summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup/cgroup.c15
-rw-r--r--kernel/events/uprobes.c4
-rw-r--r--kernel/exit.c4
-rw-r--r--kernel/fork.c8
-rw-r--r--kernel/kcsan/kcsan_test.c9
-rw-r--r--kernel/kcsan/selftest.c9
-rw-r--r--kernel/kthread.c1
-rw-r--r--kernel/ptrace.c2
-rw-r--r--kernel/rcu/tree.c21
-rw-r--r--kernel/rcu/tree_nocb.h19
-rw-r--r--kernel/sched/fair.c12
-rw-r--r--kernel/sched/wait.c60
-rw-r--r--kernel/sys.c32
13 files changed, 89 insertions, 107 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 484adb375b15..1d5b9de3b1b9 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1908,6 +1908,7 @@ enum cgroup2_param {
Opt_favordynmods,
Opt_memory_localevents,
Opt_memory_recursiveprot,
+ Opt_memory_hugetlb_accounting,
nr__cgroup2_params
};
@@ -1916,6 +1917,7 @@ static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
fsparam_flag("favordynmods", Opt_favordynmods),
fsparam_flag("memory_localevents", Opt_memory_localevents),
fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot),
+ fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting),
{}
};
@@ -1942,6 +1944,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param
case Opt_memory_recursiveprot:
ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
return 0;
+ case Opt_memory_hugetlb_accounting:
+ ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
+ return 0;
}
return -EINVAL;
}
@@ -1966,6 +1971,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
else
cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT;
+
+ if (root_flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)
+ cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
+ else
+ cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
}
}
@@ -1979,6 +1989,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
seq_puts(seq, ",memory_localevents");
if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
seq_puts(seq, ",memory_recursiveprot");
+ if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)
+ seq_puts(seq, ",memory_hugetlb_accounting");
return 0;
}
@@ -7068,7 +7080,8 @@ static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
"nsdelegate\n"
"favordynmods\n"
"memory_localevents\n"
- "memory_recursiveprot\n");
+ "memory_recursiveprot\n"
+ "memory_hugetlb_accounting\n");
}
static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 3048589e2e85..435aac1d8c27 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -474,8 +474,8 @@ retry:
gup_flags |= FOLL_SPLIT_PMD;
/* Read the page with vaddr into memory */
old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
- if (IS_ERR_OR_NULL(old_page))
- return old_page ? PTR_ERR(old_page) : 0;
+ if (IS_ERR(old_page))
+ return PTR_ERR(old_page);
ret = verify_opcode(old_page, vaddr, &opcode);
if (ret <= 0)
diff --git a/kernel/exit.c b/kernel/exit.c
index 2b4a232f2f68..61ebba96909b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -541,7 +541,6 @@ static void exit_mm(void)
exit_mm_release(current, mm);
if (!mm)
return;
- sync_mm_rss(mm);
mmap_read_lock(mm);
mmgrab_lazy_tlb(mm);
BUG_ON(mm != current->active_mm);
@@ -831,9 +830,6 @@ void __noreturn do_exit(long code)
io_uring_files_cancel();
exit_signals(tsk); /* sets PF_EXITING */
- /* sync mm's RSS info before statistics gathering */
- if (tsk->mm)
- sync_mm_rss(tsk->mm);
acct_update_integrals(tsk);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
diff --git a/kernel/fork.c b/kernel/fork.c
index 70e301b63a7b..373fa2f739bc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -733,7 +733,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
get_file(file);
i_mmap_lock_write(mapping);
- if (tmp->vm_flags & VM_SHARED)
+ if (vma_is_shared_maywrite(tmp))
mapping_allow_writable(mapping);
flush_dcache_mmap_lock(mapping);
/* insert tmp into the share list, just after mpnt */
@@ -1288,7 +1288,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
hugetlb_count_init(mm);
if (current->mm) {
- mm->flags = current->mm->flags & MMF_INIT_MASK;
