summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/ringbuf.c4
-rw-r--r--kernel/bpf/syscall.c4
-rw-r--r--kernel/crash_core.c4
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/events/uprobes.c5
-rw-r--r--kernel/fork.c23
-rw-r--r--kernel/kcov.c2
-rw-r--r--kernel/pid_namespace.c5
-rw-r--r--kernel/pid_sysctl.h60
-rw-r--r--kernel/relay.c2
-rw-r--r--kernel/sched/fair.c14
-rw-r--r--kernel/sys.c33
12 files changed, 126 insertions, 32 deletions
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 80f4b4d88aaf..8732e0aadf36 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -269,7 +269,7 @@ static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma
if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE)
return -EPERM;
} else {
- vma->vm_flags &= ~VM_MAYWRITE;
+ vm_flags_clear(vma, VM_MAYWRITE);
}
/* remap_vmalloc_range() checks size and offset constraints */
return remap_vmalloc_range(vma, rb_map->rb,
@@ -290,7 +290,7 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma
*/
return -EPERM;
} else {
- vma->vm_flags &= ~VM_MAYWRITE;
+ vm_flags_clear(vma, VM_MAYWRITE);
}
/* remap_vmalloc_range() checks size and offset constraints */
return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e3fcdc9836a6..adc83cb82f37 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -895,10 +895,10 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
/* set default open/close callbacks */
vma->vm_ops = &bpf_map_default_vmops;
vma->vm_private_data = map;
- vma->vm_flags &= ~VM_MAYEXEC;
+ vm_flags_clear(vma, VM_MAYEXEC);
if (!(vma->vm_flags & VM_WRITE))
/* disallow re-mapping with PROT_WRITE */
- vma->vm_flags &= ~VM_MAYWRITE;
+ vm_flags_clear(vma, VM_MAYWRITE);
err = map->ops->map_mmap(map, vma);
if (err)
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 87ef6096823f..755f5f08ab38 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -455,8 +455,8 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_OFFSET(page, lru);
VMCOREINFO_OFFSET(page, _mapcount);
VMCOREINFO_OFFSET(page, private);
- VMCOREINFO_OFFSET(page, compound_dtor);
- VMCOREINFO_OFFSET(page, compound_order);
+ VMCOREINFO_OFFSET(folio, _folio_dtor);
+ VMCOREINFO_OFFSET(folio, _folio_order);
VMCOREINFO_OFFSET(page, compound_head);
VMCOREINFO_OFFSET(pglist_data, node_zones);
VMCOREINFO_OFFSET(pglist_data, nr_zones);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7099c77bc53b..a5a51dfdd622 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6568,7 +6568,7 @@ aux_unlock:
* Since pinned accounting is per vm we cannot allow fork() to copy our
* vma.
*/
- vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
+ vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
vma->vm_ops = &perf_mmap_vmops;
if (event->pmu->event_mapped)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index d9e357b7e17c..59887c69d54c 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -22,7 +22,6 @@
#include <linux/swap.h> /* folio_free_swap */
#include <linux/ptrace.h> /* user_enable_single_step */
#include <linux/kdebug.h> /* notifier mechanism */
-#include "../../mm/internal.h" /* munlock_vma_page */
#include <linux/percpu-rwsem.h>
#include <linux/task_work.h>
#include <linux/shmem_fs.h>
@@ -161,7 +160,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
int err;
struct mmu_notifier_range range;
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr,
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr,
addr + PAGE_SIZE);
if (new_page) {
@@ -1352,7 +1351,7 @@ static int delayed_ref_ctr_inc(struct vm_area_struct *vma)
}
/*
- * Called from mmap_region/vma_adjust with mm->mmap_lock acquired.
+ * Called from mmap_region/vma_merge with mm->mmap_lock acquired.
*
* Currently we ignore all errors and always return 0, the callers
* can't handle the failure anyway.
diff --git a/kernel/fork.c b/kernel/fork.c
index 038b898dad52..f68954d05e89 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -472,7 +472,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
* orig->shared.rb may be modified concurrently, but the clone
* will be reinitialized.
