summary refs log tree commit diff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/auditsc.c2
-rw-r--r--kernel/cgroup.c48
-rw-r--r--kernel/configs/tiny.config4
-rw-r--r--kernel/cpuset.c9
-rw-r--r--kernel/events/core.c14
-rw-r--r--kernel/fork.c5
-rw-r--r--kernel/futex.c1
-rw-r--r--kernel/gcov/Kconfig2
-rw-r--r--kernel/irq/devres.c2
-rw-r--r--kernel/kcmp.c7
-rw-r--r--kernel/module.c4
-rw-r--r--kernel/params.c17
-rw-r--r--kernel/power/snapshot.c50
-rw-r--r--kernel/printk/printk.c6
-rw-r--r--kernel/sys_ni.c3
-rw-r--r--kernel/sysctl_binary.c1
-rw-r--r--kernel/time/alarmtimer.c34
-rw-r--r--kernel/time/time.c56
-rw-r--r--kernel/trace/ring_buffer.c2
19 files changed, 158 insertions, 109 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 21eae3c05ec0..7208c1df248d 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2406,7 +2406,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
  * @new: the new credentials
  * @old: the old (current) credentials
  *
- * Record the aguments userspace sent to sys_capset for later printing by the
+ * Record the arguments userspace sent to sys_capset for later printing by the
  * audit system if applicable
  */
 void __audit_log_capset(const struct cred *new, const struct cred *old)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 7dc8788cfd52..3a73f995a81e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1035,6 +1035,11 @@ static void cgroup_get(struct cgroup *cgrp)
 	css_get(&cgrp->self);
 }
 
+static bool cgroup_tryget(struct cgroup *cgrp)
+{
+	return css_tryget(&cgrp->self);
+}
+
 static void cgroup_put(struct cgroup *cgrp)
 {
 	css_put(&cgrp->self);
@@ -1147,7 +1152,8 @@ static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn)
 	 * protection against removal.  Ensure @cgrp stays accessible and
 	 * break the active_ref protection.
 	 */
-	cgroup_get(cgrp);
+	if (!cgroup_tryget(cgrp))
+		return NULL;
 	kernfs_break_active_protection(kn);
 
 	mutex_lock(&cgroup_mutex);
@@ -3271,8 +3277,17 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
 	struct cftype *cft;
 
-	for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
-		cft->flags |= __CFTYPE_NOT_ON_DFL;
+	/*
+	 * If legacy_flies_on_dfl, we want to show the legacy files on the
+	 * dfl hierarchy but iff the target subsystem hasn't been updated
+	 * for the dfl hierarchy yet.
+	 */
+	if (!cgroup_legacy_files_on_dfl ||
+	    ss->dfl_cftypes != ss->legacy_cftypes) {
+		for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
+			cft->flags |= __CFTYPE_NOT_ON_DFL;
+	}
+
 	return cgroup_add_cftypes(ss, cfts);
 }
 
@@ -3970,7 +3985,6 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 
 	l = cgroup_pidlist_find_create(cgrp, type);
 	if (!l) {
-		mutex_unlock(&cgrp->pidlist_mutex);
 		pidlist_free(array);
 		return -ENOMEM;
 	}
@@ -4387,6 +4401,15 @@ static void css_release_work_fn(struct work_struct *work)
 		/* cgroup release path */
 		cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
 		cgrp->id = -1;
+
+		/*
+		 * There are two control paths which try to determine
+		 * cgroup from dentry without going through kernfs -
+		 * cgroupstats_build() and css_tryget_online_from_dir().
+		 * Those are supported by RCU protecting clearing of
+		 * cgrp->kn->priv backpointer.
+		 */
+		RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
 	}
 
 	mutex_unlock(&cgroup_mutex);
@@ -4543,6 +4566,11 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	struct cftype *base_files;
 	int ssid, ret;
 
+	/* Do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable.
+	 */
+	if (strchr(name, '\n'))
+		return -EINVAL;
+
 	parent = cgroup_kn_lock_live(parent_kn);
 	if (!parent)
 		return -ENODEV;
@@ -4820,16 +4848,6 @@ static int cgroup_rmdir(struct kernfs_node *kn)
 
 	cgroup_kn_unlock(kn);
 
