aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/memalloc.c9
-rw-r--r--kernel/bpf/syscall.c6
-rw-r--r--kernel/bpf/verifier.c4
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/events/uprobes.c2
-rw-r--r--kernel/exit.c81
-rw-r--r--kernel/fork.c18
-rw-r--r--kernel/power/swap.c5
-rw-r--r--kernel/trace/ftrace.c1
9 files changed, 67 insertions, 61 deletions
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index a546aba46d5d..dec892ded031 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -155,12 +155,9 @@ static void *__alloc(struct bpf_mem_cache *c, int node, gfp_t flags)
static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
{
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
if (c->objcg)
return get_mem_cgroup_from_objcg(c->objcg);
-#endif
-
-#ifdef CONFIG_MEMCG
return root_mem_cgroup;
#else
return NULL;
@@ -534,7 +531,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
size += LLIST_NODE_SZ; /* room for llist_node */
unit_size = size;
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
if (memcg_bpf_enabled())
objcg = get_obj_cgroup_from_current();
#endif
@@ -556,7 +553,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
if (!pcc)
return -ENOMEM;
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
objcg = get_obj_cgroup_from_current();
#endif
ma->objcg = objcg;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 869265852d51..0719192a3482 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -385,7 +385,7 @@ void bpf_map_free_id(struct bpf_map *map)
spin_unlock_irqrestore(&map_idr_lock, flags);
}
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
static void bpf_map_save_memcg(struct bpf_map *map)
{
/* Currently if a map is created by a process belonging to the root
@@ -486,7 +486,7 @@ int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid,
unsigned long i, j;
struct page *pg;
int ret = 0;
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
struct mem_cgroup *memcg, *old_memcg;
memcg = bpf_map_get_memcg(map);
@@ -505,7 +505,7 @@ int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid,
break;
}
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
set_active_memcg(old_memcg);
mem_cgroup_put(memcg);
#endif
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8da132a1ef28..4cb5441ad75f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21132,8 +21132,12 @@ BTF_SET_START(btf_non_sleepable_error_inject)
* Assume non-sleepable from bpf safety point of view.
*/
BTF_ID(func, __filemap_add_folio)
+#ifdef CONFIG_FAIL_PAGE_ALLOC
BTF_ID(func, should_fail_alloc_page)
+#endif
+#ifdef CONFIG_FAILSLAB
BTF_ID(func, should_failslab)
+#endif
BTF_SET_END(btf_non_sleepable_error_inject)
static int check_non_sleepable_error_inject(u32 btf_id)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ab6c4c942f79..a2f3545f31b2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7634,7 +7634,7 @@ again:
pte = ptep_get_lockless(ptep);
if (pte_present(pte))
- size = pte_leaf_size(pte);
+ size = __pte_leaf_size(pmd, pte);
pte_unmap(ptep);
#endif /* CONFIG_HAVE_GUP_FAST */
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 99be2adedbc0..73cc47708679 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -181,7 +181,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
if (new_page) {
folio_get(new_folio);
- folio_add_new_anon_rmap(new_folio, vma, addr);
+ folio_add_new_anon_rmap(new_folio, vma, addr, RMAP_EXCLUSIVE);
folio_add_lru_vma(new_folio, vma);
} else
/* no new page, just dec_mm_counter for old_page */
diff --git a/kernel/exit.c b/kernel/exit.c
index be81342caf1b..7430852a8571 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -438,14 +438,46 @@ static void coredump_task_exit(struct task_struct *tsk)
}
#ifdef CONFIG_MEMCG
+/* drops tasklist_lock if succeeds */
+static bool __try_to_set_owner(struct task_struct *tsk, struct mm_struct *mm)
+{
+ bool ret = false;
+
+ task_lock(tsk);
+ if (likely(tsk->mm == mm)) {
+ /* tsk can't pass exit_mm/exec_mmap and exit */
+ read_unlock(&tasklist_lock);
+ WRITE_ONCE(mm->owner, tsk);
+ lru_gen_migrate_mm(mm);
+ ret = true;
+ }
+ task_unlock(tsk);
+ return ret;
+}
+
+static bool try_to_set_owner(struct task_struct *g, struct mm_struct *mm)
+{
+ struct task_struct *t;
+
+ for_each_thread(g, t) {
+ struct mm_struct *t_mm = READ_ONCE(t->mm);
+ if (t_mm == mm) {
+ if (__try_to_set_owner(t, mm))
+ return true;
+ } else if (t_mm)
+ break;
+ }
+
+ return false;
+}
+
/*
* A task is exiting. If it owned this mm, find a new owner for the mm.