*/
- *new = data_race(*orig);
+ data_race(memcpy(new, orig, sizeof(*new)));
INIT_LIST_HEAD(&new->anon_vma_chain);
dup_anon_vma_name(orig, new);
}
@@ -585,8 +585,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
int retval;
unsigned long charge = 0;
LIST_HEAD(uf);
- MA_STATE(old_mas, &oldmm->mm_mt, 0, 0);
- MA_STATE(mas, &mm->mm_mt, 0, 0);
+ VMA_ITERATOR(old_vmi, oldmm, 0);
+ VMA_ITERATOR(vmi, mm, 0);
uprobe_start_dup_mmap();
if (mmap_write_lock_killable(oldmm)) {
@@ -613,11 +613,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
goto out;
khugepaged_fork(mm, oldmm);
- retval = mas_expected_entries(&mas, oldmm->map_count);
+ retval = vma_iter_bulk_alloc(&vmi, oldmm->map_count);
if (retval)
goto out;
- mas_for_each(&old_mas, mpnt, ULONG_MAX) {
+ for_each_vma(old_vmi, mpnt) {
struct file *file;
if (mpnt->vm_flags & VM_DONTCOPY) {
@@ -659,7 +659,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
tmp->anon_vma = NULL;
} else if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
- tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
+ vm_flags_clear(tmp, VM_LOCKED_MASK);
file = tmp->vm_file;
if (file) {
struct address_space *mapping = file->f_mapping;
@@ -683,11 +683,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
hugetlb_dup_vma_private(tmp);
/* Link the vma into the MT */
- mas.index = tmp->vm_start;
- mas.last = tmp->vm_end - 1;
- mas_store(&mas, tmp);
- if (mas_is_err(&mas))
- goto fail_nomem_mas_store;
+ if (vma_iter_bulk_store(&vmi, tmp))
+ goto fail_nomem_vmi_store;
mm->map_count++;
if (!(tmp->vm_flags & VM_WIPEONFORK))
@@ -702,7 +699,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
/* a new mm has just been created */
retval = arch_dup_mmap(oldmm, mm);
loop_out:
- mas_destroy(&mas);
+ vma_iter_free(&vmi);
out:
mmap_write_unlock(mm);
flush_tlb_mm(oldmm);
@@ -712,7 +709,7 @@ fail_uprobe_end:
uprobe_end_dup_mmap();
return retval;
-fail_nomem_mas_store:
+fail_nomem_vmi_store:
unlink_anon_vmas(tmp);
fail_nomem_anon_vma_fork:
mpol_put(vma_policy(tmp));
diff --git a/kernel/kcov.c b/kernel/kcov.c
index e5cd09fd8a05..84c717337df0 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -489,7 +489,7 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma)
goto exit;
}
spin_unlock_irqrestore(&kcov->lock, flags);
- vma->vm_flags |= VM_DONTEXPAND;
+ vm_flags_set(vma, VM_DONTEXPAND);
for (off = 0; off < size; off += PAGE_SIZE) {
page = vmalloc_to_page(kcov->area + off);
res = vm_insert_page(vma, vma->vm_start + off, page);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index fc21c5d5fd5d..46e0d5a3f91f 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -23,6 +23,7 @@
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
#include <linux/idr.h>
+#include "pid_sysctl.h"
static DEFINE_MUTEX(pid_caches_mutex);
static struct kmem_cache *pid_ns_cachep;
@@ -110,6 +111,8 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
ns->ucounts = ucounts;
ns->pid_allocated = PIDNS_ADDING;
+ initialize_memfd_noexec_scope(ns);
+
return ns;
out_free_idr:
@@ -472,6 +475,8 @@ static __init int pid_namespaces_init(void)
#ifdef CONFIG_CHECKPOINT_RESTORE
register_sysctl_paths(kern_path, pid_ns_ctl_table);
#endif
+
+ register_pid_ns_sysctl_table_vm();
return 0;
}
diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h
new file mode 100644
index 000000000000..e22d072e1e24
--- /dev/null
+++ b/kernel/pid_sysctl.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_PID_SYSCTL_H
+#define LINUX_PID_SYSCTL_H
+
+#include <linux/pid_namespace.h>
+
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns)
+{
+ ns->memfd_noexec_scope =
+ task_active_pid_ns(current)->memfd_noexec_scope;
+}
+
+static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table,
+ int write, void *buf, size_t *lenp, loff_t *ppos)
+{
+ struct pid_namespace *ns = task_active_pid_ns(current);
+ struct ctl_table table_copy;
+
+ if (write && !ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ table_copy = *table;
+ if (ns != &init_pid_ns)
+ table_copy.data = &ns->memfd_noexec_scope;
+
+ /*
+ * set minimum to current value, the effect is only bigger
+ * value is accepted.
