aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c4
-rw-r--r--kernel/audit.h6
-rw-r--r--kernel/auditfilter.c17
-rw-r--r--kernel/auditsc.c738
-rw-r--r--kernel/capability.c2
-rw-r--r--kernel/events/callchain.c2
-rw-r--r--kernel/events/core.c125
-rw-r--r--kernel/exit.c19
-rw-r--r--kernel/fork.c24
-rw-r--r--kernel/kprobes.c8
-rw-r--r--kernel/params.c3
-rw-r--r--kernel/pid.c4
-rw-r--r--kernel/power/power.h24
-rw-r--r--kernel/power/process.c26
-rw-r--r--kernel/power/snapshot.c3
-rw-r--r--kernel/power/user.c15
-rw-r--r--kernel/rcutorture.c8
-rw-r--r--kernel/relay.c10
-rw-r--r--kernel/res_counter.c25
-rw-r--r--kernel/sched/core.c19
-rw-r--r--kernel/sched/cpupri.c3
-rw-r--r--kernel/sched/fair.c34
-rw-r--r--kernel/sched/rt.c5
-rw-r--r--kernel/seccomp.c2
-rw-r--r--kernel/tracepoint.c7
-rw-r--r--kernel/watchdog.c2
26 files changed, 750 insertions, 385 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 57e3f5107937..bb0eb5bb9a0a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -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 91e7071c4d2c..816766803371 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -36,12 +36,8 @@ enum audit_state {
AUDIT_DISABLED, /* Do not create per-task audit_context.
* No syscall-specific audit records can
* be generated. */
- AUDIT_SETUP_CONTEXT, /* Create the per-task audit_context,
- * but don't necessarily fill it in at
- * syscall entry time (i.e., filter
- * instead). */
AUDIT_BUILD_CONTEXT, /* Create the per-task audit_context,
- * and always fill it in at syscall
+ * and fill it in at syscall
* entry time. This makes a full
* syscall record available if some
* other part of the kernel decides it
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index f8277c80d678..a6c3f1abd206 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -235,13 +235,15 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule *rule)
switch(listnr) {
default:
goto exit_err;
- case AUDIT_FILTER_USER:
- case AUDIT_FILTER_TYPE:
#ifdef CONFIG_AUDITSYSCALL
case AUDIT_FILTER_ENTRY:
+ if (rule->action == AUDIT_ALWAYS)
+ goto exit_err;
case AUDIT_FILTER_EXIT:
case AUDIT_FILTER_TASK:
#endif
+ case AUDIT_FILTER_USER:
+ case AUDIT_FILTER_TYPE:
;
}
if (unlikely(rule->action == AUDIT_POSSIBLE)) {
@@ -385,7 +387,7 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
goto exit_free;
break;
case AUDIT_FILETYPE:
- if ((f->val & ~S_IFMT) > S_IFMT)
+ if (f->val & ~S_IFMT)
goto exit_free;
break;
case AUDIT_INODE:
@@ -459,6 +461,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
case AUDIT_ARG1:
case AUDIT_ARG2:
case AUDIT_ARG3:
+ case AUDIT_OBJ_UID:
+ case AUDIT_OBJ_GID:
break;
case AUDIT_ARCH:
entry->rule.arch_f = f;
@@ -522,7 +526,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
goto exit_free;
break;
case AUDIT_FILTERKEY:
- err = -EINVAL;
if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN)
goto exit_free;
str = audit_unpack_string(&bufp, &remain, f->val);
@@ -536,7 +539,11 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
goto exit_free;
break;
case AUDIT_FILETYPE:
- if ((f->val & ~S_IFMT) > S_IFMT)
+ if (f->val & ~S_IFMT)
+ goto exit_free;
+ break;
+ case AUDIT_FIELD_COMPARE:
+ if (f->val > AUDIT_MAX_FIELD_COMPARE)
goto exit_free;
break;
default:
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index e7fe2b0d29b3..af1de0f34eae 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 0fcf1c14a297..3f1adb6c6470 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -384,7 +384,7 @@ bool ns_capable(struct user_namespace *ns, int cap)
BUG();
}
- if (has_ns_capability(current, ns, cap)) {
+ if (security_capable(current_cred(), ns, cap) == 0) {
current->flags |= PF_SUPERPRIV;
return true;
}
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 057e24b665cf..6581a040f399 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 a8f4ac001a00..1b5c081d8b9f 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
@@ -2300,7 +2300,10 @@ do { \
return div64_u64(dividend, divisor);
}
-static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
+static DEFINE_PER_CPU(int, perf_throttled_count);
+static DEFINE_PER_CPU(u64, perf_throttled_seq);
+
+static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count, bool disable)
{
struct hw_perf_event *hwc = &event->hw;
s64 period, sample_period;
@@ -2319,22 +2322,40 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
hwc->sample_period = sample_period;
if (local64_read(&hwc->period_left) > 8*sample_period) {
- event->pmu->stop(event, PERF_EF_UPDATE);
+ if (disable)
+ event->pmu->stop(event, PERF_EF_UPDATE);
+
local64_set(&hwc->period_left, 0);
- event->pmu->start(event, PERF_EF_RELOAD);
+
+ if (disable)
+ event->pmu->start(event, PERF_EF_RELOAD);
}
}
-static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
+/*
+ * combine freq adjustment with unthrottling to avoid two passes over the
+ * events. At the same time, make sure, having freq events does not change
+ * the rate of unthrottling as that would introduce bias.
