already in the cgroup */ - oldcgrp = task_cgroup_from_root(tsk, root); - if (cgrp == oldcgrp) - continue; - /* get old css_set pointer */ - task_lock(tsk); - oldcg = tsk->cgroups; - get_css_set(oldcg); - task_unlock(tsk); - /* see if the new one for us is already in the list? */ - if (css_set_check_fetched(cgrp, tsk, oldcg, &newcg_list)) { - /* was already there, nothing to do. */ - put_css_set(oldcg); - } else { - /* we don't already have it. get new one. */ + tc = flex_array_get(group, i); + oldcg = tc->task->cgroups; + + /* if we don't already have it in the list get a new one */ + if (!css_set_check_fetched(cgrp, tc->task, oldcg, + &newcg_list)) { retval = css_set_prefetch(cgrp, oldcg, &newcg_list); - put_css_set(oldcg); if (retval) goto out_list_teardown; } } /* - * step 3: now that we're guaranteed success wrt the css_sets, proceed - * to move all tasks to the new cgroup, calling ss->attach_task for each - * one along the way. there are no failure cases after here, so this is - * the commit point. + * step 3: now that we're guaranteed success wrt the css_sets, + * proceed to move all tasks to the new cgroup. There are no + * failure cases after here, so this is the commit point. */ - for_each_subsys(root, ss) { - if (ss->pre_attach) - ss->pre_attach(cgrp); - } for (i = 0; i < group_size; i++) { - tsk = flex_array_get_ptr(group, i); - /* leave current thread as it is if it's already there */ - oldcgrp = task_cgroup_from_root(tsk, root); - if (cgrp == oldcgrp) - continue; - /* if the thread is PF_EXITING, it can just get skipped. */ - retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, true); - if (retval == 0) { - /* attach each task to each subsystem */ - for_each_subsys(root, ss) { - if (ss->attach_task) - ss->attach_task(cgrp, tsk); - } - } else { - BUG_ON(retval != -ESRCH); - } + tc = flex_array_get(group, i); + retval = cgroup_task_migrate(cgrp, tc->cgrp, tc->task, true); + BUG_ON(retval); } /* nothing is sensitive to fork() after this point. */ /* - * step 4: do expensive, non-thread-specific subsystem callbacks. - * TODO: if ever a subsystem needs to know the oldcgrp for each task - * being moved, this call will need to be reworked to communicate that. + * step 4: do subsystem attach callbacks. */ for_each_subsys(root, ss) { if (ss->attach) - ss->attach(ss, cgrp, oldcgrp, leader); + ss->attach(ss, cgrp, &tset); } /* @@ -2171,20 +2220,12 @@ out_cancel_attach: /* same deal as in cgroup_attach_task */ if (retval) { for_each_subsys(root, ss) { - if (ss == failed_ss) { - if (cancel_failed_ss && ss->cancel_attach) - ss->cancel_attach(ss, cgrp, leader); + if (ss == failed_ss) break; - } if (ss->cancel_attach) - ss->cancel_attach(ss, cgrp, leader); + ss->cancel_attach(ss, cgrp, &tset); } } - /* clean up the array of referenced threads in the group. */ - for (i = 0; i < group_size; i++) { - tsk = flex_array_get_ptr(group, i); - put_task_struct(tsk); - } out_free_group_list: flex_array_free(group); return retval; @@ -2192,8 +2233,8 @@ out_free_group_list: /* * Find the task_struct of the task to attach by vpid and pass it along to the - * function to attach either it or all tasks in its threadgroup. Will take - * cgroup_mutex; may take task_lock of task. + * function to attach either it or all tasks in its threadgroup. Will lock + * cgroup_mutex and threadgroup; may take task_lock of task. */ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) { @@ -2220,13 +2261,7 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) * detect it later. */ tsk = tsk->group_leader; - } else if (tsk->flags & PF_EXITING) { - /* optimization for the single-task-only case */ - rcu_read_unlock(); - cgroup_unlock(); - return -ESRCH; } - /* * even if we're attaching all tasks in the thread group, we * only need to check permissions on one of them. @@ -2249,13 +2284,15 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) get_task_struct(tsk); } - if (threadgroup) { - threadgroup_fork_write_lock(tsk); + threadgroup_lock(tsk); + + if (threadgroup) ret = cgroup_attach_proc(cgrp, tsk); - threadgroup_fork_write_unlock(tsk); - } else { + else ret = cgroup_attach_task(cgrp, tsk); - } + + threadgroup_unlock(tsk); + put_task_struct(tsk); cgroup_unlock(); return ret; @@ -2306,7 +2343,9 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft, return -EINVAL; if (!cgroup_lock_live_group(cgrp)) return -ENODEV; + mutex_lock(&cgroup_root_mutex); strcpy(cgrp->root->release_agent_path, buffer); + mutex_unlock(&cgroup_root_mutex); cgroup_unlock(); return 0; } @@ -2585,7 +2624,7 @@ static inline struct cftype *__file_cft(struct file *file) return __d_cft(file->f_dentry); } -static int cgroup_create_file(struct dentry *dentry, mode_t mode, +static int cgroup_create_file(struct dentry *dentry, umode_t mode, struct super_block *sb) { struct inode *inode; @@ -2626,7 +2665,7 @@ static int cgroup_create_file(struct dentry *dentry, mode_t mode, * @mode: mode to set on new directory. */ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry, - mode_t mode) + umode_t mode) { struct dentry *parent; int error = 0; @@ -2653,9 +2692,9 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry, * returns S_IRUGO if it has only a read handler * returns S_IWUSR if it has only a write hander */ -static mode_t cgroup_file_mode(const struct cftype *cft) +static umode_t cgroup_file_mode(const struct cftype *cft) { - mode_t mode = 0; + umode_t mode = 0; if (cft->mode) return cft->mode; @@ -2678,7 +2717,7 @@ int cgroup_add_file(struct cgroup *cgrp, struct dentry *dir = cgrp->dentry; struct dentry *dentry; int error; - mode_t mode; + umode_t mode; char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) { @@ -2789,6 +2828,7 @@ static void cgroup_enable_task_cg_lists(void) } void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it) + __acquires(css_set_lock) { /* * The first time anyone tries to iterate across a cgroup, @@ -2828,6 +2868,7 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, } void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it) + __releases(css_set_lock) { read_unlock(&css_set_lock); } @@ -3752,7 +3793,7 @@ static void cgroup_unlock_hierarchy(struct cgroupfs_root *root) * Must be called with the mutex on the parent inode held */ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, - mode_t mode) + umode_t mode) { struct cgroup *cgrp; struct cgroupfs_root *root = parent->root; @@ -3846,7 +3887,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, return err; } -static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode) +static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { struct cgroup *c_parent = dentry->d_parent->d_fsdata; @@ -4491,20 +4532,31 @@ static const struct file_operations proc_cgroupstats_operations = { * * A pointer to the shared css_set was automatically copied in * fork.c by dup_task_struct(). However, we ignore that copy, since - * it was not made under the protection of RCU or cgroup_mutex, so - * might no longer be a valid cgroup pointer. cgroup_attach_task() might - * have already changed current->cgroups, allowing the previously - * referenced cgroup group to be removed and freed. + * it was not made under the protection of RCU, cgroup_mutex or + * threadgroup_change_begin(), so it might no longer be a valid + * cgroup pointer. cgroup_attach_task() might have already changed + * current->cgroups, allowing the previously referenced cgroup + * group to be removed and freed. + * + * Outside the pointer validity we also need to process the css_set + * inheritance between threadgoup_change_begin() and + * threadgoup_change_end(), this way there is no leak in any process + * wide migration performed by cgroup_attach_proc() that could otherwise + * miss a thread because it is too early or too late in the fork stage. * * At the point that cgroup_fork() is called, 'current' is the parent * task, and the passed argument 'child' points to the child task. */ void cgroup_fork(struct task_struct *child) { - task_lock(current); + /* + * We don't need to task_lock() current because current->cgroups + * can't be changed concurrently here. The parent obviously hasn't + * exited and called cgroup_exit(), and we are synchronized against + * cgroup migration through threadgroup_change_begin(). + */ child->cgroups = current->cgroups; get_css_set(child->cgroups); - task_unlock(current); INIT_LIST_HEAD(&child->cg_list); } @@ -4546,10 +4598,19 @@ void cgroup_post_fork(struct task_struct *child) { if (use_task_css_set_links) { write_lock(&css_set_lock); - task_lock(child); - if (list_empty(&child->cg_list)) + if (list_empty(&child->cg_list)) { + /* + * It's safe to use child->cgroups without task_lock() + * here because we are protected through + * threadgroup_change_begin() against concurrent + * css_set change in cgroup_task_migrate(). Also + * the task can't exit at that point until + * wake_up_new_task() is called, so we are protected + * against cgroup_exit() setting child->cgroup to + * init_css_set. + */ list_add(&child->cg_list, &child->cgroups->tasks); - task_unlock(child); + } write_unlock(&css_set_lock); } } diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 213c0351dad8..fc0646b78a64 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -48,19 +48,17 @@ static inline struct freezer *task_freezer(struct task_struct *task) struct freezer, css); } -static inline int __cgroup_freezing_or_frozen(struct task_struct *task) +bool cgroup_freezing(struct task_struct *task) { - enum freezer_state state = task_freezer(task)->state; - return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN); -} + enum freezer_state state; + bool ret; -int cgroup_freezing_or_frozen(struct task_struct *task) -{ - int result; - task_lock(task); - result = __cgroup_freezing_or_frozen(task); - task_unlock(task); - return result; + rcu_read_lock(); + state = task_freezer(task)->state; + ret = state == CGROUP_FREEZING || state == CGROUP_FROZEN; + rcu_read_unlock(); + + return ret; } /* @@ -102,9 +100,6 @@ struct cgroup_subsys freezer_subsys; * freezer_can_attach(): * cgroup_mutex (held by caller of can_attach) * - * cgroup_freezing_or_frozen(): - * task->alloc_lock (to get task's cgroup) - * * freezer_fork() (preserving fork() performance means can't take cgroup_mutex): * freezer->lock * sighand->siglock (if the cgroup is freezing) @@ -130,7 +125,7 @@ struct cgroup_subsys freezer_subsys; * write_lock css_set_lock (cgroup iterator start) * task->alloc_lock * read_lock css_set_lock (cgroup iterator start) - * task->alloc_lock (inside thaw_process(), prevents race with refrigerator()) + * task->alloc_lock (inside __thaw_task(), prevents race with refrigerator()) * sighand->siglock */ static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss, @@ -150,7 +145,11 @@ static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss, static void freezer_destroy(struct cgroup_subsys *ss, struct cgroup *cgroup) { - kfree(cgroup_freezer(cgroup)); + struct freezer *freezer = cgroup_freezer(cgroup); + + if (freezer->state != CGROUP_THAWED) + atomic_dec(&system_freezing_cnt); + kfree(freezer); } /* task is frozen or will freeze immediately when next it gets woken */ @@ -167,13 +166,17 @@ static bool is_task_frozen_enough(struct task_struct *task) */ static int freezer_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup, - struct task_struct *task) + struct cgroup_taskset *tset) { struct freezer *freezer; + struct task_struct *task; /* * Anything frozen can't move or be moved to/from. */ + cgroup_taskset_for_each(task, new_cgroup, tset) + if (cgroup_freezing(task)) + return -EBUSY; freezer = cgroup_freezer(new_cgroup); if (freezer->state != CGROUP_THAWED) @@ -182,17 +185,6 @@ static int freezer_can_attach(struct cgroup_subsys *ss, return 0; } -static int freezer_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) -{ - rcu_read_lock(); - if (__cgroup_freezing_or_frozen(tsk)) { - rcu_read_unlock(); - return -EBUSY; - } - rcu_read_unlock(); - return 0; -} - static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) { struct freezer *freezer; @@ -220,7 +212,7 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) /* Locking avoids race with FREEZING -> THAWED transitions. */ if (freezer->state == CGROUP_FREEZING) - freeze_task(task, true); + freeze_task(task); spin_unlock_irq(&freezer->lock); } @@ -238,7 +230,7 @@ static void update_if_frozen(struct cgroup *cgroup, cgroup_iter_start(cgroup, &it); while ((task = cgroup_iter_next(cgroup, &it))) { ntotal++; - if (is_task_frozen_enough(task)) + if (freezing(task) && is_task_frozen_enough(task)) nfrozen++; } @@ -286,10 +278,9 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) struct task_struct *task; unsigned int num_cant_freeze_now = 0; - freezer->state = CGROUP_FREEZING; cgroup_iter_start(cgroup, &it); while ((task = cgroup_iter_next(cgroup, &it))) { - if (!freeze_task(task, true)) + if (!freeze_task(task)) continue; if (is_task_frozen_enough(task)) continue; @@ -307,12 +298,9 @@ static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) struct task_struct *task; cgroup_iter_start(cgroup, &it); - while ((task = cgroup_iter_next(cgroup, &it))) { - thaw_process(task); - } + while ((task = cgroup_iter_next(cgroup, &it))) + __thaw_task(task); cgroup_iter_end(cgroup, &it); - - freezer->state = CGROUP_THAWED; } static int freezer_change_state(struct cgroup *cgroup, @@ -326,20 +314,24 @@ static int freezer_change_state(struct cgroup *cgroup, spin_lock_irq(&freezer->lock); update_if_frozen(cgroup, freezer); - if (goal_state == freezer->state) - goto out; switch (goal_state) { case CGROUP_THAWED: + if (freezer->state != CGROUP_THAWED) + atomic_dec(&system_freezing_cnt); + freezer->state = CGROUP_THAWED; unfreeze_cgroup(cgroup, freezer); break; case CGROUP_FROZEN: + if (freezer->state == CGROUP_THAWED) + atomic_inc(&system_freezing_cnt); + freezer->state = CGROUP_FREEZING; retval = try_to_freeze_cgroup(cgroup, freezer); break; default: BUG(); } -out: + spin_unlock_irq(&freezer->lock); return retval; @@ -388,10 +380,5 @@ struct cgroup_subsys freezer_subsys = { .populate = freezer_populate, .subsys_id = freezer_subsys_id, .can_attach = freezer_can_attach, - .can_attach_task = freezer_can_attach_task, - .pre_attach = NULL, - .attach_task = NULL, - .attach = NULL, .fork = freezer_fork, - .exit = NULL, }; diff --git a/kernel/cpu.c b/kernel/cpu.c index 5ca38d5d238a..2060c6e57027 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -470,7 +470,7 @@ out: cpu_maps_update_done(); } -static int alloc_frozen_cpus(void) +static int __init alloc_frozen_cpus(void) { if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) return -ENOMEM; @@ -543,7 +543,7 @@ cpu_hotplug_pm_callback(struct notifier_block *nb, } -int cpu_hotplug_pm_sync_init(void) +static int __init cpu_hotplug_pm_sync_init(void) { pm_notifier(cpu_hotplug_pm_callback, 0); return 0; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 0b1712dba587..a09ac2b9a661 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1389,79 +1389,73 @@ static int fmeter_getrate(struct fmeter *fmp) return val; } -/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ -static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, - struct task_struct *tsk) -{ - struct cpuset *cs = cgroup_cs(cont); - - if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) - return -ENOSPC; - - /* - * Kthreads bound to specific cpus cannot be moved to a new cpuset; we - * cannot change their cpu affinity and isolating such threads by their - * set of allowed nodes is unnecessary. Thus, cpusets are not - * applicable for such threads. This prevents checking for success of - * set_cpus_allowed_ptr() on all attached tasks before cpus_allowed may - * be changed. - */ - if (tsk->flags & PF_THREAD_BOUND) - return -EINVAL; - - return 0; -} - -static int cpuset_can_attach_task(struct cgroup *cgrp, struct task_struct *task) -{ - return security_task_setscheduler(task); -} - /* * Protected by cgroup_lock. The nodemasks must be stored globally because - * dynamically allocating them is not allowed in pre_attach, and they must - * persist among pre_attach, attach_task, and attach. + * dynamically allocating them is not allowed in can_attach, and they must + * persist until attach. */ static cpumask_var_t cpus_attach; static nodemask_t cpuset_attach_nodemask_from; static nodemask_t cpuset_attach_nodemask_to; -/* Set-up work for before attaching each task. */ -static void cpuset_pre_attach(struct cgroup *cont) +/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ +static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup_taskset *tset) { - struct cpuset *cs = cgroup_cs(cont); + struct cpuset *cs = cgroup_cs(cgrp); + struct task_struct *task; + int ret; + + if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) + return -ENOSPC; + + cgroup_taskset_for_each(task, cgrp, tset) { + /* + * Kthreads bound to specific cpus cannot be moved to a new + * cpuset; we cannot change their cpu affinity and + * isolating such threads by their set of allowed nodes is + * unnecessary. Thus, cpusets are not applicable for such + * threads. This prevents checking for success of + * set_cpus_allowed_ptr() on all attached tasks before + * cpus_allowed may be changed. + */ + if (task->flags & PF_THREAD_BOUND) + return -EINVAL; + if ((ret = security_task_setscheduler(task))) + return ret; + } + /* prepare for attach */ if (cs == &top_cpuset) cpumask_copy(cpus_attach, cpu_possible_mask); else guarantee_online_cpus(cs, cpus_attach); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); -} - -/* Per-thread attachment work. */ -static void cpuset_attach_task(struct cgroup *cont, struct task_struct *tsk) -{ - int err; - struct cpuset *cs = cgroup_cs(cont); - /* - * can_attach beforehand should guarantee that this doesn't fail. - * TODO: have a better way to handle failure here - */ - err = set_cpus_allowed_ptr(tsk, cpus_attach); - WARN_ON_ONCE(err); - - cpuset_change_task_nodemask(tsk, &cpuset_attach_nodemask_to); - cpuset_update_task_spread_flag(cs, tsk); + return 0; } -static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, - struct cgroup *oldcont, struct task_struct *tsk) +static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup_taskset *tset) { struct mm_struct *mm; - struct cpuset *cs = cgroup_cs(cont); - struct cpuset *oldcs = cgroup_cs(oldcont); + struct task_struct *task; + struct task_struct *leader = cgroup_taskset_first(tset); + struct cgroup *oldcgrp = cgroup_taskset_cur_cgroup(tset); + struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *oldcs = cgroup_cs(oldcgrp); + + cgroup_taskset_for_each(task, cgrp, tset) { + /* + * can_attach beforehand should guarantee that this doesn't + * fail. TODO: have a better way to handle failure here + */ + WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); + + cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); + cpuset_update_task_spread_flag(cs, task); + } /* * Change mm, possibly for multiple threads in a threadgroup. This is @@ -1469,7 +1463,7 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, */ cpuset_attach_nodemask_from = oldcs->mems_allowed; cpuset_attach_nodemask_to = cs->mems_allowed; - mm = get_task_mm(tsk); + mm = get_task_mm(leader); if (mm) { mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); if (is_memory_migrate(cs)) @@ -1925,9 +1919,6 @@ struct cgroup_subsys cpuset_subsys = { .create = cpuset_create, .destroy = cpuset_destroy, .can_attach = cpuset_can_attach, - .can_attach_task = cpuset_can_attach_task, - .pre_attach = cpuset_pre_attach, - .attach_task = cpuset_attach_task, .attach = cpuset_attach, .populate = cpuset_populate, .post_clone = cpuset_post_clone, diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 63786e71a3cd..e2ae7349437f 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1982,7 +1982,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf("%-20s%8u 0x%p ", mod->name, mod->core_size, (void *)mod); #ifdef CONFIG_MODULE_UNLOAD - kdb_printf("%4d ", module_refcount(mod)); + kdb_printf("%4ld ", module_refcount(mod)); #endif if (mod->state == MODULE_STATE_GOING) kdb_printf(" (Unloading)"); diff --git a/kernel/events/core.c b/kernel/events/core.c index 890eb02c2f21..a8f4ac001a00 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4,7 +4,7 @@ * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> - * Copyright 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> * * For licensing details see kernel-base/COPYING */ @@ -6941,10 +6941,13 @@ static int __perf_cgroup_move(void *info) return 0; } -static void -perf_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *task) +static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup_taskset *tset) { - task_function_call(task, __perf_cgroup_move, task); + struct task_struct *task; + + cgroup_taskset_for_each(task, cgrp, tset) + task_function_call(task, __perf_cgroup_move, task); } static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, @@ -6958,7 +6961,7 @@ static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, if (!