summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/verifier.c5
-rw-r--r--kernel/cpu.c12
-rw-r--r--kernel/crash_reserve.c3
-rw-r--r--kernel/dma/debug.c5
-rw-r--r--kernel/events/core.c31
-rw-r--r--kernel/fork.c25
-rw-r--r--kernel/irq/irqdesc.c1
-rw-r--r--kernel/jump_label.c4
-rw-r--r--kernel/kallsyms.c55
-rw-r--r--kernel/kallsyms_selftest.c22
-rw-r--r--kernel/kcov.c15
-rw-r--r--kernel/kprobes.c4
-rw-r--r--kernel/ksysfs.c7
-rw-r--r--kernel/locking/lockdep.c6
-rw-r--r--kernel/locking/qspinlock_paravirt.h2
-rw-r--r--kernel/module/main.c41
-rw-r--r--kernel/padata.c7
-rw-r--r--kernel/profile.c242
-rw-r--r--kernel/sched/core.c68
-rw-r--r--kernel/sched/cputime.c6
-rw-r--r--kernel/sched/stats.c10
-rw-r--r--kernel/task_work.c6
-rw-r--r--kernel/time/clocksource.c2
-rw-r--r--kernel/time/ntp.c9
-rw-r--r--kernel/time/tick-broadcast.c3
-rw-r--r--kernel/time/timekeeping.c2
-rw-r--r--kernel/time/timer_migration.c393
-rw-r--r--kernel/time/timer_migration.h27
-rw-r--r--kernel/trace/fgraph.c2
-rw-r--r--kernel/trace/preemptirq_delay_test.c2
-rw-r--r--kernel/trace/ring_buffer.c12
-rw-r--r--kernel/trace/trace.c2
-rw-r--r--kernel/trace/trace.h23
-rw-r--r--kernel/trace/trace_events.c41
-rw-r--r--kernel/trace/trace_events_hist.c4
-rw-r--r--kernel/trace/trace_events_inject.c2
-rw-r--r--kernel/trace/trace_events_trigger.c6
-rw-r--r--kernel/trace/tracing_map.c6
38 files changed, 481 insertions, 632 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4cb5441ad75f..d8520095ca03 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -16884,8 +16884,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
spi = i / BPF_REG_SIZE;
if (exact != NOT_EXACT &&
- old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
- cur->stack[spi].slot_type[i % BPF_REG_SIZE])
+ (i >= cur->allocated_stack ||
+ old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
+ cur->stack[spi].slot_type[i % BPF_REG_SIZE]))
return false;
if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 1209ddaec026..b1fd2a3db91a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2689,6 +2689,16 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
return ret;
}
+/**
+ * Check if the core a CPU belongs to is online
+ */
+#if !defined(topology_is_core_online)
+static inline bool topology_is_core_online(unsigned int cpu)
+{
+ return true;
+}
+#endif
+
int cpuhp_smt_enable(void)
{
int cpu, ret = 0;
@@ -2699,7 +2709,7 @@ int cpuhp_smt_enable(void)
/* Skip online CPUs and CPUs on offline nodes */
if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
continue;
- if (!cpu_smt_thread_allowed(cpu))
+ if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu))
continue;
ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
if (ret)
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index d3b4cd12bdd1..64d44a52c011 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -423,7 +423,8 @@ retry:
if (high && search_end == CRASH_ADDR_HIGH_MAX) {
search_end = CRASH_ADDR_LOW_MAX;
search_base = 0;
- goto retry;
+ if (search_end != CRASH_ADDR_HIGH_MAX)
+ goto retry;
}
pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
crash_size);
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index a6e3792b15f8..d570535342cb 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -416,8 +416,11 @@ static unsigned long long phys_addr(struct dma_debug_entry *entry)
* dma_active_cacheline entry to track per event. dma_map_sg(), on the
* other hand, consumes a single dma_debug_entry, but inserts 'nents'
* entries into the tree.
+ *
+ * Use __GFP_NOWARN because the printk from an OOM, to netconsole, could end
+ * up right back in the DMA debugging code, leading to a deadlock.
*/
-static RADIX_TREE(dma_active_cacheline, GFP_ATOMIC);
+static RADIX_TREE(dma_active_cacheline, GFP_ATOMIC | __GFP_NOWARN);
static DEFINE_SPINLOCK(radix_lock);
#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0d9c4985b0aa..c973e3c11e03 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9328,21 +9328,19 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
int i;
- if (prog->aux->func_cnt == 0) {
- perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
- (u64)(unsigned long)prog->bpf_func,
- prog->jited_len, unregister,
- prog->aux->ksym.name);
- } else {
- for (i = 0; i < prog->aux->func_cnt; i++) {
- struct bpf_prog *subprog = prog->aux->func[i];
-
- perf_event_ksymbol(
- PERF_RECORD_KSYMBOL_TYPE_BPF,
- (u64)(unsigned long)subprog->bpf_func,
- subprog->jited_len, unregister,
- subprog->aux->ksym.name);
- }
+ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
+ (u64)(unsigned long)prog->bpf_func,
+ prog->jited_len, unregister,
+ prog->aux->ksym.name);
+
+ for (i = 1; i < prog->aux->func_cnt; i++) {
+ struct bpf_prog *subprog = prog->aux->func[i];
+
+ perf_event_ksymbol(
+ PERF_RECORD_KSYMBOL_TYPE_BPF,
+ (u64)(unsigned long)subprog->bpf_func,
+ subprog->jited_len, unregister,
+ subprog->aux->ksym.name);
}
}
@@ -9708,7 +9706,8 @@ static int __perf_event_overflow(struct perf_event *event,
ret = __perf_event_account_interrupt(event, throttle);
- if (event->prog && !bpf_overflow_handler(event, data, regs))
+ if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT &&
+ !bpf_overflow_handler(event, data, regs))
return ret;
/*
diff --git a/kernel/fork.c b/kernel/fork.c
index cc760491f201..18bdc87209d0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2053,11 +2053,24 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
*/
int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
{
- bool thread = flags & PIDFD_THREAD;
-
- if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID))
+ if (!pid)
return -EINVAL;
+ scoped_guard(rcu) {
+ struct task_struct *tsk;
+
+ if (flags & PIDFD_THREAD)
+ tsk = pid_task(pid, PIDTYPE_PID);
+ else
+ tsk = pid_task(pid, PIDTYPE_TGID);
+ if (!tsk)
+ return -EINVAL;
+
+ /* Don't create pidfds for kernel threads for now. */
+ if (tsk->flags & PF_KTHREAD)
+ return -EINVAL;
+ }
+
return __pidfd_prepare(pid, flags, ret);
}
@@ -2403,6 +2416,12 @@ __latent_entropy struct task_struct *copy_process(
if (clone_flags & CLONE_PIDFD) {
int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0;
+ /* Don't create pidfds for kernel threads for now. */
+ if (args->kthread) {
+ retval = -EINVAL;
+ goto bad_fork_free_pid;
+ }
+
/* Note that no task has been attached to @pid yet. */
retval = __pidfd_prepare(pid, flags, &pidfile);
if (retval < 0)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 07e99c936ba5..1dee88ba0ae4 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -530,6 +530,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
flags = IRQD_AFFINITY_MANAGED |
IRQD_MANAGED_SHUTDOWN;
}
+ flags |= IRQD_AFFINITY_SET;
mask = &affinity->mask;
node = cpu_to_node(cpumask_first(mask));
affinity++;
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 4ad5ed8adf96..6dc76b590703 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -236,7 +236,7 @@ void static_key_disable_cpuslocked(struct static_key *key)
}
jump_label_lock();
- if (atomic_cmpxchg(&key->enabled, 1, 0))
+ if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
jump_label_update(key);
jump_label_unlock();
}
@@ -289,7 +289,7 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key)
return;
guard(mutex)(&jump_label_mutex);
- if (atomic_cmpxchg(&key->enabled, 1, 0))
+ if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
jump_label_update(key);
else
WARN_ON_ONCE(!static_key_slow_try_dec(key));
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index fb2c77368d18..a9a0ca605d4a 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -160,38 +160,6 @@ unsigned long kallsyms_sym_address(int idx)
return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
}
-static void cleanup_symbol_name(char *s)
-{
- char *res;
-
- if (!IS_ENABLED(CONFIG_LTO_CLANG))
- return;
-
- /*
- * LLVM appends various suffixes for local functions and variables that
- * must be promoted to global scope as part of LTO. This can break
- * hooking of static functions with kprobes. '.' is not a valid
- * character in an identifier in C. Suffixes only in LLVM LTO observed:
- * - foo.llvm.[0-9a-f]+
- */
- res = strstr(s, ".llvm.");
- if (res)
- *res = '\0';
-
- return;
-}
-
-static int compare_symbol_name(const char *name, char *namebuf)
-{
- /* The kallsyms_seqs_of_names is sorted based on names after
- * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled.
- * To ensure correct bisection in kallsyms_lookup_names(), do
- * cleanup_symbol_name(namebuf) before comparing name and namebuf.