+ */
+static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
+ int needs_unthr)
{
struct perf_event *event;
struct hw_perf_event *hwc;
- u64 interrupts, now;
+ u64 now, period = TICK_NSEC;
s64 delta;
- if (!ctx->nr_freq)
+ /*
+ * only need to iterate over all events iff:
+ * - context have events in frequency mode (needs freq adjust)
+ * - there are events to unthrottle on this cpu
+ */
+ if (!(ctx->nr_freq || needs_unthr))
return;
+ raw_spin_lock(&ctx->lock);
+ perf_pmu_disable(ctx->pmu);
+
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (event->state != PERF_EVENT_STATE_ACTIVE)
continue;
@@ -2344,13 +2365,8 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
hwc = &event->hw;
- interrupts = hwc->interrupts;
- hwc->interrupts = 0;
-
- /*
- * unthrottle events on the tick
- */
- if (interrupts == MAX_INTERRUPTS) {
+ if (needs_unthr && hwc->interrupts == MAX_INTERRUPTS) {
+ hwc->interrupts = 0;
perf_log_throttle(event, 1);
event->pmu->start(event, 0);
}
@@ -2358,14 +2374,30 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
if (!event->attr.freq || !event->attr.sample_freq)
continue;
- event->pmu->read(event);
+ /*
+ * stop the event and update event->count
+ */
+ event->pmu->stop(event, PERF_EF_UPDATE);
+
now = local64_read(&event->count);
delta = now - hwc->freq_count_stamp;
hwc->freq_count_stamp = now;
+ /*
+ * restart the event
+ * reload only if value has changed
+ * we have stopped the event so tell that
+ * to perf_adjust_period() to avoid stopping it
+ * twice.
+ */
if (delta > 0)
- perf_adjust_period(event, period, delta);
+ perf_adjust_period(event, period, delta, false);
+
+ event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
}
+
+ perf_pmu_enable(ctx->pmu);
+ raw_spin_unlock(&ctx->lock);
}
/*
@@ -2388,16 +2420,13 @@ static void rotate_ctx(struct perf_event_context *ctx)
*/
static void perf_rotate_context(struct perf_cpu_context *cpuctx)
{
- u64 interval = (u64)cpuctx->jiffies_interval * TICK_NSEC;
struct perf_event_context *ctx = NULL;
- int rotate = 0, remove = 1, freq = 0;
+ int rotate = 0, remove = 1;
if (cpuctx->ctx.nr_events) {
remove = 0;
if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
rotate = 1;
- if (cpuctx->ctx.nr_freq)
- freq = 1;
}
ctx = cpuctx->task_ctx;
@@ -2405,37 +2434,26 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
remove = 0;
if (ctx->nr_events != ctx->nr_active)
rotate = 1;
- if (ctx->nr_freq)
- freq = 1;
}
- if (!rotate && !freq)
+ if (!rotate)
goto done;
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
perf_pmu_disable(cpuctx->ctx.pmu);
- if (freq) {
- perf_ctx_adjust_freq(&cpuctx->ctx, interval);
- if (ctx)
- perf_ctx_adjust_freq(ctx, interval);
- }
-
- if (rotate) {
- cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
- if (ctx)
- ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
+ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+ if (ctx)
+ ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
- rotate_ctx(&cpuctx->ctx);
- if (ctx)
- rotate_ctx(ctx);
+ rotate_ctx(&cpuctx->ctx);
+ if (ctx)
+ rotate_ctx(ctx);
- perf_event_sched_in(cpuctx, ctx, current);
- }
+ perf_event_sched_in(cpuctx, ctx, current);
perf_pmu_enable(cpuctx->ctx.pmu);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
-
done:
if (remove)
list_del_init(&cpuctx->rotation_list);
@@ -2445,10 +2463,22 @@ void perf_event_task_tick(void)
{
struct list_head *head = &__get_cpu_var(rotation_list);