(task->flags & PF_EXITING)) return; - perf_cgroup_attach_task(cgrp, task); + task_function_call(task, __perf_cgroup_move, task); } struct cgroup_subsys perf_subsys = { @@ -6967,6 +6970,6 @@ struct cgroup_subsys perf_subsys = { .create = perf_cgroup_create, .destroy = perf_cgroup_destroy, .exit = perf_cgroup_exit, - .attach_task = perf_cgroup_attach_task, + .attach = perf_cgroup_attach, }; #endif /* CONFIG_CGROUP_PERF */ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 7f3011c6b57f..6ddaba43fb7a 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -4,7 +4,7 @@ * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> - * Copyright 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> * * For licensing details see kernel-base/COPYING */ diff --git a/kernel/exit.c b/kernel/exit.c index d579a459309d..294b1709170d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -51,6 +51,7 @@ #include <trace/events/sched.h> #include <linux/hw_breakpoint.h> #include <linux/oom.h> +#include <linux/writeback.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -679,8 +680,6 @@ static void exit_mm(struct task_struct * tsk) tsk->mm = NULL; up_read(&mm->mmap_sem); enter_lazy_tlb(mm, current); - /* We don't want this task to be frozen prematurely */ - clear_freeze_flag(tsk); task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); @@ -888,7 +887,7 @@ static void check_stack_usage(void) static inline void check_stack_usage(void) {} #endif -NORET_TYPE void do_exit(long code) +void do_exit(long code) { struct task_struct *tsk = current; int group_dead; @@ -965,8 +964,7 @@ NORET_TYPE void do_exit(long code) acct_collect(code, group_dead); if (group_dead) tty_audit_exit(); - if (unlikely(tsk->audit_context)) - audit_free(tsk); + audit_free(tsk); tsk->exit_code = code; taskstats_exit(tsk, group_dead); @@ -1037,9 +1035,12 @@ NORET_TYPE void do_exit(long code) validate_creds_for_do_exit(tsk); preempt_disable(); + if (tsk->nr_dirtied) + __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; + tsk->flags |= PF_NOFREEZE; /* tell freezer to ignore us */ schedule(); BUG(); /* Avoid "noreturn function does return". */ @@ -1049,7 +1050,7 @@ NORET_TYPE void do_exit(long code) EXPORT_SYMBOL_GPL(do_exit); -NORET_TYPE void complete_and_exit(struct completion *comp, long code) +void complete_and_exit(struct completion *comp, long code) { if (comp) complete(comp); @@ -1068,7 +1069,7 @@ SYSCALL_DEFINE1(exit, int, error_code) * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). */ -NORET_TYPE void +void do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; diff --git a/kernel/fork.c b/kernel/fork.c index b058c5820ecd..051f090d40c1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -76,6 +76,9 @@ #include <trace/events/sched.h> +#define CREATE_TRACE_POINTS +#include <trace/events/task.h> + /* * Protected counters by write_lock_irq(&tasklist_lock) */ @@ -870,6 +873,7 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk) { #ifdef CONFIG_BLOCK struct io_context *ioc = current->io_context; + struct io_context *new_ioc; if (!ioc) return 0; @@ -881,11 +885,12 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk) if (unlikely(!tsk->io_context)) return -ENOMEM; } else if (ioprio_valid(ioc->ioprio)) { - tsk->io_context = alloc_io_context(GFP_KERNEL, -1); - if (unlikely(!tsk->io_context)) + new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE); + if (unlikely(!new_ioc)) return -ENOMEM; - tsk->io_context->ioprio = ioc->ioprio; + new_ioc->ioprio = ioc->ioprio; + put_io_context(new_ioc, NULL); } #endif return 0; @@ -972,7 +977,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sched_autogroup_fork(sig); #ifdef CONFIG_CGROUPS - init_rwsem(&sig->threadgroup_fork_lock); + init_rwsem(&sig->group_rwsem); #endif sig->oom_adj = current->signal->oom_adj; @@ -992,7 +997,6 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p) new_flags |= PF_FORKNOEXEC; new_flags |= PF_STARTING; p->flags = new_flags; - clear_freeze_flag(p); } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) @@ -1154,7 +1158,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->io_context = NULL; p->audit_context = NULL; if (clone_flags & CLONE_THREAD) - threadgroup_fork_read_lock(current); + threadgroup_change_begin(current); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); @@ -1292,6 +1296,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); + p->dirty_paused_when = 0; /* * Ok, make it visible to the rest of the system. @@ -1369,8 +1374,11 @@ static struct task_struct *copy_process(unsigned long clone_flags, proc_fork_connector(p); cgroup_post_fork(p); if (clone_flags & CLONE_THREAD) - threadgroup_fork_read_unlock(current); + threadgroup_change_end(current); perf_event_fork(p); + + trace_task_newtask(p, clone_flags); + return p; bad_fork_free_pid: @@ -1404,7 +1412,7 @@ bad_fork_cleanup_policy: bad_fork_cleanup_cgroup: #endif if (clone_flags & CLONE_THREAD) - threadgroup_fork_read_unlock(current); + threadgroup_change_end(current); cgroup_exit(p, cgroup_callbacks_done); delayacct_tsk_free(p); module_put(task_thread_info(p)->exec_domain->module); @@ -1519,8 +1527,6 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } - audit_finish_fork(p); - /* * We set PF_STARTING at creation in case tracing wants to * use this to distinguish a fully live task from one that diff --git a/kernel/freezer.c b/kernel/freezer.c index 7be56c534397..9815b8d1eed5 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -9,101 +9,114 @@ #include <linux/export.h> #include <linux/syscalls.h> #include <linux/freezer.h> +#include <linux/kthread.h> -/* - * freezing is complete, mark current process as frozen +/* total number of freezing conditions in effect */ +atomic_t system_freezing_cnt = ATOMIC_INIT(0); +EXPORT_SYMBOL(system_freezing_cnt); + +/* indicate whether PM freezing is in effect, protected by pm_mutex */ +bool pm_freezing; +bool pm_nosig_freezing; + +/* protects freezing and frozen transitions */ +static DEFINE_SPINLOCK(freezer_lock); + +/** + * freezing_slow_path - slow path for testing whether a task needs to be frozen + * @p: task to be tested + * + * This function is called by freezing() if system_freezing_cnt isn't zero + * and tests whether @p needs to enter and stay in frozen state. Can be + * called under any context. The freezers are responsible for ensuring the + * target tasks see the updated state. */ -static inline void frozen_process(void) +bool freezing_slow_path(struct task_struct *p) { - if (!unlikely(current->flags & PF_NOFREEZE)) { - current->flags |= PF_FROZEN; - smp_wmb(); - } - clear_freeze_flag(current); + if (p->flags & PF_NOFREEZE) + return false; + + if (pm_nosig_freezing || cgroup_freezing(p)) + return true; + + if (pm_freezing && !(p->flags & PF_KTHREAD)) + return true; + + return false; } +EXPORT_SYMBOL(freezing_slow_path); /* Refrigerator is place where frozen processes are stored :-). */ -void refrigerator(void) +bool __refrigerator(bool check_kthr_stop) { /* Hmm, should we be allowed to suspend when there are realtime processes around? */ - long save; + bool was_frozen = false; + long save = current->state; - task_lock(current); - if (freezing(current)) { - frozen_process(); - task_unlock(current); - } else { - task_unlock(current); - return; - } - save = current->state; pr_debug("%s entered refrigerator\n", current->comm); - spin_lock_irq(¤t->sighand->siglock); - recalc_sigpending(); /* We sent fake signal, clean it up */ - spin_unlock_irq(¤t->sighand->siglock); - - /* prevent accounting of that task to load */ - current->flags |= PF_FREEZING; - for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - if (!frozen(current)) + + spin_lock_irq(&freezer_lock); + current->flags |= PF_FROZEN; + if (!freezing(current) || + (check_kthr_stop && kthread_should_stop())) + current->flags &= ~PF_FROZEN; + spin_unlock_irq(&freezer_lock); + + if (!(current->flags & PF_FROZEN)) break; + was_frozen = true; schedule(); } - /* Remove the accounting blocker */ - current->flags &= ~PF_FREEZING; - pr_debug("%s left refrigerator\n", current->comm); - __set_current_state(save); + + /* + * Restore saved task state before returning. The mb'd version + * needs to be used; otherwise, it might silently break + * synchronization which depends on ordered task state change. + */ + set_current_state(save); + + return was_frozen; } -EXPORT_SYMBOL(refrigerator); +EXPORT_SYMBOL(__refrigerator); static void fake_signal_wake_up(struct task_struct *p) { unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - signal_wake_up(p, 0); - spin_unlock_irqrestore(&p->sighand->siglock, flags); + if (lock_task_sighand(p, &flags)) { + signal_wake_up(p, 0); + unlock_task_sighand(p, &flags); + } } /** - * freeze_task - send a freeze request to given task - * @p: task to send the request to - * @sig_only: if set, the request will only be sent if the task has the - * PF_FREEZER_NOSIG flag unset - * Return value: 'false', if @sig_only is set and the task has - * PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise + * freeze_task - send a freeze request to given task + * @p: task to send the request to + * + * If @p is freezing, the freeze request is sent by setting %TIF_FREEZE + * flag and either sending a fake signal to it or waking it up, depending + * on whether it has %PF_FREEZER_NOSIG set. * - * The freeze request is sent by setting the tasks's TIF_FREEZE flag and - * either sending a fake signal to it or waking it up, depending on whether - * or not it has PF_FREEZER_NOSIG set. If @sig_only is set and the task - * has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its - * TIF_FREEZE flag will not be set. + * RETURNS: + * %false, if @p is not freezing or already frozen; %true, otherwise */ -bool freeze_task(struct task_struct *p, bool sig_only) +bool freeze_task(struct task_struct *p) { - /* - * We first check if the task is freezing and next if it has already - * been frozen to avoid the race with frozen_process() which first marks - * the task as frozen and next clears its TIF_FREEZE. - */ - if (!freezing(p)) { - smp_rmb(); - if (frozen(p)) - return false; - - if (!sig_only || should_send_signal(p)) - set_freeze_flag(p); - else - return false; + unsigned long flags; + + spin_lock_irqsave(&freezer_lock, flags); + if (!freezing(p) || frozen(p)) { + spin_unlock_irqrestore(&freezer_lock, flags); + return false; } - if (should_send_signal(p)) { + if (!(p->flags & PF_KTHREAD)) { fake_signal_wake_up(p); /* * fake_signal_wake_up() goes through p's scheduler @@ -111,56 +124,48 @@ bool freeze_task(struct task_struct *p, bool sig_only) * TASK_RUNNING transition can't race with task state * testing in try_to_freeze_tasks(). */ - } else if (sig_only) { - return false; } else { wake_up_state(p, TASK_INTERRUPTIBLE); } + spin_unlock_irqrestore(&freezer_lock, flags); return true; } -void cancel_freezing(struct task_struct *p) +void __thaw_task(struct task_struct *p) { unsigned long flags; - if (freezing(p)) { - pr_debug(" clean up: %s\n", p->comm); - clear_freeze_flag(p); - spin_lock_irqsave(&p->sighand->siglock, flags); - recalc_sigpending_and_wake(p); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - } -} - -static int __thaw_process(struct task_struct *p) -{ - if (frozen(p)) { - p->flags &= ~PF_FROZEN; - return 1; - } - clear_freeze_flag(p); - return 0; + /* + * Clear freezing and kick @p if FROZEN. Clearing is guaranteed to + * be visible to @p as waking up implies wmb. Waking up inside + * freezer_lock also prevents wakeups from leaking outside + * refrigerator. + */ + spin_lock_irqsave(&freezer_lock, flags); + if (frozen(p)) + wake_up_process(p); + spin_unlock_irqrestore(&freezer_lock, flags); } -/* - * Wake up a frozen process +/** + * set_freezable - make %current freezable * - * task_lock() is needed to prevent the race with refrigerator() which may - * occur if the freezing of tasks fails. Namely, without the lock, if the - * freezing of tasks failed, thaw_tasks() might have run before a task in - * refrigerator() could call frozen_process(), in which case the task would be - * frozen and no one would thaw it. + * Mark %current freezable and enter refrigerator if necessary. */ -int thaw_process(struct task_struct *p) +bool set_freezable(void) { - task_lock(p); - if (__thaw_process(p) == 1) { - task_unlock(p); - wake_up_process(p); - return 1; - } - task_unlock(p); - return 0; + might_sleep(); + + /* + * Modify flags while holding freezer_lock. This ensures the + * freezer notices that we aren't frozen yet or the freezing + * condition is visible to try_to_freeze() below. + */ + spin_lock_irq(&freezer_lock); + current->flags &= ~PF_NOFREEZE; + spin_unlock_irq(&freezer_lock); + + return try_to_freeze(); } -EXPORT_SYMBOL(thaw_process); +EXPORT_SYMBOL(set_freezable); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index a73dd6c7372d..b7952316016a 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -15,7 +15,7 @@ #define istate core_internal_state__do_not_mess_with_it -extern int noirqdebug; +extern bool noirqdebug; /* * Bits used by threaded handlers: diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 200ce832c585..1f9e26526b69 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -135,6 +135,9 @@ int irq_domain_simple_dt_translate(struct irq_domain *d, return -EINVAL; if (intsize < 1) return -EINVAL; + if (d->nr_irq && ((intspec[0] < d->hwirq_base) || + (intspec[0] >= d->hwirq_base + d->nr_irq))) + return -EINVAL; *out_hwirq = intspec[0]; *out_type = IRQ_TYPE_NONE; @@ -143,11 +146,6 @@ int irq_domain_simple_dt_translate(struct irq_domain *d, return 0; } -struct irq_domain_ops irq_domain_simple_ops = { - .dt_translate = irq_domain_simple_dt_translate, -}; -EXPORT_SYMBOL_GPL(irq_domain_simple_ops); - /** * irq_domain_create_simple() - Set up a 'simple' translation range */ @@ -182,3 +180,10 @@ void irq_domain_generate_simple(const struct of_device_id *match, } EXPORT_SYMBOL_GPL(irq_domain_generate_simple); #endif /* CONFIG_OF_IRQ */ + +struct irq_domain_ops irq_domain_simple_ops = { +#ifdef CONFIG_OF_IRQ + .dt_translate = irq_domain_simple_dt_translate, +#endif /* CONFIG_OF_IRQ */ +}; +EXPORT_SYMBOL_GPL(irq_domain_simple_ops); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1da999f5e746..a9a9dbe49fea 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1292,7 +1292,7 @@ EXPORT_SYMBOL(free_irq); * and to set up the interrupt handler in the right order. * * If you want to set up a threaded irq handler for your device - * then you need to supply @handler and @thread_fn. @handler ist + * then you need to supply @handler and @thread_fn. @handler is * still called in hard interrupt context and has to check * whether the interrupt originates from the device. If yes it * needs to disable the interrupt on the device and return diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index dc813a948be2..611cd6003c45 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -325,7 +325,7 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, desc->irqs_unhandled = 0; } -int noirqdebug __read_mostly; +bool noirqdebug __read_mostly; int noirqdebug_setup(char *str) { diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 30c3c7708132..01d3b70fc98a 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -71,6 +71,7 @@ void jump_label_inc(struct jump_label_key *key) atomic_inc(&key->enabled); jump_label_unlock(); } +EXPORT_SYMBOL_GPL(jump_label_inc); static void __jump_label_dec(struct jump_label_key *key, unsigned long rate_limit, struct delayed_work *work) @@ -86,6 +87,7 @@ static void __jump_label_dec(struct jump_label_key *key, jump_label_unlock(); } +EXPORT_SYMBOL_GPL(jump_label_dec); static void jump_label_update_timeout(struct work_struct *work) { diff --git a/kernel/kexec.c b/kernel/kexec.c index dc7bc0829286..7b0886786701 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -32,7 +32,6 @@ #include <linux/console.h> #include <linux/vmalloc.h> #include <linux/swap.h> -#include <linux/kmsg_dump.h> #include <linux/syscore_ops.h> #include <asm/page.h> @@ -1094,8 +1093,6 @@ void crash_kexec(struct pt_regs *regs) if (kexec_crash_image) { struct pt_regs fixed_regs; - kmsg_dump(KMSG_DUMP_KEXEC); - crash_setup_regs(&fixed_regs, regs); crash_save_vmcoreinfo(); machine_crash_shutdown(&fixed_regs); @@ -1132,6 +1129,8 @@ int crash_shrink_memory(unsigned long new_size) { int ret = 0; unsigned long start, end; + unsigned long old_size; + struct resource *ram_res; mutex_lock(&kexec_mutex); @@ -1141,11 +1140,15 @@ int crash_shrink_memory(unsigned long new_size) } start = crashk_res.start; end = crashk_res.end; + old_size = (end == 0) ? 0 : end - start + 1; + if (new_size >= old_size) { + ret = (new_size == old_size) ? 