- */
- cleanup_symbol_name(namebuf);
- return strcmp(name, namebuf);
-}
-
static unsigned int get_symbol_seq(int index)
{
unsigned int i, seq = 0;
@@ -219,7 +187,7 @@ static int kallsyms_lookup_names(const char *name,
seq = get_symbol_seq(mid);
off = get_symbol_offset(seq);
kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
- ret = compare_symbol_name(name, namebuf);
+ ret = strcmp(name, namebuf);
if (ret > 0)
low = mid + 1;
else if (ret < 0)
@@ -236,7 +204,7 @@ static int kallsyms_lookup_names(const char *name,
seq = get_symbol_seq(low - 1);
off = get_symbol_offset(seq);
kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
- if (compare_symbol_name(name, namebuf))
+ if (strcmp(name, namebuf))
break;
low--;
}
@@ -248,7 +216,7 @@ static int kallsyms_lookup_names(const char *name,
seq = get_symbol_seq(high + 1);
off = get_symbol_offset(seq);
kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
- if (compare_symbol_name(name, namebuf))
+ if (strcmp(name, namebuf))
break;
high++;
}
@@ -407,8 +375,7 @@ static int kallsyms_lookup_buildid(unsigned long addr,
if (modbuildid)
*modbuildid = NULL;
- ret = strlen(namebuf);
- goto found;
+ return strlen(namebuf);
}
/* See if it's in a module or a BPF JITed image. */
@@ -422,8 +389,6 @@ static int kallsyms_lookup_buildid(unsigned long addr,
ret = ftrace_mod_address_lookup(addr, symbolsize,
offset, modname, namebuf);
-found:
- cleanup_symbol_name(namebuf);
return ret;
}
@@ -450,8 +415,6 @@ const char *kallsyms_lookup(unsigned long addr,
int lookup_symbol_name(unsigned long addr, char *symname)
{
- int res;
-
symname[0] = '\0';
symname[KSYM_NAME_LEN - 1] = '\0';
@@ -462,16 +425,10 @@ int lookup_symbol_name(unsigned long addr, char *symname)
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
symname, KSYM_NAME_LEN);
- goto found;
+ return 0;
}
/* See if it's in a module. */
- res = lookup_module_symbol_name(addr, symname);
- if (res)
- return res;
-
-found:
- cleanup_symbol_name(symname);
- return 0;
+ return lookup_module_symbol_name(addr, symname);
}
/* Look up a kernel symbol and return it in a text buffer. */
diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c
index 2f84896a7bcb..873f7c445488 100644
--- a/kernel/kallsyms_selftest.c
+++ b/kernel/kallsyms_selftest.c
@@ -187,31 +187,11 @@ static void test_perf_kallsyms_lookup_name(void)
stat.min, stat.max, div_u64(stat.sum, stat.real_cnt));
}
-static bool match_cleanup_name(const char *s, const char *name)
-{
- char *p;
- int len;
-
- if (!IS_ENABLED(CONFIG_LTO_CLANG))
- return false;
-
- p = strstr(s, ".llvm.");
- if (!p)
- return false;
-
- len = strlen(name);
- if (p - s != len)
- return false;
-
- return !strncmp(s, name, len);
-}
-
static int find_symbol(void *data, const char *name, unsigned long addr)
{
struct test_stat *stat = (struct test_stat *)data;
- if (strcmp(name, stat->name) == 0 ||
- (!stat->perf && match_cleanup_name(name, stat->name))) {
+ if (!strcmp(name, stat->name)) {
stat->real_cnt++;
stat->addr = addr;
diff --git a/kernel/kcov.c b/kernel/kcov.c
index f0a69d402066..274b6b7c718d 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -161,6 +161,15 @@ static void kcov_remote_area_put(struct kcov_remote_area *area,
kmsan_unpoison_memory(&area->list, sizeof(area->list));
}
+/*
+ * Unlike in_serving_softirq(), this function returns false when called during
+ * a hardirq or an NMI that happened in the softirq context.
+ */
+static inline bool in_softirq_really(void)
+{
+ return in_serving_softirq() && !in_hardirq() && !in_nmi();
+}
+
static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
{
unsigned int mode;
@@ -170,7 +179,7 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru
* so we ignore code executed in interrupts, unless we are in a remote
* coverage collection section in a softirq.
*/
- if (!in_task() && !(in_serving_softirq() && t->kcov_softirq))
+ if (!in_task() && !(in_softirq_really() && t->kcov_softirq))
return false;
mode = READ_ONCE(t->kcov_mode);
/*
@@ -849,7 +858,7 @@ void kcov_remote_start(u64 handle)
if (WARN_ON(!kcov_check_handle(handle, true, true, true)))
return;
- if (!in_task() && !in_serving_softirq())
+ if (!in_task() && !in_softirq_really())
return;
local_lock_irqsave(&kcov_percpu_data.lock, flags);
@@ -991,7 +1000,7 @@ void kcov_remote_stop(void)
int sequence;
unsigned long flags;
- if (!in_task() && !in_serving_softirq())
+ if (!in_task() && !in_softirq_really())
return;
local_lock_irqsave(&kcov_percpu_data.lock, flags);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e85de37d9e1e..da59c68df841 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1557,8 +1557,8 @@ static bool is_cfi_preamble_symbol(unsigned long addr)
if (lookup_symbol_name(addr, symbuf))
return false;
- return str_has_prefix("__cfi_", symbuf) ||
- str_has_prefix("__pfx_", symbuf);
+ return str_has_prefix(symbuf, "__cfi_") ||
+ str_has_prefix(symbuf, "__pfx_");
}
static int check_kprobe_address_safe(struct kprobe *p,
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 07fb5987b42b..1bab21b4718f 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -92,7 +92,14 @@ static ssize_t profiling_store(struct kobject *kobj,
const char *buf, size_t count)
{
int ret;
+ static DEFINE_MUTEX(lock);
+ /*
+ * We need serialization, for profile_setup() initializes prof_on
+ * value and profile_init() must not reallocate prof_buffer after
+ * once allocated.
+ */
+ guard(mutex)(&lock);
if (prof_on)
return -EEXIST;
/*
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 58c88220a478..0349f957e672 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -5936,6 +5936,9 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
if (DEBUG_LOCKS_WARN_ON(!depth))
return;
+ if (unlikely(lock->key == &__lockdep_no_track__))
+ return;
+
hlock = find_held_lock(curr, lock, depth, &i);
if (!hlock) {
print_lock_contention_bug(curr, lock, ip);
@@ -5978,6 +5981,9 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
if (DEBUG_LOCKS_WARN_ON(!depth))
return;
+ if (unlikely(lock->key == &__lockdep_no_track__))
+ return;
+
hlock = find_held_lock(curr, lock, depth, &i);
if (!hlock) {
print_lock_contention_bug(curr, lock, _RET_IP_);
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index f5a36e67b593..ac2e22502741 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -357,7 +357,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
{
struct pv_node *pn = (struct pv_node *)node;
- enum vcpu_state old = vcpu_halted;
+ u8 old = vcpu_halted;
/*
* If the vCPU is indeed halted, advance its state to match that of
* pv_wait_node(). If OTOH this fails, the vCPU was running and will
diff --git a/kernel/module/main.c b/kernel/module/main.c
index d9592195c5bb..71396e297499 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -3104,7 +3104,7 @@ static bool idempotent(struct idempotent *u, const void *cookie)
struct idempotent *existing;
bool first;
- u->ret = 0;
+ u->ret = -EINTR;
u->cookie = cookie;
init_completion(&u->complete);
@@ -3140,7 +3140,7 @@ static int idempotent_complete(struct idempotent *u, int ret)
hlist_for_each_entry_safe(pos, next, head, entry) {
if (pos->cookie != cookie)
continue;
- hlist_del(&pos->entry);
+ hlist_del_init(&pos->entry);
pos->ret = ret;
complete(&pos->complete);
}
@@ -3148,6 +3148,28 @@ static int idempotent_complete(struct idempotent *u, int ret)
return ret;
}
+/*
+ * Wait for the idempotent worker.
+ *
+ * If we get interrupted, we need to remove ourselves from the
+ * the idempotent list, and the completion may still come in.
+ *
+ * The 'idem_lock' protects against the race, and 'idem.ret' was
+ * initialized to -EINTR and is thus always the right return
+ * value even if the idempotent work then completes between
+ * the wait_for_completion and the cleanup.
+ */
+static int idempotent_wait_for_completion(struct idempotent *u)
+{
+ if (wait_for_completion_interruptible(&u->complete)) {
+ spin_lock(&idem_lock);
+ if (!hlist_unhashed(&u->entry))
+ hlist_del(&u->entry);
+ spin_unlock(&idem_lock);
+ }
+ return u->ret;
+}
+
static int init_module_from_file(struct file *f, const char __user * uargs, int flags)
{
struct load_info info = { };
@@ -3183,15 +3205,16 @@ static int idempotent_init_module(struct file *f, const char __user * uargs, int
if (!f || !(f->f_mode & FMODE_READ))
return -EBADF;
- /* See if somebody else is doing the operation? */
- if (idempotent(&idem, file_inode(f))) {
- wait_for_completion(&idem.complete);
- return idem.ret;
+ /* Are we the winners of the race and get to do this? */
+ if (!idempotent(&idem, file_inode(f))) {
+ int ret = init_module_from_file(f, uargs, flags);
+ return idempotent_complete(&idem, ret);
}
- /* Otherwise, we'll do it and complete others */
- return idempotent_complete(&idem,
- init_module_from_file(f, uargs, flags));
+ /*
+ * Somebody else won the race and is loading the module.