struct perf_cpu_context *cpuctx, *tmp;
+ struct perf_event_context *ctx;
+ int throttled;
WARN_ON(!irqs_disabled());
+ __this_cpu_inc(perf_throttled_seq);
+ throttled = __this_cpu_xchg(perf_throttled_count, 0);
+
list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) {
+ ctx = &cpuctx->ctx;
+ perf_adjust_freq_unthr_context(ctx, throttled);
+
+ ctx = cpuctx->task_ctx;
+ if (ctx)
+ perf_adjust_freq_unthr_context(ctx, throttled);
+
if (cpuctx->jiffies_interval == 1 ||
!(jiffies % cpuctx->jiffies_interval))
perf_rotate_context(cpuctx);
@@ -4509,6 +4539,7 @@ static int __perf_event_overflow(struct perf_event *event,
{
int events = atomic_read(&event->event_limit);
struct hw_perf_event *hwc = &event->hw;
+ u64 seq;
int ret = 0;
/*
@@ -4518,14 +4549,20 @@ static int __perf_event_overflow(struct perf_event *event,
if (unlikely(!is_sampling_event(event)))
return 0;
- if (unlikely(hwc->interrupts >= max_samples_per_tick)) {
- if (throttle) {
+ seq = __this_cpu_read(perf_throttled_seq);
+ if (seq != hwc->interrupts_seq) {
+ hwc->interrupts_seq = seq;
+ hwc->interrupts = 1;
+ } else {
+ hwc->interrupts++;
+ if (unlikely(throttle
+ && hwc->interrupts >= max_samples_per_tick)) {
+ __this_cpu_inc(perf_throttled_count);
hwc->interrupts = MAX_INTERRUPTS;
perf_log_throttle(event, 0);
ret = 1;
}
- } else
- hwc->interrupts++;
+ }
if (event->attr.freq) {
u64 now = perf_clock();
@@ -4534,7 +4571,7 @@ static int __perf_event_overflow(struct perf_event *event,
hwc->freq_time_stamp = now;
if (delta > 0 && delta < 2*TICK_NSEC)
- perf_adjust_period(event, delta, hwc->last_period);
+ perf_adjust_period(event, delta, hwc->last_period, true);
}
/*
diff --git a/kernel/exit.c b/kernel/exit.c
index c44738267be7..4b4042f9bc6a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -964,8 +964,7 @@ 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);
@@ -1039,6 +1038,22 @@ void do_exit(long code)
if (tsk->nr_dirtied)
__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
exit_rcu();
+
+ /*
+ * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
+ * when the following two conditions become true.
+ * - There is race condition of mmap_sem (It is acquired by
+ * exit_mm()), and
+ * - SMI occurs before setting TASK_RUNINNG.
+ * (or hypervisor of virtual machine switches to other guest)
+ * As a result, we may become TASK_RUNNING after becoming TASK_DEAD
+ *
+ * To avoid it, we have to wait for releasing tsk->pi_lock which
+ * is held by try_to_wake_up()
+ */
+ smp_mb();
+ raw_spin_unlock_wait(&tsk->pi_lock);
+
/* causes final put_task_struct in finish_task_switch(). */
tsk->state = TASK_DEAD;
tsk->flags |= PF_NOFREEZE; /* tell freezer to ignore us */
diff --git a/kernel/fork.c b/kernel/fork.c
index f3fa18887cc9..b77fd559c78e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -647,6 +647,26 @@ struct mm_struct *get_task_mm(struct task_struct *task)
}
EXPORT_SYMBOL_GPL(get_task_mm);
+struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
+{
+ struct mm_struct *mm;
+ int err;
+
+ err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ if (err)
+ return ERR_PTR(err);
+
+ mm = get_task_mm(task);
+ if (mm && mm != current->mm &&
+ !ptrace_may_access(task, mode)) {
+ mmput(mm);
+ mm = ERR_PTR(-EACCES);
+ }
+ mutex_unlock(&task->signal->cred_guard_mutex);
+
+ return mm;
+}
+
/* Please note the differences between mmput and mm_release.