*/
void mm_update_next_owner(struct mm_struct *mm)
{
- struct task_struct *c, *g, *p = current;
+ struct task_struct *g, *p = current;
-retry:
/*
* If the exiting or execing task is not the owner, it's
* someone else's problem.
@@ -466,19 +498,17 @@ retry:
/*
* Search in the children
*/
- list_for_each_entry(c, &p->children, sibling) {
- if (c->mm == mm)
- goto assign_new_owner;
+ list_for_each_entry(g, &p->children, sibling) {
+ if (try_to_set_owner(g, mm))
+ goto ret;
}
-
/*
* Search in the siblings
*/
- list_for_each_entry(c, &p->real_parent->children, sibling) {
- if (c->mm == mm)
- goto assign_new_owner;
+ list_for_each_entry(g, &p->real_parent->children, sibling) {
+ if (try_to_set_owner(g, mm))
+ goto ret;
}
-
/*
* Search through everything else, we should not get here often.
*/
@@ -487,12 +517,8 @@ retry:
break;
if (g->flags & PF_KTHREAD)
continue;
- for_each_thread(g, c) {
- if (c->mm == mm)
- goto assign_new_owner;
- if (c->mm)
- break;
- }
+ if (try_to_set_owner(g, mm))
+ goto ret;
}
read_unlock(&tasklist_lock);
/*
@@ -501,30 +527,9 @@ retry:
* ptrace or page migration (get_task_mm()). Mark owner as NULL.
*/
WRITE_ONCE(mm->owner, NULL);
+ ret:
return;
-assign_new_owner:
- BUG_ON(c == p);
- get_task_struct(c);
- /*
- * The task_lock protects c->mm from changing.
- * We always want mm->owner->mm == mm
- */
- task_lock(c);
- /*
- * Delay read_unlock() till we have the task_lock()
- * to ensure that c does not slip away underneath us
- */
- read_unlock(&tasklist_lock);
- if (c->mm != mm) {
- task_unlock(c);
- put_task_struct(c);
- goto retry;
- }
- WRITE_ONCE(mm->owner, c);
- lru_gen_migrate_mm(mm);
- task_unlock(c);
- put_task_struct(c);
}
#endif /* CONFIG_MEMCG */
diff --git a/kernel/fork.c b/kernel/fork.c
index 942e3d8617bf..ef48f6bdf175 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -44,6 +44,7 @@
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
+#include <linux/memblock.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
@@ -992,10 +993,10 @@ void __init __weak arch_task_cache_init(void) { }
/*
* set_max_threads
*/
-static void set_max_threads(unsigned int max_threads_suggested)
+static void __init set_max_threads(unsigned int max_threads_suggested)
{
u64 threads;
- unsigned long nr_pages = totalram_pages();
+ unsigned long nr_pages = PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size());
/*
* The number of threads shall be limited such that the thread
@@ -1018,7 +1019,7 @@ static void set_max_threads(unsigned int max_threads_suggested)
int arch_task_struct_size __read_mostly;
#endif
-static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
+static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size)
{
/* Fetch thread_struct whitelist for the architecture. */
arch_thread_struct_whitelist(offset, size);
@@ -1519,14 +1520,13 @@ struct mm_struct *get_task_mm(struct task_struct *task)
{
struct mm_struct *mm;
+ if (task->flags & PF_KTHREAD)
+ return NULL;
+
task_lock(task);
mm = task->mm;
- if (mm) {
- if (task->flags & PF_KTHREAD)
- mm = NULL;
- else
- mmget(mm);
- }
+ if (mm)
+ mmget(mm);
task_unlock(task);
return mm;
}
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 753b8dd42a59..82b884b67152 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -200,12 +200,11 @@ void free_all_swap_pages(int swap)
while ((node = swsusp_extents.rb_node)) {
struct swsusp_extent *ext;
- unsigned long offset;
ext = rb_entry(node, struct swsusp_extent, node);
rb_erase(node, &swsusp_extents);
- for (offset = ext->start; offset <= ext->end; offset++)
- swap_free(swp_entry(swap, offset));
+ swap_free_nr(swp_entry(swap, ext->start),
+ ext->end - ext->start + 1);
kfree(ext);
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e5d6a4ab433b..0f579430f02a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7920,6 +7920,7 @@ out:
void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
+ kmsan_unpoison_memory(fregs, sizeof(*fregs));
__ftrace_ops_list_func(ip, parent_ip, NULL, fregs);
}
#else
generated by cgit v1.2.3 (git 2.39.1) at 2026-01-09 20:01:54 +0000