+ */
+ return idempotent_wait_for_completion(&idem);
}
SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
diff --git a/kernel/padata.c b/kernel/padata.c
index 53f4bc912712..0fa6c2895460 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -517,6 +517,13 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
ps.chunk_size = max(ps.chunk_size, job->min_chunk);
ps.chunk_size = roundup(ps.chunk_size, job->align);
+ /*
+ * chunk_size can be 0 if the caller sets min_chunk to 0. So force it
+ * to at least 1 to prevent divide-by-0 panic in padata_mt_helper().`
+ */
+ if (!ps.chunk_size)
+ ps.chunk_size = 1U;
+
list_for_each_entry(pw, &works, pw_list)
if (job->numa_aware) {
int old_node = atomic_read(&last_used_nid);
diff --git a/kernel/profile.c b/kernel/profile.c
index 2b775cc5c28f..1fcf1adcf4eb 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -47,30 +47,14 @@ static unsigned short int prof_shift;
int prof_on __read_mostly;
EXPORT_SYMBOL_GPL(prof_on);
-static cpumask_var_t prof_cpu_mask;
-#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS)
-static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits);
-static DEFINE_PER_CPU(int, cpu_profile_flip);
-static DEFINE_MUTEX(profile_flip_mutex);
-#endif /* CONFIG_SMP */
-
int profile_setup(char *str)
{
static const char schedstr[] = "schedule";
- static const char sleepstr[] = "sleep";
static const char kvmstr[] = "kvm";
const char *select = NULL;
int par;
- if (!strncmp(str, sleepstr, strlen(sleepstr))) {
-#ifdef CONFIG_SCHEDSTATS
- force_schedstat_enabled();
- prof_on = SLEEP_PROFILING;
- select = sleepstr;
-#else
- pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
-#endif /* CONFIG_SCHEDSTATS */
- } else if (!strncmp(str, schedstr, strlen(schedstr))) {
+ if (!strncmp(str, schedstr, strlen(schedstr))) {
prof_on = SCHED_PROFILING;
select = schedstr;
} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
@@ -114,11 +98,6 @@ int __ref profile_init(void)
buffer_bytes = prof_len*sizeof(atomic_t);
- if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
- return -ENOMEM;
-
- cpumask_copy(prof_cpu_mask, cpu_possible_mask);
-
prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN);
if (prof_buffer)
return 0;
@@ -132,195 +111,16 @@ int __ref profile_init(void)
if (prof_buffer)
return 0;
- free_cpumask_var(prof_cpu_mask);
return -ENOMEM;
}
-#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS)
-/*
- * Each cpu has a pair of open-addressed hashtables for pending
- * profile hits. read_profile() IPI's all cpus to request them
- * to flip buffers and flushes their contents to prof_buffer itself.
- * Flip requests are serialized by the profile_flip_mutex. The sole
- * use of having a second hashtable is for avoiding cacheline
- * contention that would otherwise happen during flushes of pending
- * profile hits required for the accuracy of reported profile hits
- * and so resurrect the interrupt livelock issue.
- *
- * The open-addressed hashtables are indexed by profile buffer slot
- * and hold the number of pending hits to that profile buffer slot on
- * a cpu in an entry. When the hashtable overflows, all pending hits
- * are accounted to their corresponding profile buffer slots with
- * atomic_add() and the hashtable emptied. As numerous pending hits
- * may be accounted to a profile buffer slot in a hashtable entry,
- * this amortizes a number of atomic profile buffer increments likely
- * to be far larger than the number of entries in the hashtable,
- * particularly given that the number of distinct profile buffer
- * positions to which hits are accounted during short intervals (e.g.
- * several seconds) is usually very small. Exclusion from buffer
- * flipping is provided by interrupt disablement (note that for
- * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from
- * process context).
- * The hash function is meant to be lightweight as opposed to strong,
- * and was vaguely inspired by ppc64 firmware-supported inverted
- * pagetable hash functions, but uses a full hashtable full of finite
- * collision chains, not just pairs of them.
- *
- * -- nyc
- */
-static void __profile_flip_buffers(void *unused)
-{
- int cpu = smp_processor_id();
-
- per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu);
-}
-
-static void profile_flip_buffers(void)
-{
- int i, j, cpu;
-
- mutex_lock(&profile_flip_mutex);
- j = per_cpu(cpu_profile_flip, get_cpu());
- put_cpu();
- on_each_cpu(__profile_flip_buffers, NULL, 1);
- for_each_online_cpu(cpu) {
- struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j];
- for (i = 0; i < NR_PROFILE_HIT; ++i) {
- if (!hits[i].hits) {
- if (hits[i].pc)
- hits[i].pc = 0;
- continue;
- }
- atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]);
- hits[i].hits = hits[i].pc = 0;
- }
- }
- mutex_unlock(&profile_flip_mutex);
-}
-
-static void profile_discard_flip_buffers(void)
-{
- int i, cpu;
-
- mutex_lock(&profile_flip_mutex);
- i = per_cpu(cpu_profile_flip, get_cpu());
- put_cpu();
- on_each_cpu(__profile_flip_buffers, NULL, 1);
- for_each_online_cpu(cpu) {
- struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i];
- memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit));
- }
- mutex_unlock(&profile_flip_mutex);
-}
-
-static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
-{
- unsigned long primary, secondary, flags, pc = (unsigned long)__pc;
- int i, j, cpu;
- struct profile_hit *hits;
-
- pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1);
- i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
- secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
- cpu = get_cpu();
- hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)];
- if (!hits) {
- put_cpu();
- return;
- }
- /*
- * We buffer the global profiler buffer into a per-CPU
- * queue and thus reduce the number of global (and possibly
- * NUMA-alien) accesses. The write-queue is self-coalescing:
- */
- local_irq_save(flags);
- do {
- for (j = 0; j < PROFILE_GRPSZ; ++j) {
- if (hits[i + j].pc == pc) {
- hits[i + j].hits += nr_hits;
- goto out;
- } else if (!hits[i + j].hits) {
- hits[i + j].pc = pc;
- hits[i + j].hits = nr_hits;
- goto out;
- }
- }
- i = (i + secondary) & (NR_PROFILE_HIT - 1);
- } while (i != primary);
-
- /*
- * Add the current hit(s) and flush the write-queue out
- * to the global buffer:
- */
- atomic_add(nr_hits, &prof_buffer[pc]);
- for (i = 0; i < NR_PROFILE_HIT; ++i) {
- atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]);
- hits[i].pc = hits[i].hits = 0;
- }
-out:
- local_irq_restore(flags);
- put_cpu();
-}
-
-static int profile_dead_cpu(unsigned int cpu)
-{
- struct page *page;
- int i;
-
- if (cpumask_available(prof_cpu_mask))
- cpumask_clear_cpu(cpu, prof_cpu_mask);
-
- for (i = 0; i < 2; i++) {
- if (per_cpu(cpu_profile_hits, cpu)[i]) {
- page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]);
- per_cpu(cpu_profile_hits, cpu)[i] = NULL;
- __free_page(page);
- }
- }
- return 0;
-}
-
-static int profile_prepare_cpu(unsigned int cpu)
-{
- int i, node = cpu_to_mem(cpu);
- struct page *page;
-
- per_cpu(cpu_profile_flip, cpu) = 0;
-
- for (i = 0; i < 2; i++) {
- if (per_cpu(cpu_profile_hits, cpu)[i])
- continue;
-
- page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
- if (!page) {
- profile_dead_cpu(cpu);
- return -ENOMEM;
- }
- per_cpu(cpu_profile_hits, cpu)[i] = page_address(page);
-
- }
- return 0;
-}
-
-static int profile_online_cpu(unsigned int cpu)
-{
- if (cpumask_available(prof_cpu_mask))
- cpumask_set_cpu(cpu, prof_cpu_mask);
-
- return 0;
-}
-
-#else /* !CONFIG_SMP */
-#define profile_flip_buffers() do { } while (0)
-#define profile_discard_flip_buffers() do { } while (0)
-
static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
{
unsigned long pc;
pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift;
- atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]);
+ if (pc < prof_len)
+ atomic_add(nr_hits, &prof_buffer[pc]);
}
-#endif /* !CONFIG_SMP */
void profile_hits(int type, void *__pc, unsigned int nr_hits)
{
@@ -334,8 +134,8 @@ void profile_tick(int type)
{
struct pt_regs *regs = get_irq_regs();
- if (!user_mode(regs) && cpumask_available(prof_cpu_mask) &&
- cpumask_test_cpu(smp_processor_id(), prof_cpu_mask))
+ /* This is the old kernel-only legacy profiling */
+ if (!user_mode(regs))
profile_hit(type, (void *)profile_pc(regs));
}
@@ -358,7 +158,6 @@ read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos)
char *pnt;
unsigned long sample_step = 1UL << prof_shift;
- profile_flip_buffers();