* mmput is called whenever we stop holding onto a mm_struct,
* error success whatever.
@@ -890,7 +910,7 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
return -ENOMEM;
new_ioc->ioprio = ioc->ioprio;
- put_io_context(new_ioc, NULL);
+ put_io_context(new_ioc);
}
#endif
return 0;
@@ -1527,8 +1547,6 @@ 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/kprobes.c b/kernel/kprobes.c
index 95dd7212e610..9788c0ec6f43 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);
@@ -1673,8 +1673,12 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
ri->rp = rp;
ri->task = current;
- if (rp->entry_handler && rp->entry_handler(ri, regs))
+ if (rp->entry_handler && rp->entry_handler(ri, regs)) {
+ raw_spin_lock_irqsave(&rp->lock, flags);
+ hlist_add_head(&ri->hlist, &rp->free_instances);
+ raw_spin_unlock_irqrestore(&rp->lock, flags);
return 0;
+ }
arch_prepare_kretprobe(ri, regs);
diff --git a/kernel/params.c b/kernel/params.c
index 32ee04308285..4bc965d8a1fe 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -97,7 +97,8 @@ static int parse_one(char *param,
for (i = 0; i < num_params; i++) {
if (parameq(param, params[i].name)) {
/* No one handled NULL, so do it here. */
- if (!val && params[i].ops->set != param_set_bool)
+ if (!val && params[i].ops->set != param_set_bool
+ && params[i].ops->set != param_set_bint)
return -EINVAL;
pr_debug("They are equal! Calling %p\n",
params[i].ops->set);
diff --git a/kernel/pid.c b/kernel/pid.c
index ce8e00deaccb..9f08dfabaf13 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -543,12 +543,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
*/
void __init pidhash_init(void)
{
- int i, pidhash_size;
+ unsigned int i, pidhash_size;
pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
HASH_EARLY | HASH_SMALL,
&pidhash_shift, NULL, 4096);
- pidhash_size = 1 << pidhash_shift;
+ pidhash_size = 1U << pidhash_shift;
for (i = 0; i < pidhash_size; i++)
INIT_HLIST_HEAD(&pid_hash[i]);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 0c4defe6d3b8..21724eee5206 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -231,8 +231,28 @@ extern int pm_test_level;
#ifdef CONFIG_SUSPEND_FREEZER
static inline int suspend_freeze_processes(void)
{
- int error = freeze_processes();
- return error ? : freeze_kernel_threads();
+ int error;
+
+ error = freeze_processes();
+
+ /*
+ * freeze_processes() automatically thaws every task if freezing
+ * fails. So we need not do anything extra upon error.
+ */
+ if (error)
+ goto Finish;
+
+ error = freeze_kernel_threads();
+
+ /*
+ * freeze_kernel_threads() thaws only kernel threads upon freezing
+ * failure. So we have to thaw the userspace tasks ourselves.
+ */
+ if (error)
+ thaw_processes();
+
+ Finish:
+ return error;
}
static inline void suspend_thaw_processes(void)
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 77274c9ba2f1..7e426459e60a 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -143,7 +143,10 @@ int freeze_processes(void)
/**
* freeze_kernel_threads - Make freezable kernel threads go to the refrigerator.
*
- * On success, returns 0. On failure, -errno and system is fully thawed.
+ * On success, returns 0. On failure, -errno and only the kernel threads are
+ * thawed, so as to give a chance to the caller to do additional cleanups
+ * (if any) before thawing the userspace tasks. So, it is the responsibility
+ * of the caller to thaw the userspace tasks, when the time is right.