0 : -EINVAL; + goto unlock; + } - if (new_size >= end - start + 1) { - ret = -EINVAL; - if (new_size == end - start + 1) - ret = 0; + ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL); + if (!ram_res) { + ret = -ENOMEM; goto unlock; } @@ -1157,7 +1160,15 @@ int crash_shrink_memory(unsigned long new_size) if ((start == end) && (crashk_res.parent != NULL)) release_resource(&crashk_res); + + ram_res->start = end; + ram_res->end = crashk_res.end; + ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + ram_res->name = "System RAM"; + crashk_res.end = end - 1; + + insert_resource(&iomem_resource, ram_res); crash_unmap_reserved_pages(); unlock: @@ -1523,7 +1534,7 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { - mutex_lock(&pm_mutex); + lock_system_sleep(); pm_prepare_console(); error = freeze_processes(); if (error) { @@ -1576,7 +1587,7 @@ int kernel_kexec(void) thaw_processes(); Restore_console: pm_restore_console(); - mutex_unlock(&pm_mutex); + unlock_system_sleep(); } #endif diff --git a/kernel/kmod.c b/kernel/kmod.c index a4bea97c75b6..a0a88543934e 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -36,6 +36,7 @@ #include <linux/resource.h> #include <linux/notifier.h> #include <linux/suspend.h> +#include <linux/rwsem.h> #include <asm/uaccess.h> #include <trace/events/module.h> @@ -50,6 +51,7 @@ static struct workqueue_struct *khelper_wq; static kernel_cap_t usermodehelper_bset = CAP_FULL_SET; static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET; static DEFINE_SPINLOCK(umh_sysctl_lock); +static DECLARE_RWSEM(umhelper_sem); #ifdef CONFIG_MODULES @@ -275,6 +277,7 @@ static void __call_usermodehelper(struct work_struct *work) * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY * (used for preventing user land processes from being created after the user * land has been frozen during a system-wide hibernation or suspend operation). + * Should always be manipulated under umhelper_sem acquired for write. */ static int usermodehelper_disabled = 1; @@ -282,17 +285,29 @@ static int usermodehelper_disabled = 1; static atomic_t running_helpers = ATOMIC_INIT(0); /* - * Wait queue head used by usermodehelper_pm_callback() to wait for all running + * Wait queue head used by usermodehelper_disable() to wait for all running * helpers to finish. */ static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq); /* * Time to wait for running_helpers to become zero before the setting of - * usermodehelper_disabled in usermodehelper_pm_callback() fails + * usermodehelper_disabled in usermodehelper_disable() fails */ #define RUNNING_HELPERS_TIMEOUT (5 * HZ) +void read_lock_usermodehelper(void) +{ + down_read(&umhelper_sem); +} +EXPORT_SYMBOL_GPL(read_lock_usermodehelper); + +void read_unlock_usermodehelper(void) +{ + up_read(&umhelper_sem); +} +EXPORT_SYMBOL_GPL(read_unlock_usermodehelper); + /** * usermodehelper_disable - prevent new helpers from being started */ @@ -300,8 +315,10 @@ int usermodehelper_disable(void) { long retval; + down_write(&umhelper_sem); usermodehelper_disabled = 1; - smp_mb(); + up_write(&umhelper_sem); + /* * From now on call_usermodehelper_exec() won't start any new * helpers, so it is sufficient if running_helpers turns out to @@ -314,7 +331,9 @@ int usermodehelper_disable(void) if (retval) return 0; + down_write(&umhelper_sem); usermodehelper_disabled = 0; + up_write(&umhelper_sem); return -EAGAIN; } @@ -323,7 +342,9 @@ int usermodehelper_disable(void) */ void usermodehelper_enable(void) { + down_write(&umhelper_sem); usermodehelper_disabled = 0; + up_write(&umhelper_sem); } /** diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e5d84644823b..95dd7212e610 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2198,7 +2198,7 @@ static ssize_t write_enabled_file_bool(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { char buf[32]; - int buf_size; + size_t buf_size; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) diff --git a/kernel/kthread.c b/kernel/kthread.c index b6d216a92639..3d3de633702e 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -59,6 +59,31 @@ int kthread_should_stop(void) EXPORT_SYMBOL(kthread_should_stop); /** + * kthread_freezable_should_stop - should this freezable kthread return now? + * @was_frozen: optional out parameter, indicates whether %current was frozen + * + * kthread_should_stop() for freezable kthreads, which will enter + * refrigerator if necessary. This function is safe from kthread_stop() / + * freezer deadlock and freezable kthreads should use this function instead + * of calling try_to_freeze() directly. + */ +bool kthread_freezable_should_stop(bool *was_frozen) +{ + bool frozen = false; + + might_sleep(); + + if (unlikely(freezing(current))) + frozen = __refrigerator(true); + + if (was_frozen) + *was_frozen = frozen; + + return kthread_should_stop(); +} +EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); + +/** * kthread_data - return data value specified on kthread creation * @task: kthread task in question * @@ -257,7 +282,7 @@ int kthreadd(void *unused) set_cpus_allowed_ptr(tsk, cpu_all_mask); set_mems_allowed(node_states[N_HIGH_MEMORY]); - current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG; + current->flags |= PF_NOFREEZE; for (;;) { set_current_state(TASK_INTERRUPTIBLE); diff --git a/kernel/module.c b/kernel/module.c index 178333c48d1e..2c932760fd33 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -62,12 +62,6 @@ #define CREATE_TRACE_POINTS #include <trace/events/module.h> -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(fmt , a...) -#endif - #ifndef ARCH_SHF_SMALL #define ARCH_SHF_SMALL 0 #endif @@ -138,7 +132,6 @@ struct load_info { unsigned long len; Elf_Shdr *sechdrs; char *secstrings, *strtab; - unsigned long *strmap; unsigned long symoffs, stroffs; struct _ddebug *debug; unsigned int num_debug; @@ -410,7 +403,7 @@ const struct kernel_symbol *find_symbol(const char *name, return fsa.sym; } - DEBUGP("Failed to find symbol %s\n", name); + pr_debug("Failed to find symbol %s\n", name); return NULL; } EXPORT_SYMBOL_GPL(find_symbol); @@ -600,11 +593,11 @@ static int already_uses(struct module *a, struct module *b) list_for_each_entry(use, &b->source_list, source_list) { if (use->source == a) { - DEBUGP("%s uses %s!\n", a->name, b->name); + pr_debug("%s uses %s!\n", a->name, b->name); return 1; } } - DEBUGP("%s does not use %s!\n", a->name, b->name); + pr_debug("%s does not use %s!\n", a->name, b->name); return 0; } @@ -619,7 +612,7 @@ static int add_module_usage(struct module *a, struct module *b) { struct module_use *use; - DEBUGP("Allocating new usage for %s.\n", a->name); + pr_debug("Allocating new usage for %s.\n", a->name); use = kmalloc(sizeof(*use), GFP_ATOMIC); if (!use) { printk(KERN_WARNING "%s: out of memory loading\n", a->name); @@ -663,7 +656,7 @@ static void module_unload_free(struct module *mod) mutex_lock(&module_mutex); list_for_each_entry_safe(use, tmp, &mod->target_list, target_list) { struct module *i = use->target; - DEBUGP("%s unusing %s\n", mod->name, i->name); + pr_debug("%s unusing %s\n", mod->name, i->name); module_put(i); list_del(&use->source_list); list_del(&use->target_list); @@ -726,9 +719,9 @@ static int try_stop_module(struct module *mod, int flags, int *forced) } } -unsigned int module_refcount(struct module *mod) +unsigned long module_refcount(struct module *mod) { - unsigned int incs = 0, decs = 0; + unsigned long incs = 0, decs = 0; int cpu; for_each_possible_cpu(cpu) @@ -761,7 +754,7 @@ static void wait_for_zero_refcount(struct module *mod) /* Since we might sleep for some time, release the mutex first */ mutex_unlock(&module_mutex); for (;;) { - DEBUGP("Looking at refcount...\n"); + pr_debug("Looking at refcount...\n"); set_current_state(TASK_UNINTERRUPTIBLE); if (module_refcount(mod) == 0) break; @@ -804,7 +797,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, if (mod->state != MODULE_STATE_LIVE) { /* FIXME: if (force), slam module count and wake up waiter --RR */ - DEBUGP("%s already dying\n", mod->name); + pr_debug("%s already dying\n", mod->name); ret = -EBUSY; goto out; } @@ -854,7 +847,7 @@ static inline void print_unload_info(struct seq_file *m, struct module *mod) struct module_use *use; int printed_something = 0; - seq_printf(m, " %u ", module_refcount(mod)); + seq_printf(m, " %lu ", module_refcount(mod)); /* Always include a trailing , so userspace can differentiate between this and the old multi-field proc format. */ @@ -904,13 +897,11 @@ EXPORT_SYMBOL_GPL(symbol_put_addr); static ssize_t show_refcnt(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", module_refcount(mk->mod)); + return sprintf(buffer, "%lu\n", module_refcount(mk->mod)); } -static struct module_attribute refcnt = { - .attr = { .name = "refcnt", .mode = 0444 }, - .show = show_refcnt, -}; +static struct module_attribute modinfo_refcnt = + __ATTR(refcnt, 0444, show_refcnt, NULL); void module_put(struct module *module) { @@ -951,6 +942,26 @@ static inline int module_unload_init(struct module *mod) } #endif /* CONFIG_MODULE_UNLOAD */ +static size_t module_flags_taint(struct module *mod, char *buf) +{ + size_t l = 0; + + if (mod->taints & (1 << TAINT_PROPRIETARY_MODULE)) + buf[l++] = 'P'; + if (mod->taints & (1 << TAINT_OOT_MODULE)) + buf[l++] = 'O'; + if (mod->taints & (1 << TAINT_FORCED_MODULE)) + buf[l++] = 'F'; + if (mod->taints & (1 << TAINT_CRAP)) + buf[l++] = 'C'; + /* + * TAINT_FORCED_RMMOD: could be added. + * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't + * apply to modules. + */ + return l; +} + static ssize_t show_initstate(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { @@ -970,10 +981,8 @@ static ssize_t show_initstate(struct module_attribute *mattr, return sprintf(buffer, "%s\n", state); } -static struct module_attribute initstate = { - .attr = { .name = "initstate", .mode = 0444 }, - .show = show_initstate, -}; +static struct module_attribute modinfo_initstate = + __ATTR(initstate, 0444, show_initstate, NULL); static ssize_t store_uevent(struct module_attribute *mattr, struct module_kobject *mk, @@ -986,18 +995,50 @@ static ssize_t store_uevent(struct module_attribute *mattr, return count; } -struct module_attribute module_uevent = { - .attr = { .name = "uevent", .mode = 0200 }, - .store = store_uevent, -}; +struct module_attribute module_uevent = + __ATTR(uevent, 0200, NULL, store_uevent); + +static ssize_t show_coresize(struct module_attribute *mattr, + struct module_kobject *mk, char *buffer) +{ + return sprintf(buffer, "%u\n", mk->mod->core_size); +} + +static struct module_attribute modinfo_coresize = + __ATTR(coresize, 0444, show_coresize, NULL); + +static ssize_t show_initsize(struct module_attribute *mattr, + struct module_kobject *mk, char *buffer) +{ + return sprintf(buffer, "%u\n", mk->mod->init_size); +} + +static struct module_attribute modinfo_initsize = + __ATTR(initsize, 0444, show_initsize, NULL); + +static ssize_t show_taint(struct module_attribute *mattr, + struct module_kobject *mk, char *buffer) +{ + size_t l; + + l = module_flags_taint(mk->mod, buffer); + buffer[l++] = '\n'; + return l; +} + +static struct module_attribute modinfo_taint = + __ATTR(taint, 0444, show_taint, NULL); static struct module_attribute *modinfo_attrs[] = { + &module_uevent, &modinfo_version, &modinfo_srcversion, - &initstate, - &module_uevent, + &modinfo_initstate, + &modinfo_coresize, + &modinfo_initsize, + &modinfo_taint, #ifdef CONFIG_MODULE_UNLOAD - &refcnt, + &modinfo_refcnt, #endif NULL, }; @@ -1057,7 +1098,7 @@ static int check_version(Elf_Shdr *sechdrs, if (versions[i].crc == maybe_relocated(*crc, crc_owner)) return 1; - DEBUGP("Found checksum %lX vs module %lX\n", + pr_debug("Found checksum %lX vs module %lX\n", maybe_relocated(*crc, crc_owner), versions[i].crc); goto bad_version; } @@ -1834,7 +1875,7 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) case SHN_COMMON: /* We compiled with -fno-common. These are not supposed to happen. */ - DEBUGP("Common symbol: %s\n", name); + pr_debug("Common symbol: %s\n", name); printk("%s: please compile with -fno-common\n", mod->name); ret = -ENOEXEC; @@ -1842,7 +1883,7 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) case SHN_ABS: /* Don't need to do anything */ - DEBUGP("Absolute symbol: 0x%08lx\n", + pr_debug("Absolute symbol: 0x%08lx\n", (long)sym[i].st_value); break; @@ -1966,7 +2007,7 @@ static void layout_sections(struct module *mod, struct load_info *info) for (i = 0; i < info->hdr->e_shnum; i++) info->sechdrs[i].sh_entsize = ~0UL; - DEBUGP("Core section allocation order:\n"); + pr_debug("Core section allocation order:\n"); for (m = 0; m < ARRAY_SIZE(masks); ++m) { for (i = 0; i < info->hdr->e_shnum; ++i) { Elf_Shdr *s = &info->sechdrs[i]; @@ -1978,7 +2019,7 @@ static void layout_sections(struct module *mod, struct load_info *info) || strstarts(sname, ".init")) continue; s->sh_entsize = get_offset(mod, &mod->core_size, s, i); - DEBUGP("\t%s\n", name); + pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ @@ -1995,7 +2036,7 @@ static void layout_sections(struct module *mod, struct load_info *info) } } - DEBUGP("Init section allocation order:\n"); + pr_debug("Init section allocation order:\n"); for (m = 0; m < ARRAY_SIZE(masks); ++m) { for (i = 0; i < info->hdr->e_shnum; ++i) { Elf_Shdr *s = &info->sechdrs[i]; @@ -2008,7 +2049,7 @@ static void layout_sections(struct module *mod, struct load_info *info) continue; s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) | INIT_OFFSET_MASK); - DEBUGP("\t%s\n", sname); + pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ @@ -2178,45 +2219,46 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, return true; } +/* + * We only allocate and copy the strings needed by the parts of symtab + * we keep. This is simple, but has the effect of making multiple + * copies of duplicates. We could be more sophisticated, see + * linux-kernel thread starting with + * <73defb5e4bca04a6431392cc341112b1@localhost>. + */ static void layout_symtab(struct module *mod, struct load_info *info) { Elf_Shdr *symsect = info->sechdrs + info->index.sym; Elf_Shdr *strsect = info->sechdrs + info->index.str; const Elf_Sym *src; - unsigned int i, nsrc, ndst; + unsigned int i, nsrc, ndst, strtab_size; /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, info->index.sym) | INIT_OFFSET_MASK; - DEBUGP("\t%s\n", info->secstrings + symsect->sh_name); + pr_debug("\t%s\n", info->secstrings + symsect->sh_name); src = (void *)info->hdr + symsect->sh_offset; nsrc = symsect->sh_size / sizeof(*src); - for (ndst = i = 1; i < nsrc; ++i, ++src) - if (is_core_symbol(src, info->sechdrs, info->hdr->e_shnum)) { - unsigned int j = src->st_name; - while (!__test_and_set_bit(j, info->strmap) - && info->strtab[j]) - ++j; - ++ndst; + /* Compute total space required for the core symbols' strtab. */ + for (ndst = i = strtab_size = 1; i < nsrc; ++i, ++src) + if (is_core_symbol(src, info->sechdrs, info->hdr->e_shnum)) { + strtab_size += strlen(&info->strtab[src->st_name]) + 1; + ndst++; } /* Append room for core symbols at end of core part. */ info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); - mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym); + info->stroffs = mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym); + mod->core_size += strtab_size; /* Put string table section at end of init part of module. */ strsect->sh_flags |= SHF_ALLOC; strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, info->index.str) | INIT_OFFSET_MASK; - DEBUGP("\t%s\n", info->secstrings + strsect->sh_name); - - /* Append room for core symbols' strings at end of core part. */ - info->stroffs = mod->core_size; - __set_bit(0, info->strmap); - mod->core_size += bitmap_weight(info->strmap, strsect->sh_size); + pr_debug("\t%s\n", info->secstrings + strsect->sh_name); } static void add_kallsyms(struct module *mod, const struct load_info *info) @@ -2237,22 +2279,19 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); mod->core_symtab = dst = mod->module_core + info->symoffs; + mod->core_strtab = s = mod->module_core + info->stroffs; src = mod->symtab; *dst = *src; + *s++ = 0; for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) { if (!is_core_symbol(src, info->sechdrs, info->hdr->e_shnum)) continue; + dst[ndst] = *src; - dst[ndst].st_name = bitmap_weight(info->strmap, - dst[ndst].st_name); - ++ndst; + dst[ndst++].st_name = s - mod->core_strtab; + s += strlcpy(s, &mod->strtab[src->st_name], KSYM_NAME_LEN) + 1; } mod->core_num_syms = ndst; - - mod->core_strtab = s = mod->module_core + info->stroffs; - for (*s = 0, i = 1; i < info->sechdrs[info->index.str].sh_size; ++i) - if (test_bit(i, info->strmap)) - *++s = mod->strtab[i]; } #else static inline void layout_symtab(struct module *mod, struct load_info *info) @@ -2621,7 +2660,7 @@ static int move_module(struct module *mod, struct load_info *info) mod->module_init = ptr; /* Transfer each section which specifies SHF_ALLOC */ - DEBUGP("final section addresses:\n"); + pr_debug("final section addresses:\n"); for (i = 0; i < info->hdr->e_shnum; i++) { void *dest; Elf_Shdr *shdr = &info->sechdrs[i]; @@ -2639,8 +2678,8 @@ static int move_module(struct module *mod, struct load_info *info) memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); /* Update sh_addr to point to copy in image. */ shdr->sh_addr = (unsigned long)dest; - DEBUGP("\t0x%lx %s\n", - shdr->sh_addr, info->secstrings + shdr->sh_name); + pr_debug("\t0x%lx %s\n", + (long)shdr->sh_addr, info->secstrings + shdr->sh_name); } return 0; @@ -2742,27 +2781,18 @@ static struct module *layout_and_allocate(struct load_info *info) this is done generically; there doesn't appear to be any special cases for the architectures. */ layout_sections(mod, info); - - info->strmap = kzalloc(BITS_TO_LONGS(info->sechdrs[info->index.str].sh_size) - * sizeof(long), GFP_KERNEL); - if (!info->strmap) { - err = -ENOMEM; - goto free_percpu; - } layout_symtab(mod, info); /* Allocate and move to the final place */ err = move_module(mod, info); if (err) - goto free_strmap; + goto free_percpu; /* Module has been copied to its final place now: return it. */ mod = (void *)info->sechdrs[info->index.mod].sh_addr; kmemleak_load_module(mod, info); return mod; -free_strmap: - kfree(info->strmap); free_percpu: percpu_modfree(mod); out: @@ -2772,7 +2802,6 @@ out: /* mod is no longer valid after this! */ static void module_deallocate(struct module *mod, struct load_info *info) { - kfree(info->strmap); percpu_modfree(mod); module_free(mod, mod->module_init); module_free(mod, mod->module_core); @@ -2811,7 +2840,7 @@ static struct module *load_module(void __user *umod, struct module *mod; long err; - DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", + pr_debug("load_module: umod=%p, len=%lu, uargs=%p\n", umod, len, uargs); /* Copy in the blobs from userspace, check they are vaguely sane. */ @@ -2902,8 +2931,7 @@ static struct module *load_module(void __user *umod, if (err < 0) goto unlink; - /* Get rid of temporary copy and strmap. */ - kfree(info.strmap); + /* Get rid of temporary copy. */ free_copy(&info); /* Done! */ @@ -3256,20 +3284,7 @@ static char *module_flags(struct module *mod, char *buf) mod->state == MODULE_STATE_GOING || mod->state == MODULE_STATE_COMING) { buf[bx++] = '('; - if (mod->taints & (1 << TAINT_PROPRIETARY_MODULE)) - buf[bx++] = 'P'; - else if (mod->taints & (1 << TAINT_OOT_MODULE)) - buf[bx++] = 'O'; - if (mod->taints & (1 << TAINT_FORCED_MODULE)) - buf[bx++] = 'F'; - if (mod->taints & (1 << TAINT_CRAP)) - buf[bx++] = 'C'; - /* - * TAINT_FORCED_RMMOD: could be added. - * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't - * apply to modules. - */ - + bx += module_flags_taint(mod, buf + bx); /* Show a - for module-is-being-unloaded */ if (mod->state == MODULE_STATE_GOING) buf[bx++] = '-'; diff --git a/kernel/panic.c b/kernel/panic.c index 3458469eb7c3..80aed44e345a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -49,6 +49,15 @@ static long no_blink(int state) long (*panic_blink)(int state); EXPORT_SYMBOL(panic_blink); +/* + * Stop ourself in panic -- architecture code may override this + */ +void __weak panic_smp_self_stop(void) +{ + while (1) + cpu_relax(); +} + /** * panic - halt the system * @fmt: The text string to print @@ -57,8 +66,9 @@ EXPORT_SYMBOL(panic_blink); * * This function never returns. */ -NORET_TYPE void panic(const char * fmt, ...) +void panic(const char *fmt, ...) { + static DEFINE_SPINLOCK(panic_lock); static char buf[1024]; va_list args; long i, i_next = 0; @@ -68,8 +78,14 @@ NORET_TYPE void panic(const char * fmt, ...) * It's possible to come here directly from a panic-assertion and * not have preempt disabled. Some functions called from here want * preempt to be disabled. No point enabling it later though... + * + * Only one CPU is allowed to execute the panic code from here. For + * multiple parallel invocations of panic, all other CPUs either + * stop themself or will wait until they are stopped by the 1st CPU + * with smp_send_stop(). */ - preempt_disable(); + if (!spin_trylock(&panic_lock)) + panic_smp_self_stop(); console_verbose(); bust_spinlocks(1); @@ -78,7 +94,11 @@ NORET_TYPE void panic(const char * fmt, ...) va_end(args); printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf); #ifdef CONFIG_DEBUG_BUGVERBOSE - dump_stack(); + /* + * Avoid nested stack-dumping if a panic occurs during oops processing + */ + if (!oops_in_progress) + dump_stack(); #endif /* diff --git a/kernel/params.c b/kernel/params.c index 65aae11eb93f..32ee04308285 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -25,12 +25,6 @@ #include <linux/slab.h> #include <linux/ctype.h> -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(fmt, a...) -#endif - /* Protects all parameters, and incidentally kmalloced_param list. */ static DEFINE_MUTEX(param_lock); @@ -105,7 +99,7 @@ static int parse_one(char *param, /* No one handled NULL, so do it here. */ if (!val && params[i].ops->set != param_set_bool) return -EINVAL; - DEBUGP("They are equal! Calling %p\n", + pr_debug("They are equal! Calling %p\n", params[i].ops->set); mutex_lock(¶m_lock); err = params[i].ops->set(val, ¶ms[i]); @@ -115,11 +109,11 @@ static int parse_one(char *param, } if (handle_unknown) { - DEBUGP("Unknown argument: calling %p\n", handle_unknown); + pr_debug("Unknown argument: calling %p\n", handle_unknown); return handle_unknown(param, val); } - DEBUGP("Unknown argument `%s'\n", param); + pr_debug("Unknown argument `%s'\n", param); return -ENOENT; } @@ -184,7 +178,7 @@ int parse_args(const char *name, { char *param, *val; - DEBUGP("Parsing ARGS: %s\n", args); + pr_debug("Parsing ARGS: %s\n", args); /* Chew leading spaces */ args = skip_spaces(args); @@ -369,6 +363,30 @@ struct kernel_param_ops param_ops_invbool = { }; EXPORT_SYMBOL(param_ops_invbool); +int param_set_bint(const char *val, const struct kernel_param *kp) +{ + struct kernel_param boolkp; + bool v; + int ret; + + /* Match bool exactly, by re-using it. */ + boolkp = *kp; + boolkp.arg = &v; + boolkp.flags |= KPARAM_ISBOOL; + + ret = param_set_bool(val, &boolkp); + if (ret == 0) + *(int *)kp->arg = v; + return ret; +} +EXPORT_SYMBOL(param_set_bint); + +struct kernel_param_ops param_ops_bint = { + .set = param_set_bint, + .get = param_get_int, +}; +EXPORT_SYMBOL(param_ops_bint); + /* We break the rule and mangle the string. */ static int param_array(const char *name, const char *val, diff --git a/kernel/pid.c b/kernel/pid.c index fa5f72227e5f..ce8e00deaccb 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -137,7 +137,9 @@ static int pid_before(int base, int a, int b) } /* - * We might be racing with someone else trying to set pid_ns->last_pid. + * We might be racing with someone else trying to set pid_ns->last_pid + * at the pid allocation time (there's also a sysctl for this, but racing + * with this one is OK, see comment in kernel/pid_namespace.c about it). * We want the winner to have the "later" value, because if the * "earlier" value prevails, then a pid may get reused immediately. * diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index e9c9adc84ca6..a8968396046d 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -191,9 +191,40 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) return; } +static int pid_ns_ctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* + * Writing directly to ns' last_pid field is OK, since this field + * is volatile in a living namespace anyway and a code writing to + * it should synchronize its usage with external means. + */ + + tmp.data = ¤t->nsproxy->pid_ns->last_pid; + return proc_dointvec(&tmp, write, buffer, lenp, ppos); +} + +static struct ctl_table pid_ns_ctl_table[] = { + { + .procname = "ns_last_pid", + .maxlen = sizeof(int), + .mode = 0666, /* permissions are checked in the handler */ + .proc_handler = pid_ns_ctl_handler, + }, + { } +}; + +static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } }; + static __init int pid_namespaces_init(void) { pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC); + register_sysctl_paths(kern_path, pid_ns_ctl_table); return 0; } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a6b0503574ee..6d6d28870335 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -43,8 +43,6 @@ int in_suspend __nosavedata; enum { HIBERNATION_INVALID, HIBERNATION_PLATFORM, - HIBERNATION_TEST, - HIBERNATION_TESTPROC, HIBERNATION_SHUTDOWN, HIBERNATION_REBOOT, /* keep last */ @@ -55,7 +53,7 @@ enum { static int hibernation_mode = HIBERNATION_SHUTDOWN; -static bool freezer_test_done; +bool freezer_test_done; static const struct platform_hibernation_ops *hibernation_ops; @@ -71,14 +69,14 @@ void hibernation_set_ops(const struct platform_hibernation_ops *ops) WARN_ON(1); return; } - mutex_lock(&pm_mutex); + lock_system_sleep(); hibernation_ops = ops; if (ops) hibernation_mode = HIBERNATION_PLATFORM; else if (hibernation_mode == HIBERNATION_PLATFORM) hibernation_mode = HIBERNATION_SHUTDOWN; - mutex_unlock(&pm_mutex); + unlock_system_sleep(); } static bool entering_platform_hibernation; @@ -96,15 +94,6 @@ static void hibernation_debug_sleep(void) mdelay(5000); } -static int hibernation_testmode(int mode) -{ - if (hibernation_mode == mode) { - hibernation_debug_sleep(); - return 1; - } - return 0; -} - static int hibernation_test(int level) { if (pm_test_level == level) { @@ -114,7 +103,6 @@ static int hibernation_test(int level) return 0; } #else /* !CONFIG_PM_DEBUG */ -static int hibernation_testmode(int mode) { return 0; } static int hibernation_test(int level) { return 0; } #endif /* !CONFIG_PM_DEBUG */ @@ -278,8 +266,7 @@ static int create_image(int platform_mode) goto Platform_finish; error = disable_nonboot_cpus(); - if (error || hibernation_test(TEST_CPUS) - || hibernation_testmode(HIBERNATION_TEST)) + if (error || hibernation_test(TEST_CPUS)) goto Enable_cpus; local_irq_disable(); @@ -333,7 +320,7 @@ static int create_image(int platform_mode) */ int hibernation_snapshot(int platform_mode) { - pm_message_t msg = PMSG_RECOVER; + pm_message_t msg; int error; error = platform_begin(platform_mode); @@ -349,8 +336,7 @@ int hibernation_snapshot(int platform_mode) if (error) goto Cleanup; - if (hibernation_test(TEST_FREEZER) || - hibernation_testmode(HIBERNATION_TESTPROC)) { + if (hibernation_test(TEST_FREEZER)) { /* * Indicate to the caller that we are returning due to a @@ -362,26 +348,26 @@ int hibernation_snapshot(int platform_mode) error = dpm_prepare(PMSG_FREEZE); if (error) { - dpm_complete(msg); + dpm_complete(PMSG_RECOVER); goto Cleanup; } suspend_console(); pm_restrict_gfp_mask(); + error = dpm_suspend(PMSG_FREEZE); - if (error) - goto Recover_platform; - if (hibernation_test(TEST_DEVICES)) - goto Recover_platform; + if (error || hibernation_test(TEST_DEVICES)) + platform_recover(platform_mode); + else + error = create_image(platform_mode); - error = create_image(platform_mode); /* - * Control returns here (1) after the image has been created or the + * In the case that we call create_image() above, the control + * returns here (1) after the image has been created or the * image creation has failed and (2) after a successful restore. */ - Resume_devices: /* We may need to release the preallocated image pages here. */ if (error || !in_suspend) swsusp_free(); @@ -399,10 +385,6 @@ int hibernation_snapshot(int platform_mode) platform_end(platform_mode); return error; - Recover_platform: - platform_recover(platform_mode); - goto Resume_devices; - Cleanup: swsusp_free(); goto Close; @@ -590,9 +572,6 @@ int hibernation_platform_enter(void) static void power_down(void) { switch (hibernation_mode) { - case HIBERNATION_TEST: - case HIBERNATION_TESTPROC: - break; case HIBERNATION_REBOOT: kernel_restart(NULL); break; @@ -611,17 +590,6 @@ static void power_down(void) while(1); } -static int prepare_processes(void) -{ - int error = 0; - - if (freeze_processes()) { - error = -EBUSY; - thaw_processes(); - } - return error; -} - /** * hibernate - Carry out system hibernation, including saving the image. */ @@ -629,7 +597,7 @@ int hibernate(void) { int error; - mutex_lock(&pm_mutex); + lock_system_sleep(); /* The snapshot device should not be opened while we're running */ if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { error = -EBUSY; @@ -654,7 +622,7 @@ int hibernate(void) sys_sync(); printk("done.\n"); - error = prepare_processes(); + error = freeze_processes(); if (error) goto Finish; @@ -697,7 +665,7 @@ int hibernate(void) pm_restore_console(); atomic_inc(&snapshot_device_available); Unlock: - mutex_unlock(&pm_mutex); + unlock_system_sleep(); return error; } @@ -811,11 +779,13 @@ static int software_resume(void) goto close_finish; error = create_basic_memory_bitmaps(); - if (error) + if (error) { + usermodehelper_enable(); goto close_finish; + } pr_debug("PM: Preparing processes for restore.\n"); - error = prepare_processes(); + error = freeze_processes(); if (error) { swsusp_close(FMODE_READ); goto Done; @@ -855,8 +825,6 @@ static const char * const hibernation_modes[] = { [HIBERNATION_PLATFORM] = "platform", [HIBERNATION_SHUTDOWN] = "shutdown", [HIBERNATION_REBOOT] = "reboot", - [HIBERNATION_TEST] = "test", - [HIBERNATION_TESTPROC] = "testproc", }; /* @@ -865,17 +833,15 @@ static const char * const hibernation_modes[] = { * Hibernation can be handled in several ways. There are a few different ways * to put the system into the sleep state: using the platform driver (e.g. ACPI * or other hibernation_ops), powering it off or rebooting it (for testing - * mostly), or using one of the two available test modes. + * mostly). * * The sysfs file /sys/power/disk provides an interface for selecting the * hibernation mode to use. Reading from this file causes the available modes - * to be printed. There are 5 modes that can be supported: + * to be printed. There are 3 modes that can be supported: * * 'platform' * 'shutdown' * 'reboot' - * 'test' - * 'testproc' * * If a platform hibernation driver is in use, 'platform' will be supported * and will be used by default. Otherwise, 'shutdown' will be used by default. @@ -899,8 +865,6 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, switch (i) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: - case HIBERNATION_TEST: - case HIBERNATION_TESTPROC: break; case HIBERNATION_PLATFORM: if (hibernation_ops) @@ -929,7 +893,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, p = memchr(buf, '\n', n); len = p ? p - buf : n; - mutex_lock(&pm_mutex); + lock_system_sleep(); for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) { if (len == strlen(hibernation_modes[i]) && !strncmp(buf, hibernation_modes[i], len)) { @@ -941,8 +905,6 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, switch (mode) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: - case HIBERNATION_TEST: - case HIBERNATION_TESTPROC: hibernation_mode = mode; break; case HIBERNATION_PLATFORM: @@ -957,7 +919,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, if (!error) pr_debug("PM: Hibernation mode set to '%s'\n", hibernation_modes[mode]); - mutex_unlock(&pm_mutex); + unlock_system_sleep(); return error ? error : n; } @@ -984,9 +946,9 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, if (maj != MAJOR(res) || min != MINOR(res)) goto out; - mutex_lock(&pm_mutex); + lock_system_sleep(); swsusp_resume_device = res; - mutex_unlock(&pm_mutex); + unlock_system_sleep(); printk(KERN_INFO "PM: Starting manual resume from disk\n"); noresume = 0; software_resume(); diff --git a/kernel/power/main.c b/kernel/power/main.c index 36e0f0903c32..9824b41e5a18 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -3,7 +3,7 @@ * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab - * + * * This file is released under the GPLv2 * */ @@ -116,7 +116,7 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr, p = memchr(buf, '\n', n); len = p ? p - buf : n; - mutex_lock(&pm_mutex); + lock_system_sleep(); level = TEST_FIRST; for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++) @@ -126,7 +126,7 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr, break; } - mutex_unlock(&pm_mutex); + unlock_system_sleep(); return error ? error : n; } @@ -240,7 +240,7 @@ struct kobject *power_kobj; * 'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and * 'disk' (Suspend-to-Disk). * - * store() accepts one of those strings, translates it into the + * store() accepts one of those strings, translates it into the * proper enumerated value, and initiates a suspend transition. */ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, @@ -282,7 +282,7 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, /* First, check if we are requested to hibernate */ if (len == 4 && !strncmp(buf, "disk", len)) { error = hibernate(); - goto Exit; + goto Exit; } #ifdef CONFIG_SUSPEND diff --git a/kernel/power/power.h b/kernel/power/power.h index 23a2db1ec442..0c4defe6d3b8 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -50,6 +50,8 @@ static inline char *check_image_kernel(struct swsusp_info *info) #define SPARE_PAGES ((1024 * 1024) >> PAGE_SHIFT) /* kernel/power/hibernate.c */ +extern bool freezer_test_done; + extern int hibernation_snapshot(int platform_mode); extern int hibernation_restore(int platform_mode); extern int hibernation_platform_enter(void); diff --git a/kernel/power/process.c b/kernel/power/process.c index addbbe5531bc..77274c9ba2f1 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -22,16 +22,7 @@ */ #define TIMEOUT (20 * HZ) -static inline int freezable(struct task_struct * p) -{ - if ((p == current) || - (p->flags & PF_NOFREEZE) || - (p->exit_state != 0)) - return 0; - return 1; -} - -static int try_to_freeze_tasks(bool sig_only) +static int try_to_freeze_tasks(bool user_only) { struct task_struct *g, *p; unsigned long end_time; @@ -46,17 +37,14 @@ static int try_to_freeze_tasks(bool sig_only) end_time = jiffies + TIMEOUT; - if (!sig_only) + if (!user_only) freeze_workqueues_begin(); while (true) { todo = 0; read_lock(&tasklist_lock); do_each_thread(g, p) { - if (frozen(p) || !freezable(p)) - continue; - - if (!freeze_task(p, sig_only)) + if (p == current || !freeze_task(p)) continue; /* @@ -77,7 +65,7 @@ static int try_to_freeze_tasks(bool sig_only) } while_each_thread(g, p); read_unlock(&tasklist_lock); - if (!sig_only) { + if (!user_only) { wq_busy = freeze_workqueues_busy(); todo += wq_busy; } @@ -103,11 +91,6 @@ static int try_to_freeze_tasks(bool sig_only) elapsed_csecs = elapsed_csecs64; if (todo) { - /* This does not unfreeze processes that are already frozen - * (we have slightly ugly calling convention in that respect, - * and caller must call thaw_processes() if something fails), - * but it cleans up leftover PF_FREEZE requests. - */ printk("\n"); printk(KERN_ERR "Freezing of tasks %s after %d.%02d seconds " "(%d tasks refusing to freeze, wq_busy=%d):\n", @@ -115,15 +98,11 @@ static int try_to_freeze_tasks(bool sig_only) elapsed_csecs / 100, elapsed_csecs % 100, todo - wq_busy, wq_busy); - thaw_workqueues(); - read_lock(&tasklist_lock); do_each_thread(g, p) { - task_lock(p); - if (!wakeup && freezing(p) && !freezer_should_skip(p)) + if (!wakeup && !freezer_should_skip(p) && + p != current && freezing(p) && !frozen(p)) sched_show_task(p); - cancel_freezing(p); - task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); } else { @@ -136,12 +115,18 @@ static int try_to_freeze_tasks(bool sig_only) /** * freeze_processes - Signal user space processes to enter the refrigerator. + * + * On success, returns 0. On failure, -errno and system is fully thawed. */ int freeze_processes(void) { int error; + if (!pm_freezing) + atomic_inc(&system_freezing_cnt); + printk("Freezing user space processes ... "); + pm_freezing = true; error = try_to_freeze_tasks(true); if (!error) { printk("done."); @@ -150,17 +135,22 @@ int freeze_processes(void) printk("\n"); BUG_ON(in_atomic()); + if (error) + thaw_processes(); return error; } /** * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator. + * + * On success, returns 0. On failure, -errno and system is fully thawed. */ int freeze_kernel_threads(void) { int error; printk("Freezing remaining freezable tasks ... "); + pm_nosig_freezing = true; error = try_to_freeze_tasks(false); if (!error) printk("done."); @@ -168,37 +158,32 @@ int freeze_kernel_threads(void) printk("\n"); BUG_ON(in_atomic()); + if (error) + thaw_processes(); return error; } -static void thaw_tasks(bool nosig_only) +void thaw_processes(void) { struct task_struct *g, *p; - read_lock(&tasklist_lock); - do_each_thread(g, p) { - if (!freezable(p)) - continue; + if (pm_freezing) + atomic_dec(&system_freezing_cnt); + pm_freezing = false; + pm_nosig_freezing = false; - if (nosig_only && should_send_signal(p)) - continue; + oom_killer_enable(); + + printk("Restarting tasks ... "); - if (cgroup_freezing_or_frozen(p)) - continue; + thaw_workqueues(); - thaw_process(p); + read_lock(&tasklist_lock); + do_each_thread(g, p) { + __thaw_task(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); -} -void thaw_processes(void) -{ - oom_killer_enable(); - - printk("Restarting tasks ... "); - thaw_workqueues(); - thaw_tasks(true); - thaw_tasks(false); schedule(); printk("done.\n"); } diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index cbe2c1441392..1cf88900ec4f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -858,6 +858,9 @@ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) PageReserved(page)) return NULL; + if (page_is_guard(page)) + return NULL; + return page; } @@ -920,6 +923,9 @@ static struct page *saveable_page(struct zone *zone, unsigned long pfn) && (!kernel_page_present(page) || pfn_is_nosave(pfn))) return NULL; + if (page_is_guard(page)) + return NULL; + return page; } diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 4953dc054c53..4fd51beed879 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -42,9 +42,9 @@ static const struct platform_suspend_ops *suspend_ops; */ void suspend_set_ops(const struct platform_suspend_ops *ops) { - mutex_lock(&pm_mutex); + lock_system_sleep(); suspend_ops = ops; - mutex_unlock(&pm_mutex); + unlock_system_sleep(); } EXPORT_SYMBOL_GPL(suspend_set_ops); @@ -106,13 +106,11 @@ static int suspend_prepare(void) goto Finish; error = suspend_freeze_processes(); - if (error) { - suspend_stats.failed_freeze++; - dpm_save_failed_step(SUSPEND_FREEZE); - } else + if (!error) return 0; - suspend_thaw_processes(); + suspend_stats.failed_freeze++; + dpm_save_failed_step(SUSPEND_FREEZE); usermodehelper_enable(); Finish: pm_notifier_call_chain(PM_POST_SUSPEND); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 11a594c4ba25..8742fd013a94 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -18,7 +18,6 @@ #include <linux/bitops.h> #include <linux/genhd.h> #include <linux/device.h> -#include <linux/buffer_head.