summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/kasan/kasan.h4
-rw-r--r--mm/kasan/shadow.c38
-rw-r--r--mm/madvise.c2
-rw-r--r--mm/memcontrol.c18
-rw-r--r--mm/mincore.c2
-rw-r--r--mm/page_io.c8
-rw-r--r--mm/secretmem.c4
-rw-r--r--mm/shmem.c69
-rw-r--r--mm/swap.c30
-rw-r--r--mm/swapfile.c2
10 files changed, 106 insertions, 71 deletions
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index ea8cf1310b1e..71c15438afcf 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -618,6 +618,10 @@ void __asan_set_shadow_f3(const void *addr, size_t size);
void __asan_set_shadow_f5(const void *addr, size_t size);
void __asan_set_shadow_f8(const void *addr, size_t size);
+void *__asan_memset(void *addr, int c, size_t len);
+void *__asan_memmove(void *dest, const void *src, size_t len);
+void *__asan_memcpy(void *dest, const void *src, size_t len);
+
void __hwasan_load1_noabort(unsigned long addr);
void __hwasan_store1_noabort(unsigned long addr);
void __hwasan_load2_noabort(unsigned long addr);
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index 15cfb34d16a1..3703983a8e55 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -38,6 +38,12 @@ bool __kasan_check_write(const volatile void *p, unsigned int size)
}
EXPORT_SYMBOL(__kasan_check_write);
+#ifndef CONFIG_GENERIC_ENTRY
+/*
+ * CONFIG_GENERIC_ENTRY relies on compiler emitted mem*() calls to not be
+ * instrumented. KASAN enabled toolchains should emit __asan_mem*() functions
+ * for the sites they want to instrument.
+ */
#undef memset
void *memset(void *addr, int c, size_t len)
{
@@ -68,6 +74,38 @@ void *memcpy(void *dest, const void *src, size_t len)
return __memcpy(dest, src, len);
}
+#endif
+
+void *__asan_memset(void *addr, int c, size_t len)
+{
+ if (!kasan_check_range((unsigned long)addr, len, true, _RET_IP_))
+ return NULL;
+
+ return __memset(addr, c, len);
+}
+EXPORT_SYMBOL(__asan_memset);
+
+#ifdef __HAVE_ARCH_MEMMOVE
+void *__asan_memmove(void *dest, const void *src, size_t len)
+{
+ if (!kasan_check_range((unsigned long)src, len, false, _RET_IP_) ||
+ !kasan_check_range((unsigned long)dest, len, true, _RET_IP_))
+ return NULL;
+
+ return __memmove(dest, src, len);
+}
+EXPORT_SYMBOL(__asan_memmove);
+#endif
+
+void *__asan_memcpy(void *dest, const void *src, size_t len)
+{
+ if (!kasan_check_range((unsigned long)src, len, false, _RET_IP_) ||
+ !kasan_check_range((unsigned long)dest, len, true, _RET_IP_))
+ return NULL;
+
+ return __memcpy(dest, src, len);
+}
+EXPORT_SYMBOL(__asan_memcpy);
void kasan_poison(const void *addr, size_t size, u8 value, bool init)
{
diff --git a/mm/madvise.c b/mm/madvise.c
index b6ea204d4e23..18c2e2affac4 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -329,7 +329,7 @@ static inline bool can_do_file_pageout(struct vm_area_struct *vma)
* otherwise we'd be including shared non-exclusive mappings, which
* opens a side channel.