-	/*
-	 * There are two control paths which try to determine cgroup from
-	 * dentry without going through kernfs - cgroupstats_build() and
-	 * css_tryget_online_from_dir().  Those are supported by RCU
-	 * protecting clearing of cgrp->kn->priv backpointer, which should
-	 * happen after all files under it have been removed.
-	 */
-	if (!ret)
-		RCU_INIT_POINTER(*(void __rcu __force **)&kn->priv, NULL);
-
 	cgroup_put(cgrp);
 	return ret;
 }
@@ -5416,7 +5434,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 	/*
 	 * This path doesn't originate from kernfs and @kn could already
 	 * have been or be removed at any point.  @kn->priv is RCU
-	 * protected for this access.  See cgroup_rmdir() for details.
+	 * protected for this access.  See css_release_work_fn() for details.
 	 */
 	cgrp = rcu_dereference(kn->priv);
 	if (cgrp)
diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config
new file mode 100644
index 000000000000..c2de56ab0fce
--- /dev/null
+++ b/kernel/configs/tiny.config
@@ -0,0 +1,4 @@
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_KERNEL_XZ=y
+CONFIG_OPTIMIZE_INLINING=y
+CONFIG_SLOB=y
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 22874d7cf2c0..52cb04c993b7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -365,13 +365,14 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs,
 					struct task_struct *tsk)
 {
 	if (is_spread_page(cs))
-		tsk->flags |= PF_SPREAD_PAGE;
+		task_set_spread_page(tsk);
 	else
-		tsk->flags &= ~PF_SPREAD_PAGE;
+		task_clear_spread_page(tsk);
+
 	if (is_spread_slab(cs))
-		tsk->flags |= PF_SPREAD_SLAB;
+		task_set_spread_slab(tsk);
 	else
-		tsk->flags &= ~PF_SPREAD_SLAB;
+		task_clear_spread_slab(tsk);
 }
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f9c1ed002dbc..963bf139e2b2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1524,6 +1524,11 @@ retry:
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -1967,6 +1972,11 @@ retry:
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -7938,8 +7948,10 @@ int perf_event_init_task(struct task_struct *child)
 
 	for_each_task_context_nr(ctxn) {
 		ret = perf_event_init_context(child, ctxn);
-		if (ret)
+		if (ret) {
+			perf_event_free_task(child);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/kernel/fork.c b/kernel/fork.c
index 0cf9cdb6e491..a91e47d86de2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1360,7 +1360,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_policy;
 	retval = audit_alloc(p);
 	if (retval)
-		goto bad_fork_cleanup_policy;
+		goto bad_fork_cleanup_perf;
 	/* copy all the process information */
 	shm_init_task(p);
 	retval = copy_semundo(clone_flags, p);
@@ -1566,8 +1566,9 @@ bad_fork_cleanup_semundo:
 	exit_sem(p);
 bad_fork_cleanup_audit:
 	audit_free(p);
-bad_fork_cleanup_policy:
+bad_fork_cleanup_perf:
 	perf_event_free_task(p);
+bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
diff --git a/kernel/futex.c b/kernel/futex.c
index d3a9d946d0b7..815d7af2ffe8 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2592,6 +2592,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * shared futexes. We need to compare the keys:
 	 */
 	if (match_futex(&q.key, &key2)) {
+		queue_unlock(hb);
 		ret = -EINVAL;
 		goto out_put_keys;
 	}
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index d04ce8ac4399..cf66c5c8458e 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -35,7 +35,7 @@ config GCOV_KERNEL
 config GCOV_PROFILE_ALL
 	bool "Profile entire Kernel"
 	depends on GCOV_KERNEL
-	depends on SUPERH || S390 || X86 || PPC || MICROBLAZE
+	depends on SUPERH || S390 || X86 || PPC || MICROBLAZE || ARM
 	default n
 	---help---
 	This options activates profiling for the entire kernel.
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index 1ef0606797c9..d5d0f7345c54 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -38,7 +38,7 @@ static int devm_irq_match(struct device *dev, void *res, void *data)
  *
  *	Except for the extra @dev argument, this function takes the
  *	same arguments and performs the same function as
- *	request_irq().  IRQs requested with this function will be
+ *	request_threaded_irq().  IRQs requested with this function will be
  *	automatically freed on driver detach.
  *
  *	If an IRQ allocated with this function needs to be freed
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index e30ac0fe61c3..0aa69ea1d8fd 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -44,11 +44,12 @@ static long kptr_obfuscate(long v, int type)
  */
 static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
 {
-	long ret;
+	long t1, t2;
 