if (p >= (prof_len+1)*sizeof(unsigned int))
return 0;
if (count > (prof_len+1)*sizeof(unsigned int) - p)
@@ -404,7 +203,6 @@ static ssize_t write_profile(struct file *file, const char __user *buf,
return -EINVAL;
}
#endif
- profile_discard_flip_buffers();
memset(prof_buffer, 0, prof_len * sizeof(atomic_t));
return count;
}
@@ -418,40 +216,14 @@ static const struct proc_ops profile_proc_ops = {
int __ref create_proc_profile(void)
{
struct proc_dir_entry *entry;
-#ifdef CONFIG_SMP
- enum cpuhp_state online_state;
-#endif
-
int err = 0;
if (!prof_on)
return 0;
-#ifdef CONFIG_SMP
- err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE",
- profile_prepare_cpu, profile_dead_cpu);
- if (err)
- return err;
-
- err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PROFILE_ONLINE",
- profile_online_cpu, NULL);
- if (err < 0)
- goto err_state_prep;
- online_state = err;
- err = 0;
-#endif
entry = proc_create("profile", S_IWUSR | S_IRUGO,
NULL, &profile_proc_ops);
- if (!entry)
- goto err_state_onl;
- proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t));
-
- return err;
-err_state_onl:
-#ifdef CONFIG_SMP
- cpuhp_remove_state(online_state);
-err_state_prep:
- cpuhp_remove_state(CPUHP_PROFILE_PREPARE);
-#endif
+ if (entry)
+ proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t));
return err;
}
subsys_initcall(create_proc_profile);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a9f655025607..f3951e4a55e5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7845,6 +7845,30 @@ void set_rq_offline(struct rq *rq)
}
}
+static inline void sched_set_rq_online(struct rq *rq, int cpu)
+{
+ struct rq_flags rf;
+
+ rq_lock_irqsave(rq, &rf);
+ if (rq->rd) {
+ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+ set_rq_online(rq);
+ }
+ rq_unlock_irqrestore(rq, &rf);
+}
+
+static inline void sched_set_rq_offline(struct rq *rq, int cpu)
+{
+ struct rq_flags rf;
+
+ rq_lock_irqsave(rq, &rf);
+ if (rq->rd) {
+ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+ set_rq_offline(rq);
+ }
+ rq_unlock_irqrestore(rq, &rf);
+}
+
/*
* used to mark begin/end of suspend/resume:
*/
@@ -7895,10 +7919,25 @@ static int cpuset_cpu_inactive(unsigned int cpu)
return 0;
}
+static inline void sched_smt_present_inc(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ static_branch_inc_cpuslocked(&sched_smt_present);
+#endif
+}
+
+static inline void sched_smt_present_dec(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ static_branch_dec_cpuslocked(&sched_smt_present);
+#endif
+}
+
int sched_cpu_activate(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
- struct rq_flags rf;
/*
* Clear the balance_push callback and prepare to schedule
@@ -7906,13 +7945,10 @@ int sched_cpu_activate(unsigned int cpu)
*/
balance_push_set(cpu, false);
-#ifdef CONFIG_SCHED_SMT
/*
* When going up, increment the number of cores with SMT present.
*/
- if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
- static_branch_inc_cpuslocked(&sched_smt_present);
-#endif
+ sched_smt_present_inc(cpu);
set_cpu_active(cpu, true);
if (sched_smp_initialized) {
@@ -7930,12 +7966,7 @@ int sched_cpu_activate(unsigned int cpu)
* 2) At runtime, if cpuset_cpu_active() fails to rebuild the
* domains.
*/
- rq_lock_irqsave(rq, &rf);
- if (rq->rd) {
- BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
- set_rq_online(rq);
- }
- rq_unlock_irqrestore(rq, &rf);
+ sched_set_rq_online(rq, cpu);
return 0;
}
@@ -7943,7 +7974,6 @@ int sched_cpu_activate(unsigned int cpu)
int sched_cpu_deactivate(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
- struct rq_flags rf;
int ret;
/*
@@ -7974,20 +8004,14 @@ int sched_cpu_deactivate(unsigned int cpu)
*/
synchronize_rcu();
- rq_lock_irqsave(rq, &rf);
- if (rq->rd) {
- BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
- set_rq_offline(rq);
- }
- rq_unlock_irqrestore(rq, &rf);
+ sched_set_rq_offline(rq, cpu);
-#ifdef CONFIG_SCHED_SMT
/*
* When going down, decrement the number of cores with SMT present.
*/
- if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
- static_branch_dec_cpuslocked(&sched_smt_present);
+ sched_smt_present_dec(cpu);
+#ifdef CONFIG_SCHED_SMT
sched_core_cpu_deactivate(cpu);
#endif
@@ -7997,6 +8021,8 @@ int sched_cpu_deactivate(unsigned int cpu)
sched_update_numa(cpu, false);
ret = cpuset_cpu_inactive(cpu);
if (ret) {
+ sched_smt_present_inc(cpu);
+ sched_set_rq_online(rq, cpu);
balance_push_set(cpu, false);
set_cpu_active(cpu, true);
sched_update_numa(cpu, true);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index a5e00293ae43..0bed0fa1acd9 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -582,6 +582,12 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
}
stime = mul_u64_u64_div_u64(stime, rtime, stime + utime);
+ /*
+ * Because mul_u64_u64_div_u64() can approximate on some
+ * achitectures; enforce the constraint that: a*b/(b+c) <= a.
+ */
+ if (unlikely(stime > rtime))
+ stime = rtime;
update:
/*
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 78e48f5426ee..eb0cdcd4d921 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -92,16 +92,6 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
trace_sched_stat_blocked(p, delta);
- /*
- * Blocking time is in units of nanosecs, so shift by
- * 20 to get a milliseconds-range estimation of the
- * amount of time that the task spent sleeping:
- */
- if (unlikely(prof_on == SLEEP_PROFILING)) {
- profile_hits(SLEEP_PROFILING,
- (void *)get_wchan(p),
- delta >> 20);
- }
account_scheduler_latency(p, delta >> 10, 0);
}
}
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 5c2daa7ad3f9..5d14d639ac71 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -6,12 +6,14 @@
static struct callback_head work_exited; /* all we need is ->next == NULL */
+#ifdef CONFIG_IRQ_WORK
static void task_work_set_notify_irq(struct irq_work *entry)
{
test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
}
static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) =
IRQ_WORK_INIT_HARD(task_work_set_notify_irq);
+#endif
/**
* task_work_add - ask the @task to execute @work->func()
@@ -57,6 +59,8 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
if (notify == TWA_NMI_CURRENT) {
if (WARN_ON_ONCE(task != current))
return -EINVAL;
+ if (!IS_ENABLED(CONFIG_IRQ_WORK))
+ return -EINVAL;
} else {
/* record the work call stack in order to print it in KASAN reports */
kasan_record_aux_stack(work);
@@ -81,9 +85,11 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
case TWA_SIGNAL_NO_IPI:
__set_notify_signal(task);
break;
+#ifdef CONFIG_IRQ_WORK
case TWA_NMI_CURRENT:
irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume));
break;
+#endif
default:
WARN_ON_ONCE(1);
break;
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index d25ba49e313c..d0538a75f4c6 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -246,7 +246,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow,
wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end);
if (wd_delay <= WATCHDOG_MAX_SKEW) {
- if (nretries > 1 || nretries >= max_retries) {
+ if (nretries > 1 && nretries >= max_retries) {
pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n",
smp_processor_id(), watchdog->name, nretries);
}
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 406dccb79c2b..8d2dd214ec68 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -727,17 +727,16 @@ static inline void process_adjtimex_modes(const struct __kernel_timex *txc,
}
if (txc->modes & ADJ_MAXERROR)
- time_maxerror = txc->maxerror;
+ time_maxerror = clamp(txc->maxerror, 0, NTP_PHASE_LIMIT);
if (txc->modes & ADJ_ESTERROR)
- time_esterror = txc->esterror;
+ time_esterror = clamp(txc->esterror, 0, NTP_PHASE_LIMIT);
if (txc->modes & ADJ_TIMECONST) {
- time_constant = txc->constant;
+ time_constant = clamp(txc->constant, 0, MAXTC);
if (!(time_status & STA_NANO))
time_constant += 4;
- time_constant = min(time_constant, (long)MAXTC);
- time_constant = max(time_constant, 0l);
+ time_constant = clamp(time_constant, 0, MAXTC);
}
if (txc->modes & ADJ_TAI &&
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index b4843099a8da..ed58eebb4e8f 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -1141,7 +1141,6 @@ void tick_broadcast_switch_to_oneshot(void)
#ifdef CONFIG_HOTPLUG_CPU
void hotplug_cpu__broadcast_tick_pull(int deadcpu)
{
- struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
struct clock_event_device *bc;
unsigned long flags;
@@ -1167,6 +1166,8 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
* device to avoid the starvation.