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/swap.h> @@ -774,8 +773,7 @@ static int enough_swap(unsigned int nr_pages, unsigned int flags) pr_debug("PM: Free swap pages: %u\n", free_swap); - required = PAGES_FOR_IO + ((flags & SF_NOCOMPRESS_MODE) ? - nr_pages : (nr_pages * LZO_CMP_PAGES) / LZO_UNC_PAGES + 1); + required = PAGES_FOR_IO + nr_pages; return free_swap > required; } @@ -803,10 +801,12 @@ int swsusp_write(unsigned int flags) printk(KERN_ERR "PM: Cannot get swap writer\n"); return error; } - if (!enough_swap(pages, flags)) { - printk(KERN_ERR "PM: Not enough free swap\n"); - error = -ENOSPC; - goto out_finish; + if (flags & SF_NOCOMPRESS_MODE) { + if (!enough_swap(pages, flags)) { + printk(KERN_ERR "PM: Not enough free swap\n"); + error = -ENOSPC; + goto out_finish; + } } memset(&snapshot, 0, sizeof(struct snapshot_handle)); error = snapshot_read_next(&snapshot); diff --git a/kernel/power/user.c b/kernel/power/user.c index 6d8f535c2b88..6b1ab7a88522 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -21,6 +21,7 @@ #include <linux/swapops.h> #include <linux/pm.h> #include <linux/fs.h> +#include <linux/compat.h> #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> @@ -30,28 +31,6 @@ #include "power.h" -/* - * NOTE: The SNAPSHOT_SET_SWAP_FILE and SNAPSHOT_PMOPS ioctls are obsolete and - * will be removed in the future. They are only preserved here for - * compatibility with existing userland utilities. - */ -#define SNAPSHOT_SET_SWAP_FILE _IOW(SNAPSHOT_IOC_MAGIC, 10, unsigned int) -#define SNAPSHOT_PMOPS _IOW(SNAPSHOT_IOC_MAGIC, 12, unsigned int) - -#define PMOPS_PREPARE 1 -#define PMOPS_ENTER 2 -#define PMOPS_FINISH 3 - -/* - * NOTE: The following ioctl definitions are wrong and have been replaced with - * correct ones. They are only preserved here for compatibility with existing - * userland utilities and will be removed in the future. - */ -#define SNAPSHOT_ATOMIC_SNAPSHOT _IOW(SNAPSHOT_IOC_MAGIC, 3, void *) -#define SNAPSHOT_SET_IMAGE_SIZE _IOW(SNAPSHOT_IOC_MAGIC, 6, unsigned long) -#define SNAPSHOT_AVAIL_SWAP _IOR(SNAPSHOT_IOC_MAGIC, 7, void *) -#define SNAPSHOT_GET_SWAP_PAGE _IOR(SNAPSHOT_IOC_MAGIC, 8, void *) - #define SNAPSHOT_MINOR 231 @@ -71,7 +50,7 @@ static int snapshot_open(struct inode *inode, struct file *filp) struct snapshot_data *data; int error; - mutex_lock(&pm_mutex); + lock_system_sleep(); if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { error = -EBUSY; @@ -123,7 +102,7 @@ static int snapshot_open(struct inode *inode, struct file *filp) data->platform_support = 0; Unlock: - mutex_unlock(&pm_mutex); + unlock_system_sleep(); return error; } @@ -132,7 +111,7 @@ static int snapshot_release(struct inode *inode, struct file *filp) { struct snapshot_data *data; - mutex_lock(&pm_mutex); + lock_system_sleep(); swsusp_free(); free_basic_memory_bitmaps(); @@ -146,7 +125,7 @@ static int snapshot_release(struct inode *inode, struct file *filp) PM_POST_HIBERNATION : PM_POST_RESTORE); atomic_inc(&snapshot_device_available); - mutex_unlock(&pm_mutex); + unlock_system_sleep(); return 0; } @@ -158,7 +137,7 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf, ssize_t res; loff_t pg_offp = *offp & ~PAGE_MASK; - mutex_lock(&pm_mutex); + lock_system_sleep(); data = filp->private_data; if (!data->ready) { @@ -179,7 +158,7 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf, *offp += res; Unlock: - mutex_unlock(&pm_mutex); + unlock_system_sleep(); return res; } @@ -191,7 +170,7 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, ssize_t res; loff_t pg_offp = *offp & ~PAGE_MASK; - mutex_lock(&pm_mutex); + lock_system_sleep(); data = filp->private_data; @@ -208,20 +187,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, if (res > 0) *offp += res; unlock: - mutex_unlock(&pm_mutex); + unlock_system_sleep(); return res; } -static void snapshot_deprecated_ioctl(unsigned int cmd) -{ - if (printk_ratelimit()) - printk(KERN_NOTICE "%pf: ioctl '%.8x' is deprecated and will " - "be removed soon, update your suspend-to-disk " - "utilities\n", - __builtin_return_address(0), cmd); -} - static long snapshot_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { @@ -257,11 +227,9 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, break; error = freeze_processes(); - if (error) { - thaw_processes(); + if (error) usermodehelper_enable(); - } - if (!error) + else data->frozen = 1; break; @@ -274,8 +242,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, data->frozen = 0; break; - case SNAPSHOT_ATOMIC_SNAPSHOT: - snapshot_deprecated_ioctl(cmd); case SNAPSHOT_CREATE_IMAGE: if (data->mode != O_RDONLY || !data->frozen || data->ready) { error = -EPERM; @@ -283,10 +249,15 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, } pm_restore_gfp_mask(); error = hibernation_snapshot(data->platform_support); - if (!error) + if (!error) { error = put_user(in_suspend, (int __user *)arg); - if (!error) - data->ready = 1; + if (!error && !freezer_test_done) + data->ready = 1; + if (freezer_test_done) { + freezer_test_done = false; + thaw_processes(); + } + } break; case SNAPSHOT_ATOMIC_RESTORE: @@ -305,8 +276,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, data->ready = 0; break; - case SNAPSHOT_SET_IMAGE_SIZE: - snapshot_deprecated_ioctl(cmd); case SNAPSHOT_PREF_IMAGE_SIZE: image_size = arg; break; @@ -321,16 +290,12 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, error = put_user(size, (loff_t __user *)arg); break; - case SNAPSHOT_AVAIL_SWAP: - snapshot_deprecated_ioctl(cmd); case SNAPSHOT_AVAIL_SWAP_SIZE: size = count_swap_pages(data->swap, 1); size <<= PAGE_SHIFT; error = put_user(size, (loff_t __user *)arg); break; - case SNAPSHOT_GET_SWAP_PAGE: - snapshot_deprecated_ioctl(cmd); case SNAPSHOT_ALLOC_SWAP_PAGE: if (data->swap < 0 || data->swap >= MAX_SWAPFILES) { error = -ENODEV; @@ -353,27 +318,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, free_all_swap_pages(data->swap); break; - case SNAPSHOT_SET_SWAP_FILE: /* This ioctl is deprecated */ - snapshot_deprecated_ioctl(cmd); - if (!swsusp_swap_in_use()) { - /* - * User space encodes device types as two-byte values, - * so we need to recode them - */ - if (old_decode_dev(arg)) { - data->swap = swap_type_of(old_decode_dev(arg), - 0, NULL); - if (data->swap < 0) - error = -ENODEV; - } else { - data->swap = -1; - error = -EINVAL; - } - } else { - error = -EPERM; - } - break; - case SNAPSHOT_S2RAM: if (!data->frozen) { error = -EPERM; @@ -396,33 +340,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, error = hibernation_platform_enter(); break; - case SNAPSHOT_PMOPS: /* This ioctl is deprecated */ - snapshot_deprecated_ioctl(cmd); - error = -EINVAL; - - switch (arg) { - - case PMOPS_PREPARE: - data->platform_support = 1; - error = 0; - break; - - case PMOPS_ENTER: - if (data->platform_support) - error = hibernation_platform_enter(); - break; - - case PMOPS_FINISH: - if (data->platform_support) - error = 0; - break; - - default: - printk(KERN_ERR "SNAPSHOT_PMOPS: invalid argument %ld\n", arg); - - } - break; - case SNAPSHOT_SET_SWAP_AREA: if (swsusp_swap_in_use()) { error = -EPERM; @@ -464,6 +381,66 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, return error; } +#ifdef CONFIG_COMPAT + +struct compat_resume_swap_area { + compat_loff_t offset; + u32 dev; +} __packed; + +static long +snapshot_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + BUILD_BUG_ON(sizeof(loff_t) != sizeof(compat_loff_t)); + + switch (cmd) { + case SNAPSHOT_GET_IMAGE_SIZE: + case SNAPSHOT_AVAIL_SWAP_SIZE: + case SNAPSHOT_ALLOC_SWAP_PAGE: { + compat_loff_t __user *uoffset = compat_ptr(arg); + loff_t offset; + mm_segment_t old_fs; + int err; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + err = snapshot_ioctl(file, cmd, (unsigned long) &offset); + set_fs(old_fs); + if (!err && put_user(offset, uoffset)) + err = -EFAULT; + return err; + } + + case SNAPSHOT_CREATE_IMAGE: + return snapshot_ioctl(file, cmd, + (unsigned long) compat_ptr(arg)); + + case SNAPSHOT_SET_SWAP_AREA: { + struct compat_resume_swap_area __user *u_swap_area = + compat_ptr(arg); + struct resume_swap_area swap_area; + mm_segment_t old_fs; + int err; + + err = get_user(swap_area.offset, &u_swap_area->offset); + err |= get_user(swap_area.dev, &u_swap_area->dev); + if (err) + return -EFAULT; + old_fs = get_fs(); + set_fs(KERNEL_DS); + err = snapshot_ioctl(file, SNAPSHOT_SET_SWAP_AREA, + (unsigned long) &swap_area); + set_fs(old_fs); + return err; + } + + default: + return snapshot_ioctl(file, cmd, arg); + } +} + +#endif /* CONFIG_COMPAT */ + static const struct file_operations snapshot_fops = { .open = snapshot_open, .release = snapshot_release, @@ -471,6 +448,9 @@ static const struct file_operations snapshot_fops = { .write = snapshot_write, .llseek = no_llseek, .unlocked_ioctl = snapshot_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = snapshot_compat_ioctl, +#endif }; static struct miscdevice snapshot_device = { diff --git a/kernel/printk.c b/kernel/printk.c index 989e4a52da76..13c0a1143f49 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -521,7 +521,7 @@ static void __call_console_drivers(unsigned start, unsigned end) } } -static int __read_mostly ignore_loglevel; +static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) { @@ -532,7 +532,7 @@ static int __init ignore_loglevel_setup(char *str) } early_param("ignore_loglevel", ignore_loglevel_setup); -module_param_named(ignore_loglevel, ignore_loglevel, bool, S_IRUGO | S_IWUSR); +module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to" "print all kernel messages to the console."); @@ -696,9 +696,9 @@ static void zap_locks(void) } #if defined(CONFIG_PRINTK_TIME) -static int printk_time = 1; +static bool printk_time = 1; #else -static int printk_time = 0; +static bool printk_time = 0; #endif module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); @@ -1098,7 +1098,7 @@ int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, cha return -1; } -int console_suspend_enabled = 1; +bool console_suspend_enabled = 1; EXPORT_SYMBOL(console_suspend_enabled); static int __init console_suspend_disable(char *str) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 78ab24a7b0e4..00ab2ca5ed11 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -172,6 +172,14 @@ int ptrace_check_attach(struct task_struct *child, bool ignore_state) return ret; } +static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) +{ + if (mode & PTRACE_MODE_NOAUDIT) + return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); + else + return has_ns_capability(current, ns, CAP_SYS_PTRACE); +} + int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; @@ -198,7 +206,7 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) cred->gid == tcred->sgid && cred->gid == tcred->gid)) goto ok; - if (ns_capable(tcred->user->user_ns, CAP_SYS_PTRACE)) + if (ptrace_has_cap(tcred->user->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; @@ -207,7 +215,7 @@ ok: smp_rmb(); if (task->mm) dumpable = get_dumpable(task->mm); - if (!dumpable && !task_ns_capable(task, CAP_SYS_PTRACE)) + if (!dumpable && !ptrace_has_cap(task_user_ns(task), mode)) return -EPERM; return security_ptrace_access_check(task, mode); @@ -277,7 +285,7 @@ static int ptrace_attach(struct task_struct *task, long request, task->ptrace = PT_PTRACED; if (seize) task->ptrace |= PT_SEIZED; - if (task_ns_capable(task, CAP_SYS_PTRACE)) + if (ns_capable(task_user_ns(task), CAP_SYS_PTRACE)) task->ptrace |= PT_PTRACE_CAP; __ptrace_link(task, current); diff --git a/kernel/relay.c b/kernel/relay.c index 226fade4d727..4335e1d7ee2d 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -302,7 +302,7 @@ static void buf_unmapped_default_callback(struct rchan_buf *buf, */ static struct dentry *create_buf_file_default_callback(const char *filename, struct dentry *parent, - int mode, + umode_t mode, struct rchan_buf *buf, int *is_global) { diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 34683efa2cce..6d269cce7aa1 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -159,8 +159,7 @@ int res_counter_memparse_write_strategy(const char *buf, return 0; } - /* FIXME - make memparse() take const char* args */ - *res = memparse((char *)buf, &end); + *res = memparse(buf, &end); if (*end != '\0') return -EINVAL; diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c index 3d9f31cd79e7..98ec49475460 100644 --- a/kernel/rtmutex-tester.c +++ b/kernel/rtmutex-tester.c @@ -6,11 +6,11 @@ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> * */ +#include <linux/device.h> #include <linux/kthread.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/spinlock.h> -#include <linux/sysdev.h> #include <linux/timer.h> #include <linux/freezer.h> @@ -27,7 +27,7 @@ struct test_thread_data { int opdata; int mutexes[MAX_RT_TEST_MUTEXES]; int event; - struct sys_device sysdev; + struct device dev; }; static struct test_thread_data thread_data[MAX_RT_TEST_THREADS]; @@ -271,7 +271,7 @@ static int test_func(void *data) * * opcode:data */ -static ssize_t sysfs_test_command(struct sys_device *dev, struct sysdev_attribute *attr, +static ssize_t sysfs_test_command(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct sched_param schedpar; @@ -279,8 +279,8 @@ static ssize_t sysfs_test_command(struct sys_device *dev, struct sysdev_attribut char cmdbuf[32]; int op, dat, tid, ret; - td = container_of(dev, struct test_thread_data, sysdev); - tid = td->sysdev.id; + td = container_of(dev, struct test_thread_data, dev); + tid = td->dev.id; /* strings from sysfs write are not 0 terminated! */ if (count >= sizeof(cmdbuf)) @@ -334,7 +334,7 @@ static ssize_t sysfs_test_command(struct sys_device *dev, struct sysdev_attribut * @dev: thread to query * @buf: char buffer to be filled with thread status info */ -static ssize_t sysfs_test_status(struct sys_device *dev, struct sysdev_attribute *attr, +static ssize_t sysfs_test_status(struct device *dev, struct device_attribute *attr, char *buf) { struct test_thread_data *td; @@ -342,8 +342,8 @@ static ssize_t sysfs_test_status(struct sys_device *dev, struct sysdev_attribute char *curr = buf; int i; - td = container_of(dev, struct test_thread_data, sysdev); - tsk = threads[td->sysdev.id]; + td = container_of(dev, struct test_thread_data, dev); + tsk = threads[td->dev.id]; spin_lock(&rttest_lock); @@ -360,28 +360,29 @@ static ssize_t sysfs_test_status(struct sys_device *dev, struct sysdev_attribute spin_unlock(&rttest_lock); curr += sprintf(curr, ", T: %p, R: %p\n", tsk, - mutexes[td->sysdev.id].owner); + mutexes[td->dev.id].owner); return curr - buf; } -static SYSDEV_ATTR(status, 0600, sysfs_test_status, NULL); -static SYSDEV_ATTR(command, 0600, NULL, sysfs_test_command); +static DEVICE_ATTR(status, 0600, sysfs_test_status, NULL); +static DEVICE_ATTR(command, 0600, NULL, sysfs_test_command); -static struct sysdev_class rttest_sysclass = { +static struct bus_type rttest_subsys = { .name = "rttest", + .dev_name = "rttest", }; static int init_test_thread(int id) { - thread_data[id].sysdev.cls = &rttest_sysclass; - thread_data[id].sysdev.id = id; + thread_data[id].dev.bus = &rttest_subsys; + thread_data[id].dev.id = id; threads[id] = kthread_run(test_func, &thread_data[id], "rt-test-%d", id); if (IS_ERR(threads[id])) return PTR_ERR(threads[id]); - return sysdev_register(&thread_data[id].sysdev); + return device_register(&thread_data[id].dev); } static int init_rttest(void) @@ -393,7 +394,7 @@ static int init_rttest(void) for (i = 0; i < MAX_RT_TEST_MUTEXES; i++) rt_mutex_init(&mutexes[i]); - ret = sysdev_class_register(&rttest_sysclass); + ret = subsys_system_register(&rttest_subsys, NULL); if (ret) return ret; @@ -401,10 +402,10 @@ static int init_rttest(void) ret = init_test_thread(i); if (ret) break; - ret = sysdev_create_file(&thread_data[i].sysdev, &attr_status); + ret = device_create_file(&thread_data[i].dev, &dev_attr_status); if (ret) break; - ret = sysdev_create_file(&thread_data[i].sysdev, &attr_command); + ret = device_create_file(&thread_data[i].dev, &dev_attr_command); if (ret) break; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 457c881873cb..df00cb09263e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4330,7 +4330,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) goto out_free_cpus_allowed; } retval = -EPERM; - if (!check_same_owner(p) && !task_ns_capable(p, CAP_SYS_NICE)) + if (!check_same_owner(p) && !ns_capable(task_user_ns(p), CAP_SYS_NICE)) goto out_unlock; retval = security_task_setscheduler(p); @@ -5176,7 +5176,7 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) static void set_table_entry(struct ctl_table *entry, const char *procname, void *data, int maxlen, - mode_t mode, proc_handler *proc_handler) + umode_t mode, proc_handler *proc_handler) { entry->procname = procname; entry->data = data; @@ -6675,54 +6675,52 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) } #ifdef CONFIG_SCHED_MC -static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, - struct sysdev_class_attribute *attr, - char *page) +static ssize_t sched_mc_power_savings_show(struct device *dev, + struct device_attribute *attr, + char *buf) { - return sprintf(page, "%u\n", sched_mc_power_savings); + return sprintf(buf, "%u\n", sched_mc_power_savings); } -static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, - struct sysdev_class_attribute *attr, +static ssize_t sched_mc_power_savings_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 0); } -static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, - sched_mc_power_savings_show, - sched_mc_power_savings_store); +static DEVICE_ATTR(sched_mc_power_savings, 0644, + sched_mc_power_savings_show, + sched_mc_power_savings_store); #endif #ifdef CONFIG_SCHED_SMT -static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, - struct sysdev_class_attribute *attr, - char *page) +static ssize_t sched_smt_power_savings_show(struct device *dev, + struct device_attribute *attr, + char *buf) { - return sprintf(page, "%u\n", sched_smt_power_savings); + return sprintf(buf, "%u\n", sched_smt_power_savings); } -static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, - struct sysdev_class_attribute *attr, +static ssize_t sched_smt_power_savings_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 1); } -static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, +static DEVICE_ATTR(sched_smt_power_savings, 0644, sched_smt_power_savings_show, sched_smt_power_savings_store); #endif -int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) +int __init sched_create_sysfs_power_savings_entries(struct