-	ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);
+	t1 = kptr_obfuscate((long)v1, type);
+	t2 = kptr_obfuscate((long)v2, type);
 
-	return (ret < 0) | ((ret > 0) << 1);
+	return (t1 < t2) | ((t1 > t2) << 1);
 }
 
 /* The caller must have pinned the task */
diff --git a/kernel/module.c b/kernel/module.c
index 03214bd288e9..65586ffa0c98 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -135,7 +135,7 @@ static int param_set_bool_enable_only(const char *val,
 }
 
 static const struct kernel_param_ops param_ops_bool_enable_only = {
-	.flags = KERNEL_PARAM_FL_NOARG,
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_bool_enable_only,
 	.get = param_get_bool,
 };
@@ -3388,7 +3388,7 @@ static inline int is_arm_mapping_symbol(const char *str)
 {
 	if (str[0] == '.' && str[1] == 'L')
 		return true;
-	return str[0] == '$' && strchr("atd", str[1])
+	return str[0] == '$' && strchr("axtd", str[1])
 	       && (str[2] == '\0' || str[2] == '.');
 }
 
diff --git a/kernel/params.c b/kernel/params.c
index 34f527023794..041b5899d5e2 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -83,6 +83,15 @@ bool parameq(const char *a, const char *b)
 	return parameqn(a, b, strlen(a)+1);
 }
 
+static void param_check_unsafe(const struct kernel_param *kp)
+{
+	if (kp->flags & KERNEL_PARAM_FL_UNSAFE) {
+		pr_warn("Setting dangerous option %s - tainting kernel\n",
+			kp->name);
+		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+	}
+}
+
 static int parse_one(char *param,
 		     char *val,
 		     const char *doing,
@@ -104,11 +113,12 @@ static int parse_one(char *param,
 				return 0;
 			/* No one handled NULL, so do it here. */
 			if (!val &&
-			    !(params[i].ops->flags & KERNEL_PARAM_FL_NOARG))
+			    !(params[i].ops->flags & KERNEL_PARAM_OPS_FL_NOARG))
 				return -EINVAL;
 			pr_debug("handling %s with %p\n", param,
 				params[i].ops->set);
 			mutex_lock(&param_lock);
+			param_check_unsafe(&params[i]);
 			err = params[i].ops->set(val, &params[i]);
 			mutex_unlock(&param_lock);
 			return err;
@@ -318,7 +328,7 @@ int param_get_bool(char *buffer, const struct kernel_param *kp)
 EXPORT_SYMBOL(param_get_bool);
 
 struct kernel_param_ops param_ops_bool = {
-	.flags = KERNEL_PARAM_FL_NOARG,
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_bool,
 	.get = param_get_bool,
 };
@@ -369,7 +379,7 @@ int param_set_bint(const char *val, const struct kernel_param *kp)
 EXPORT_SYMBOL(param_set_bint);
 
 struct kernel_param_ops param_ops_bint = {
-	.flags = KERNEL_PARAM_FL_NOARG,
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_bint,
 	.get = param_get_int,
 };
@@ -552,6 +562,7 @@ static ssize_t param_attr_store(struct module_attribute *mattr,
 		return -EPERM;
 
 	mutex_lock(&param_lock);
+	param_check_unsafe(attribute->param);
 	err = attribute->param->ops->set(buf, attribute->param);
 	mutex_unlock(&param_lock);
 	if (!err)
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index c4b8093c80b3..f1604d8cf489 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -725,14 +725,6 @@ static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn)
 	clear_bit(bit, addr);
 }
 
-static void memory_bm_clear_current(struct memory_bitmap *bm)
-{
-	int bit;
-
-	bit = max(bm->cur.node_bit - 1, 0);
-	clear_bit(bit, bm->cur.node->data);
-}
-
 static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
 	void *addr;
@@ -1341,35 +1333,23 @@ static struct memory_bitmap copy_bm;
 
