summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile12
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/fork.c3
-rw-r--r--kernel/kcov.c431
-rw-r--r--kernel/locking/Makefile3
-rw-r--r--kernel/rcu/Makefile4
-rw-r--r--kernel/sched/Makefile4
-rw-r--r--kernel/sched/deadline.c62
-rw-r--r--kernel/sched/rt.c8
-rw-r--r--kernel/trace/trace.c29
10 files changed, 531 insertions, 27 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 53abf008ecb3..2dea801370f2 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -19,6 +19,17 @@ CFLAGS_REMOVE_cgroup-debug.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_irq_work.o = $(CC_FLAGS_FTRACE)
endif
+# Prevents flicker of uninteresting __do_softirq()/__local_bh_disable_ip()
+# in coverage traces.
+KCOV_INSTRUMENT_softirq.o := n
+# These are called from save_stack_trace() on slub debug path,
+# and produce insane amounts of uninteresting coverage.
+KCOV_INSTRUMENT_module.o := n
+KCOV_INSTRUMENT_extable.o := n
+# Don't self-instrument.
+KCOV_INSTRUMENT_kcov.o := n
+KASAN_SANITIZE_kcov.o := n
+
# cond_syscall is currently not LTO compatible
CFLAGS_sys_ni.o = $(DISABLE_LTO)
@@ -69,6 +80,7 @@ obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o audit_fsnotify.o
obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
obj-$(CONFIG_GCOV_KERNEL) += gcov/
+obj-$(CONFIG_KCOV) += kcov.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_KGDB) += debug/
obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
diff --git a/kernel/exit.c b/kernel/exit.c
index d8a12cc06aee..6aebd44b3a9b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -53,6 +53,7 @@
#include <linux/oom.h>
#include <linux/writeback.h>
#include <linux/shm.h>
+#include <linux/kcov.h>
#include "sched/tune.h"
@@ -669,6 +670,7 @@ void do_exit(long code)
TASKS_RCU(int tasks_rcu_i);
profile_task_exit(tsk);
+ kcov_task_exit(tsk);
WARN_ON(blk_needs_flush_plug(tsk));
diff --git a/kernel/fork.c b/kernel/fork.c
index 1d168ba55118..fd49017ad521 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -76,6 +76,7 @@
#include <linux/aio.h>
#include <linux/compiler.h>
#include <linux/sysctl.h>
+#include <linux/kcov.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -389,6 +390,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
account_kernel_stack(stack, 1);
+ kcov_task_init(tsk);
+
return tsk;
free_stack:
diff --git a/kernel/kcov.c b/kernel/kcov.c
new file mode 100644
index 000000000000..5813e9375a93
--- /dev/null
+++ b/kernel/kcov.c
@@ -0,0 +1,431 @@
+#define pr_fmt(fmt) "kcov: " fmt
+
+#define DISABLE_BRANCH_PROFILING
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/preempt.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/kcov.h>
+#include <asm/setup.h>
+
+/* Number of 64-bit words written per one comparison: */
+#define KCOV_WORDS_PER_CMP 4
+
+/*
+ * kcov descriptor (one per opened debugfs file).
+ * State transitions of the descriptor:
+ * - initial state after open()
+ * - then there must be a single ioctl(KCOV_INIT_TRACE) call
+ * - then, mmap() call (several calls are allowed but not useful)
+ * - then, ioctl(KCOV_ENABLE, arg), where arg is
+ * KCOV_TRACE_PC - to trace only the PCs
+ * or
+ * KCOV_TRACE_CMP - to trace only the comparison operands
+ * - then, ioctl(KCOV_DISABLE) to disable the task.
+ * Enabling/disabling ioctls can be repeated (only one task a time allowed).
+ */
+struct kcov {
+ /*
+ * Reference counter. We keep one for:
+ * - opened file descriptor
+ * - task with enabled coverage (we can't unwire it from another task)
+ */
+ atomic_t refcount;
+ /* The lock protects mode, size, area and t. */
+ spinlock_t lock;
+ enum kcov_mode mode;
+ /* Size of arena (in long's for KCOV_MODE_TRACE). */
+ unsigned size;
+ /* Coverage buffer shared with user space. */
+ void *area;
+ /* Task for which we collect coverage, or NULL. */
+ struct task_struct *t;
+};
+
+static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
+{
+ enum kcov_mode mode;
+
+ /*
+ * We are interested in code coverage as a function of a syscall inputs,
+ * so we ignore code executed in interrupts.