*/
- return inode_owner_or_capable(&init_user_ns,
+ return inode_owner_or_capable(&nop_mnt_idmap,
file_inode(vma->vm_file)) ||
file_permission(vma->vm_file, MAY_WRITE) == 0;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 73afff8062f9..49f40730e711 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -88,6 +88,9 @@ static bool cgroup_memory_nosocket __ro_after_init;
/* Kernel memory accounting disabled? */
static bool cgroup_memory_nokmem __ro_after_init;
+/* BPF memory accounting disabled? */
+static bool cgroup_memory_nobpf __ro_after_init;
+
#ifdef CONFIG_CGROUP_WRITEBACK
static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
#endif
@@ -347,6 +350,9 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
*/
DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
EXPORT_SYMBOL(memcg_kmem_enabled_key);
+
+DEFINE_STATIC_KEY_FALSE(memcg_bpf_enabled_key);
+EXPORT_SYMBOL(memcg_bpf_enabled_key);
#endif
/**
@@ -5357,6 +5363,11 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
static_branch_inc(&memcg_sockets_enabled_key);
+#if defined(CONFIG_MEMCG_KMEM)
+ if (!cgroup_memory_nobpf)
+ static_branch_inc(&memcg_bpf_enabled_key);
+#endif
+
return &memcg->css;
}
@@ -5441,6 +5452,11 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_active)
static_branch_dec(&memcg_sockets_enabled_key);
+#if defined(CONFIG_MEMCG_KMEM)
+ if (!cgroup_memory_nobpf)
+ static_branch_dec(&memcg_bpf_enabled_key);
+#endif
+
vmpressure_cleanup(&memcg->vmpressure);
cancel_work_sync(&memcg->high_work);
mem_cgroup_remove_from_trees(memcg);
@@ -7269,6 +7285,8 @@ static int __init cgroup_memory(char *s)
cgroup_memory_nosocket = true;
if (!strcmp(token, "nokmem"))
cgroup_memory_nokmem = true;
+ if (!strcmp(token, "nobpf"))
+ cgroup_memory_nobpf = true;
}
return 1;
}
diff --git a/mm/mincore.c b/mm/mincore.c
index a085a2aeabd8..cd69b9db0081 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -168,7 +168,7 @@ static inline bool can_do_mincore(struct vm_area_struct *vma)
* for writing; otherwise we'd be including shared non-exclusive
* mappings, which opens a side channel.
*/
- return inode_owner_or_capable(&init_user_ns,
+ return inode_owner_or_capable(&nop_mnt_idmap,
file_inode(vma->vm_file)) ||
file_permission(vma->vm_file, MAY_WRITE) == 0;
}
diff --git a/mm/page_io.c b/mm/page_io.c
index 3a5f921b932e..233f6e6eb1c5 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -318,9 +318,7 @@ static int swap_writepage_fs(struct page *page, struct writeback_control *wbc)
sio->pages = 0;
sio->len = 0;
}
- sio->bvec[sio->pages].bv_page = page;
- sio->bvec[sio->pages].bv_len = thp_size(page);
- sio->bvec[sio->pages].bv_offset = 0;
+ bvec_set_page(&sio->bvec[sio->pages], page, thp_size(page), 0);
sio->len += thp_size(page);
sio->pages += 1;
if (sio->pages == ARRAY_SIZE(sio->bvec) || !wbc->swap_plug) {
@@ -432,9 +430,7 @@ static void swap_readpage_fs(struct page *page,
sio->pages = 0;
sio->len = 0;
}
- sio->bvec[sio->pages].bv_page = page;
- sio->bvec[sio->pages].bv_len = thp_size(page);
- sio->bvec[sio->pages].bv_offset = 0;
+ bvec_set_page(&sio->bvec[sio->pages], page, thp_size(page), 0);
sio->len += thp_size(page);
sio->pages += 1;
if (sio->pages == ARRAY_SIZE(sio->bvec) || !plug) {
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 04c3ac9448a1..afcf46e99cda 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -162,7 +162,7 @@ const struct address_space_operations secretmem_aops = {
.migrate_folio = secretmem_migrate_folio,
};
-static int secretmem_setattr(struct user_namespace *mnt_userns,
+static int secretmem_setattr(struct mnt_idmap *idmap,
struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
@@ -175,7 +175,7 @@ static int secretmem_setattr(struct user_namespace *mnt_userns,
if ((ia_valid & ATTR_SIZE) && inode->i_size)
ret = -EINVAL;
else
- ret = simple_setattr(mnt_userns, dentry, iattr);
+ ret = simple_setattr(idmap, dentry, iattr);
filemap_invalidate_unlock(mapping);
diff --git a/mm/shmem.c b/mm/shmem.c
index 0005ab2c29af..41f82c5a5e28 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1045,7 +1045,7 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
-static int shmem_getattr(struct user_namespace *mnt_userns,
+static int shmem_getattr(struct mnt_idmap *idmap,
const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
@@ -1066,7 +1066,7 @@ static int shmem_getattr(struct user_namespace *mnt_userns,