*/
int freeze_kernel_threads(void)
{
@@ -159,7 +162,7 @@ int freeze_kernel_threads(void)
BUG_ON(in_atomic());
if (error)
- thaw_processes();
+ thaw_kernel_threads();
return error;
}
@@ -188,3 +191,22 @@ void thaw_processes(void)
printk("done.\n");
}
+void thaw_kernel_threads(void)
+{
+ struct task_struct *g, *p;
+
+ pm_nosig_freezing = false;
+ printk("Restarting kernel threads ... ");
+
+ thaw_workqueues();
+
+ read_lock(&tasklist_lock);
+ do_each_thread(g, p) {
+ if (p->flags & (PF_KTHREAD | PF_WQ_WORKER))
+ __thaw_task(p);
+ } while_each_thread(g, p);
+ read_unlock(&tasklist_lock);
+
+ schedule();
+ printk("done.\n");
+}
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 1cf88900ec4f..6a768e537001 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;
}
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 6b1ab7a88522..3e100075b13c 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -249,13 +249,15 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
}
pm_restore_gfp_mask();
error = hibernation_snapshot(data->platform_support);
- if (!error) {
+ if (error) {
+ thaw_kernel_threads();
+ } else {
error = put_user(in_suspend, (int __user *)arg);
if (!error && !freezer_test_done)
data->ready = 1;
if (freezer_test_done) {
freezer_test_done = false;
- thaw_processes();
+ thaw_kernel_threads();
}
}
break;
@@ -274,6 +276,15 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
swsusp_free();
memset(&data->handle, 0, sizeof(struct snapshot_handle));
data->ready = 0;
+ /*
+ * It is necessary to thaw kernel threads here, because
+ * SNAPSHOT_CREATE_IMAGE may be invoked directly after
+ * SNAPSHOT_FREE. In that case, if kernel threads were not
+ * thawed, the preallocation of memory carried out by
+ * hibernation_snapshot() might run into problems (i.e. it
+ * might fail or even deadlock).
+ */
+ thaw_kernel_threads();
break;
case SNAPSHOT_PREF_IMAGE_SIZE:
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 88f17b8a3b1d..a58ac285fc69 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/relay.c b/kernel/relay.c
index 4335e1d7ee2d..ab56a1764d4d 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -164,10 +164,14 @@ depopulate:
*/
static struct rchan_buf *relay_create_buf(struct rchan *chan)
{
- struct rchan_buf *buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);
- if (!buf)
+ struct rchan_buf *buf;
+
+ if (chan->n_subbufs > UINT_MAX / sizeof(size_t *))
return NULL;
+ buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);
+ if (!buf)
+ return NULL;
buf->padding = kmalloc(chan->n_subbufs * sizeof(size_t *), GFP_KERNEL);
if (!buf->padding)
goto free_buf;
@@ -574,6 +578,8 @@ struct rchan *relay_open(const char *base_filename,
if (!(subbuf_size && n_subbufs))
return NULL;
+ if (subbuf_size > UINT_MAX / n_subbufs)
+ return NULL;
chan = kzalloc(sizeof(struct rchan), GFP_KERNEL);
if (!chan)
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 6d269cce7aa1..d508363858b3 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 df00cb09263e..5255c9d2e053 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -74,6 +74,7 @@
#include <asm/tlb.h>
#include <asm/irq_regs.h>
+#include <asm/mutex.h>
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#endif
@@ -723,9 +724,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
p->sched_class->dequeue_task(rq, p, flags);
}
-/*
- * activate_task - move a task to the runqueue.
- */
void activate_task(struct rq *rq, struct task_struct *p, int flags)
{
if (task_contributes_to_load(p))
@@ -734,9 +732,6 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
enqueue_task(rq, p, flags);
}
-/*
- * deactivate_task - remove a task from the runqueue.
- */
void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{
if (task_contributes_to_load(p))
@@ -4134,7 +4129,7 @@ recheck:
on_rq = p->on_rq;
running = task_current(rq, p);
if (on_rq)
- deactivate_task(rq, p, 0);
+ dequeue_task(rq, p, 0);
if (running)
p->sched_class->put_prev_task(rq, p);
@@ -4147,7 +4142,7 @@ recheck:
if (running)
p->sched_class->set_curr_task(rq);
if (on_rq)
- activate_task(rq, p, 0);
+ enqueue_task(rq, p, 0);
check_class_changed(rq, p, prev_class, oldprio);
task_rq_unlock(rq, p, &flags);
@@ -4998,9 +4993,9 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
* placed properly.