device *dev) { int err = 0; #ifdef CONFIG_SCHED_SMT if (smt_capable()) - err = sysfs_create_file(&cls->kset.kobj, - &attr_sched_smt_power_savings.attr); + err = device_create_file(dev, &dev_attr_sched_smt_power_savings); #endif #ifdef CONFIG_SCHED_MC if (!err && mc_capable()) - err = sysfs_create_file(&cls->kset.kobj, - &attr_sched_mc_power_savings.attr); + err = device_create_file(dev, &dev_attr_sched_mc_power_savings); #endif return err; } @@ -7558,24 +7556,31 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) sched_destroy_group(tg); } -static int -cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) +static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup_taskset *tset) { + struct task_struct *task; + + cgroup_taskset_for_each(task, cgrp, tset) { #ifdef CONFIG_RT_GROUP_SCHED - if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) - return -EINVAL; + if (!sched_rt_can_attach(cgroup_tg(cgrp), task)) + return -EINVAL; #else - /* We don't support RT-tasks being in separate groups */ - if (tsk->sched_class != &fair_sched_class) - return -EINVAL; + /* We don't support RT-tasks being in separate groups */ + if (task->sched_class != &fair_sched_class) + return -EINVAL; #endif + } return 0; } -static void -cpu_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) +static void cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup_taskset *tset) { - sched_move_task(tsk); + struct task_struct *task; + + cgroup_taskset_for_each(task, cgrp, tset) + sched_move_task(task); } static void @@ -7910,8 +7915,8 @@ struct cgroup_subsys cpu_cgroup_subsys = { .name = "cpu", .create = cpu_cgroup_create, .destroy = cpu_cgroup_destroy, - .can_attach_task = cpu_cgroup_can_attach_task, - .attach_task = cpu_cgroup_attach_task, + .can_attach = cpu_cgroup_can_attach, + .attach = cpu_cgroup_attach, .exit = cpu_cgroup_exit, .populate = cpu_cgroup_populate, .subsys_id = cpu_cgroup_subsys_id, diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 57d4b13b631d..e8d76c5895ea 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -6,6 +6,7 @@ * This defines a simple but solid secure-computing mode. */ +#include <linux/audit.h> #include <linux/seccomp.h> #include <linux/sched.h> #include <linux/compat.h> @@ -54,6 +55,7 @@ void __secure_computing(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif + audit_seccomp(this_syscall); do_exit(SIGKILL); } diff --git a/kernel/signal.c b/kernel/signal.c index 56ce3a618b28..c73c4284160e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -28,6 +28,7 @@ #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <linux/nsproxy.h> +#include <linux/user_namespace.h> #define CREATE_TRACE_POINTS #include <trace/events/signal.h> @@ -1019,6 +1020,34 @@ static inline int legacy_queue(struct sigpending *signals, int sig) return (sig < SIGRTMIN) && sigismember(&signals->signal, sig); } +/* + * map the uid in struct cred into user namespace *ns + */ +static inline uid_t map_cred_ns(const struct cred *cred, + struct user_namespace *ns) +{ + return user_ns_map_uid(ns, cred, cred->uid); +} + +#ifdef CONFIG_USER_NS +static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +{ + if (current_user_ns() == task_cred_xxx(t, user_ns)) + return; + + if (SI_FROMKERNEL(info)) + return; + + info->si_uid = user_ns_map_uid(task_cred_xxx(t, user_ns), + current_cred(), info->si_uid); +} +#else +static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +{ + return; +} +#endif + static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, int group, int from_ancestor_ns) { @@ -1088,6 +1117,9 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, q->info.si_pid = 0; break; } + + userns_fixup_signal_uid(&q->info, t); + } else if (!is_si_special(info)) { if (sig >= SIGRTMIN && info->si_code != SI_USER) { /* @@ -1626,7 +1658,8 @@ bool do_notify_parent(struct task_struct *tsk, int sig) */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns); - info.si_uid = __task_cred(tsk)->uid; + info.si_uid = map_cred_ns(__task_cred(tsk), + task_cred_xxx(tsk->parent, user_ns)); rcu_read_unlock(); info.si_utime = cputime_to_clock_t(tsk->utime + tsk->signal->utime); @@ -1709,7 +1742,8 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns); - info.si_uid = __task_cred(tsk)->uid; + info.si_uid = map_cred_ns(__task_cred(tsk), + task_cred_xxx(parent, user_ns)); rcu_read_unlock(); info.si_utime = cputime_to_clock_t(tsk->utime); @@ -2125,8 +2159,11 @@ static int ptrace_signal(int signr, siginfo_t *info, info->si_signo = signr; info->si_errno = 0; info->si_code = SI_USER; + rcu_read_lock(); info->si_pid = task_pid_vnr(current->parent); - info->si_uid = task_uid(current->parent); + info->si_uid = map_cred_ns(__task_cred(current->parent), + current_user_ns()); + rcu_read_unlock(); } /* If the (new) signal is now blocked, requeue it. */ @@ -2318,6 +2355,27 @@ relock: return signr; } +/** + * block_sigmask - add @ka's signal mask to current->blocked + * @ka: action for @signr + * @signr: signal that has been successfully delivered + * + * This function should be called when a signal has succesfully been + * delivered. It adds the mask of signals for @ka to current->blocked + * so that they are blocked during the execution of the signal + * handler. In addition, @signr will be blocked unless %SA_NODEFER is + * set in @ka->sa.sa_flags. + */ +void block_sigmask(struct k_sigaction *ka, int signr) +{ + sigset_t blocked; + + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); + if (!(ka->sa.sa_flags & SA_NODEFER)) + sigaddset(&blocked, signr); + set_current_blocked(&blocked); +} + /* * It could be that complete_signal() picked us to notify about the * group-wide signal. Other threads should be notified now to take @@ -2355,8 +2413,15 @@ void exit_signals(struct task_struct *tsk) int group_stop = 0; sigset_t unblocked; + /* + * @tsk is about to have PF_EXITING set - lock out users which + * expect stable threadgroup. + */ + threadgroup_change_begin(tsk); + if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) { tsk->flags |= PF_EXITING; + threadgroup_change_end(tsk); return; } @@ -2366,6 +2431,9 @@ void exit_signals(struct task_struct *tsk) * see wants_signal(), do_signal_stop(). */ tsk->flags |= PF_EXITING; + + threadgroup_change_end(tsk); + if (!signal_pending(tsk)) goto out; diff --git a/kernel/sys.c b/kernel/sys.c index ddf8155bf3f8..40701538fbd1 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1692,6 +1692,124 @@ SYSCALL_DEFINE1(umask, int, mask) return mask; } +#ifdef CONFIG_CHECKPOINT_RESTORE +static int prctl_set_mm(int opt, unsigned long addr, + unsigned long arg4, unsigned long arg5) +{ + unsigned long rlim = rlimit(RLIMIT_DATA); + unsigned long vm_req_flags; + unsigned long vm_bad_flags; + struct vm_area_struct *vma; + int error = 0; + struct mm_struct *mm = current->mm; + + if (arg4 | arg5) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (addr >= TASK_SIZE) + return -EINVAL; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, addr); + + if (opt != PR_SET_MM_START_BRK && opt != PR_SET_MM_BRK) { + /* It must be existing VMA */ + if (!vma || vma->vm_start > addr) + goto out; + } + + error = -EINVAL; + switch (opt) { + case PR_SET_MM_START_CODE: + case PR_SET_MM_END_CODE: + vm_req_flags = VM_READ | VM_EXEC; + vm_bad_flags = VM_WRITE | VM_MAYSHARE; + + if ((vma->vm_flags & vm_req_flags) != vm_req_flags || + (vma->vm_flags & vm_bad_flags)) + goto out; + + if (opt == PR_SET_MM_START_CODE) + mm->start_code = addr; + else + mm->end_code = addr; + break; + + case PR_SET_MM_START_DATA: + case PR_SET_MM_END_DATA: + vm_req_flags = VM_READ | VM_WRITE; + vm_bad_flags = VM_EXEC | VM_MAYSHARE; + + if ((vma->vm_flags & vm_req_flags) != vm_req_flags || + (vma->vm_flags & vm_bad_flags)) + goto out; + + if (opt == PR_SET_MM_START_DATA) + mm->start_data = addr; + else + mm->end_data = addr; + break; + + case PR_SET_MM_START_STACK: + +#ifdef CONFIG_STACK_GROWSUP + vm_req_flags = VM_READ | VM_WRITE | VM_GROWSUP; +#else + vm_req_flags = VM_READ | VM_WRITE | VM_GROWSDOWN; +#endif + if ((vma->vm_flags & vm_req_flags) != vm_req_flags) + goto out; + + mm->start_stack = addr; + break; + + case PR_SET_MM_START_BRK: + if (addr <= mm->end_data) + goto out; + + if (rlim < RLIM_INFINITY && + (mm->brk - addr) + + (mm->end_data - mm->start_data) > rlim) + goto out; + + mm->start_brk = addr; + break; + + case PR_SET_MM_BRK: + if (addr <= mm->end_data) + goto out; + + if (rlim < RLIM_INFINITY && + (addr - mm->start_brk) + + (mm->end_data - mm->start_data) > rlim) + goto out; + + mm->brk = addr; + break; + + default: + error = -EINVAL; + goto out; + } + + error = 0; + +out: + up_read(&mm->mmap_sem); + + return error; +} +#else /* CONFIG_CHECKPOINT_RESTORE */ +static int prctl_set_mm(int opt, unsigned long addr, + unsigned long arg4, unsigned long arg5) +{ + return -EINVAL; +} +#endif + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -1841,6 +1959,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, else error = PR_MCE_KILL_DEFAULT; break; + case PR_SET_MM: + error = prctl_set_mm(arg2, arg3, arg4, arg5); + break; default: error = -EINVAL; break; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ae2719643854..f487f257e05e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -803,6 +803,15 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_DEBUG_STACKOVERFLOW + { + .procname = "panic_on_stackoverflow", + .data = &sysctl_panic_on_stackoverflow, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif { .procname = "bootloader_type", .data = &bootloader_type, diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index b26c2228fe92..2cf9cc7aa103 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -25,7 +25,7 @@ config HIGH_RES_TIMERS config GENERIC_CLOCKEVENTS_BUILD bool default y - depends on GENERIC_CLOCKEVENTS || GENERIC_CLOCKEVENTS_MIGR + depends on GENERIC_CLOCKEVENTS config GENERIC_CLOCKEVENTS_MIN_ADJUST bool diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 1ecd6ba36d6c..9cd928f7a7c6 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -17,7 +17,6 @@ #include <linux/module.h> #include <linux/notifier.h> #include <linux/smp.h> -#include <linux/sysdev.h> #include "tick-internal.h" diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index d3ad022136e5..a45ca167ab24 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -23,8 +23,8 @@ * o Allow clocksource drivers to be unregistered */ +#include <linux/device.h> #include <linux/clocksource.h> -#include <linux/sysdev.h> #include <linux/init.h> #include <linux/module.h> #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */ @@ -796,8 +796,8 @@ EXPORT_SYMBOL(clocksource_unregister); * Provides sysfs interface for listing current clocksource. */ static ssize_t -sysfs_show_current_clocksources(struct sys_device *dev, - struct sysdev_attribute *attr, char *buf) +sysfs_show_current_clocksources(struct device *dev, + struct device_attribute *attr, char *buf) { ssize_t count = 0; @@ -818,8 +818,8 @@ sysfs_show_current_clocksources(struct sys_device *dev, * Takes input from sysfs interface for manually overriding the default * clocksource selection. */ -static ssize_t sysfs_override_clocksource(struct sys_device *dev, - struct sysdev_attribute *attr, +static ssize_t sysfs_override_clocksource(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { size_t ret = count; @@ -853,8 +853,8 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev, * Provides sysfs interface for listing registered clocksources */ static ssize_t -sysfs_show_available_clocksources(struct sys_device *dev, - struct sysdev_attribute *attr, +sysfs_show_available_clocksources(struct device *dev, + struct device_attribute *attr, char *buf) { struct clocksource *src; @@ -883,35 +883,36 @@ sysfs_show_available_clocksources(struct sys_device *dev, /* * Sysfs setup bits: */ -static SYSDEV_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, +static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, sysfs_override_clocksource); -static SYSDEV_ATTR(available_clocksource, 0444, +static DEVICE_ATTR(available_clocksource, 0444, sysfs_show_available_clocksources, NULL); -static struct sysdev_class clocksource_sysclass = { +static struct bus_type clocksource_subsys = { .name = "clocksource", + .dev_name = "clocksource", }; -static struct sys_device device_clocksource = { +static struct device device_clocksource = { .id = 0, - .cls = &clocksource_sysclass, + .bus = &clocksource_subsys, }; static int __init init_clocksource_sysfs(void) { - int error = sysdev_class_register(&clocksource_sysclass); + int error = subsys_system_register(&clocksource_subsys, NULL); if (!error) - error = sysdev_register(&device_clocksource); + error = device_register(&device_clocksource); if (!error) - error = sysdev_create_file( + error = device_create_file( &device_clocksource, - &attr_current_clocksource); + &dev_attr_current_clocksource); if (!error) - error = sysdev_create_file( + error = device_create_file( &device_clocksource, - &attr_available_clocksource); + &dev_attr_available_clocksource); return error; } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 16fc34a0806f..cdea7b56b0c9 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -402,7 +402,7 @@ static int blk_remove_buf_file_callback(struct dentry *dentry) static struct dentry *blk_create_buf_file_callback(const char *filename, struct dentry *parent, - int mode, + umode_t mode, struct rchan_buf *buf, int *is_global) { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b1e8943fed1d..683d559a0eef 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -22,11 +22,13 @@ #include <linux/hardirq.h> #include <linux/kthread.h> #include <linux/uaccess.h> +#include <linux/bsearch.h> #include <linux/module.h> #include <linux/ftrace.h> #include <linux/sysctl.h> #include <linux/slab.h> #include <linux/ctype.h> +#include <linux/sort.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/rcupdate.h> @@ -947,13 +949,6 @@ struct ftrace_func_probe { struct rcu_head rcu; }; -enum { - FTRACE_ENABLE_CALLS = (1 << 0), - FTRACE_DISABLE_CALLS = (1 << 1), - FTRACE_UPDATE_TRACE_FUNC = (1 << 2), - FTRACE_START_FUNC_RET = (1 << 3), - FTRACE_STOP_FUNC_RET = (1 << 4), -}; struct ftrace_func_entry { struct hlist_node hlist; unsigned long ip; @@ -984,18 +979,19 @@ static struct ftrace_ops global_ops = { .filter_hash = EMPTY_HASH, }; -static struct dyn_ftrace *ftrace_new_addrs; - static DEFINE_MUTEX(ftrace_regex_lock); struct ftrace_page { struct ftrace_page *next; + struct dyn_ftrace *records; int index; - struct dyn_ftrace records[]; + int size; }; -#define ENTRIES_PER_PAGE \ - ((PAGE_SIZE - sizeof(struct ftrace_page)) / sizeof(struct dyn_ftrace)) +static struct ftrace_page *ftrace_new_pgs; + +#define ENTRY_SIZE sizeof(struct dyn_ftrace) +#define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) /* estimate from running different kernels */ #define NR_TO_INIT 10000 @@ -1003,7 +999,10 @@ struct ftrace_page { static struct ftrace_page *ftrace_pages_start; static struct ftrace_page *ftrace_pages; -static struct dyn_ftrace *ftrace_free_records; +static bool ftrace_hash_empty(struct ftrace_hash *hash) +{ + return !hash || !hash->count; +} static struct ftrace_func_entry * ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) @@ -1013,7 +1012,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) struct hlist_head *hhd; struct hlist_node *n; - if (!hash->count) + if (ftrace_hash_empty(hash)) return NULL; if (hash->size_bits > 0) @@ -1157,7 +1156,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) return NULL; /* Empty hash? */ - if (!hash || !hash->count) + if (ftrace_hash_empty(hash)) return new_hash; size = 1 << hash->size_bits; @@ -1282,9 +1281,9 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) filter_hash = rcu_dereference_raw(ops->filter_hash); notrace_hash = rcu_dereference_raw(ops->notrace_hash); - if ((!filter_hash || !filter_hash->count || + if ((ftrace_hash_empty(filter_hash) || ftrace_lookup_ip(filter_hash, ip)) && - (!notrace_hash || !notrace_hash->count || + (ftrace_hash_empty(notrace_hash) || !ftrace_lookup_ip(notrace_hash, ip))) ret = 1; else @@ -1307,6 +1306,47 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) } \ } + +static int ftrace_cmp_recs(const void *a, const void *b) +{ + const struct dyn_ftrace *reca = a; + const struct dyn_ftrace *recb = b; + + if (reca->ip > recb->ip) + return 1; + if (reca->ip < recb->ip) + return -1; + return 0; +} + +/** + * ftrace_location - return true if the ip giving is a traced location + * @ip: the instruction pointer to check + * + * Returns 1 if @ip given is a pointer to a ftrace location. + * That is, the instruction that is either a NOP or call to + * the function tracer. It checks the ftrace internal tables to + * determine if the address belongs or not. + */ +int ftrace_location(unsigned long ip) +{ + struct ftrace_page *pg; + struct dyn_ftrace *rec; + struct dyn_ftrace key; + + key.ip = ip; + + for (pg = ftrace_pages_start; pg; pg = pg->next) { + rec = bsearch(&key, pg->records, pg->index, + sizeof(struct dyn_ftrace), + ftrace_cmp_recs); + if (rec) + return 1; + } + + return 0; +} + static void __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) @@ -1336,7 +1376,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (filter_hash) { hash = ops->filter_hash; other_hash = ops->notrace_hash; - if (!hash || !hash->count) + if (ftrace_hash_empty(hash)) all = 1; } else { inc = !inc; @@ -1346,7 +1386,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * If the notrace hash has no items, * then there's nothing to do. */ - if (hash && !hash->count) + if (ftrace_hash_empty(hash)) return; } @@ -1363,8 +1403,8 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (!other_hash || !ftrace_lookup_ip(other_hash, rec->ip)) match = 1; } else { - in_hash = hash && !!ftrace_lookup_ip(hash, rec->ip); - in_other_hash = other_hash && !!ftrace_lookup_ip(other_hash, rec->ip); + in_hash = !!ftrace_lookup_ip(hash, rec->ip); + in_other_hash = !!ftrace_lookup_ip(other_hash, rec->ip); /* * @@ -1372,7 +1412,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (filter_hash && in_hash && !in_other_hash) match = 1; else if (!filter_hash && in_hash && - (in_other_hash || !other_hash->count)) + (in_other_hash || ftrace_hash_empty(other_hash))) match = 1; } if (!match) @@ -1406,40 +1446,12 @@ static void ftrace_hash_rec_enable(struct ftrace_ops *ops, __ftrace_hash_rec_update(ops, filter_hash, 1); } -static void ftrace_free_rec(struct dyn_ftrace *rec) -{ - rec->freelist = ftrace_free_records; - ftrace_free_records = rec; - rec->flags |= FTRACE_FL_FREE; -} - static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) { - struct dyn_ftrace *rec; - - /* First check for freed records */ - if (ftrace_free_records) { - rec = ftrace_free_records; - - if (unlikely(!