summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/auditsc.c332
-rw-r--r--kernel/capability.c46
-rw-r--r--kernel/cred.c2
-rw-r--r--kernel/events/uprobes.c5
-rw-r--r--kernel/fork.c4
-rw-r--r--kernel/irq/msi.c19
-rw-r--r--kernel/module.c13
-rw-r--r--kernel/sched/core.c5
-rw-r--r--kernel/sched/cputime.c15
-rw-r--r--kernel/sched/fair.c30
-rw-r--r--kernel/time/clocksource.c52
-rw-r--r--kernel/time/hrtimer.c7
-rw-r--r--kernel/time/ntp.c20
-rw-r--r--kernel/time/timekeeping.c7
-rw-r--r--kernel/time/timekeeping_debug.c9
15 files changed, 344 insertions, 222 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index b86cc04959de..48f45987dc6c 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -73,6 +73,7 @@
#include <linux/compat.h>
#include <linux/ctype.h>
#include <linux/string.h>
+#include <linux/uaccess.h>
#include <uapi/linux/limits.h>
#include "audit.h"
@@ -82,7 +83,8 @@
#define AUDITSC_SUCCESS 1
#define AUDITSC_FAILURE 2
-/* no execve audit message should be longer than this (userspace limits) */
+/* no execve audit message should be longer than this (userspace limits),
+ * see the note near the top of audit_log_execve_info() about this value */
#define MAX_EXECVE_AUDIT_LEN 7500
/* max length to print of cmdline/proctitle value during audit */
@@ -988,184 +990,178 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid,
return rc;
}
-/*
- * to_send and len_sent accounting are very loose estimates. We aren't
- * really worried about a hard cap to MAX_EXECVE_AUDIT_LEN so much as being
- * within about 500 bytes (next page boundary)
- *
- * why snprintf? an int is up to 12 digits long. if we just assumed when
- * logging that a[%d]= was going to be 16 characters long we would be wasting
- * space in every audit message. In one 7500 byte message we can log up to
- * about 1000 min size arguments. That comes down to about 50% waste of space
- * if we didn't do the snprintf to find out how long arg_num_len was.
- */
-static int audit_log_single_execve_arg(struct audit_context *context,
- struct audit_buffer **ab,
- int arg_num,
- size_t *len_sent,
- const char __user *p,
- char *buf)
+static void audit_log_execve_info(struct audit_context *context,
+ struct audit_buffer **ab)
{
- char arg_num_len_buf[12];
- const char __user *tmp_p = p;
- /* how many digits are in arg_num? 5 is the length of ' a=""' */
- size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5;
- size_t len, len_left, to_send;
- size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN;
- unsigned int i, has_cntl = 0, too_long = 0;
- int ret;
-
- /* strnlen_user includes the null we don't want to send */
- len_left = len = strnlen_user(p, MAX_ARG_STRLEN) - 1;
-
- /*
- * We just created this mm, if we can't find the strings
- * we just copied into it something is _very_ wrong. Similar
- * for strings that are too long, we should not have created
- * any.
- */
- if (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) {
- send_sig(SIGKILL, current, 0);
- return -1;
+ long len_max;
+ long len_rem;
+ long len_full;
+ long len_buf;
+ long len_abuf;
+ long len_tmp;
+ bool require_data;
+ bool encode;
+ unsigned int iter;
+ unsigned int arg;
+ char *buf_head;
+ char *buf;
+ const char __user *p = (const char __user *)current->mm->arg_start;
+
+ /* NOTE: this buffer needs to be large enough to hold all the non-arg
+ * data we put in the audit record for this argument (see the
+ * code below) ... at this point in time 96 is plenty */
+ char abuf[96];
+
+ /* NOTE: we set MAX_EXECVE_AUDIT_LEN to a rather arbitrary limit, the
+ * current value of 7500 is not as important as the fact that it
+ * is less than 8k, a setting of 7500 gives us plenty of wiggle
+ * room if we go over a little bit in the logging below */
+ WARN_ON_ONCE(MAX_EXECVE_AUDIT_LEN > 7500);
+ len_max = MAX_EXECVE_AUDIT_LEN;
+
+ /* scratch buffer to hold the userspace args */
+ buf_head = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL);
+ if (!buf_head) {
+ audit_panic("out of memory for argv string");
+ return;
}
+ buf = buf_head;
- /* walk the whole argument looking for non-ascii chars */
+ audit_log_format(*ab, "argc=%d", context->execve.argc);
+
+ len_rem = len_max;
+ len_buf = 0;
+ len_full = 0;
+ require_data = true;
+ encode = false;
+ iter = 0;
+ arg = 0;
do {
- if (len_left > MAX_EXECVE_AUDIT_LEN)
- to_send = MAX_EXECVE_AUDIT_LEN;
- else
- to_send = len_left;
- ret = copy_from_user(buf, tmp_p, to_send);
- /*
- * There is no reason for this copy to be short. We just
- * copied them here, and the mm hasn't been exposed to user-
- * space yet.