+ */
+ if (*(int *)table_copy.data > *(int *)table_copy.extra1)
+ table_copy.extra1 = table_copy.data;
+
+ return proc_dointvec_minmax(&table_copy, write, buf, lenp, ppos);
+}
+
+static struct ctl_table pid_ns_ctl_table_vm[] = {
+ {
+ .procname = "memfd_noexec",
+ .data = &init_pid_ns.memfd_noexec_scope,
+ .maxlen = sizeof(init_pid_ns.memfd_noexec_scope),
+ .mode = 0644,
+ .proc_handler = pid_mfd_noexec_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_TWO,
+ },
+ { }
+};
+static struct ctl_path vm_path[] = { { .procname = "vm", }, { } };
+static inline void register_pid_ns_sysctl_table_vm(void)
+{
+ register_sysctl_paths(vm_path, pid_ns_ctl_table_vm);
+}
+#else
+static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {}
+static inline void set_memfd_noexec_scope(struct pid_namespace *ns) {}
+static inline void register_pid_ns_sysctl_table_vm(void) {}
+#endif
+
+#endif /* LINUX_PID_SYSCTL_H */
diff --git a/kernel/relay.c b/kernel/relay.c
index ef12532168d9..9aa70ae53d24 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -91,7 +91,7 @@ static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma)
return -EINVAL;
vma->vm_ops = &relay_file_mmap_ops;
- vma->vm_flags |= VM_DONTEXPAND;
+ vm_flags_set(vma, VM_DONTEXPAND);
vma->vm_private_data = buf;
return 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ff4dbbae3b10..7a1b1f855b96 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2938,11 +2938,11 @@ static void task_numa_work(struct callback_head *work)
struct task_struct *p = current;
struct mm_struct *mm = p->mm;
u64 runtime = p->se.sum_exec_runtime;
- MA_STATE(mas, &mm->mm_mt, 0, 0);
struct vm_area_struct *vma;
unsigned long start, end;
unsigned long nr_pte_updates = 0;
long pages, virtpages;
+ struct vma_iterator vmi;
SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work));
@@ -2995,16 +2995,16 @@ static void task_numa_work(struct callback_head *work)
if (!mmap_read_trylock(mm))
return;
- mas_set(&mas, start);
- vma = mas_find(&mas, ULONG_MAX);
+ vma_iter_init(&vmi, mm, start);
+ vma = vma_next(&vmi);
if (!vma) {
reset_ptenuma_scan(p);
start = 0;
- mas_set(&mas, start);
- vma = mas_find(&mas, ULONG_MAX);
+ vma_iter_set(&vmi, start);
+ vma = vma_next(&vmi);
}
- for (; vma; vma = mas_find(&mas, ULONG_MAX)) {
+ do {
if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
continue;
@@ -3051,7 +3051,7 @@ static void task_numa_work(struct callback_head *work)
cond_resched();
} while (end != vma->vm_end);
- }
+ } for_each_vma(vmi, vma);
out:
/*
diff --git a/kernel/sys.c b/kernel/sys.c
index 88b31f096fb2..495cd87d9bf4 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2350,6 +2350,33 @@ static int prctl_set_vma(unsigned long opt, unsigned long start,
}
#endif /* CONFIG_ANON_VMA_NAME */
+static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5)
+{
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN))
+ return -EINVAL;
+
+ 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;
+}
+
+static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5)
+{
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ return test_bit(MMF_HAS_MDWE, &current->mm->flags) ?
+ PR_MDWE_REFUSE_EXEC_GAIN : 0;
+}
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -2625,6 +2652,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = sched_core_share_pid(arg2, arg3, arg4, arg5);
break;
#endif
+ case PR_SET_MDWE:
+ error = prctl_set_mdwe(arg2, arg3, arg4, arg5);
+ break;
+ case PR_GET_MDWE:
+ error = prctl_get_mdwe(arg2, arg3, arg4, arg5);
+ break;
case PR_SET_VMA:
error = prctl_set_vma(arg2, arg3, arg4, arg5);
break;
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-03 01:55:55 +0000