*/
if (p->on_rq) {
- deactivate_task(rq_src, p, 0);
+ dequeue_task(rq_src, p, 0);
set_task_cpu(p, dest_cpu);
- activate_task(rq_dest, p, 0);
+ enqueue_task(rq_dest, p, 0);
check_preempt_curr(rq_dest, p, 0);
}
done:
@@ -7032,10 +7027,10 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
on_rq = p->on_rq;
if (on_rq)
- deactivate_task(rq, p, 0);
+ dequeue_task(rq, p, 0);
__setscheduler(rq, p, SCHED_NORMAL, 0);
if (on_rq) {
- activate_task(rq, p, 0);
+ enqueue_task(rq, p, 0);
resched_task(rq->curr);
}
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index b0d798eaf130..d72586fdf660 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 84adb2d66cbd..7c6414fc669d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4866,6 +4866,15 @@ static void nohz_balancer_kick(int cpu)
return;
}
+static inline void clear_nohz_tick_stopped(int cpu)
+{
+ if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
+ cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
+ atomic_dec(&nohz.nr_cpus);
+ clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
+ }
+}
+
static inline void set_cpu_sd_state_busy(void)
{
struct sched_domain *sd;
@@ -4904,6 +4913,12 @@ void select_nohz_load_balancer(int stop_tick)
{
int cpu = smp_processor_id();
+ /*
+ * If this cpu is going down, then nothing needs to be done.
+ */
+ if (!cpu_active(cpu))
+ return;
+
if (stop_tick) {
if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
return;
@@ -4914,6 +4929,18 @@ void select_nohz_load_balancer(int stop_tick)
}
return;
}
+
+static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DYING:
+ clear_nohz_tick_stopped(smp_processor_id());
+ return NOTIFY_OK;
+ default:
+ return NOTIFY_DONE;
+ }
+}
#endif
static DEFINE_SPINLOCK(balancing);
@@ -5070,11 +5097,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
* busy tick after returning from idle, we will update the busy stats.
*/
set_cpu_sd_state_busy();
- if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
- clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
- cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
- atomic_dec(&nohz.nr_cpus);
- }
+ clear_nohz_tick_stopped(cpu);
/*
* None are in tickless mode and hence no need for NOHZ idle load
@@ -5590,6 +5613,7 @@ __init void init_sched_fair_class(void)
#ifdef CONFIG_NO_HZ
zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
+ cpu_notifier(sched_ilb_notifier, 0);
#endif
#endif /* SMP */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 3640ebbb466b..f42ae7fb5ec5 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1587,6 +1587,11 @@ static int push_rt_task(struct rq *rq)
if (!next_task)
return 0;
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+ if (unlikely(task_running(rq, next_task)))
+ return 0;
+#endif
+
retry:
if (unlikely(next_task == rq->curr)) {
WARN_ON(1);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 57d4b13b631d..e8d76c5895ea 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -6,6 +6,7 @@
* This defines a simple but solid secure-computing mode.
*/
+#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/sched.h>
#include <linux/compat.h>
@@ -54,6 +55,7 @@ void __secure_computing(int this_syscall)
#ifdef SECCOMP_DEBUG
dump_stack();
#endif
+ audit_seccomp(this_syscall);
do_exit(SIGKILL);
}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index db110b8ae030..f1539decd99d 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -634,10 +634,11 @@ static int tracepoint_module_coming(struct module *mod)
int ret = 0;
/*
- * We skip modules that tain the kernel, especially those with different
- * module header (for forced load), to make sure we don't cause a crash.
+ * We skip modules that taint the kernel, especially those with different
+ * module headers (for forced load), to make sure we don't cause a crash.
+ * Staging and out-of-tree GPL modules are fine.
*/
- if (mod->taints)
+ if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
return 0;
mutex_lock(&tracepoints_mutex);
tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 1d7bca7f4f52..d117262deba3 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -296,7 +296,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
if (__this_cpu_read(soft_watchdog_warn) == true)
return HRTIMER_RESTART;
- printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
+ printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
smp_processor_id(), duration,
current->comm, task_pid_nr(current));
print_modules();
generated by cgit v1.2.3 (git 2.39.1) at 2024-10-06 22:39:26 +0000