- */
- if (ret) {
- WARN_ON(1);
- send_sig(SIGKILL, current, 0);
- return -1;
- }
- buf[to_send] = '\0';
- has_cntl = audit_string_contains_control(buf, to_send);
- if (has_cntl) {
- /*
- * hex messages get logged as 2 bytes, so we can only
- * send half as much in each message
- */
- max_execve_audit_len = MAX_EXECVE_AUDIT_LEN / 2;
- break;
- }
- len_left -= to_send;
- tmp_p += to_send;
- } while (len_left > 0);
-
- len_left = len;
-
- if (len > max_execve_audit_len)
- too_long = 1;
-
- /* rewalk the argument actually logging the message */
- for (i = 0; len_left > 0; i++) {
- int room_left;
-
- if (len_left > max_execve_audit_len)
- to_send = max_execve_audit_len;
- else
- to_send = len_left;
-
- /* do we have space left to send this argument in this ab? */
- room_left = MAX_EXECVE_AUDIT_LEN - arg_num_len - *len_sent;
- if (has_cntl)
- room_left -= (to_send * 2);
- else
- room_left -= to_send;
- if (room_left < 0) {
- *len_sent = 0;
- audit_log_end(*ab);
- *ab = audit_log_start(context, GFP_KERNEL, AUDIT_EXECVE);
- if (!*ab)
- return 0;
- }
+ /* NOTE: we don't ever want to trust this value for anything
+ * serious, but the audit record format insists we
+ * provide an argument length for really long arguments,
+ * e.g. > MAX_EXECVE_AUDIT_LEN, so we have no choice but
+ * to use strncpy_from_user() to obtain this value for
+ * recording in the log, although we don't use it
+ * anywhere here to avoid a double-fetch problem */
+ if (len_full == 0)
+ len_full = strnlen_user(p, MAX_ARG_STRLEN) - 1;
+
+ /* read more data from userspace */
+ if (require_data) {
+ /* can we make more room in the buffer? */
+ if (buf != buf_head) {
+ memmove(buf_head, buf, len_buf);
+ buf = buf_head;
+ }
+
+ /* fetch as much as we can of the argument */
+ len_tmp = strncpy_from_user(&buf_head[len_buf], p,
+ len_max - len_buf);
+ if (len_tmp == -EFAULT) {
+ /* unable to copy from userspace */
+ send_sig(SIGKILL, current, 0);
+ goto out;
+ } else if (len_tmp == (len_max - len_buf)) {
+ /* buffer is not large enough */
+ require_data = true;
+ /* NOTE: if we are going to span multiple
+ * buffers force the encoding so we stand
+ * a chance at a sane len_full value and
+ * consistent record encoding */
+ encode = true;
+ len_full = len_full * 2;
+ p += len_tmp;
+ } else {
+ require_data = false;
+ if (!encode)
+ encode = audit_string_contains_control(
+ buf, len_tmp);
+ /* try to use a trusted value for len_full */
+ if (len_full < len_max)
+ len_full = (encode ?
+ len_tmp * 2 : len_tmp);
+ p += len_tmp + 1;
+ }
+ len_buf += len_tmp;
+ buf_head[len_buf] = '\0';
- /*
- * first record needs to say how long the original string was
- * so we can be sure nothing was lost.