(rec->flags & FTRACE_FL_FREE))) { - FTRACE_WARN_ON_ONCE(1); - ftrace_free_records = NULL; + if (ftrace_pages->index == ftrace_pages->size) { + /* We should have allocated enough */ + if (WARN_ON(!ftrace_pages->next)) return NULL; - } - - ftrace_free_records = rec->freelist; - memset(rec, 0, sizeof(*rec)); - return rec; - } - - if (ftrace_pages->index == ENTRIES_PER_PAGE) { - if (!ftrace_pages->next) { - /* allocate another page */ - ftrace_pages->next = - (void *)get_zeroed_page(GFP_KERNEL); - if (!ftrace_pages->next) - return NULL; - } ftrace_pages = ftrace_pages->next; } @@ -1459,8 +1471,6 @@ ftrace_record_ip(unsigned long ip) return NULL; rec->ip = ip; - rec->newlist = ftrace_new_addrs; - ftrace_new_addrs = rec; return rec; } @@ -1475,7 +1485,19 @@ static void print_ip_ins(const char *fmt, unsigned char *p) printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); } -static void ftrace_bug(int failed, unsigned long ip) +/** + * ftrace_bug - report and shutdown function tracer + * @failed: The failed type (EFAULT, EINVAL, EPERM) + * @ip: The address that failed + * + * The arch code that enables or disables the function tracing + * can call ftrace_bug() when it has detected a problem in + * modifying the code. @failed should be one of either: + * EFAULT - if the problem happens on reading the @ip address + * EINVAL - if what is read at @ip is not what was expected + * EPERM - if the problem happens on writting to the @ip address + */ +void ftrace_bug(int failed, unsigned long ip) { switch (failed) { case -EFAULT: @@ -1517,24 +1539,19 @@ int ftrace_text_reserved(void *start, void *end) return 0; } - -static int -__ftrace_replace_code(struct dyn_ftrace *rec, int enable) +static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) { - unsigned long ftrace_addr; unsigned long flag = 0UL; - ftrace_addr = (unsigned long)FTRACE_ADDR; - /* - * If we are enabling tracing: + * If we are updating calls: * * If the record has a ref count, then we need to enable it * because someone is using it. * * Otherwise we make sure its disabled. * - * If we are disabling tracing, then disable all records that + * If we are disabling calls, then disable all records that * are enabled. */ if (enable && (rec->flags & ~FTRACE_FL_MASK)) @@ -1542,18 +1559,72 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) - return 0; + return FTRACE_UPDATE_IGNORE; if (flag) { - rec->flags |= FTRACE_FL_ENABLED; + if (update) + rec->flags |= FTRACE_FL_ENABLED; + return FTRACE_UPDATE_MAKE_CALL; + } + + if (update) + rec->flags &= ~FTRACE_FL_ENABLED; + + return FTRACE_UPDATE_MAKE_NOP; +} + +/** + * ftrace_update_record, set a record that now is tracing or not + * @rec: the record to update + * @enable: set to 1 if the record is tracing, zero to force disable + * + * The records that represent all functions that can be traced need + * to be updated when tracing has been enabled. + */ +int ftrace_update_record(struct dyn_ftrace *rec, int enable) +{ + return ftrace_check_record(rec, enable, 1); +} + +/** + * ftrace_test_record, check if the record has been enabled or not + * @rec: the record to test + * @enable: set to 1 to check if enabled, 0 if it is disabled + * + * The arch code may need to test if a record is already set to + * tracing to determine how to modify the function code that it + * represents. + */ +int ftrace_test_record(struct dyn_ftrace *rec, int enable) +{ + return ftrace_check_record(rec, enable, 0); +} + +static int +__ftrace_replace_code(struct dyn_ftrace *rec, int enable) +{ + unsigned long ftrace_addr; + int ret; + + ftrace_addr = (unsigned long)FTRACE_ADDR; + + ret = ftrace_update_record(rec, enable); + + switch (ret) { + case FTRACE_UPDATE_IGNORE: + return 0; + + case FTRACE_UPDATE_MAKE_CALL: return ftrace_make_call(rec, ftrace_addr); + + case FTRACE_UPDATE_MAKE_NOP: + return ftrace_make_nop(NULL, rec, ftrace_addr); } - rec->flags &= ~FTRACE_FL_ENABLED; - return ftrace_make_nop(NULL, rec, ftrace_addr); + return -1; /* unknow ftrace bug */ } -static void ftrace_replace_code(int enable) +static void ftrace_replace_code(int update) { struct dyn_ftrace *rec; struct ftrace_page *pg; @@ -1563,11 +1634,7 @@ static void ftrace_replace_code(int enable) return; do_for_each_ftrace_rec(pg, rec) { - /* Skip over free records */ - if (rec->flags & FTRACE_FL_FREE) - continue; - - failed = __ftrace_replace_code(rec, enable); + failed = __ftrace_replace_code(rec, update); if (failed) { ftrace_bug(failed, rec->ip); /* Stop processing */ @@ -1576,6 +1643,78 @@ static void ftrace_replace_code(int enable) } while_for_each_ftrace_rec(); } +struct ftrace_rec_iter { + struct ftrace_page *pg; + int index; +}; + +/** + * ftrace_rec_iter_start, start up iterating over traced functions + * + * Returns an iterator handle that is used to iterate over all + * the records that represent address locations where functions + * are traced. + * + * May return NULL if no records are available. + */ +struct ftrace_rec_iter *ftrace_rec_iter_start(void) +{ + /* + * We only use a single iterator. + * Protected by the ftrace_lock mutex. + */ + static struct ftrace_rec_iter ftrace_rec_iter; + struct ftrace_rec_iter *iter = &ftrace_rec_iter; + + iter->pg = ftrace_pages_start; + iter->index = 0; + + /* Could have empty pages */ + while (iter->pg && !iter->pg->index) + iter->pg = iter->pg->next; + + if (!iter->pg) + return NULL; + + return iter; +} + +/** + * ftrace_rec_iter_next, get the next record to process. + * @iter: The handle to the iterator. + * + * Returns the next iterator after the given iterator @iter. + */ +struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter) +{ + iter->index++; + + if (iter->index >= iter->pg->index) { + iter->pg = iter->pg->next; + iter->index = 0; + + /* Could have empty pages */ + while (iter->pg && !iter->pg->index) + iter->pg = iter->pg->next; + } + + if (!iter->pg) + return NULL; + + return iter; +} + +/** + * ftrace_rec_iter_record, get the record at the iterator location + * @iter: The current iterator location + * + * Returns the record that the current @iter is at. + */ +struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter) +{ + return &iter->pg->records[iter->index]; +} + static int ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) { @@ -1617,13 +1756,7 @@ static int __ftrace_modify_code(void *data) { int *command = data; - /* - * Do not call function tracer while we update the code. - * We are in stop machine, no worrying about races. - */ - function_trace_stop++; - - if (*command & FTRACE_ENABLE_CALLS) + if (*command & FTRACE_UPDATE_CALLS) ftrace_replace_code(1); else if (*command & FTRACE_DISABLE_CALLS) ftrace_replace_code(0); @@ -1636,21 +1769,33 @@ static int __ftrace_modify_code(void *data) else if (*command & FTRACE_STOP_FUNC_RET) ftrace_disable_ftrace_graph_caller(); -#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - /* - * For archs that call ftrace_test_stop_func(), we must - * wait till after we update all the function callers - * before we update the callback. This keeps different - * ops that record different functions from corrupting - * each other. - */ - __ftrace_trace_function = __ftrace_trace_function_delay; -#endif - function_trace_stop--; - return 0; } +/** + * ftrace_run_stop_machine, go back to the stop machine method + * @command: The command to tell ftrace what to do + * + * If an arch needs to fall back to the stop machine method, the + * it can call this function. + */ +void ftrace_run_stop_machine(int command) +{ + stop_machine(__ftrace_modify_code, &command, NULL); +} + +/** + * arch_ftrace_update_code, modify the code to trace or not trace + * @command: The command that needs to be done + * + * Archs can override this function if it does not need to + * run stop_machine() to modify code. + */ +void __weak arch_ftrace_update_code(int command) +{ + ftrace_run_stop_machine(command); +} + static void ftrace_run_update_code(int command) { int ret; @@ -1659,8 +1804,31 @@ static void ftrace_run_update_code(int command) FTRACE_WARN_ON(ret); if (ret) return; + /* + * Do not call function tracer while we update the code. + * We are in stop machine. + */ + function_trace_stop++; - stop_machine(__ftrace_modify_code, &command, NULL); + /* + * By default we use stop_machine() to modify the code. + * But archs can do what ever they want as long as it + * is safe. The stop_machine() is the safest, but also + * produces the most overhead. + */ + arch_ftrace_update_code(command); + +#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST + /* + * For archs that call ftrace_test_stop_func(), we must + * wait till after we update all the function callers + * before we update the callback. This keeps different + * ops that record different functions from corrupting + * each other. + */ + __ftrace_trace_function = __ftrace_trace_function_delay; +#endif + function_trace_stop--; ret = ftrace_arch_code_modify_post_process(); FTRACE_WARN_ON(ret); @@ -1691,7 +1859,7 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) return -ENODEV; ftrace_start_up++; - command |= FTRACE_ENABLE_CALLS; + command |= FTRACE_UPDATE_CALLS; /* ops marked global share the filter hashes */ if (ops->flags & FTRACE_OPS_FL_GLOBAL) { @@ -1743,8 +1911,7 @@ static void ftrace_shutdown(struct ftrace_ops *ops, int command) if (ops != &global_ops || !global_start_up) ops->flags &= ~FTRACE_OPS_FL_ENABLED; - if (!ftrace_start_up) - command |= FTRACE_DISABLE_CALLS; + command |= FTRACE_UPDATE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; @@ -1766,7 +1933,7 @@ static void ftrace_startup_sysctl(void) saved_ftrace_func = NULL; /* ftrace_start_up is true if we want ftrace running */ if (ftrace_start_up) - ftrace_run_update_code(FTRACE_ENABLE_CALLS); + ftrace_run_update_code(FTRACE_UPDATE_CALLS); } static void ftrace_shutdown_sysctl(void) @@ -1788,14 +1955,16 @@ static int ops_traces_mod(struct ftrace_ops *ops) struct ftrace_hash *hash; hash = ops->filter_hash; - return !!(!hash || !hash->count); + return ftrace_hash_empty(hash); } static int ftrace_update_code(struct module *mod) { + struct ftrace_page *pg; struct dyn_ftrace *p; cycle_t start, stop; unsigned long ref = 0; + int i; /* * When adding a module, we need to check if tracers are @@ -1817,46 +1986,44 @@ static int ftrace_update_code(struct module *mod) start = ftrace_now(raw_smp_processor_id()); ftrace_update_cnt = 0; - while (ftrace_new_addrs) { + for (pg = ftrace_new_pgs; pg; pg = pg->next) { - /* If something went wrong, bail without enabling anything */ - if (unlikely(ftrace_disabled)) - return -1; + for (i = 0; i < pg->index; i++) { + /* If something went wrong, bail without enabling anything */ + if (unlikely(ftrace_disabled)) + return -1; - p = ftrace_new_addrs; - ftrace_new_addrs = p->newlist; - p->flags = ref; + p = &pg->records[i]; + p->flags = ref; - /* - * Do the initial record conversion from mcount jump - * to the NOP instructions. - */ - if (!ftrace_code_disable(mod, p)) { - ftrace_free_rec(p); - /* Game over */ - break; - } + /* + * Do the initial record conversion from mcount jump + * to the NOP instructions. + */ + if (!ftrace_code_disable(mod, p)) + break; - ftrace_update_cnt++; + ftrace_update_cnt++; - /* - * If the tracing is enabled, go ahead and enable the record. - * - * The reason not to enable the record immediatelly is the - * inherent check of ftrace_make_nop/ftrace_make_call for - * correct previous instructions. Making first the NOP - * conversion puts the module to the correct state, thus - * passing the ftrace_make_call check. - */ - if (ftrace_start_up && ref) { - int failed = __ftrace_replace_code(p, 1); - if (failed) { - ftrace_bug(failed, p->ip); - ftrace_free_rec(p); + /* + * If the tracing is enabled, go ahead and enable the record. + * + * The reason not to enable the record immediatelly is the + * inherent check of ftrace_make_nop/ftrace_make_call for + * correct previous instructions. Making first the NOP + * conversion puts the module to the correct state, thus + * passing the ftrace_make_call check. + */ + if (ftrace_start_up && ref) { + int failed = __ftrace_replace_code(p, 1); + if (failed) + ftrace_bug(failed, p->ip); } } } + ftrace_new_pgs = NULL; + stop = ftrace_now(raw_smp_processor_id()); ftrace_update_time = stop - start; ftrace_update_tot_cnt += ftrace_update_cnt; @@ -1864,57 +2031,108 @@ static int ftrace_update_code(struct module *mod) return 0; } -static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) +static int ftrace_allocate_records(struct ftrace_page *pg, int count) { - struct ftrace_page *pg; + int order; int cnt; - int i; - /* allocate a few pages */ - ftrace_pages_start = (void *)get_zeroed_page(GFP_KERNEL); - if (!ftrace_pages_start) - return -1; + if (WARN_ON(!count)) + return -EINVAL; + + order = get_count_order(DIV_ROUND_UP(count, ENTRIES_PER_PAGE)); /* - * Allocate a few more pages. - * - * TODO: have some parser search vmlinux before - * final linking to find all calls to ftrace. - * Then we can: - * a) know how many pages to allocate. - * and/or - * b) set up the table then. - * - * The dynamic code is still necessary for - * modules. + * We want to fill as much as possible. No more than a page + * may be empty. */ + while ((PAGE_SIZE << order) / ENTRY_SIZE >= count + ENTRIES_PER_PAGE) + order--; - pg = ftrace_pages = ftrace_pages_start; + again: + pg->records = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order); - cnt = num_to_init / ENTRIES_PER_PAGE; - pr_info("ftrace: allocating %ld entries in %d pages\n", - num_to_init, cnt + 1); + if (!pg->records) { + /* if we can't allocate this size, try something smaller */ + if (!order) + return -ENOMEM; + order >>= 1; + goto again; + } - for (i = 0; i < cnt; i++) { - pg->next = (void *)get_zeroed_page(GFP_KERNEL); + cnt = (PAGE_SIZE << order) / ENTRY_SIZE; + pg->size = cnt; - /* If we fail, we'll try later anyway */ - if (!pg->next) + if (cnt > count) + cnt = count; + + return cnt; +} + +static struct ftrace_page * +ftrace_allocate_pages(unsigned long num_to_init) +{ + struct ftrace_page *start_pg; + struct ftrace_page *pg; + int order; + int cnt; + + if (!num_to_init) + return 0; + + start_pg = pg = kzalloc(sizeof(*pg), GFP_KERNEL); + if (!pg) + return NULL; + + /* + * Try to allocate as much as possible in one continues + * location that fills in all of the space. We want to + * waste as little space as possible. + */ + for (;;) { + cnt = ftrace_allocate_records(pg, num_to_init); + if (cnt < 0) + goto free_pages; + + num_to_init -= cnt; + if (!num_to_init) break; + pg->next = kzalloc(sizeof(*pg), GFP_KERNEL); + if (!pg->next) + goto free_pages; + pg = pg->next; } - return 0; + return start_pg; + + free_pages: + while (start_pg) { + order = get_count_order(pg->size / ENTRIES_PER_PAGE); + free_pages((unsigned long)pg->records, order); + start_pg = pg->next; + kfree(pg); + pg = start_pg; + } + pr_info("ftrace: FAILED to allocate memory for functions\n"); + return NULL; } -enum { - FTRACE_ITER_FILTER = (1 << 0), - FTRACE_ITER_NOTRACE = (1 << 1), - FTRACE_ITER_PRINTALL = (1 << 2), - FTRACE_ITER_HASH = (1 << 3), - FTRACE_ITER_ENABLED = (1 << 4), -}; +static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) +{ + int cnt; + + if (!num_to_init) { + pr_info("ftrace: No functions to be traced?\n"); + return -1; + } + + cnt = num_to_init / ENTRIES_PER_PAGE; + pr_info("ftrace: allocating %ld entries in %d pages\n", + num_to_init, cnt + 1); + + return 0; +} #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ @@ -1980,6 +2198,9 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos) void *p = NULL; loff_t l; + if (!(iter->flags & FTRACE_ITER_DO_HASH)) + return NULL; + if (iter->func_pos > *pos) return NULL; @@ -2023,7 +2244,7 @@ static void * t_next(struct seq_file *m, void *v, loff_t *pos) { struct ftrace_iterator *iter = m->private; - struct ftrace_ops *ops = &global_ops; + struct ftrace_ops *ops = iter->ops; struct dyn_ftrace *rec = NULL; if (unlikely(ftrace_disabled)) @@ -2047,9 +2268,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) } } else { rec = &iter->pg->records[iter->idx++]; - if ((rec->flags & FTRACE_FL_FREE) || - - ((iter->flags & FTRACE_ITER_FILTER) && + if (((iter->flags & FTRACE_ITER_FILTER) && !(ftrace_lookup_ip(ops->filter_hash, rec->ip))) || ((iter->flags & FTRACE_ITER_NOTRACE) && @@ -2081,7 +2300,7 @@ static void reset_iter_read(struct ftrace_iterator *iter) static void *t_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; - struct ftrace_ops *ops = &global_ops; + struct ftrace_ops *ops = iter->ops; void *p = NULL; loff_t l; @@ -2101,7 +2320,8 @@ static void *t_start(struct seq_file *m, loff_t *pos) * off, we can short cut and just print out that all * functions are enabled. */ - if (iter->flags & FTRACE_ITER_FILTER && !ops->filter_hash->count) { + if (iter->flags & FTRACE_ITER_FILTER && + ftrace_hash_empty(ops->filter_hash)) { if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; @@ -2126,12 +2346,8 @@ static void *t_start(struct seq_file *m, loff_t *pos) break; } - if (!p) { - if (iter->flags & FTRACE_ITER_FILTER) - return t_hash_start(m, pos); - - return NULL; - } + if (!p) + return t_hash_start(m, pos); return iter; } @@ -2189,6 +2405,7 @@ ftrace_avail_open(struct inode *inode, struct file *file) return -ENOMEM; iter->pg = ftrace_pages_start; + iter->ops = &global_ops; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -2217,6 +2434,7 @@ ftrace_enabled_open(struct inode *inode, struct file *file) iter->pg = ftrace_pages_start; iter->flags = FTRACE_ITER_ENABLED; + iter->ops = &global_ops; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -2237,7 +2455,23 @@ static void ftrace_filter_reset(struct ftrace_hash *hash) mutex_unlock(&ftrace_lock); } -static int +/** + * ftrace_regex_open - initialize function tracer filter files + * @ops: The ftrace_ops that hold the hash filters + * @flag: The type of filter to process + * @inode: The inode, usually passed in to your open routine + * @file: The file, usually passed in to your open routine + * + * ftrace_regex_open() initializes the filter files for the + * @ops. Depending on @flag it may process the filter hash or + * the notrace hash of @ops. With this called from the open + * routine, you can use ftrace_filter_write() for the write + * routine if @flag has FTRACE_ITER_FILTER set, or + * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set. + * ftrace_regex_lseek() should be used as the lseek routine, and + * release must call ftrace_regex_release(). + */ +int ftrace_regex_open(struct ftrace_ops *ops, int flag, struct inode *inode, struct file *file) { @@ -2306,8 +2540,9 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, static int ftrace_filter_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(&global_ops, FTRACE_ITER_FILTER, - inode, file); + return ftrace_regex_open(&global_ops, + FTRACE_ITER_FILTER | FTRACE_ITER_DO_HASH, + inode, file); } static int @@ -2317,7 +2552,7 @@ ftrace_notrace_open(struct inode *inode, struct file *file) inode, file); } -static loff_t +loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int origin) { loff_t ret; @@ -2426,7 +2661,6 @@ match_records(struct ftrace_hash *hash, char *buff, goto out_unlock; do_for_each_ftrace_rec(pg, rec) { - if (ftrace_match_record(rec, mod, search, search_len, type)) { ret = enter_record(hash, rec, not); if (ret < 0) { @@ -2871,14 +3105,14 @@ out_unlock: return ret; } -static ssize_t +ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { return ftrace_regex_write(file, ubuf, cnt, ppos, 1); } -static ssize_t +ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { @@ -2919,7 +3153,7 