+ mm->flags = mmf_init_flags(current->mm->flags);
mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
} else {
mm->flags = default_dump_filter;
@@ -2411,10 +2411,6 @@ __latent_entropy struct task_struct *copy_process(
p->io_uring = NULL;
#endif
-#if defined(SPLIT_RSS_COUNTING)
- memset(&p->rss_stat, 0, sizeof(p->rss_stat));
-#endif
-
p->default_timer_slack_ns = current->timer_slack_ns;
#ifdef CONFIG_PSI
diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index 0ddbdab5903d..015586217875 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -699,12 +699,9 @@ static void test_barrier_nothreads(struct kunit *test)
KCSAN_EXPECT_RW_BARRIER(spin_unlock(&test_spinlock), true);
KCSAN_EXPECT_RW_BARRIER(mutex_lock(&test_mutex), false);
KCSAN_EXPECT_RW_BARRIER(mutex_unlock(&test_mutex), true);
-
-#ifdef clear_bit_unlock_is_negative_byte
- KCSAN_EXPECT_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
- KCSAN_EXPECT_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
- KCSAN_EXPECT_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
-#endif
+ KCSAN_EXPECT_READ_BARRIER(xor_unlock_is_negative_byte(1, &test_var), true);
+ KCSAN_EXPECT_WRITE_BARRIER(xor_unlock_is_negative_byte(1, &test_var), true);
+ KCSAN_EXPECT_RW_BARRIER(xor_unlock_is_negative_byte(1, &test_var), true);
kcsan_nestable_atomic_end();
}
diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c
index 8679322450f2..84a1200271af 100644
--- a/kernel/kcsan/selftest.c
+++ b/kernel/kcsan/selftest.c
@@ -227,12 +227,9 @@ static bool __init test_barrier(void)
KCSAN_CHECK_RW_BARRIER(arch_spin_unlock(&arch_spinlock));
spin_lock(&test_spinlock);
KCSAN_CHECK_RW_BARRIER(spin_unlock(&test_spinlock));
-
-#ifdef clear_bit_unlock_is_negative_byte
- KCSAN_CHECK_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
- KCSAN_CHECK_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
- KCSAN_CHECK_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
-#endif
+ KCSAN_CHECK_RW_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
+ KCSAN_CHECK_READ_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
+ KCSAN_CHECK_WRITE_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
kcsan_nestable_atomic_end();
return ret;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 1eea53050bab..c46128ec0c0a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1469,7 +1469,6 @@ void kthread_unuse_mm(struct mm_struct *mm)
* clearing tsk->mm.
*/
smp_mb__after_spinlock();
- sync_mm_rss(mm);
local_irq_disable();
tsk->mm = NULL;
membarrier_update_current_mm(NULL);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 443057bee87c..d8b5e13a2229 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -59,7 +59,7 @@ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
return 0;
}
- ret = __access_remote_vm(mm, addr, buf, len, gup_flags);
+ ret = access_remote_vm(mm, addr, buf, len, gup_flags);
mmput(mm);
return ret;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 700524726079..d3a97e129020 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3471,13 +3471,6 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
return freed == 0 ? SHRINK_STOP : freed;
}
-static struct shrinker kfree_rcu_shrinker = {
- .count_objects = kfree_rcu_shrink_count,
- .scan_objects = kfree_rcu_shrink_scan,
- .batch = 0,
- .seeks = DEFAULT_SEEKS,
-};
-
void __init kfree_rcu_scheduler_running(void)
{
int cpu;
@@ -5029,6 +5022,7 @@ static void __init kfree_rcu_batch_init(void)
{
int cpu;
int i, j;
+ struct shrinker *kfree_rcu_shrinker;
/* Clamp it to [0:100] seconds interval. */
if (rcu_delay_page_cache_fill_msec < 0 ||
@@ -5060,8 +5054,17 @@ static void __init kfree_rcu_batch_init(void)
INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func);
krcp->initialized = true;
}
- if (register_shrinker(&kfree_rcu_shrinker, "rcu-kfree"))
- pr_err("Failed to register kfree_rcu() shrinker!\n");
+
+ kfree_rcu_shrinker = shrinker_alloc(0, "rcu-kfree");
+ if (!kfree_rcu_shrinker) {