 void swsusp_free(void)
 {
-	unsigned long fb_pfn, fr_pfn;
-
-	memory_bm_position_reset(forbidden_pages_map);
-	memory_bm_position_reset(free_pages_map);
-
-loop:
-	fr_pfn = memory_bm_next_pfn(free_pages_map);
-	fb_pfn = memory_bm_next_pfn(forbidden_pages_map);
-
-	/*
-	 * Find the next bit set in both bitmaps. This is guaranteed to
-	 * terminate when fb_pfn == fr_pfn == BM_END_OF_MAP.
-	 */
-	do {
-		if (fb_pfn < fr_pfn)
-			fb_pfn = memory_bm_next_pfn(forbidden_pages_map);
-		if (fr_pfn < fb_pfn)
-			fr_pfn = memory_bm_next_pfn(free_pages_map);
-	} while (fb_pfn != fr_pfn);
-
-	if (fr_pfn != BM_END_OF_MAP && pfn_valid(fr_pfn)) {
-		struct page *page = pfn_to_page(fr_pfn);
+	struct zone *zone;
+	unsigned long pfn, max_zone_pfn;
 
-		memory_bm_clear_current(forbidden_pages_map);
-		memory_bm_clear_current(free_pages_map);
-		__free_page(page);
-		goto loop;
+	for_each_populated_zone(zone) {
+		max_zone_pfn = zone_end_pfn(zone);
+		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
+			if (pfn_valid(pfn)) {
+				struct page *page = pfn_to_page(pfn);
+
+				if (swsusp_page_is_forbidden(page) &&
+				    swsusp_page_is_free(page)) {
+					swsusp_unset_page_forbidden(page);
+					swsusp_unset_page_free(page);
+					__free_page(page);
+				}
+			}
 	}
-
 	nr_copy_pages = 0;
 	nr_meta_pages = 0;
 	restore_pblist = NULL;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index e04c455a0e38..1ce770687ea8 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1665,15 +1665,15 @@ asmlinkage int vprintk_emit(int facility, int level,
 	raw_spin_lock(&logbuf_lock);
 	logbuf_cpu = this_cpu;
 
-	if (recursion_bug) {
+	if (unlikely(recursion_bug)) {
 		static const char recursion_msg[] =
 			"BUG: recent printk recursion!";
 
 		recursion_bug = 0;
-		text_len = strlen(recursion_msg);
 		/* emit KERN_CRIT message */
 		printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0,
-					 NULL, 0, recursion_msg, text_len);
+					 NULL, 0, recursion_msg,
+					 strlen(recursion_msg));
 	}
 
 	/*
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 391d4ddb6f4b..d4709d481053 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -156,6 +156,9 @@ cond_syscall(sys_process_vm_writev);
 cond_syscall(compat_sys_process_vm_readv);
 cond_syscall(compat_sys_process_vm_writev);
 cond_syscall(sys_uselib);
+cond_syscall(sys_fadvise64);
+cond_syscall(sys_fadvise64_64);
+cond_syscall(sys_madvise);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index e4ba9a5a5ccb..9a4f750a2963 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -390,7 +390,6 @@ static const struct bin_table bin_net_ipv4_table[] = {
 	{ CTL_INT,	NET_TCP_MTU_PROBING,			"tcp_mtu_probing" },
 	{ CTL_INT,	NET_TCP_BASE_MSS,			"tcp_base_mss" },
 	{ CTL_INT,	NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS,	"tcp_workaround_signed_windows" },
-	{ CTL_INT,	NET_TCP_DMA_COPYBREAK,			"tcp_dma_copybreak" },
 	{ CTL_INT,	NET_TCP_SLOW_START_AFTER_IDLE,		"tcp_slow_start_after_idle" },
 	{ CTL_INT,	NET_CIPSOV4_CACHE_ENABLE,		"cipso_cache_enable" },
 	{ CTL_INT,	NET_CIPSOV4_CACHE_BUCKET_SIZE,		"cipso_cache_bucket_size" },
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 4aec4a457431..a7077d3ae52f 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -464,18 +464,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid)
 static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
 							ktime_t now)
 {
+	unsigned long flags;
 	struct k_itimer *ptr = container_of(alarm, struct k_itimer,
 						it.alarm.alarmtimer);
-	if (posix_timer_event(ptr, 0) != 0)
-		ptr->it_overrun++;
+	enum alarmtimer_restart result = ALARMTIMER_NORESTART;
+
+	spin_lock_irqsave(&ptr->it_lock, flags);
+	if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) {
+		if (posix_timer_event(ptr, 0) != 0)
+			ptr->it_overrun++;
+	}
 