- */
- if ((i == 0) && (too_long))
- audit_log_format(*ab, " a%d_len=%zu", arg_num,
- has_cntl ? 2*len : len);
-
- /*
- * normally arguments are small enough to fit and we already
- * filled buf above when we checked for control characters
- * so don't bother with another copy_from_user
- */
- if (len >= max_execve_audit_len)
- ret = copy_from_user(buf, p, to_send);
- else
- ret = 0;
- if (ret) {
- WARN_ON(1);
- send_sig(SIGKILL, current, 0);
- return -1;
+ /* length of the buffer in the audit record? */
+ len_abuf = (encode ? len_buf * 2 : len_buf + 2);
}
- buf[to_send] = '\0';
-
- /* actually log it */
- audit_log_format(*ab, " a%d", arg_num);
- if (too_long)
- audit_log_format(*ab, "[%d]", i);
- audit_log_format(*ab, "=");
- if (has_cntl)
- audit_log_n_hex(*ab, buf, to_send);
- else
- audit_log_string(*ab, buf);
-
- p += to_send;
- len_left -= to_send;
- *len_sent += arg_num_len;
- if (has_cntl)
- *len_sent += to_send * 2;
- else
- *len_sent += to_send;
- }
- /* include the null we didn't log */
- return len + 1;
-}
-static void audit_log_execve_info(struct audit_context *context,
- struct audit_buffer **ab)
-{
- int i, len;
- size_t len_sent = 0;
- const char __user *p;
- char *buf;
+ /* write as much as we can to the audit log */
+ if (len_buf > 0) {
+ /* NOTE: some magic numbers here - basically if we
+ * can't fit a reasonable amount of data into the
+ * existing audit buffer, flush it and start with
+ * a new buffer */
+ if ((sizeof(abuf) + 8) > len_rem) {
+ len_rem = len_max;
+ audit_log_end(*ab);
+ *ab = audit_log_start(context,
+ GFP_KERNEL, AUDIT_EXECVE);
+ if (!*ab)
+ goto out;
+ }
- p = (const char __user *)current->mm->arg_start;
+ /* create the non-arg portion of the arg record */
+ len_tmp = 0;
+ if (require_data || (iter > 0) ||
+ ((len_abuf + sizeof(abuf)) > len_rem)) {
+ if (iter == 0) {
+ len_tmp += snprintf(&abuf[len_tmp],
+ sizeof(abuf) - len_tmp,
+ " a%d_len=%lu",
+ arg, len_full);
+ }
+ len_tmp += snprintf(&abuf[len_tmp],
+ sizeof(abuf) - len_tmp,
+ " a%d[%d]=", arg, iter++);
+ } else
+ len_tmp += snprintf(&abuf[len_tmp],
+ sizeof(abuf) - len_tmp,
+ " a%d=", arg);
+ WARN_ON(len_tmp >= sizeof(abuf));
+ abuf[sizeof(abuf) - 1] = '\0';
+
+ /* log the arg in the audit record */
+ audit_log_format(*ab, "%s", abuf);
+ len_rem -= len_tmp;
+ len_tmp = len_buf;
+ if (encode) {
+ if (len_abuf > len_rem)
+ len_tmp = len_rem / 2; /* encoding */
+ audit_log_n_hex(*ab, buf, len_tmp);
+ len_rem -= len_tmp * 2;
+ len_abuf -= len_tmp * 2;
+ } else {
+ if (len_abuf > len_rem)
+ len_tmp = len_rem - 2; /* quotes */
+ audit_log_n_string(*ab, buf, len_tmp);
+ len_rem -= len_tmp + 2;
+ /* don't subtract the "2" because we still need
+ * to add quotes to the remaining string */
+ len_abuf -= len_tmp;
+ }
+ len_buf -= len_tmp;
+ buf += len_tmp;
+ }
- audit_log_format(*ab, "argc=%d", context->execve.argc);
+ /* ready to move to the next argument? */
+ if ((len_buf == 0) && !require_data) {
+ arg++;
+ iter = 0;
+ len_full = 0;
+ require_data = true;
+ encode = false;
+ }
+ } while (arg < context->execve.argc);
- /*
- * we need some kernel buffer to hold the userspace args. Just
- * allocate one big one rather than allocating one of the right size
- * for every single argument inside audit_log_single_execve_arg()
- * should be <8k allocation so should be pretty safe.