*/
if (tick_check_broadcast_expired()) {
+ struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+
cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask);
tick_program_event(td->evtdev->next_event, 1);
}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2fa87dcfeda9..5391e4167d60 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2606,7 +2606,7 @@ int do_adjtimex(struct __kernel_timex *txc)
clock_set |= timekeeping_advance(TK_ADV_FREQ);
if (clock_set)
- clock_was_set(CLOCK_REALTIME);
+ clock_was_set(CLOCK_SET_WALL);
ntp_notify_cmos_timer();
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 84413114db5c..8d57f7686bb0 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -475,9 +475,54 @@ static bool tmigr_check_lonely(struct tmigr_group *group)
return bitmap_weight(&active, BIT_CNT) <= 1;
}
-typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, void *);
+/**
+ * struct tmigr_walk - data required for walking the hierarchy
+ * @nextexp: Next CPU event expiry information which is handed into
+ * the timer migration code by the timer code
+ * (get_next_timer_interrupt())
+ * @firstexp: Contains the first event expiry information when
+ * hierarchy is completely idle. When CPU itself was the
+ * last going idle, information makes sure, that CPU will
+ * be back in time. When using this value in the remote
+ * expiry case, firstexp is stored in the per CPU tmigr_cpu
+ * struct of CPU which expires remote timers. It is updated
+ * in top level group only. Be aware, there could occur a
+ * new top level of the hierarchy between the 'top level
+ * call' in tmigr_update_events() and the check for the
+ * parent group in walk_groups(). Then @firstexp might
+ * contain a value != KTIME_MAX even if it was not the
+ * final top level. This is not a problem, as the worst
+ * outcome is a CPU which might wake up a little early.
+ * @evt: Pointer to tmigr_event which needs to be queued (of idle
+ * child group)
+ * @childmask: groupmask of child group
+ * @remote: Is set, when the new timer path is executed in
+ * tmigr_handle_remote_cpu()
+ * @basej: timer base in jiffies
+ * @now: timer base monotonic
+ * @check: is set if there is the need to handle remote timers;
+ * required in tmigr_requires_handle_remote() only
+ * @tmc_active: this flag indicates, whether the CPU which triggers
+ * the hierarchy walk is !idle in the timer migration
+ * hierarchy. When the CPU is idle and the whole hierarchy is
+ * idle, only the first event of the top level has to be
+ * considered.
+ */
+struct tmigr_walk {
+ u64 nextexp;
+ u64 firstexp;
+ struct tmigr_event *evt;
+ u8 childmask;
+ bool remote;
+ unsigned long basej;
+ u64 now;
+ bool check;
+ bool tmc_active;
+};
+
+typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, struct tmigr_walk *);
-static void __walk_groups(up_f up, void *data,
+static void __walk_groups(up_f up, struct tmigr_walk *data,
struct tmigr_cpu *tmc)
{
struct tmigr_group *child = NULL, *group = tmc->tmgroup;
@@ -490,64 +535,17 @@ static void __walk_groups(up_f up, void *data,
child = group;
group = group->parent;
+ data->childmask = child->groupmask;
} while (group);
}
-static void walk_groups(up_f up, void *data, struct tmigr_cpu *tmc)
+static void walk_groups(up_f up, struct tmigr_walk *data, struct tmigr_cpu *tmc)
{
lockdep_assert_held(&tmc->lock);
__walk_groups(up, data, tmc);
}
-/**
- * struct tmigr_walk - data required for walking the hierarchy
- * @nextexp: Next CPU event expiry information which is handed into
- * the timer migration code by the timer code
- * (get_next_timer_interrupt())
- * @firstexp: Contains the first event expiry information when last
- * active CPU of hierarchy is on the way to idle to make
- * sure CPU will be back in time.
- * @evt: Pointer to tmigr_event which needs to be queued (of idle
- * child group)
- * @childmask: childmask of child group
- * @remote: Is set, when the new timer path is executed in
- * tmigr_handle_remote_cpu()
- */
-struct tmigr_walk {
- u64 nextexp;
- u64 firstexp;
- struct tmigr_event *evt;
- u8 childmask;
- bool remote;
-};
-
-/**
- * struct tmigr_remote_data - data required for remote expiry hierarchy walk
- * @basej: timer base in jiffies
- * @now: timer base monotonic
- * @firstexp: returns expiry of the first timer in the idle timer
- * migration hierarchy to make sure the timer is handled in
- * time; it is stored in the per CPU tmigr_cpu struct of
- * CPU which expires remote timers
- * @childmask: childmask of child group
- * @check: is set if there is the need to handle remote timers;
- * required in tmigr_requires_handle_remote() only
- * @tmc_active: this flag indicates, whether the CPU which triggers
- * the hierarchy walk is !idle in the timer migration
- * hierarchy. When the CPU is idle and the whole hierarchy is
- * idle, only the first event of the top level has to be
- * considered.
- */
-struct tmigr_remote_data {
- unsigned long basej;
- u64 now;
- u64 firstexp;
- u8 childmask;
- bool check;
- bool tmc_active;
-};
-
/*
* Returns the next event of the timerqueue @group->events
*
@@ -618,10 +616,9 @@ static u64 tmigr_next_groupevt_expires(struct tmigr_group *group)
static bool tmigr_active_up(struct tmigr_group *group,
struct tmigr_group *child,
- void *ptr)
+ struct tmigr_walk *data)
{
union tmigr_state curstate, newstate;
- struct tmigr_walk *data = ptr;
bool walk_done;
u8 childmask;
@@ -649,8 +646,7 @@ static bool tmigr_active_up(struct tmigr_group *group,
} while (!atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state));
- if ((walk_done == false) && group->parent)
- data->childmask = group->childmask;
+ trace_tmigr_group_set_cpu_active(group, newstate, childmask);
/*
* The group is active (again). The group event might be still queued
@@ -666,8 +662,6 @@ static bool tmigr_active_up(struct tmigr_group *group,
*/
group->groupevt.ignore = true;
- trace_tmigr_group_set_cpu_active(group, newstate, childmask);
-
return walk_done;
}
@@ -675,7 +669,7 @@ static void __tmigr_cpu_activate(struct tmigr_cpu *tmc)
{
struct tmigr_walk data;
- data.childmask = tmc->childmask;
+ data.childmask = tmc->groupmask;
trace_tmigr_cpu_active(tmc);
@@ -860,10 +854,8 @@ unlock:
static bool tmigr_new_timer_up(struct tmigr_group *group,
struct tmigr_group *child,
- void *ptr)
+ struct tmigr_walk *data)
{
- struct tmigr_walk *data = ptr;
-
return tmigr_update_events(group, child, data);
}
@@ -995,9 +987,8 @@ unlock:
static bool tmigr_handle_remote_up(struct tmigr_group *group,
struct tmigr_group *child,
- void *ptr)
+ struct tmigr_walk *data)
{
- struct tmigr_remote_data *data = ptr;
struct tmigr_event *evt;
unsigned long jif;
u8 childmask;
@@ -1034,12 +1025,10 @@ again:
}
/*
- * Update of childmask for the next level and keep track of the expiry
- * of the first event that needs to be handled (group->next_expiry was
- * updated by tmigr_next_expired_groupevt(), next was set by
- * tmigr_handle_remote_cpu()).
+ * Keep track of the expiry of the first event that needs to be handled
+ * (group->next_expiry was updated by tmigr_next_expired_groupevt(),
+ * next was set by tmigr_handle_remote_cpu()).
*/
- data->childmask = group->childmask;
data->firstexp = group->next_expiry;
raw_spin_unlock_irq(&group->lock);
@@ -1055,12 +1044,12 @@ again:
void tmigr_handle_remote(void)
{
struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
- struct tmigr_remote_data data;
+ struct tmigr_walk data;
if (tmigr_is_not_available(tmc))
return;
- data.childmask = tmc->childmask;
+ data.childmask = tmc->groupmask;
data.firstexp = KTIME_MAX;
/*
@@ -1068,7 +1057,7 @@ void tmigr_handle_remote(void)
* in tmigr_handle_remote_up() anyway. Keep this check to speed up the
* return when nothing has to be done.
*/
- if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) {
+ if (!tmigr_check_migrator(tmc->tmgroup, tmc->groupmask)) {
/*
* If this CPU was an idle migrator, make sure to clear its wakeup
* value so it won't chase timers that have already expired elsewhere.
@@ -1097,9 +1086,8 @@ void tmigr_handle_remote(void)
static bool tmigr_requires_handle_remote_up(struct tmigr_group *group,
struct tmigr_group *child,
- void *ptr)
+ struct tmigr_walk *data)
{
- struct tmigr_remote_data *data = ptr;
u8 childmask;
childmask = data->childmask;
@@ -1118,7 +1106,7 @@ static bool tmigr_requires_handle_remote_up(struct tmigr_group *group,
* group before reading the next_expiry value.