+ pr_err("Failed to allocate kfree_rcu() shrinker!\n");
+ return;
+ }
+
+ kfree_rcu_shrinker->count_objects = kfree_rcu_shrink_count;
+ kfree_rcu_shrinker->scan_objects = kfree_rcu_shrink_scan;
+
+ shrinker_register(kfree_rcu_shrinker);
}
void __init rcu_init(void)
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 5598212d1f27..4efbf7333d4e 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1396,13 +1396,6 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
return count ? count : SHRINK_STOP;
}
-
-static struct shrinker lazy_rcu_shrinker = {
- .count_objects = lazy_rcu_shrink_count,
- .scan_objects = lazy_rcu_shrink_scan,
- .batch = 0,
- .seeks = DEFAULT_SEEKS,
-};
#endif // #ifdef CONFIG_RCU_LAZY
void __init rcu_init_nohz(void)
@@ -1410,6 +1403,7 @@ void __init rcu_init_nohz(void)
int cpu;
struct rcu_data *rdp;
const struct cpumask *cpumask = NULL;
+ struct shrinker * __maybe_unused lazy_rcu_shrinker;
#if defined(CONFIG_NO_HZ_FULL)
if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask))
@@ -1436,8 +1430,15 @@ void __init rcu_init_nohz(void)
return;
#ifdef CONFIG_RCU_LAZY
- if (register_shrinker(&lazy_rcu_shrinker, "rcu-lazy"))
- pr_err("Failed to register lazy_rcu shrinker!\n");
+ lazy_rcu_shrinker = shrinker_alloc(0, "rcu-lazy");
+ if (!lazy_rcu_shrinker) {
+ pr_err("Failed to allocate lazy_rcu shrinker!\n");
+ } else {
+ lazy_rcu_shrinker->count_objects = lazy_rcu_shrink_count;
+ lazy_rcu_shrinker->scan_objects = lazy_rcu_shrink_scan;
+
+ shrinker_register(lazy_rcu_shrinker);
+ }
#endif // #ifdef CONFIG_RCU_LAZY
if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8767988242ee..2048138ce54b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1759,12 +1759,12 @@ static bool pgdat_free_space_enough(struct pglist_data *pgdat)
* The smaller the hint page fault latency, the higher the possibility
* for the page to be hot.
*/
-static int numa_hint_fault_latency(struct page *page)
+static int numa_hint_fault_latency(struct folio *folio)
{
int last_time, time;
time = jiffies_to_msecs(jiffies);
- last_time = xchg_page_access_time(page, time);
+ last_time = folio_xchg_access_time(folio, time);
return (time - last_time) & PAGE_ACCESS_TIME_MASK;
}
@@ -1821,7 +1821,7 @@ static void numa_promotion_adjust_threshold(struct pglist_data *pgdat,
}
}
-bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
+bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
int src_nid, int dst_cpu)
{
struct numa_group *ng = deref_curr_numa_group(p);
@@ -1851,16 +1851,16 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
numa_promotion_adjust_threshold(pgdat, rate_limit, def_th);
th = pgdat->nbp_threshold ? : def_th;
- latency = numa_hint_fault_latency(page);
+ latency = numa_hint_fault_latency(folio);
if (latency >= th)
return false;
return !numa_promotion_rate_limit(pgdat, rate_limit,
- thp_nr_pages(page));
+ folio_nr_pages(folio));
}
this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
- last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+ last_cpupid = folio_xchg_last_cpupid(folio, this_cpupid);
if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
!node_is_toptier(src_nid) && !cpupid_valid(last_cpupid))
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 802d98cf2de3..51e38f5f4701 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -58,13 +58,6 @@ void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry
EXPORT_SYMBOL(remove_wait_queue);
/*
- * Scan threshold to break wait queue walk.
- * This allows a waker to take a break from holding the
- * wait queue lock during the wait queue walk.
- */
-#define WAITQUEUE_WALK_BREAK_CNT 64
-
-/*
* The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
* wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
* number) then we wake that number of exclusive tasks, and potentially all
@@ -78,21 +71,13 @@ EXPORT_SYMBOL(remove_wait_queue);
* zero in this (rare) case, and we handle it by continuing to scan the queue.