- */
- buf = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL);
- if (!buf) {
- audit_panic("out of memory for argv string");
- return;
- }
+ /* NOTE: the caller handles the final audit_log_end() call */
- for (i = 0; i < context->execve.argc; i++) {
- len = audit_log_single_execve_arg(context, ab, i,
- &len_sent, p, buf);
- if (len <= 0)
- break;
- p += len;
- }
- kfree(buf);
+out:
+ kfree(buf_head);
}
static void show_special(struct audit_context *context, int *call_panic)
diff --git a/kernel/capability.c b/kernel/capability.c
index 45432b54d5c6..00411c82dac5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -361,6 +361,24 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
return has_ns_capability_noaudit(t, &init_user_ns, cap);
}
+static bool ns_capable_common(struct user_namespace *ns, int cap, bool audit)
+{
+ int capable;
+
+ if (unlikely(!cap_valid(cap))) {
+ pr_crit("capable() called with invalid cap=%u\n", cap);
+ BUG();
+ }
+
+ capable = audit ? security_capable(current_cred(), ns, cap) :
+ security_capable_noaudit(current_cred(), ns, cap);
+ if (capable == 0) {
+ current->flags |= PF_SUPERPRIV;
+ return true;
+ }
+ return false;
+}
+
/**
* ns_capable - Determine if the current task has a superior capability in effect
* @ns: The usernamespace we want the capability in
@@ -374,19 +392,27 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
*/
bool ns_capable(struct user_namespace *ns, int cap)
{
- if (unlikely(!cap_valid(cap))) {
- pr_crit("capable() called with invalid cap=%u\n", cap);
- BUG();
- }
-
- if (security_capable(current_cred(), ns, cap) == 0) {
- current->flags |= PF_SUPERPRIV;
- return true;
- }
- return false;
+ return ns_capable_common(ns, cap, true);
}
EXPORT_SYMBOL(ns_capable);
+/**
+ * ns_capable_noaudit - Determine if the current task has a superior capability
+ * (unaudited) in effect
+ * @ns: The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+bool ns_capable_noaudit(struct user_namespace *ns, int cap)
+{
+ return ns_capable_common(ns, cap, false);
+}
+EXPORT_SYMBOL(ns_capable_noaudit);
/**
* capable - Determine if the current task has a superior capability in effect
diff --git a/kernel/cred.c b/kernel/cred.c
index 71179a09c1d6..ff8606f77d90 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -689,6 +689,8 @@ EXPORT_SYMBOL(set_security_override_from_ctx);
*/
int set_create_files_as(struct cred *new, struct inode *inode)
{
+ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+ return -EINVAL;
new->fsuid = inode->i_uid;
new->fsgid = inode->i_gid;
return security_kernel_create_files_as(new, inode);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 4dcc16991b67..7b1b772ab1ce 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -171,8 +171,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
err = -EAGAIN;
ptep = page_check_address(page, mm, addr, &ptl, 0);
- if (!ptep)
+ if (!ptep) {
+ mem_cgroup_cancel_charge(kpage, memcg);
goto unlock;
+ }
get_page(kpage);
page_add_new_anon_rmap(kpage, vma, addr);
@@ -199,7 +201,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
err = 0;
unlock:
- mem_cgroup_cancel_charge(kpage, memcg);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
unlock_page(page);
return err;
diff --git a/kernel/fork.c b/kernel/fork.c
index 1155eac61687..c485cb156772 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1369,7 +1369,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
- threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
@@ -1521,6 +1520,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
+ threadgroup_change_begin(current);
/*
* Ensure that the cgroup subsystem policies allow the new process to be
* forked. It should be noted the the new process's css_set can be changed
@@ -1621,6 +1621,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
bad_fork_cancel_cgroup:
cgroup_cancel_fork(p, cgrp_ss_priv);
bad_fork_free_pid:
+ threadgroup_change_end(current);
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_io:
@@ -1651,7 +1652,6 @@ bad_fork_cleanup_policy:
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
- threadgroup_change_end(current);
delayacct_tsk_free(p);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 6b0c0b74a2a1..4b21779d5163 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -268,7 +268,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
struct msi_domain_ops *ops = info->ops;
msi_alloc_info_t arg;
struct msi_desc *desc;
- int i, ret, virq = -1;
+ int i, ret, virq;
ret = ops->msi_check(domain, info, dev);
if (ret == 0)
@@ -278,12 +278,8 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
for_each_msi_entry(desc, dev) {
ops->set_desc(&arg, desc);
- if (info->flags & MSI_FLAG_IDENTITY_MAP)
- virq = (int)ops->get_hwirq(info, &arg);
- else
- virq = -1;
- virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used,
+ virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
dev_to_node(dev), &arg, false);
if (virq < 0) {
ret = -ENOSPC;
@@ -307,6 +303,17 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
else
dev_dbg(dev, "irq [%d-%d] for MSI\n",
virq, virq + desc->nvec_used - 1);
+ /*
+ * This flag is set by the PCI layer as we need to activate
+ * the MSI entries before the PCI layer enables MSI in the
+ * card. Otherwise the card latches a random msi message.
+ */
+ if (info->flags & MSI_FLAG_ACTIVATE_EARLY) {
+ struct irq_data *irq_data;
+
+ irq_data = irq_domain_get_irq_data(domain, desc->irq);
+ irq_domain_activate_irq(irq_data);
+ }
}
return 0;
diff --git a/kernel/module.c b/kernel/module.c
index 0e5c71195f18..b14a4f31221f 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2606,13 +2606,18 @@ static inline void kmemleak_load_module(const struct module *mod,
#endif
#ifdef CONFIG_MODULE_SIG
-static int module_sig_check(struct load_info *info)
+static int module_sig_check(struct load_info *info, int flags)
{
int err = -ENOKEY;
const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1;
const void *mod = info->hdr;
- if (info->len > markerlen &&
+ /*
+ * Require flags == 0, as a module with version information
+ * removed is no longer the module that was signed
+ */
+ if (flags == 0 &&
+ info->len > markerlen &&
memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) {
/* We truncate the module to discard the signature */
info->len -= markerlen;
@@ -2631,7 +2636,7 @@ static int module_sig_check(struct load_info *info)
return err;
}
#else /* !CONFIG_MODULE_SIG */
-static int module_sig_check(struct load_info *info)
+static int module_sig_check(struct load_info *info, int flags)
{
return 0;
}
@@ -3444,7 +3449,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
long err;
char *after_dashes;
- err = module_sig_check(info);
+ err = module_sig_check(info, flags);
if (err)
goto free_copy;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 67d1e1597d9c..ea863bc22caf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -627,7 +627,10 @@ int get_nohz_timer_target(void)
rcu_read_lock();
for_each_domain(cpu, sd) {
for_each_cpu(i, sched_domain_span(sd)) {
- if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) {
+ if (cpu == i)
+ continue;
+
+ if (!idle_cpu(i) && is_housekeeping_cpu(i)) {
cpu = i;
goto unlock;
}
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index f74ea89e77a8..a1aecbedf5b1 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -600,19 +600,25 @@ static void cputime_adjust(struct task_cputime *curr,
stime = curr->stime;
utime = curr->utime;
- if (utime == 0) {
- stime = rtime;
+ /*
+ * If either stime or both stime and utime are 0, assume all runtime is
+ * userspace. Once a task gets some ticks, the monotonicy code at
+ * 'update' will ensure things converge to the observed ratio.
+ */
+ if (stime == 0) {
+ utime = rtime;
goto update;
}
- if (stime == 0) {
- utime = rtime;
+ if (utime == 0) {
+ stime = rtime;
goto update;
}
stime = scale_stime((__force u64)stime, (__force u64)rtime,
(__force u64)(stime + utime));
+update:
/*
* Make sure stime doesn't go backwards; this preserves monotonicity
* for utime because rtime is monotonic.