*/
if (group->parent && !data->tmc_active)
- goto out;
+ return false;
/*
* The lock is required on 32bit architectures to read the variable
@@ -1143,9 +1131,6 @@ static bool tmigr_requires_handle_remote_up(struct tmigr_group *group,
raw_spin_unlock(&group->lock);
}
-out:
- /* Update of childmask for the next level */
- data->childmask = group->childmask;
return false;
}
@@ -1157,7 +1142,7 @@ out:
bool tmigr_requires_handle_remote(void)
{
struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
- struct tmigr_remote_data data;
+ struct tmigr_walk data;
unsigned long jif;
bool ret = false;
@@ -1165,7 +1150,7 @@ bool tmigr_requires_handle_remote(void)
return ret;
data.now = get_jiffies_update(&jif);
- data.childmask = tmc->childmask;
+ data.childmask = tmc->groupmask;
data.firstexp = KTIME_MAX;
data.tmc_active = !tmc->idle;
data.check = false;
@@ -1230,14 +1215,13 @@ u64 tmigr_cpu_new_timer(u64 nextexp)
if (nextexp != tmc->cpuevt.nextevt.expires ||
tmc->cpuevt.ignore) {
ret = tmigr_new_timer(tmc, nextexp);
+ /*
+ * Make sure the reevaluation of timers in idle path
+ * will not miss an event.
+ */
+ WRITE_ONCE(tmc->wakeup, ret);
}
}
- /*
- * Make sure the reevaluation of timers in idle path will not miss an
- * event.
- */
- WRITE_ONCE(tmc->wakeup, ret);
-
trace_tmigr_cpu_new_timer_idle(tmc, nextexp);
raw_spin_unlock(&tmc->lock);
return ret;
@@ -1245,10 +1229,9 @@ u64 tmigr_cpu_new_timer(u64 nextexp)
static bool tmigr_inactive_up(struct tmigr_group *group,
struct tmigr_group *child,
- void *ptr)
+ struct tmigr_walk *data)
{
union tmigr_state curstate, newstate, childstate;
- struct tmigr_walk *data = ptr;
bool walk_done;
u8 childmask;
@@ -1299,9 +1282,10 @@ static bool tmigr_inactive_up(struct tmigr_group *group,
WARN_ON_ONCE((newstate.migrator != TMIGR_NONE) && !(newstate.active));
- if (atomic_try_cmpxchg(&group->migr_state, &curstate.state,
- newstate.state))
+ if (atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state)) {
+ trace_tmigr_group_set_cpu_inactive(group, newstate, childmask);
break;
+ }
/*
* The memory barrier is paired with the cmpxchg() in
@@ -1317,22 +1301,6 @@ static bool tmigr_inactive_up(struct tmigr_group *group,
/* Event Handling */
tmigr_update_events(group, child, data);
- if (group->parent && (walk_done == false))
- data->childmask = group->childmask;
-
- /*
- * data->firstexp was set by tmigr_update_events() and contains the
- * expiry of the first global event which needs to be handled. It
- * differs from KTIME_MAX if:
- * - group is the top level group and
- * - group is idle (which means CPU was the last active CPU in the
- * hierarchy) and
- * - there is a pending event in the hierarchy
- */
- WARN_ON_ONCE(data->firstexp != KTIME_MAX && group->parent);
-
- trace_tmigr_group_set_cpu_inactive(group, newstate, childmask);
-
return walk_done;
}
@@ -1341,7 +1309,7 @@ static u64 __tmigr_cpu_deactivate(struct tmigr_cpu *tmc, u64 nextexp)
struct tmigr_walk data = { .nextexp = nextexp,
.firstexp = KTIME_MAX,
.evt = &tmc->cpuevt,
- .childmask = tmc->childmask };
+ .childmask = tmc->groupmask };
/*
* If nextexp is KTIME_MAX, the CPU event will be ignored because the
@@ -1400,7 +1368,7 @@ u64 tmigr_cpu_deactivate(u64 nextexp)
* the only one in the level 0 group; and if it is the
* only one in level 0 group, but there are more than a
* single group active on the way to top level)
- * * nextevt - when CPU is offline and has to handle timer on his own
+ * * nextevt - when CPU is offline and has to handle timer on its own
* or when on the way to top in every group only a single
* child is active but @nextevt is before the lowest
* next_expiry encountered while walking up to top level.
@@ -1419,7 +1387,7 @@ u64 tmigr_quick_check(u64 nextevt)
if (WARN_ON_ONCE(tmc->idle))
return nextevt;
- if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->childmask))
+ if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->groupmask))
return KTIME_MAX;
do {
@@ -1442,6 +1410,66 @@ u64 tmigr_quick_check(u64 nextevt)
return KTIME_MAX;
}
+/*
+ * tmigr_trigger_active() - trigger a CPU to become active again
+ *
+ * This function is executed on a CPU which is part of cpu_online_mask, when the
+ * last active CPU in the hierarchy is offlining. With this, it is ensured that
+ * the other CPU is active and takes over the migrator duty.
+ */
+static long tmigr_trigger_active(void *unused)
+{
+ struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+
+ WARN_ON_ONCE(!tmc->online || tmc->idle);
+
+ return 0;
+}
+
+static int tmigr_cpu_offline(unsigned int cpu)
+{
+ struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+ int migrator;
+ u64 firstexp;
+
+ raw_spin_lock_irq(&tmc->lock);
+ tmc->online = false;
+ WRITE_ONCE(tmc->wakeup, KTIME_MAX);
+
+ /*
+ * CPU has to handle the local events on his own, when on the way to
+ * offline; Therefore nextevt value is set to KTIME_MAX
+ */
+ firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX);
+ trace_tmigr_cpu_offline(tmc);
+ raw_spin_unlock_irq(&tmc->lock);
+
+ if (firstexp != KTIME_MAX) {
+ migrator = cpumask_any_but(cpu_online_mask, cpu);
+ work_on_cpu(migrator, tmigr_trigger_active, NULL);
+ }
+
+ return 0;
+}
+
+static int tmigr_cpu_online(unsigned int cpu)
+{
+ struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+
+ /* Check whether CPU data was successfully initialized */
+ if (WARN_ON_ONCE(!tmc->tmgroup))
+ return -EINVAL;
+
+ raw_spin_lock_irq(&tmc->lock);
+ trace_tmigr_cpu_online(tmc);
+ tmc->idle = timer_base_is_idle();
+ if (!tmc->idle)
+ __tmigr_cpu_activate(tmc);
+ tmc->online = true;
+ raw_spin_unlock_irq(&tmc->lock);
+ return 0;
+}
+
static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl,
int node)
{
@@ -1514,21 +1542,25 @@ static struct tmigr_group *tmigr_get_group(unsigned int cpu, int node,
}
static void tmigr_connect_child_parent(struct tmigr_group *child,
- struct tmigr_group *parent)
+ struct tmigr_group *parent,
+ bool activate)
{
- union tmigr_state childstate;
+ struct tmigr_walk data;
raw_spin_lock_irq(&child->lock);
raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING);
child->parent = parent;
- child->childmask = BIT(parent->num_children++);
+ child->groupmask = BIT(parent->num_children++);
raw_spin_unlock(&parent->lock);
raw_spin_unlock_irq(&child->lock);
trace_tmigr_connect_child_parent(child);
+ if (!activate)
+ return;
+
/*
* To prevent inconsistent states, active children need to be active in
* the new parent as well. Inactive children are already marked inactive
@@ -1544,21 +1576,24 @@ static void tmigr_connect_child_parent(struct tmigr_group *child,
* child to the new parent. So tmigr_connect_child_parent() is
* executed with the formerly top level group (child) and the newly
* created group (parent).
+ *
+ * * It is ensured that the child is active, as this setup path is
+ * executed in hotplug prepare callback. This is exectued by an
+ * already connected and !idle CPU. Even if all other CPUs go idle,
+ * the CPU executing the setup will be responsible up to current top
+ * level group. And the next time it goes inactive, it will release
+ * the new childmask and parent to subsequent walkers through this
+ * @child. Therefore propagate active state unconditionally.
*/
- childstate.state = atomic_read(&child->migr_state);
- if (childstate.migrator != TMIGR_NONE) {
- struct tmigr_walk data;
-
- data.childmask = child->childmask;
+ data.childmask = child->groupmask;
- /*
- * There is only one new level per time. When connecting the
- * child and the parent and set the child active when the parent
- * is inactive, the parent needs to be the uppermost
- * level. Otherwise there went something wrong!
- */
- WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent);
- }
+ /*
+ * There is only one new level per time (which is protected by
+ * tmigr_mutex). When connecting the child and the parent and set the
+ * child active when the parent is inactive, the parent needs to be the
+ * uppermost level. Otherwise there went something wrong!