*/
static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
- int nr_exclusive, int wake_flags, void *key,
- wait_queue_entry_t *bookmark)
+ int nr_exclusive, int wake_flags, void *key)
{
wait_queue_entry_t *curr, *next;
- int cnt = 0;
lockdep_assert_held(&wq_head->lock);
- if (bookmark && (bookmark->flags & WQ_FLAG_BOOKMARK)) {
- curr = list_next_entry(bookmark, entry);
-
- list_del(&bookmark->entry);
- bookmark->flags = 0;
- } else
- curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
+ curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
if (&curr->entry == &wq_head->head)
return nr_exclusive;
@@ -101,21 +86,11 @@ static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
unsigned flags = curr->flags;
int ret;
- if (flags & WQ_FLAG_BOOKMARK)
- continue;
-
ret = curr->func(curr, mode, wake_flags, key);
if (ret < 0)
break;
if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
break;
-
- if (bookmark && (++cnt > WAITQUEUE_WALK_BREAK_CNT) &&
- (&next->entry != &wq_head->head)) {
- bookmark->flags = WQ_FLAG_BOOKMARK;
- list_add_tail(&bookmark->entry, &next->entry);
- break;
- }
}
return nr_exclusive;
@@ -125,20 +100,12 @@ static int __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int m
int nr_exclusive, int wake_flags, void *key)
{
unsigned long flags;
- wait_queue_entry_t bookmark;
- int remaining = nr_exclusive;
+ int remaining;
- bookmark.flags = 0;
- bookmark.private = NULL;
- bookmark.func = NULL;
- INIT_LIST_HEAD(&bookmark.entry);
-
- do {
- spin_lock_irqsave(&wq_head->lock, flags);
- remaining = __wake_up_common(wq_head, mode, remaining,
- wake_flags, key, &bookmark);
- spin_unlock_irqrestore(&wq_head->lock, flags);
- } while (bookmark.flags & WQ_FLAG_BOOKMARK);
+ spin_lock_irqsave(&wq_head->lock, flags);
+ remaining = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags,
+ key);
+ spin_unlock_irqrestore(&wq_head->lock, flags);
return nr_exclusive - remaining;
}
@@ -171,23 +138,16 @@ void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode
*/
void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr)
{
- __wake_up_common(wq_head, mode, nr, 0, NULL, NULL);
+ __wake_up_common(wq_head, mode, nr, 0, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_locked);
void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key)
{
- __wake_up_common(wq_head, mode, 1, 0, key, NULL);
+ __wake_up_common(wq_head, mode, 1, 0, key);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_key);
-void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head,
- unsigned int mode, void *key, wait_queue_entry_t *bookmark)
-{
- __wake_up_common(wq_head, mode, 1, 0, key, bookmark);
-}
-EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
-
/**
* __wake_up_sync_key - wake up threads blocked on a waitqueue.
* @wq_head: the waitqueue
@@ -233,7 +193,7 @@ EXPORT_SYMBOL_GPL(__wake_up_sync_key);
void __wake_up_locked_sync_key(struct wait_queue_head *wq_head,
unsigned int mode, void *key)
{
- __wake_up_common(wq_head, mode, 1, WF_SYNC, key, NULL);
+ __wake_up_common(wq_head, mode, 1, WF_SYNC, key);
}
EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key);
diff --git a/kernel/sys.c b/kernel/sys.c
index 2410e3999ebe..4a8073c1b255 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2368,19 +2368,41 @@ static int prctl_set_vma(unsigned long opt, unsigned long start,
}
#endif /* CONFIG_ANON_VMA_NAME */
+static inline unsigned long get_current_mdwe(void)
+{
+ unsigned long ret = 0;
+
+ if (test_bit(MMF_HAS_MDWE, &current->mm->flags))
+ ret |= PR_MDWE_REFUSE_EXEC_GAIN;
+ if (test_bit(MMF_HAS_MDWE_NO_INHERIT, &current->mm->flags))
+ ret |= PR_MDWE_NO_INHERIT;
+
+ return ret;
+}
+
static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
+ unsigned long current_bits;
+
if (arg3 || arg4 || arg5)
return -EINVAL;
- if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN))
+ if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT))
+ return -EINVAL;
+
+ /* NO_INHERIT only makes sense with REFUSE_EXEC_GAIN */
+ if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN))
return -EINVAL;
+ current_bits = get_current_mdwe();
+ if (current_bits && current_bits != bits)
+ return -EPERM; /* Cannot unset the flags */
+
+ if (bits & PR_MDWE_NO_INHERIT)
+ set_bit(MMF_HAS_MDWE_NO_INHERIT, &current->mm->flags);
if (bits & PR_MDWE_REFUSE_EXEC_GAIN)
set_bit(MMF_HAS_MDWE, &current->mm->flags);
- else if (test_bit(MMF_HAS_MDWE, &current->mm->flags))
- return -EPERM; /* Cannot unset the flag */
return 0;
}
@@ -2390,9 +2412,7 @@ static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3,
{
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
-
- return test_bit(MMF_HAS_MDWE, &current->mm->flags) ?
- PR_MDWE_REFUSE_EXEC_GAIN : 0;
+ return get_current_mdwe();
}
static int prctl_get_auxv(void __user *addr, unsigned long len)
generated by cgit (git 2.34.1) at 2024-06-11 18:33:51 +0000