@@ -635,7 +641,6 @@ static void cputime_adjust(struct task_cputime *curr,
stime = rtime - utime;
}
-update:
prev->stime = stime;
prev->utime = utime;
out:
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b8b516c37bf1..8f258f437ac2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1191,8 +1191,6 @@ static void task_numa_assign(struct task_numa_env *env,
{
if (env->best_task)
put_task_struct(env->best_task);
- if (p)
- get_task_struct(p);
env->best_task = p;
env->best_imp = imp;
@@ -1260,20 +1258,30 @@ static void task_numa_compare(struct task_numa_env *env,
long imp = env->p->numa_group ? groupimp : taskimp;
long moveimp = imp;
int dist = env->dist;
+ bool assigned = false;
rcu_read_lock();
raw_spin_lock_irq(&dst_rq->lock);
cur = dst_rq->curr;
/*
- * No need to move the exiting task, and this ensures that ->curr
- * wasn't reaped and thus get_task_struct() in task_numa_assign()
- * is safe under RCU read lock.
- * Note that rcu_read_lock() itself can't protect from the final
- * put_task_struct() after the last schedule().
+ * No need to move the exiting task or idle task.
*/
if ((cur->flags & PF_EXITING) || is_idle_task(cur))
cur = NULL;
+ else {
+ /*
+ * The task_struct must be protected here to protect the
+ * p->numa_faults access in the task_weight since the
+ * numa_faults could already be freed in the following path:
+ * finish_task_switch()
+ * --> put_task_struct()
+ * --> __put_task_struct()
+ * --> task_numa_free()
+ */
+ get_task_struct(cur);
+ }
+
raw_spin_unlock_irq(&dst_rq->lock);
/*
@@ -1357,6 +1365,7 @@ balance:
*/
if (!load_too_imbalanced(src_load, dst_load, env)) {
imp = moveimp - 1;
+ put_task_struct(cur);
cur = NULL;
goto assign;
}
@@ -1382,9 +1391,16 @@ balance:
env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
assign:
+ assigned = true;
task_numa_assign(env, cur, imp);
unlock:
rcu_read_unlock();
+ /*
+ * The dst_rq->curr isn't assigned. The protection for task_struct is
+ * finished.
+ */
+ if (cur && !assigned)
+ put_task_struct(cur);
}
static void task_numa_find_cpu(struct task_numa_env *env,
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1347882d131e..b98810d2f3b4 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -323,13 +323,42 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
/* cs is a watchdog. */
if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+ }
+ spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static void clocksource_select_watchdog(bool fallback)
+{
+ struct clocksource *cs, *old_wd;
+ unsigned long flags;
+
+ spin_lock_irqsave(&watchdog_lock, flags);
+ /* save current watchdog */
+ old_wd = watchdog;
+ if (fallback)
+ watchdog = NULL;
+
+ list_for_each_entry(cs, &clocksource_list, list) {
+ /* cs is a clocksource to be watched. */
+ if (cs->flags & CLOCK_SOURCE_MUST_VERIFY)
+ continue;
+
+ /* Skip current if we were requested for a fallback. */
+ if (fallback && cs == old_wd)
+ continue;
+
/* Pick the best watchdog. */
- if (!watchdog || cs->rating > watchdog->rating) {
+ if (!watchdog || cs->rating > watchdog->rating)
watchdog = cs;
- /* Reset watchdog cycles */
- clocksource_reset_watchdog();
- }
}
+ /* If we failed to find a fallback restore the old one. */
+ if (!watchdog)
+ watchdog = old_wd;
+
+ /* If we changed the watchdog we need to reset cycles. */
+ if (watchdog != old_wd)
+ clocksource_reset_watchdog();
+
/* Check if the watchdog timer needs to be started. */
clocksource_start_watchdog();
spin_unlock_irqrestore(&watchdog_lock, flags);
@@ -404,6 +433,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
}
+static void clocksource_select_watchdog(bool fallback) { }
static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
static inline void clocksource_resume_watchdog(void) { }
static inline int __clocksource_watchdog_kthread(void) { return 0; }
@@ -736,6 +766,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
clocksource_enqueue(cs);
clocksource_enqueue_watchdog(cs);
clocksource_select();
+ clocksource_select_watchdog(false);
mutex_unlock(&clocksource_mutex);
return 0;
}
@@ -758,6 +789,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
mutex_lock(&clocksource_mutex);
__clocksource_change_rating(cs, rating);
clocksource_select();
+ clocksource_select_watchdog(false);
mutex_unlock(&clocksource_mutex);
}
EXPORT_SYMBOL(clocksource_change_rating);
@@ -767,12 +799,12 @@ EXPORT_SYMBOL(clocksource_change_rating);
*/
static int clocksource_unbind(struct clocksource *cs)
{
- /*
- * I really can't convince myself to support this on hardware
- * designed by lobotomized monkeys.