+ */
+ if (!in_task())
+ return false;
+ mode = READ_ONCE(t->kcov_mode);
+ /*
+ * There is some code that runs in interrupts but for which
+ * in_interrupt() returns false (e.g. preempt_schedule_irq()).
+ * READ_ONCE()/barrier() effectively provides load-acquire wrt
+ * interrupts, there are paired barrier()/WRITE_ONCE() in
+ * kcov_ioctl_locked().
+ */
+ barrier();
+ return mode == needed_mode;
+}
+
+static unsigned long canonicalize_ip(unsigned long ip)
+{
+#ifdef CONFIG_RANDOMIZE_BASE
+ ip -= kaslr_offset();
+#endif
+ return ip;
+}
+
+/*
+ * Entry point from instrumented code.
+ * This is called once per basic-block/edge.
+ */
+void notrace __sanitizer_cov_trace_pc(void)
+{
+ struct task_struct *t;
+ unsigned long *area;
+ unsigned long ip = canonicalize_ip(_RET_IP_);
+ unsigned long pos;
+
+ t = current;
+ if (!check_kcov_mode(KCOV_MODE_TRACE_PC, t))
+ return;
+
+ area = t->kcov_area;
+ /* The first 64-bit word is the number of subsequent PCs. */
+ pos = READ_ONCE(area[0]) + 1;
+ if (likely(pos < t->kcov_size)) {
+ area[pos] = ip;
+ WRITE_ONCE(area[0], pos);
+ }
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_pc);
+
+#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
+static void write_comp_data(u64 type, u64 arg1, u64 arg2, u64 ip)
+{
+ struct task_struct *t;
+ u64 *area;
+ u64 count, start_index, end_pos, max_pos;
+
+ t = current;
+ if (!check_kcov_mode(KCOV_MODE_TRACE_CMP, t))
+ return;
+
+ ip = canonicalize_ip(ip);
+
+ /*
+ * We write all comparison arguments and types as u64.
+ * The buffer was allocated for t->kcov_size unsigned longs.
+ */
+ area = (u64 *)t->kcov_area;
+ max_pos = t->kcov_size * sizeof(unsigned long);
+
+ count = READ_ONCE(area[0]);
+
+ /* Every record is KCOV_WORDS_PER_CMP 64-bit words. */
+ start_index = 1 + count * KCOV_WORDS_PER_CMP;
+ end_pos = (start_index + KCOV_WORDS_PER_CMP) * sizeof(u64);
+ if (likely(end_pos <= max_pos)) {
+ area[start_index] = type;
+ area[start_index + 1] = arg1;
+ area[start_index + 2] = arg2;
+ area[start_index + 3] = ip;
+ WRITE_ONCE(area[0], count + 1);
+ }
+}
+
+void notrace __sanitizer_cov_trace_cmp1(u8 arg1, u8 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(0), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp1);
+
+void notrace __sanitizer_cov_trace_cmp2(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(1), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp2);
+
+void notrace __sanitizer_cov_trace_cmp4(u32 arg1, u32 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(2), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp4);
+
+void notrace __sanitizer_cov_trace_cmp8(u64 arg1, u64 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(3), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp8);
+
+void notrace __sanitizer_cov_trace_const_cmp1(u8 arg1, u8 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(0) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp1);
+
+void notrace __sanitizer_cov_trace_const_cmp2(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(1) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp2);
+
+void notrace __sanitizer_cov_trace_const_cmp4(u32 arg1, u32 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(2) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp4);
+
+void notrace __sanitizer_cov_trace_const_cmp8(u64 arg1, u64 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(3) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp8);
+
+void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases)
+{
+ u64 i;
+ u64 count = cases[0];