+ */
+ WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent);
}
static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
@@ -1611,12 +1646,12 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
* Update tmc -> group / child -> group connection
*/
if (i == 0) {
- struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+ struct tmigr_cpu *tmc = per_cpu_ptr(&tmigr_cpu, cpu);
raw_spin_lock_irq(&group->lock);
tmc->tmgroup = group;
- tmc->childmask = BIT(group->num_children++);
+ tmc->groupmask = BIT(group->num_children++);
raw_spin_unlock_irq(&group->lock);
@@ -1626,7 +1661,8 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
continue;
} else {
child = stack[i - 1];
- tmigr_connect_child_parent(child, group);
+ /* Will be activated at online time */
+ tmigr_connect_child_parent(child, group, false);
}
/* check if uppermost level was newly created */
@@ -1637,12 +1673,21 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
lvllist = &tmigr_level_list[top];
if (group->num_children == 1 && list_is_singular(lvllist)) {
+ /*
+ * The target CPU must never do the prepare work, except
+ * on early boot when the boot CPU is the target. Otherwise
+ * it may spuriously activate the old top level group inside
+ * the new one (nevertheless whether old top level group is
+ * active or not) and/or release an uninitialized childmask.
+ */
+ WARN_ON_ONCE(cpu == raw_smp_processor_id());
+
lvllist = &tmigr_level_list[top - 1];
list_for_each_entry(child, lvllist, list) {
if (child->parent)
continue;
- tmigr_connect_child_parent(child, group);
+ tmigr_connect_child_parent(child, group, true);
}
}
}
@@ -1664,80 +1709,31 @@ static int tmigr_add_cpu(unsigned int cpu)
return ret;
}
-static int tmigr_cpu_online(unsigned int cpu)
-{
- struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
- int ret;
-
- /* First online attempt? Initialize CPU data */
- if (!tmc->tmgroup) {
- raw_spin_lock_init(&tmc->lock);
-
- ret = tmigr_add_cpu(cpu);
- if (ret < 0)
- return ret;
-
- if (tmc->childmask == 0)
- return -EINVAL;
-
- timerqueue_init(&tmc->cpuevt.nextevt);
- tmc->cpuevt.nextevt.expires = KTIME_MAX;
- tmc->cpuevt.ignore = true;
- tmc->cpuevt.cpu = cpu;
-
- tmc->remote = false;
- WRITE_ONCE(tmc->wakeup, KTIME_MAX);
- }
- raw_spin_lock_irq(&tmc->lock);
- trace_tmigr_cpu_online(tmc);
- tmc->idle = timer_base_is_idle();
- if (!tmc->idle)
- __tmigr_cpu_activate(tmc);
- tmc->online = true;
- raw_spin_unlock_irq(&tmc->lock);
- return 0;
-}
-
-/*
- * tmigr_trigger_active() - trigger a CPU to become active again
- *
- * This function is executed on a CPU which is part of cpu_online_mask, when the
- * last active CPU in the hierarchy is offlining. With this, it is ensured that
- * the other CPU is active and takes over the migrator duty.
- */
-static long tmigr_trigger_active(void *unused)
+static int tmigr_cpu_prepare(unsigned int cpu)
{
- struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+ struct tmigr_cpu *tmc = per_cpu_ptr(&tmigr_cpu, cpu);
+ int ret = 0;
- WARN_ON_ONCE(!tmc->online || tmc->idle);
-
- return 0;
-}
-
-static int tmigr_cpu_offline(unsigned int cpu)
-{
- struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
- int migrator;
- u64 firstexp;
+ /* Not first online attempt? */
+ if (tmc->tmgroup)
+ return ret;
- raw_spin_lock_irq(&tmc->lock);
- tmc->online = false;
+ raw_spin_lock_init(&tmc->lock);
+ timerqueue_init(&tmc->cpuevt.nextevt);
+ tmc->cpuevt.nextevt.expires = KTIME_MAX;
+ tmc->cpuevt.ignore = true;
+ tmc->cpuevt.cpu = cpu;
+ tmc->remote = false;
WRITE_ONCE(tmc->wakeup, KTIME_MAX);
- /*
- * CPU has to handle the local events on his own, when on the way to
- * offline; Therefore nextevt value is set to KTIME_MAX
- */
- firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX);
- trace_tmigr_cpu_offline(tmc);
- raw_spin_unlock_irq(&tmc->lock);
+ ret = tmigr_add_cpu(cpu);
+ if (ret < 0)
+ return ret;
- if (firstexp != KTIME_MAX) {
- migrator = cpumask_any_but(cpu_online_mask, cpu);
- work_on_cpu(migrator, tmigr_trigger_active, NULL);
- }
+ if (tmc->groupmask == 0)
+ return -EINVAL;
- return 0;
+ return ret;
}
static int __init tmigr_init(void)
@@ -1796,6 +1792,11 @@ static int __init tmigr_init(void)
tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP,
tmigr_crossnode_level);
+ ret = cpuhp_setup_state(CPUHP_TMIGR_PREPARE, "tmigr:prepare",
+ tmigr_cpu_prepare, NULL);
+ if (ret)
+ goto err;
+
ret = cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online",
tmigr_cpu_online, tmigr_cpu_offline);
if (ret)
@@ -1807,4 +1808,4 @@ err:
pr_err("Timer migration setup failed\n");
return ret;
}
-late_initcall(tmigr_init);
+early_initcall(tmigr_init);
diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h
index 6c37d94a37d9..154accc7a543 100644
--- a/kernel/time/timer_migration.h
+++ b/kernel/time/timer_migration.h
@@ -22,7 +22,17 @@ struct tmigr_event {
* struct tmigr_group - timer migration hierarchy group
* @lock: Lock protecting the event information and group hierarchy
* information during setup
- * @parent: Pointer to the parent group
+ * @parent: Pointer to the parent group. Pointer is updated when a
+ * new hierarchy level is added because of a CPU coming
+ * online the first time. Once it is set, the pointer will
+ * not be removed or updated. When accessing parent pointer
+ * lock less to decide whether to abort a propagation or
+ * not, it is not a problem. The worst outcome is an
+ * unnecessary/early CPU wake up. But do not access parent
+ * pointer several times in the same 'action' (like
+ * activation, deactivation, check for remote expiry,...)
+ * without holding the lock as it is not ensured that value
+ * will not change.
* @groupevt: Next event of the group which is only used when the
* group is !active. The group event is then queued into
* the parent timer queue.
@@ -41,9 +51,8 @@ struct tmigr_event {
* @num_children: Counter of group children to make sure the group is only
* filled with TMIGR_CHILDREN_PER_GROUP; Required for setup
* only
- * @childmask: childmask of the group in the parent group; is set
- * during setup and will never change; can be read
- * lockless
+ * @groupmask: mask of the group in the parent group; is set during
+ * setup and will never change; can be read lockless
* @list: List head that is added to the per level
* tmigr_level_list; is required during setup when a
* new group needs to be connected to the existing
@@ -59,7 +68,7 @@ struct tmigr_group {
unsigned int level;
int numa_node;
unsigned int num_children;
- u8 childmask;
+ u8 groupmask;
struct list_head list;
};
@@ -79,7 +88,7 @@ struct tmigr_group {
* hierarchy
* @remote: Is set when timers of the CPU are expired remotely
* @tmgroup: Pointer to the parent group
- * @childmask: childmask of tmigr_cpu in the parent group
+ * @groupmask: mask of tmigr_cpu in the parent group
* @wakeup: Stores the first timer when the timer migration
* hierarchy is completely idle and remote expiry was done;
* is returned to timer code in the idle path and is only
@@ -92,7 +101,7 @@ struct tmigr_cpu {
bool idle;
bool remote;
struct tmigr_group *tmgroup;
- u8 childmask;
+ u8 groupmask;
u64 wakeup;
struct tmigr_event cpuevt;
};
@@ -108,8 +117,8 @@ union tmigr_state {
u32 state;
/**
* struct - split state of tmigr_group
- * @active: Contains each childmask bit of the active children
- * @migrator: Contains childmask of the child which is migrator
+ * @active: Contains each mask bit of the active children
+ * @migrator: Contains mask of the child which is migrator
* @seq: Sequence counter needs to be increased when an update
* to the tmigr_state is done. It prevents a race when
* updates in the child groups are propagated in changed
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index fc205ad167a9..d1d5ea2d0a1b 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -902,7 +902,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
i = *idx ? : task->curr_ret_stack;
while (i > 0) {
- ret_stack = get_ret_stack(current, i, &i);
+ ret_stack = get_ret_stack(task, i, &i);
if (!ret_stack)
break;
/*
diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c
index cb0871fbdb07..314ffc143039 100644
--- a/kernel/trace/preemptirq_delay_test.c
+++ b/kernel/trace/preemptirq_delay_test.c
@@ -34,8 +34,6 @@ MODULE_PARM_DESC(cpu_affinity, "Cpu num test is running on");
static struct completion done;
-#define MIN(x, y) ((x) < (y) ? (x) : (y))
-
static void busy_wait(ulong time)
{
u64 start, end;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 28853966aa9a..cebd879a30cb 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -693,18 +693,6 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer,
}
/**
- * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer
- * @buffer: The ring_buffer to get the number of pages from
- * @cpu: The cpu of the ring_buffer to get the number of pages from
- *
- * Returns the number of pages used by a per_cpu buffer of the ring buffer.