stat->attributes_mask |= (STATX_ATTR_APPEND |
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP);
- generic_fillattr(&init_user_ns, inode, stat);
+ generic_fillattr(idmap, inode, stat);
if (shmem_is_huge(NULL, inode, 0, false))
stat->blksize = HPAGE_PMD_SIZE;
@@ -1080,7 +1080,7 @@ static int shmem_getattr(struct user_namespace *mnt_userns,
return 0;
}
-static int shmem_setattr(struct user_namespace *mnt_userns,
+static int shmem_setattr(struct mnt_idmap *idmap,
struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
@@ -1089,7 +1089,7 @@ static int shmem_setattr(struct user_namespace *mnt_userns,
bool update_mtime = false;
bool update_ctime = true;
- error = setattr_prepare(&init_user_ns, dentry, attr);
+ error = setattr_prepare(idmap, dentry, attr);
if (error)
return error;
@@ -1127,9 +1127,9 @@ static int shmem_setattr(struct user_namespace *mnt_userns,
}
}
- setattr_copy(&init_user_ns, inode, attr);
+ setattr_copy(idmap, inode, attr);
if (attr->ia_valid & ATTR_MODE)
- error = posix_acl_chmod(&init_user_ns, dentry, inode->i_mode);
+ error = posix_acl_chmod(idmap, dentry, inode->i_mode);
if (!error && update_ctime) {
inode->i_ctime = current_time(inode);
if (update_mtime)
@@ -2327,8 +2327,9 @@ static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags)
#define shmem_initxattrs NULL
#endif
-static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir,
- umode_t mode, dev_t dev, unsigned long flags)
+static struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb,
+ struct inode *dir, umode_t mode, dev_t dev,
+ unsigned long flags)
{
struct inode *inode;
struct shmem_inode_info *info;
@@ -2341,7 +2342,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir,
inode = new_inode(sb);
if (inode) {
inode->i_ino = ino;
- inode_init_owner(&init_user_ns, inode, dir, mode);
+ inode_init_owner(idmap, inode, dir, mode);
inode->i_blocks = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
inode->i_generation = get_random_u32();
@@ -2913,13 +2914,13 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
* File creation. Allocate an inode, and we're done..
*/
static int
-shmem_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+shmem_mknod(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode *inode;
int error = -ENOSPC;
- inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE);
+ inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, dev, VM_NORESERVE);
if (inode) {
error = simple_acl_create(dir, inode);
if (error)
@@ -2944,13 +2945,13 @@ out_iput:
}
static int
-shmem_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+shmem_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
struct file *file, umode_t mode)
{
struct inode *inode;
int error = -ENOSPC;
- inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE);
+ inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, 0, VM_NORESERVE);
if (inode) {
error = security_inode_init_security(inode, dir,
NULL,
@@ -2968,22 +2969,22 @@ out_iput:
return error;
}
-static int shmem_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+static int shmem_mkdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode)
{
int error;
- if ((error = shmem_mknod(&init_user_ns, dir, dentry,
- mode | S_IFDIR, 0)))
+ error = shmem_mknod(idmap, dir, dentry, mode | S_IFDIR, 0);
+ if (error)
return error;
inc_nlink(dir);
return 0;
}
-static int shmem_create(struct user_namespace *mnt_userns, struct inode *dir,
+static int shmem_create(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, bool excl)
{
- return shmem_mknod(&init_user_ns, dir, dentry, mode | S_IFREG, 0);
+ return shmem_mknod(idmap, dir, dentry, mode | S_IFREG, 0);
}
/*
@@ -3043,7 +3044,7 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry)
return shmem_unlink(dir, dentry);
}
-static int shmem_whiteout(struct user_namespace *mnt_userns,
+static int shmem_whiteout(struct mnt_idmap *idmap,
struct inode *old_dir, struct dentry *old_dentry)
{
struct dentry *whiteout;
@@ -3053,7 +3054,7 @@ static int shmem_whiteout(struct user_namespace *mnt_userns,
if (!whiteout)
return -ENOMEM;
- error = shmem_mknod(&init_user_ns, old_dir, whiteout,
+ error = shmem_mknod(idmap, old_dir, whiteout,
S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
dput(whiteout);
if (error)
@@ -3076,7 +3077,7 @@ static int shmem_whiteout(struct user_namespace *mnt_userns,
* it exists so that the VFS layer correctly free's it when it
* gets overwritten.
