diff options
Diffstat (limited to 'kernel')
39 files changed, 1731 insertions, 859 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index f70396e..2d9de86 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/async.c b/kernel/async.c index 80b74b88..bd0c168 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 2c1d6ab..bb0eb5b 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); @@ -1423,7 +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 91e7071..8167668 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 f8277c8..a6c3f1a 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 e7fe2b0..af1de0f 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 */ @@ -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; - umode_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; @@ -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=%#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); - } + 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; @@ -1658,45 +1861,29 @@ 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 + * @success: success value of the syscall + * @return_code: return value of the syscall * * Tear down after system call. If the audit context has been marked as * auditable (either because of the AUDIT_RECORD_CONTEXT state from - * filtering, or because some other part of the kernel write an audit + * filtering, or because some other part of the kernel wrote an audit * 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 +2008,30 @@ 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 +2042,7 @@ 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 +2052,15 @@ 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 +2082,13 @@ 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 +2109,11 @@ 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 +2153,25 @@ 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 +2190,11 @@ 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 +2204,7 @@ 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 +2217,7 @@ 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 +2235,29 @@ 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 +2291,28 @@ 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; @@ -2271,14 +2450,11 @@ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mo 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 +2475,10 @@ 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 +2504,10 @@ 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 +2669,25 @@ 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 +2698,6 @@ 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 +2706,17 @@ 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 b463871..3f1adb6 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/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 63786e7..e2ae734 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/callchain.c b/kernel/events/callchain.c index 057e24b..6581a04 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -115,8 +115,6 @@ int get_callchain_buffers(void) } err = alloc_callchain_buffers(); - if (err) - release_callchain_buffers(); exit: mutex_unlock(&callchain_mutex); diff --git a/kernel/events/core.c b/kernel/events/core.c index a8f4ac0..32b48c8 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -815,7 +815,7 @@ static void update_event_times(struct perf_event *event) * here. */ if (is_cgroup_event(event)) - run_end = perf_event_time(event); + run_end = perf_cgroup_event_time(event); else if (ctx->is_active) run_end = ctx->time; else diff --git a/kernel/exit.c b/kernel/exit.c index d9eab2e..294b170 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> @@ -886,7 +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; @@ -963,8 +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); @@ -1035,6 +1035,8 @@ 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; @@ -1048,7 +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); @@ -1067,7 +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 b00711c..051f090 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; @@ -1291,6 +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. @@ -1370,6 +1376,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (clone_flags & CLONE_THREAD) threadgroup_change_end(current); perf_event_fork(p); + + trace_task_newtask(p, clone_flags); + return p; bad_fork_free_pid: @@ -1518,8 +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/irq/internals.h b/kernel/irq/internals.h index a73dd6c..b795231 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/spurious.c b/kernel/irq/spurious.c index dc813a9..611cd60 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/kexec.c b/kernel/kexec.c index 090ee10..7b08867 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: diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e5d8464..29f5b65 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1077,6 +1077,7 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) /* Early boot. kretprobe_table_locks not yet initialized. */ return; + INIT_HLIST_HEAD(&empty_rp); hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; kretprobe_table_lock(hash, &flags); @@ -1085,7 +1086,6 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) recycle_rp_inst(ri, &empty_rp); } kretprobe_table_unlock(hash, &flags); - INIT_HLIST_HEAD(&empty_rp); hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); @@ -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/module.c b/kernel/module.c index 178333c..2c93276 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 3458469..80aed44 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 65aae11e..32ee043 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 fa5f722..ce8e00d 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 e9c9adc..a896839 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/snapshot.c b/kernel/power/snapshot.c