- */
- if (clocksource_is_watchdog(cs))
- return -EBUSY;
+ if (clocksource_is_watchdog(cs)) {
+ /* Select and try to install a replacement watchdog. */
+ clocksource_select_watchdog(true);
+ if (clocksource_is_watchdog(cs))
+ return -EBUSY;
+ }
if (cs == curr_clocksource) {
/* Select and try to install a replacement clock source */
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index fa909f9fd559..17f7bcff1e02 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -94,6 +94,9 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
};
static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+ /* Make sure we catch unsupported clockids */
+ [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES,
+
[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME,
[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC,
[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME,
@@ -102,7 +105,9 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
static inline int hrtimer_clockid_to_base(clockid_t clock_id)
{
- return hrtimer_clock_to_base_table[clock_id];
+ int base = hrtimer_clock_to_base_table[clock_id];
+ BUG_ON(base == HRTIMER_MAX_CLOCK_BASES);
+ return base;
}
/*
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 149cc8086aea..ab861771e37f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -674,8 +674,24 @@ int ntp_validate_timex(struct timex *txc)
return -EINVAL;
}
- if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
- return -EPERM;
+ if (txc->modes & ADJ_SETOFFSET) {
+ /* In order to inject time, you gotta be super-user! */
+ if (!capable(CAP_SYS_TIME))
+ return -EPERM;
+
+ if (txc->modes & ADJ_NANO) {
+ struct timespec ts;
+
+ ts.tv_sec = txc->time.tv_sec;
+ ts.tv_nsec = txc->time.tv_usec;
+ if (!timespec_inject_offset_valid(&ts))
+ return -EINVAL;
+
+ } else {
+ if (!timeval_inject_offset_valid(&txc->time))
+ return -EINVAL;
+ }
+ }
/*
* Check for potential multiplication overflows that can
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 99188ee5d9d0..4ff237dbc006 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -383,7 +383,10 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
do {
seq = raw_read_seqcount_latch(&tkf->seq);
tkr = tkf->base + (seq & 0x01);
- now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+ now = ktime_to_ns(tkr->base);
+
+ now += clocksource_delta(tkr->read(tkr->clock),
+ tkr->cycle_last, tkr->mask);
} while (read_seqcount_retry(&tkf->seq, seq));
return now;
@@ -958,7 +961,7 @@ int timekeeping_inject_offset(struct timespec *ts)
struct timespec64 ts64, tmp;
int ret = 0;
- if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+ if (!timespec_inject_offset_valid(ts))
return -EINVAL;
ts64 = timespec_to_timespec64(*ts);
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index f6bd65236712..107310a6f36f 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -23,7 +23,9 @@
#include "timekeeping_internal.h"
-static unsigned int sleep_time_bin[32] = {0};
+#define NUM_BINS 32
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
{
@@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init);
void tk_debug_account_sleep_time(struct timespec64 *t)
{
- sleep_time_bin[fls(t->tv_sec)]++;
+ /* Cap bin index so we don't overflow the array */
+ int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+ sleep_time_bin[bin]++;
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-10 02:49:16 +0000