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, ret = ftrace_hash_move(ops, enable, orig_hash, hash); if (!ret && ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled) - ftrace_run_update_code(FTRACE_ENABLE_CALLS); + ftrace_run_update_code(FTRACE_UPDATE_CALLS); mutex_unlock(&ftrace_lock); @@ -3045,8 +3279,8 @@ static void __init set_ftrace_early_graph(char *buf) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -static void __init -set_ftrace_early_filter(struct ftrace_ops *ops, char *buf, int enable) +void __init +ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable) { char *func; @@ -3059,17 +3293,16 @@ set_ftrace_early_filter(struct ftrace_ops *ops, char *buf, int enable) static void __init set_ftrace_early_filters(void) { if (ftrace_filter_buf[0]) - set_ftrace_early_filter(&global_ops, ftrace_filter_buf, 1); + ftrace_set_early_filter(&global_ops, ftrace_filter_buf, 1); if (ftrace_notrace_buf[0]) - set_ftrace_early_filter(&global_ops, ftrace_notrace_buf, 0); + ftrace_set_early_filter(&global_ops, ftrace_notrace_buf, 0); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (ftrace_graph_buf[0]) set_ftrace_early_graph(ftrace_graph_buf); #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ } -static int -ftrace_regex_release(struct inode *inode, struct file *file) +int ftrace_regex_release(struct inode *inode, struct file *file) { struct seq_file *m = (struct seq_file *)file->private_data; struct ftrace_iterator *iter; @@ -3107,7 +3340,7 @@ ftrace_regex_release(struct inode *inode, struct file *file) orig_hash, iter->hash); if (!ret && (iter->ops->flags & FTRACE_OPS_FL_ENABLED) && ftrace_enabled) - ftrace_run_update_code(FTRACE_ENABLE_CALLS); + ftrace_run_update_code(FTRACE_UPDATE_CALLS); mutex_unlock(&ftrace_lock); } @@ -3270,9 +3503,6 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FREE) - continue; - if (ftrace_match_record(rec, NULL, search, search_len, type)) { /* if it is in the array */ exists = false; @@ -3381,15 +3611,62 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) return 0; } +static void ftrace_swap_recs(void *a, void *b, int size) +{ + struct dyn_ftrace *reca = a; + struct dyn_ftrace *recb = b; + struct dyn_ftrace t; + + t = *reca; + *reca = *recb; + *recb = t; +} + static int ftrace_process_locs(struct module *mod, unsigned long *start, unsigned long *end) { + struct ftrace_page *pg; + unsigned long count; unsigned long *p; unsigned long addr; unsigned long flags = 0; /* Shut up gcc */ + int ret = -ENOMEM; + + count = end - start; + + if (!count) + return 0; + + pg = ftrace_allocate_pages(count); + if (!pg) + return -ENOMEM; mutex_lock(&ftrace_lock); + + /* + * Core and each module needs their own pages, as + * modules will free them when they are removed. + * Force a new page to be allocated for modules. + */ + if (!mod) { + WARN_ON(ftrace_pages || ftrace_pages_start); + /* First initialization */ + ftrace_pages = ftrace_pages_start = pg; + } else { + if (!ftrace_pages) + goto out; + + if (WARN_ON(ftrace_pages->next)) { + /* Hmm, we have free pages? */ + while (ftrace_pages->next) + ftrace_pages = ftrace_pages->next; + } + + ftrace_pages->next = pg; + ftrace_pages = pg; + } + p = start; while (p < end) { addr = ftrace_call_adjust(*p++); @@ -3401,9 +3678,18 @@ static int ftrace_process_locs(struct module *mod, */ if (!addr) continue; - ftrace_record_ip(addr); + if (!ftrace_record_ip(addr)) + break; } + /* These new locations need to be initialized */ + ftrace_new_pgs = pg; + + /* Make each individual set of pages sorted by ips */ + for (; pg; pg = pg->next) + sort(pg->records, pg->index, sizeof(struct dyn_ftrace), + ftrace_cmp_recs, ftrace_swap_recs); + /* * We only need to disable interrupts on start up * because we are modifying code that an interrupt @@ -3417,32 +3703,55 @@ static int ftrace_process_locs(struct module *mod, ftrace_update_code(mod); if (!mod) local_irq_restore(flags); + ret = 0; + out: mutex_unlock(&ftrace_lock); - return 0; + return ret; } #ifdef CONFIG_MODULES + +#define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next) + void ftrace_release_mod(struct module *mod) { struct dyn_ftrace *rec; + struct ftrace_page **last_pg; struct ftrace_page *pg; + int order; mutex_lock(&ftrace_lock); if (ftrace_disabled) goto out_unlock; - do_for_each_ftrace_rec(pg, rec) { + /* + * Each module has its own ftrace_pages, remove + * them from the list. + */ + last_pg = &ftrace_pages_start; + for (pg = ftrace_pages_start; pg; pg = *last_pg) { + rec = &pg->records[0]; if (within_module_core(rec->ip, mod)) { /* - * rec->ip is changed in ftrace_free_rec() - * It should not between s and e if record was freed. + * As core pages are first, the first + * page should never be a module page. */ - FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE); - ftrace_free_rec(rec); - } - } while_for_each_ftrace_rec(); + if (WARN_ON(pg == ftrace_pages_start)) + goto out_unlock; + + /* Check if we are deleting the last page */ + if (pg == ftrace_pages) + ftrace_pages = next_to_ftrace_page(last_pg); + + *last_pg = pg->next; + order = get_count_order(pg->size / ENTRIES_PER_PAGE); + free_pages((unsigned long)pg->records, order); + kfree(pg); + } else + last_pg = &pg->next; + } out_unlock: mutex_unlock(&ftrace_lock); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 91dc4bc8bf72..a3f1bc5d2a00 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4438,7 +4438,7 @@ static const struct file_operations trace_options_core_fops = { }; struct dentry *trace_create_file(const char *name, - mode_t mode, + umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2c2657462ac3..b93ecbadad6d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -312,7 +312,7 @@ void tracing_reset_current(int cpu); void tracing_reset_current_online_cpus(void); int tracing_open_generic(struct inode *inode, struct file *filp); struct dentry *trace_create_file(const char *name, - mode_t mode, + umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index f04cc3136bd3..24aee7127451 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1738,11 +1738,121 @@ static int replace_system_preds(struct event_subsystem *system, return -ENOMEM; } +static int create_filter_start(char *filter_str, bool set_str, + struct filter_parse_state **psp, + struct event_filter **filterp) +{ + struct event_filter *filter; + struct filter_parse_state *ps = NULL; + int err = 0; + + WARN_ON_ONCE(*psp || *filterp); + + /* allocate everything, and if any fails, free all and fail */ + filter = __alloc_filter(); + if (filter && set_str) + err = replace_filter_string(filter, filter_str); + + ps = kzalloc(sizeof(*ps), GFP_KERNEL); + + if (!filter || !ps || err) { + kfree(ps); + __free_filter(filter); + return -ENOMEM; + } + + /* we're committed to creating a new filter */ + *filterp = filter; + *psp = ps; + + parse_init(ps, filter_ops, filter_str); + err = filter_parse(ps); + if (err && set_str) + append_filter_err(ps, filter); + return err; +} + +static void create_filter_finish(struct filter_parse_state *ps) +{ + if (ps) { + filter_opstack_clear(ps); + postfix_clear(ps); + kfree(ps); + } +} + +/** + * create_filter - create a filter for a ftrace_event_call + * @call: ftrace_event_call to create a filter for + * @filter_str: filter string + * @set_str: remember @filter_str and enable detailed error in filter + * @filterp: out param for created filter (always updated on return) + * + * Creates a filter for @call with @filter_str. If @set_str is %true, + * @filter_str is copied and recorded in the new filter. + * + * On success, returns 0 and *@filterp points to the new filter. On + * failure, returns -errno and *@filterp may point to %NULL or to a new + * filter. In the latter case, the returned filter contains error + * information if @set_str is %true and the caller is responsible for + * freeing it. + */ +static int create_filter(struct ftrace_event_call *call, + char *filter_str, bool set_str, + struct event_filter **filterp) +{ + struct event_filter *filter = NULL; + struct filter_parse_state *ps = NULL; + int err; + + err = create_filter_start(filter_str, set_str, &ps, &filter); + if (!err) { + err = replace_preds(call, filter, ps, filter_str, false); + if (err && set_str) + append_filter_err(ps, filter); + } + create_filter_finish(ps); + + *filterp = filter; + return err; +} + +/** + * create_system_filter - create a filter for an event_subsystem + * @system: event_subsystem to create a filter for + * @filter_str: filter string + * @filterp: out param for created filter (always updated on return) + * + * Identical to create_filter() except that it creates a subsystem filter + * and always remembers @filter_str. + */ +static int create_system_filter(struct event_subsystem *system, + char *filter_str, struct event_filter **filterp) +{ + struct event_filter *filter = NULL; + struct filter_parse_state *ps = NULL; + int err; + + err = create_filter_start(filter_str, true, &ps, &filter); + if (!err) { + err = replace_system_preds(system, ps, filter_str); + if (!err) { + /* System filters just show a default message */ + kfree(filter->filter_string); + filter->filter_string = NULL; + } else { + append_filter_err(ps, filter); + } + } + create_filter_finish(ps); + + *filterp = filter; + return err; +} + int apply_event_filter(struct ftrace_event_call *call, char *filter_string) { - struct filter_parse_state *ps; struct event_filter *filter; - struct event_filter *tmp; int err = 0; mutex_lock(&event_mutex); @@ -1759,49 +1869,30 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) goto out_unlock; } - err = -ENOMEM; - ps = kzalloc(sizeof(*ps), GFP_KERNEL); - if (!ps) - goto out_unlock; - - filter = __alloc_filter(); - if (!filter) { - kfree(ps); - goto out_unlock; - } - - replace_filter_string(filter, filter_string); - - parse_init(ps, filter_ops, filter_string); - err = filter_parse(ps); - if (err) { - append_filter_err(ps, filter); - goto out; - } + err = create_filter(call, filter_string, true, &filter); - err = replace_preds(call, filter, ps, filter_string, false); - if (err) { - filter_disable(call); - append_filter_err(ps, filter); - } else - call->flags |= TRACE_EVENT_FL_FILTERED; -out: /* * Always swap the call filter with the new filter * even if there was an error. If there was an error * in the filter, we disable the filter and show the error * string */ - tmp = call->filter; - rcu_assign_pointer(call->filter, filter); - if (tmp) { - /* Make sure the call is done with the filter */ - synchronize_sched(); - __free_filter(tmp); + if (filter) { + struct event_filter *tmp = call->filter; + + if (!err) + call->flags |= TRACE_EVENT_FL_FILTERED; + else + filter_disable(call); + + rcu_assign_pointer(call->filter, filter); + + if (tmp) { + /* Make sure the call is done with the filter */ + synchronize_sched(); + __free_filter(tmp); + } } - filter_opstack_clear(ps); - postfix_clear(ps); - kfree(ps); out_unlock: mutex_unlock(&event_mutex); @@ -1811,7 +1902,6 @@ out_unlock: int apply_subsystem_event_filter(struct event_subsystem *system, char *filter_string) { - struct filter_parse_state *ps; struct event_filter *filter; int err = 0; @@ -1835,48 +1925,19 @@ int apply_subsystem_event_filter(struct event_subsystem *system, goto out_unlock; } - err = -ENOMEM; - ps = kzalloc(sizeof(*ps), GFP_KERNEL); - if (!ps) - goto out_unlock; - - filter = __alloc_filter(); - if (!filter) - goto out; - - /* System filters just show a default message */ - kfree(filter->filter_string); - filter->filter_string = NULL; - - /* - * No event actually uses the system filter - * we can free it without synchronize_sched(). - */ - __free_filter(system->filter); - system->filter = filter; - - parse_init(ps, filter_ops, filter_string); - err = filter_parse(ps); - if (err) - goto err_filter; - - err = replace_system_preds(system, ps, filter_string); - if (err) - goto err_filter; - -out: - filter_opstack_clear(ps); - postfix_clear(ps); - kfree(ps); + err = create_system_filter(system, filter_string, &filter); + if (filter) { + /* + * No event actually uses the system filter + * we can free it without synchronize_sched(). + */ + __free_filter(system->filter); + system->filter = filter; + } out_unlock: mutex_unlock(&event_mutex); return err; - -err_filter: - replace_filter_string(filter, filter_string); - append_filter_err(ps, system->filter); - goto out; } #ifdef CONFIG_PERF_EVENTS @@ -1894,7 +1955,6 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, { int err; struct event_filter *filter; - struct filter_parse_state *ps; struct ftrace_event_call *call; mutex_lock(&event_mutex); @@ -1909,33 +1969,10 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, if (event->filter) goto out_unlock; - filter = __alloc_filter(); - if (!filter) { - err = PTR_ERR(filter); - goto out_unlock; - } - - err = -ENOMEM; - ps = kzalloc(sizeof(*ps), GFP_KERNEL); - if (!ps) - goto free_filter; - - parse_init(ps, filter_ops, filter_str); - err = filter_parse(ps); - if (err) - goto free_ps; - - err = replace_preds(call, filter, ps, filter_str, false); + err = create_filter(call, filter_str, false, &filter); if (!err) event->filter = filter; - -free_ps: - filter_opstack_clear(ps); - postfix_clear(ps); - kfree(ps); - -free_filter: - if (err) + else __free_filter(filter); out_unlock: @@ -1954,43 +1991,6 @@ out_unlock: #define CREATE_TRACE_POINTS #include "trace_events_filter_test.h" -static int test_get_filter(char *filter_str, struct ftrace_event_call *call, - struct event_filter **pfilter) -{ - struct event_filter *filter; - struct filter_parse_state *ps; - int err = -ENOMEM; - - filter = __alloc_filter(); - if (!filter) - goto out; - - ps = kzalloc(sizeof(*ps), GFP_KERNEL); - if (!ps) - goto free_filter; - - parse_init(ps, filter_ops, filter_str); - err = filter_parse(ps); - if (err) - goto free_ps; - - err = replace_preds(call, filter, ps, filter_str, false); - if (!err) - *pfilter = filter; - - free_ps: - filter_opstack_clear(ps); - postfix_clear(ps); - kfree(ps); - - free_filter: - if (err) - __free_filter(filter); - - out: - return err; -} - #define DATA_REC(m, va, vb, vc, vd, ve, vf, vg, vh, nvisit) \ { \ .filter = FILTER, \ @@ -2109,12 +2109,13 @@ static __init int ftrace_test_event_filter(void) struct test_filter_data_t *d = &test_filter_data[i]; int err; - err = test_get_filter(d->filter, &event_ftrace_test_filter, - &filter); + err = create_filter(&event_ftrace_test_filter, d->filter, + false, &filter); if (err) { printk(KERN_INFO "Failed to get filter for '%s', err %d\n", d->filter, err); + __free_filter(filter); break; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 77575b386d97..d4545f49242e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -13,6 +13,9 @@ #include <linux/sysctl.h> #include <linux/init.h> #include <linux/fs.h> + +#include <asm/setup.h> + #include "trace.h" #define STACK_TRACE_ENTRIES 500 @@ -133,7 +136,6 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = stack_trace_call, - .flags = FTRACE_OPS_FL_GLOBAL, }; static ssize_t @@ -311,6 +313,21 @@ static const struct file_operations stack_trace_fops = { .release = seq_release, }; +static int +stack_trace_filter_open(struct inode *inode, struct file *file) +{ + return ftrace_regex_open(&trace_ops, FTRACE_ITER_FILTER, + inode, file); +} + +static const struct file_operations stack_trace_filter_fops = { + .open = stack_trace_filter_open, + .read = seq_read, + .write = ftrace_filter_write, + .llseek = ftrace_regex_lseek, + .release = ftrace_regex_release, +}; + int stack_trace_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -338,8 +355,13 @@ stack_trace_sysctl(struct ctl_table *table, int write, return ret; } +static char stack_trace_filter_buf[COMMAND_LINE_SIZE+1] __initdata; + static __init int enable_stacktrace(char *str) { + if (strncmp(str, "_filter=", 8) == 0) + strncpy(stack_trace_filter_buf, str+8, COMMAND_LINE_SIZE); + stack_tracer_enabled = 1; last_stack_tracer_enabled = 1; return 1; @@ -358,6 +380,12 @@ static __init int stack_trace_init(void) trace_create_file("stack_trace", 0444, d_tracer, NULL, &stack_trace_fops); + trace_create_file("stack_trace_filter", 0444, d_tracer, + NULL, &stack_trace_filter_fops); + + if (stack_trace_filter_buf[0]) + ftrace_set_early_filter(&trace_ops, stack_trace_filter_buf, 1); + if (stack_tracer_enabled) register_ftrace_function(&trace_ops); diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index db110b8ae030..f1539decd99d 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -634,10 +634,11 @@ static int tracepoint_module_coming(struct module *mod) int ret = 0; /* - * We skip modules that tain the kernel, especially those with different - * module header (for forced load), to make sure we don't cause a crash. + * We skip modules that taint the kernel, especially those with different + * module headers (for forced load), to make sure we don't cause a crash. + * Staging and out-of-tree GPL modules are fine. */ - if (mod->taints) + if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP))) return 0; mutex_lock(&tracepoints_mutex); tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 42fa9ad0a810..bec7b5b53e03 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -242,10 +242,10 @@ struct workqueue_struct { int nr_drainers; /* W: drain in progress */ int saved_max_active; /* W: saved cwq max_active */ - const char *name; /* I: workqueue name */ #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif + char name[]; /* I: workqueue name */ }; struct workqueue_struct *system_wq __read_mostly; @@ -2954,14 +2954,29 @@ static int wq_clamp_max_active(int max_active, unsigned int flags, return clamp_val(max_active, 1, lim); } -struct workqueue_struct *__alloc_workqueue_key(const char *name, +struct workqueue_struct *__alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, struct lock_class_key *key, - const char *lock_name) + const char *lock_name, ...) { + va_list args, args1; struct workqueue_struct *wq; unsigned int cpu; + size_t namelen; + + /* determine namelen, allocate wq and format name */ + va_start(args, lock_name); + va_copy(args1, args); + namelen = vsnprintf(NULL, 0, fmt, args) + 1; + + wq = kzalloc(sizeof(*wq) + namelen, GFP_KERNEL); + if (!wq) + goto err; + + vsnprintf(wq->name, namelen, fmt, args1); + va_end(args); + va_end(args1); /* * Workqueues which may be used during memory reclaim should @@ -2978,12 +2993,9 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, flags |= WQ_HIGHPRI; max_active = max_active ?: WQ_DFL_ACTIVE; - max_active = wq_clamp_max_active(max_active, flags, name); - - wq = kzalloc(sizeof(*wq), GFP_KERNEL); - if (!wq) - goto err; + max_active = wq_clamp_max_active(max_active, flags, wq->name); + /* init wq */ wq->flags = flags; wq->saved_max_active = max_active; mutex_init(&wq->flush_mutex); @@ -2991,7 +3003,6 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); - wq->name = name; lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); INIT_LIST_HEAD(&wq->list); @@ -3020,7 +3031,8 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, if (!rescuer) goto err; - rescuer->task = kthread_create(rescuer_thread, wq, "%s", name); + rescuer->task = kthread_create(rescuer_thread, wq, "%s", + wq->name); if (IS_ERR(rescuer->task)) goto err; |