index cbe2c14..6a768e5 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -812,7 +812,8 @@ unsigned int snapshot_additional_pages(struct zone *zone) unsigned int res; res = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK); - res += DIV_ROUND_UP(res * sizeof(struct bm_block), PAGE_SIZE); + res += DIV_ROUND_UP(res * sizeof(struct bm_block), + LINKED_PAGE_DATA_SIZE); return 2 * res; } @@ -858,6 +859,9 @@ 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 +924,9 @@ 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/swap.c b/kernel/power/swap.c index 3739ecc..8742fd0 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -773,8 +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; } @@ -802,10 +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/printk.c b/kernel/printk.c index 989e4a5..13c0a11 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 78ab24a..00ab2ca 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/rcutorture.c b/kernel/rcutorture.c index 88f17b8..a58ac28 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -56,8 +56,8 @@ static int nreaders = -1; /* # reader threads, defaults to 2*ncpus */ static int nfakewriters = 4; /* # fake writer threads */ static int stat_interval; /* Interval between stats, in seconds. */ /* Defaults to "only at end of test". */ -static int verbose; /* Print more debug info. */ -static int test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ +static bool verbose; /* Print more debug info. */ +static bool test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/ static int stutter = 5; /* Start/stop testing interval (in sec) */ static int irqreader = 1; /* RCU readers from irq (timers). */ @@ -1399,7 +1399,7 @@ rcu_torture_shutdown(void *arg) * Execute random CPU-hotplug operations at the interval specified * by the onoff_interval. */ -static int +static int __cpuinit rcu_torture_onoff(void *arg) { int cpu; @@ -1447,7 +1447,7 @@ rcu_torture_onoff(void *arg) return 0; } -static int +static int __cpuinit rcu_torture_onoff_init(void) { if (onoff_interval <= 0) diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 6d269cc..d508363 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -66,6 +66,31 @@ done: return ret; } +int res_counter_charge_nofail(struct res_counter *counter, unsigned long val, + struct res_counter **limit_fail_at) +{ + int ret, r; + unsigned long flags; + struct res_counter *c; + + r = ret = 0; + *limit_fail_at = NULL; + local_irq_save(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + r = res_counter_charge_locked(c, val); + if (r) + c->usage += val; + spin_unlock(&c->lock); + if (r < 0 && ret == 0) { + *limit_fail_at = c; + ret = r; + } + } + local_irq_restore(flags); + + return ret; +} void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) { if (WARN_ON(counter->usage < val)) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index cecbb64be..df00cb0 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); @@ -7134,10 +7134,6 @@ void set_curr_task(int cpu, struct task_struct *p) #endif -#ifdef CONFIG_RT_GROUP_SCHED -#else /* !CONFIG_RT_GROUP_SCHED */ -#endif /* CONFIG_RT_GROUP_SCHED */ - #ifdef CONFIG_CGROUP_SCHED /* task_group_lock serializes the addition/removal of task groups */ static DEFINE_SPINLOCK(task_group_lock); @@ -7246,9 +7242,6 @@ void sched_move_task(struct task_struct *tsk) } #endif /* CONFIG_CGROUP_SCHED */ -#ifdef CONFIG_FAIR_GROUP_SCHED -#endif - #if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH) static unsigned long to_ratio(u64 period, u64 runtime) { diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index b0d798e..d72586f 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -129,7 +129,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, * cpupri_set - update the cpu priority setting * @cp: The cpupri context * @cpu: The target cpu - * @pri: The priority (INVALID-RT99) to assign to this CPU + * @newpri: The priority (INVALID-RT99) to assign to this CPU * * Note: Assumes cpu_rq(cpu)->lock is locked * @@ -200,7 +200,6 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) /** * cpupri_init - initialize the cpupri structure * @cp: The cpupri context - * @bootmem: true if allocations need to use bootmem * * Returns: -ENOMEM if memory fails. */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8e42de9..84adb2d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3130,8 +3130,10 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) } #define LBF_ALL_PINNED 0x01 -#define LBF_NEED_BREAK 0x02 -#define LBF_ABORT 0x04 +#define LBF_NEED_BREAK 0x02 /* clears into HAD_BREAK */ +#define LBF_HAD_BREAK 0x04 +#define LBF_HAD_BREAKS 0x0C /* count HAD_BREAKs overflows into ABORT */ +#define LBF_ABORT 0x10 /* * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? @@ -4508,7 +4510,9 @@ redo: goto out_balanced; if (lb_flags & LBF_NEED_BREAK) { - lb_flags &= ~LBF_NEED_BREAK; + lb_flags += LBF_HAD_BREAK - LBF_NEED_BREAK; + if (lb_flags & LBF_ABORT) + goto out_balanced; goto redo; } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 57d4b13..e8d76c5 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 bb0efa5..c73c428 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 diff --git a/kernel/sys.c b/kernel/sys.c index ddf8155..4070153 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 ae27196..f487f25 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/trace/ftrace.c b/kernel/trace/ftrace.c index b1e8943..683d559 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_events_filter.c b/kernel/trace/trace_events_filter.c index f04cc31..24aee71 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 77575b3..d4545f4 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 db110b8..f1539de 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 42fa9ad..bec7b5b 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; |