+ u64 size = cases[1];
+ u64 type = KCOV_CMP_CONST;
+
+ switch (size) {
+ case 8:
+ type |= KCOV_CMP_SIZE(0);
+ break;
+ case 16:
+ type |= KCOV_CMP_SIZE(1);
+ break;
+ case 32:
+ type |= KCOV_CMP_SIZE(2);
+ break;
+ case 64:
+ type |= KCOV_CMP_SIZE(3);
+ break;
+ default:
+ return;
+ }
+ for (i = 0; i < count; i++)
+ write_comp_data(type, cases[i + 2], val, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_switch);
+#endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */
+
+static void kcov_get(struct kcov *kcov)
+{
+ atomic_inc(&kcov->refcount);
+}
+
+static void kcov_put(struct kcov *kcov)
+{
+ if (atomic_dec_and_test(&kcov->refcount)) {
+ vfree(kcov->area);
+ kfree(kcov);
+ }
+}
+
+void kcov_task_init(struct task_struct *t)
+{
+ t->kcov_mode = KCOV_MODE_DISABLED;
+ t->kcov_size = 0;
+ t->kcov_area = NULL;
+ t->kcov = NULL;
+}
+
+void kcov_task_exit(struct task_struct *t)
+{
+ struct kcov *kcov;
+
+ kcov = t->kcov;
+ if (kcov == NULL)
+ return;
+ spin_lock(&kcov->lock);
+ if (WARN_ON(kcov->t != t)) {
+ spin_unlock(&kcov->lock);
+ return;
+ }
+ /* Just to not leave dangling references behind. */
+ kcov_task_init(t);
+ kcov->t = NULL;
+ kcov->mode = KCOV_MODE_INIT;
+ spin_unlock(&kcov->lock);
+ kcov_put(kcov);
+}
+
+static int kcov_mmap(struct file *filep, struct vm_area_struct *vma)
+{
+ int res = 0;
+ void *area;
+ struct kcov *kcov = vma->vm_file->private_data;
+ unsigned long size, off;
+ struct page *page;
+
+ area = vmalloc_user(vma->vm_end - vma->vm_start);
+ if (!area)
+ return -ENOMEM;
+
+ spin_lock(&kcov->lock);
+ size = kcov->size * sizeof(unsigned long);
+ if (kcov->mode != KCOV_MODE_INIT || vma->vm_pgoff != 0 ||
+ vma->vm_end - vma->vm_start != size) {
+ res = -EINVAL;
+ goto exit;
+ }
+ if (!kcov->area) {
+ kcov->area = area;
+ vma->vm_flags |= VM_DONTEXPAND;
+ spin_unlock(&kcov->lock);
+ for (off = 0; off < size; off += PAGE_SIZE) {
+ page = vmalloc_to_page(kcov->area + off);
+ if (vm_insert_page(vma, vma->vm_start + off, page))
+ WARN_ONCE(1, "vm_insert_page() failed");
+ }
+ return 0;
+ }
+exit:
+ spin_unlock(&kcov->lock);
+ vfree(area);
+ return res;
+}
+
+static int kcov_open(struct inode *inode, struct file *filep)
+{
+ struct kcov *kcov;
+
+ kcov = kzalloc(sizeof(*kcov), GFP_KERNEL);
+ if (!kcov)
+ return -ENOMEM;
+ kcov->mode = KCOV_MODE_DISABLED;
+ atomic_set(&kcov->refcount, 1);
+ spin_lock_init(&kcov->lock);
+ filep->private_data = kcov;
+ return nonseekable_open(inode, filep);
+}
+
+static int kcov_close(struct inode *inode, struct file *filep)
+{
+ kcov_put(filep->private_data);
+ return 0;
+}
+
+static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
+ unsigned long arg)
+{
+ struct task_struct *t;
+ unsigned long size, unused;
+
+ switch (cmd) {
+ case KCOV_INIT_TRACE:
+ /*
+ * Enable kcov in trace mode and setup buffer size.
+ * Must happen before anything else.
+ */
+ if (kcov->mode != KCOV_MODE_DISABLED)
+ return -EBUSY;
+ /*
+ * Size must be at least 2 to hold current position and one PC.
+ * Later we allocate size * sizeof(unsigned long) memory,
+ * that must not overflow.
+ */
+ size = arg;
+ if (size < 2 || size > INT_MAX / sizeof(unsigned long))
+ return -EINVAL;
+ kcov->size = size;
+ kcov->mode = KCOV_MODE_INIT;
+ return 0;
+ case KCOV_ENABLE:
+ /*
+ * Enable coverage for the current task.
+ * At this point user must have been enabled trace mode,
+ * and mmapped the file. Coverage collection is disabled only
+ * at task exit or voluntary by KCOV_DISABLE. After that it can
+ * be enabled for another task.