- */
-size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu)
-{
- return buffer->buffers[cpu]->nr_pages;
-}
-
-/**
* ring_buffer_nr_dirty_pages - get the number of used pages in the ring buffer
* @buffer: The ring_buffer to get the number of pages from
* @cpu: The cpu of the ring_buffer to get the number of pages from
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 10cd38bce2f1..ebe7ce2f5f4a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7956,7 +7956,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
trace_access_unlock(iter->cpu_file);
if (ret < 0) {
- if (trace_empty(iter)) {
+ if (trace_empty(iter) && !iter->closed) {
if ((filp->f_flags & O_NONBLOCK))
return -EAGAIN;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8783bebd0562..bd3e3069300e 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1634,6 +1634,29 @@ static inline void *event_file_data(struct file *filp)
extern struct mutex event_mutex;
extern struct list_head ftrace_events;
+/*
+ * When the trace_event_file is the filp->i_private pointer,
+ * it must be taken under the event_mutex lock, and then checked
+ * if the EVENT_FILE_FL_FREED flag is set. If it is, then the
+ * data pointed to by the trace_event_file can not be trusted.
+ *
+ * Use the event_file_file() to access the trace_event_file from
+ * the filp the first time under the event_mutex and check for
+ * NULL. If it is needed to be retrieved again and the event_mutex
+ * is still held, then the event_file_data() can be used and it
+ * is guaranteed to be valid.
+ */
+static inline struct trace_event_file *event_file_file(struct file *filp)
+{
+ struct trace_event_file *file;
+
+ lockdep_assert_held(&event_mutex);
+ file = READ_ONCE(file_inode(filp)->i_private);
+ if (!file || file->flags & EVENT_FILE_FL_FREED)
+ return NULL;
+ return file;
+}
+
extern const struct file_operations event_trigger_fops;
extern const struct file_operations event_hist_fops;
extern const struct file_operations event_hist_debug_fops;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6ef29eba90ce..7266ec2a4eea 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -992,18 +992,18 @@ static void remove_subsystem(struct trace_subsystem_dir *dir)
void event_file_get(struct trace_event_file *file)
{
- atomic_inc(&file->ref);
+ refcount_inc(&file->ref);
}
void event_file_put(struct trace_event_file *file)
{
- if (WARN_ON_ONCE(!atomic_read(&file->ref))) {
+ if (WARN_ON_ONCE(!refcount_read(&file->ref))) {
if (file->flags & EVENT_FILE_FL_FREED)
kmem_cache_free(file_cachep, file);
return;
}
- if (atomic_dec_and_test(&file->ref)) {
+ if (refcount_dec_and_test(&file->ref)) {
/* Count should only go to zero when it is freed */
if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED)))
return;
@@ -1386,12 +1386,12 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
char buf[4] = "0";
mutex_lock(&event_mutex);
- file = event_file_data(filp);
+ file = event_file_file(filp);
if (likely(file))
flags = file->flags;
mutex_unlock(&event_mutex);
- if (!file || flags & EVENT_FILE_FL_FREED)
+ if (!file)
return -ENODEV;
if (flags & EVENT_FILE_FL_ENABLED &&
@@ -1424,8 +1424,8 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
case 1:
ret = -ENODEV;
mutex_lock(&event_mutex);
- file = event_file_data(filp);
- if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) {
+ file = event_file_file(filp);
+ if (likely(file)) {
ret = tracing_update_buffers(file->tr);
if (ret < 0) {
mutex_unlock(&event_mutex);
@@ -1540,7 +1540,8 @@ enum {
static void *f_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct trace_event_call *call = event_file_data(m->private);
+ struct trace_event_file *file = event_file_data(m->private);
+ struct trace_event_call *call = file->event_call;
struct list_head *common_head = &ftrace_common_fields;
struct list_head *head = trace_get_fields(call);
struct list_head *node = v;
@@ -1572,7 +1573,8 @@ static void *f_next(struct seq_file *m, void *v, loff_t *pos)
static int f_show(struct seq_file *m, void *v)
{
- struct trace_event_call *call = event_file_data(m->private);
+ struct trace_event_file *file = event_file_data(m->private);
+ struct trace_event_call *call = file->event_call;
struct ftrace_event_field *field;
const char *array_descriptor;
@@ -1627,12 +1629,14 @@ static int f_show(struct seq_file *m, void *v)
static void *f_start(struct seq_file *m, loff_t *pos)
{
+ struct trace_event_file *file;
void *p = (void *)FORMAT_HEADER;
loff_t l = 0;
/* ->stop() is called even if ->start() fails */
mutex_lock(&event_mutex);
- if (!event_file_data(m->private))
+ file = event_file_file(m->private);
+ if (!file)
return ERR_PTR(-ENODEV);
while (l < *pos && p)
@@ -1706,8 +1710,8 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
trace_seq_init(s);
mutex_lock(&event_mutex);
- file = event_file_data(filp);
- if (file && !(file->flags & EVENT_FILE_FL_FREED))
+ file = event_file_file(filp);
+ if (file)
print_event_filter(file, s);
mutex_unlock(&event_mutex);
@@ -1736,9 +1740,13 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
return PTR_ERR(buf);
mutex_lock(&event_mutex);
- file = event_file_data(filp);
- if (file)
- err = apply_event_filter(file, buf);
+ file = event_file_file(filp);
+ if (file) {
+ if (file->flags & EVENT_FILE_FL_FREED)
+ err = -ENODEV;
+ else
+ err = apply_event_filter(file, buf);
+ }
mutex_unlock(&event_mutex);
kfree(buf);
@@ -2485,7 +2493,6 @@ static int event_callback(const char *name, umode_t *mode, void **data,
if (strcmp(name, "format") == 0) {
*mode = TRACE_MODE_READ;
*fops = &ftrace_event_format_fops;
- *data = call;
return 1;
}
@@ -2996,7 +3003,7 @@ trace_create_new_event(struct trace_event_call *call,
atomic_set(&file->tm_ref, 0);
INIT_LIST_HEAD(&file->triggers);
list_add(&file->list, &tr->events);
- event_file_get(file);
+ refcount_set(&file->ref, 1);
return file;
}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 6ece1308d36a..5f9119eb7c67 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5601,7 +5601,7 @@ static int hist_show(struct seq_file *m, void *v)
mutex_lock(&event_mutex);
- event_file = event_file_data(m->private);
+ event_file = event_file_file(m->private);
if (unlikely(!event_file)) {
ret = -ENODEV;
goto out_unlock;
@@ -5880,7 +5880,7 @@ static int hist_debug_show(struct seq_file *m, void *v)
mutex_lock(&event_mutex);
- event_file = event_file_data(m->private);
+ event_file = event_file_file(m->private);
if (unlikely(!event_file)) {
ret = -ENODEV;
goto out_unlock;
diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index 8650562bdaa9..a8f076809db4 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -299,7 +299,7 @@ event_inject_write(struct file *filp, const char __user *ubuf, size_t cnt,
strim(buf);
mutex_lock(&event_mutex);
- file = event_file_data(filp);
+ file = event_file_file(filp);
if (file) {
call = file->event_call;
size = parse_entry(buf, call, &entry);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 4bec043c8690..a5e3d6acf1e1 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -159,7 +159,7 @@ static void *trigger_start(struct seq_file *m, loff_t *pos)
/* ->stop() is called even if ->start() fails */
mutex_lock(&event_mutex);
- event_file = event_file_data(m->private);
+ event_file = event_file_file(m->private);
if (unlikely(!event_file))
return ERR_PTR(-ENODEV);
@@ -213,7 +213,7 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
mutex_lock(&event_mutex);
- if (unlikely(!event_file_data(file))) {
+ if (unlikely(!event_file_file(file))) {
mutex_unlock(&event_mutex);
return -ENODEV;
}
@@ -293,7 +293,7 @@ static ssize_t event_trigger_regex_write(struct file *file,
strim(buf);
mutex_lock(&event_mutex);
- event_file = event_file_data(file);
+ event_file = event_file_file(file);
if (unlikely(!event_file)) {
mutex_unlock(&event_mutex);
kfree(buf);
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index a4dcf0f24352..3a56e7c8aa4f 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -454,7 +454,7 @@ static struct tracing_map_elt *get_free_elt(struct tracing_map *map)
struct tracing_map_elt *elt = NULL;
int idx;
- idx = atomic_inc_return(&map->next_elt);
+ idx = atomic_fetch_add_unless(&map->next_elt, 1, map->max_elts);
if (idx < map->max_elts) {
elt = *(TRACING_MAP_ELT(map->elts, idx));
if (map->ops && map->ops->elt_init)
@@ -699,7 +699,7 @@ void tracing_map_clear(struct tracing_map *map)
{
unsigned int i;
- atomic_set(&map->next_elt, -1);
+ atomic_set(&map->next_elt, 0);
atomic64_set(&map->hits, 0);
atomic64_set(&map->drops, 0);
@@ -783,7 +783,7 @@ struct tracing_map *tracing_map_create(unsigned int map_bits,
map->map_bits = map_bits;
map->max_elts = (1 << map_bits);
- atomic_set(&map->next_elt, -1);
+ atomic_set(&map->next_elt, 0);
map->map_size = (1 << (map_bits + 1));
map->ops = ops;