 	/* Re-add periodic timers */
 	if (ptr->it.alarm.interval.tv64) {
 		ptr->it_overrun += alarm_forward(alarm, now,
 						ptr->it.alarm.interval);
-		return ALARMTIMER_RESTART;
+		result = ALARMTIMER_RESTART;
 	}
-	return ALARMTIMER_NORESTART;
+	spin_unlock_irqrestore(&ptr->it_lock, flags);
+
+	return result;
 }
 
 /**
@@ -541,18 +549,22 @@ static int alarm_timer_create(struct k_itimer *new_timer)
  * @new_timer: k_itimer pointer
  * @cur_setting: itimerspec data to fill
  *
- * Copies the itimerspec data out from the k_itimer
+ * Copies out the current itimerspec data
  */
 static void alarm_timer_get(struct k_itimer *timr,
 				struct itimerspec *cur_setting)
 {
-	memset(cur_setting, 0, sizeof(struct itimerspec));
+	ktime_t relative_expiry_time =
+		alarm_expires_remaining(&(timr->it.alarm.alarmtimer));
+
+	if (ktime_to_ns(relative_expiry_time) > 0) {
+		cur_setting->it_value = ktime_to_timespec(relative_expiry_time);
+	} else {
+		cur_setting->it_value.tv_sec = 0;
+		cur_setting->it_value.tv_nsec = 0;
+	}
 
-	cur_setting->it_interval =
-			ktime_to_timespec(timr->it.alarm.interval);
-	cur_setting->it_value =
-		ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires);
-	return;
+	cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval);
 }
 
 /**
diff --git a/kernel/time/time.c b/kernel/time/time.c
index f0294ba14634..a9ae20fb0b11 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -559,17 +559,20 @@ EXPORT_SYMBOL(usecs_to_jiffies);
  * that a remainder subtract here would not do the right thing as the
  * resolution values don't fall on second boundries.  I.e. the line:
  * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
  *
  * Rather, we just shift the bits off the right.
  *
  * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
  * value to a scaled second value.
  */
-unsigned long
-timespec_to_jiffies(const struct timespec *value)
+static unsigned long
+__timespec_to_jiffies(unsigned long sec, long nsec)
 {
-	unsigned long sec = value->tv_sec;
-	long nsec = value->tv_nsec + TICK_NSEC - 1;
+	nsec = nsec + TICK_NSEC - 1;
 
 	if (sec >= MAX_SEC_IN_JIFFIES){
 		sec = MAX_SEC_IN_JIFFIES;
@@ -580,6 +583,13 @@ timespec_to_jiffies(const struct timespec *value)
 		 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 
 }
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+	return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
 EXPORT_SYMBOL(timespec_to_jiffies);
 
 void
@@ -596,31 +606,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
-/* Same for "timeval"
- *
- * Well, almost.  The problem here is that the real system resolution is
- * in nanoseconds and the value being converted is in micro seconds.
- * Also for some machines (those that use HZ = 1024, in-particular),
- * there is a LARGE error in the tick size in microseconds.
-
- * The solution we use is to do the rounding AFTER we convert the
- * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
- * Instruction wise, this should cost only an additional add with carry
- * instruction above the way it was done above.
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
+ *
+ * We could instead round in the intermediate scaled representation
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
+ * perilous: the scaling introduces a small positive error, which
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
+ * units to the intermediate before shifting) leads to accidental
+ * overflow and overestimates.
+ *
+ * At the cost of one additional multiplication by a constant, just
+ * use the timespec implementation.
  */
 unsigned long
 timeval_to_jiffies(const struct timeval *value)
 {
-	unsigned long sec = value->tv_sec;
-	long usec = value->tv_usec;
-
-	if (sec >= MAX_SEC_IN_JIFFIES){
-		sec = MAX_SEC_IN_JIFFIES;
-		usec = 0;
-	}
-	return (((u64)sec * SEC_CONVERSION) +
-		(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
-		 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+	return __timespec_to_jiffies(value->tv_sec,
+				     value->tv_usec * NSEC_PER_USEC);
 }
 EXPORT_SYMBOL(timeval_to_jiffies);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b38fb2b9e237..2d75c94ae87d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3359,7 +3359,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 	iter->head = cpu_buffer->reader_page->read;
 
 	iter->cache_reader_page = iter->head_page;
-	iter->cache_read = iter->head;
+	iter->cache_read = cpu_buffer->read;
 
 	if (iter->head)
 		iter->read_stamp = cpu_buffer->read_stamp;
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-10-01 16:27:02 +0000