+ */
+ if (kcov->mode != KCOV_MODE_INIT || !kcov->area)
+ return -EINVAL;
+ if (kcov->t != NULL)
+ return -EBUSY;
+ if (arg == KCOV_TRACE_PC)
+ kcov->mode = KCOV_MODE_TRACE_PC;
+ else if (arg == KCOV_TRACE_CMP)
+#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
+ kcov->mode = KCOV_MODE_TRACE_CMP;
+#else
+ return -ENOTSUPP;
+#endif
+ else
+ return -EINVAL;
+ t = current;
+ /* Cache in task struct for performance. */
+ t->kcov_size = kcov->size;
+ t->kcov_area = kcov->area;
+ /* See comment in check_kcov_mode(). */
+ barrier();
+ WRITE_ONCE(t->kcov_mode, kcov->mode);
+ t->kcov = kcov;
+ kcov->t = t;
+ /* This is put either in kcov_task_exit() or in KCOV_DISABLE. */
+ kcov_get(kcov);
+ return 0;
+ case KCOV_DISABLE:
+ /* Disable coverage for the current task. */
+ unused = arg;
+ if (unused != 0 || current->kcov != kcov)
+ return -EINVAL;
+ t = current;
+ if (WARN_ON(kcov->t != t))
+ return -EINVAL;
+ kcov_task_init(t);
+ kcov->t = NULL;
+ kcov->mode = KCOV_MODE_INIT;
+ kcov_put(kcov);
+ return 0;
+ default:
+ return -ENOTTY;
+ }
+}
+
+static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
+{
+ struct kcov *kcov;
+ int res;
+
+ kcov = filep->private_data;
+ spin_lock(&kcov->lock);
+ res = kcov_ioctl_locked(kcov, cmd, arg);
+ spin_unlock(&kcov->lock);
+ return res;
+}
+
+static const struct file_operations kcov_fops = {
+ .open = kcov_open,
+ .unlocked_ioctl = kcov_ioctl,
+ .compat_ioctl = kcov_ioctl,
+ .mmap = kcov_mmap,
+ .release = kcov_close,
+};
+
+static int __init kcov_init(void)
+{
+ if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) {
+ pr_err("failed to create kcov in debugfs\n");
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+device_initcall(kcov_init);
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 8e96f6cc2a4a..31322a4275cd 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,3 +1,6 @@
+# Any varying coverage in these files is non-deterministic
+# and is generally not a function of system call inputs.
+KCOV_INSTRUMENT := n
obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 61a16569ffbf..032b2c015beb 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,3 +1,7 @@
+# Any varying coverage in these files is non-deterministic
+# and is generally not a function of system call inputs.
+KCOV_INSTRUMENT := n
+
obj-y += update.o sync.o
obj-$(CONFIG_SRCU) += srcu.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 64464b44a265..7dde1b9918e4 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -2,6 +2,10 @@ ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE)
endif
+# These files are disabled because they produce non-interesting flaky coverage
+# that is not a function of syscall inputs. E.g. involuntary context switches.
+KCOV_INSTRUMENT := n
+
ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
# needed for x86 only. Why this used to be enabled for all architectures is beyond
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index bb22bcf499f8..e7b377d91043 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -463,13 +463,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
*
* This function returns true if:
*
- * runtime / (deadline - t) > dl_runtime / dl_period ,
+ * runtime / (deadline - t) > dl_runtime / dl_deadline ,
*
* IOW we can't recycle current parameters.
*
- * Notice that the bandwidth check is done against the period. For
+ * Notice that the bandwidth check is done against the deadline. For
* task with deadline equal to period this is the same of using
- * dl_deadline instead of dl_period in the equation above.
+ * dl_period instead of dl_deadline in the equation above.
*/
static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
struct sched_dl_entity *pi_se, u64 t)
@@ -494,7 +494,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
* of anything below microseconds resolution is actually fiction
* (but still we want to give the user that illusion >;).
*/
- left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+ left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
right = ((dl_se->deadline - t) >> DL_SCALE) *
(pi_se->dl_runtime >> DL_SCALE);
@@ -535,10 +535,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
}
}
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+ return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
+}
+
/*
* If the entity depleted all its runtime, and if we want it to sleep
* while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
* and try to activate it.
*
* Notice that it is important for the caller to know if the timer
@@ -560,7 +565,7 @@ static int start_dl_timer(struct task_struct *p)
* that it is actually coming from rq->clock and not from
* hrtimer's time base reading.
*/
- act = ns_to_ktime(dl_se->deadline);
+ act = ns_to_ktime(dl_next_period(dl_se));
now = hrtimer_cb_get_time(timer);
delta = ktime_to_ns(now) - rq_clock(rq);
act = ktime_add_ns(act, delta);
@@ -724,6 +729,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
timer->function = dl_task_timer;
}
+/*
+ * During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS
+ * cannot use the runtime, and so it replenishes the task. This rule
+ * works fine for implicit deadline tasks (deadline == period), and the
+ * CBS was designed for implicit deadline tasks. However, a task with
+ * constrained deadline (deadine < period) might be awakened after the
+ * deadline, but before the next period. In this case, replenishing the
+ * task would allow it to run for runtime / deadline. As in this case
+ * deadline < period, CBS enables a task to run for more than the
+ * runtime / period. In a very loaded system, this can cause a domino
+ * effect, making other tasks miss their deadlines.
+ *
+ * To avoid this problem, in the activation of a constrained deadline
+ * task after the deadline but before the next period, throttle the
+ * task and set the replenishing timer to the begin of the next period,
+ * unless it is boosted.
+ */
+static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+
+ if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+ dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
+ if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+ return;
+ dl_se->dl_throttled = 1;
+ }
+}
+
static
int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
{
@@ -1016,6 +1052,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
__dequeue_dl_entity(dl_se);
}
+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+ return dl_se->dl_deadline < dl_se->dl_period;
+}
+
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
struct task_struct *pi_task = rt_mutex_get_top_task(p);
@@ -1042,6 +1083,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
}
/*
+ * Check if a constrained deadline task was activated
+ * after the deadline but before the next period.
+ * If that is the case, the task will be throttled and
+ * the replenishment timer will be set to the next period.
+ */
+ if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+ dl_check_constrained_dl(&p->dl);
+
+ /*
* If p is throttled, we do nothing. In fact, if it exhausted
* its budget it needs a replenishment and, since it now is on
* its rq, the bandwidth timer callback (which clearly has not
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index c290db7f289a..8025828ff4e0 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2262,8 +2262,9 @@ static void pull_rt_task(struct rq *this_rq)
bool resched = false;
struct task_struct *p;
struct rq *src_rq;
+ int rt_overload_count = rt_overloaded(this_rq);
- if (likely(!rt_overloaded(this_rq)))
+ if (likely(!rt_overload_count))
return;
/*
@@ -2272,6 +2273,11 @@ static void pull_rt_task(struct rq *this_rq)
*/
smp_rmb();
+ /* If we are the only overloaded CPU do nothing */
+ if (rt_overload_count == 1 &&
+ cpumask_test_cpu(this_rq->cpu, this_rq->rd->rto_mask))
+ return;
+
#ifdef HAVE_RT_PUSH_IPI
if (sched_feat(RT_PUSH_IPI)) {
tell_cpu_to_push(this_rq);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6580ec6bc371..581650a1640e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3461,37 +3461,30 @@ static const struct file_operations show_traces_fops = {
.llseek = seq_lseek,
};
-/*
- * The tracer itself will not take this lock, but still we want
- * to provide a consistent cpumask to user-space:
- */
-static DEFINE_MUTEX(tracing_cpumask_update_lock);
-
-/*
- * Temporary storage for the character representation of the
- * CPU bitmask (and one more byte for the newline):
- */
-static char mask_str[NR_CPUS + 1];
-
static ssize_t
tracing_cpumask_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
struct trace_array *tr = file_inode(filp)->i_private;
+ char *mask_str;
int len;
- mutex_lock(&tracing_cpumask_update_lock);
+ len = snprintf(NULL, 0, "%*pb\n",
+ cpumask_pr_args(tr->tracing_cpumask)) + 1;
+ mask_str = kmalloc(len, GFP_KERNEL);
+ if (!mask_str)
+ return -ENOMEM;
- len = snprintf(mask_str, count, "%*pb\n",
+ len = snprintf(mask_str, len, "%*pb\n",
cpumask_pr_args(tr->tracing_cpumask));
if (len >= count) {
count = -EINVAL;
goto out_err;
}
- count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
+ count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
out_err:
- mutex_unlock(&tracing_cpumask_update_lock);
+ kfree(mask_str);
return count;
}
@@ -3511,8 +3504,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
if (err)
goto err_unlock;
- mutex_lock(&tracing_cpumask_update_lock);
-
local_irq_disable();
arch_spin_lock(&tr->max_lock);
for_each_tracing_cpu(cpu) {
@@ -3535,8 +3526,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
local_irq_enable();
cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
-
- mutex_unlock(&tracing_cpumask_update_lock);
free_cpumask_var(tracing_cpumask_new);
return count;
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-22 23:13:23 +0000