*/
-static int shmem_rename2(struct user_namespace *mnt_userns,
+static int shmem_rename2(struct mnt_idmap *idmap,
struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
@@ -3096,7 +3097,7 @@ static int shmem_rename2(struct user_namespace *mnt_userns,
if (flags & RENAME_WHITEOUT) {
int error;
- error = shmem_whiteout(&init_user_ns, old_dir, old_dentry);
+ error = shmem_whiteout(idmap, old_dir, old_dentry);
if (error)
return error;
}
@@ -3122,7 +3123,7 @@ static int shmem_rename2(struct user_namespace *mnt_userns,
return 0;
}
-static int shmem_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, const char *symname)
{
int error;
@@ -3134,7 +3135,7 @@ static int shmem_symlink(struct user_namespace *mnt_userns, struct inode *dir,
if (len > PAGE_SIZE)
return -ENAMETOOLONG;
- inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK | 0777, 0,
+ inode = shmem_get_inode(idmap, dir->i_sb, dir, S_IFLNK | 0777, 0,
VM_NORESERVE);
if (!inode)
return -ENOSPC;
@@ -3227,7 +3228,7 @@ static int shmem_fileattr_get(struct dentry *dentry, struct fileattr *fa)
return 0;
}
-static int shmem_fileattr_set(struct user_namespace *mnt_userns,
+static int shmem_fileattr_set(struct mnt_idmap *idmap,
struct dentry *dentry, struct fileattr *fa)
{
struct inode *inode = d_inode(dentry);
@@ -3301,7 +3302,7 @@ static int shmem_xattr_handler_get(const struct xattr_handler *handler,
}
static int shmem_xattr_handler_set(const struct xattr_handler *handler,
- struct user_namespace *mnt_userns,
+ struct mnt_idmap *idmap,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
@@ -3817,7 +3818,8 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
#endif
uuid_gen(&sb->s_uuid);
- inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE);
+ inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, S_IFDIR | sbinfo->mode, 0,
+ VM_NORESERVE);
if (!inode)
goto failed;
inode->i_uid = sbinfo->uid;
@@ -4042,7 +4044,11 @@ static struct file_system_type shmem_fs_type = {
.parameters = shmem_fs_parameters,
#endif
.kill_sb = kill_litter_super,
+#ifdef CONFIG_SHMEM
+ .fs_flags = FS_USERNS_MOUNT | FS_ALLOW_IDMAP,
+#else
.fs_flags = FS_USERNS_MOUNT,
+#endif
};
void __init shmem_init(void)
@@ -4194,7 +4200,7 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
#define shmem_vm_ops generic_file_vm_ops
#define shmem_anon_vm_ops generic_file_vm_ops
#define shmem_file_operations ramfs_file_operations
-#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev)
+#define shmem_get_inode(idmap, sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev)
#define shmem_acct_size(flags, size) 0
#define shmem_unacct_size(flags, size) do {} while (0)
@@ -4217,8 +4223,11 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
if (shmem_acct_size(flags, size))
return ERR_PTR(-ENOMEM);
- inode = shmem_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0,
- flags);
+ if (is_idmapped_mnt(mnt))
+ return ERR_PTR(-EINVAL);
+
+ inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL,
+ S_IFREG | S_IRWXUGO, 0, flags);
if (unlikely(!inode)) {
shmem_unacct_size(flags, size);
return ERR_PTR(-ENOSPC);
diff --git a/mm/swap.c b/mm/swap.c
index 70e2063ef43a..4c03ecab698e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -158,36 +158,6 @@ void put_pages_list(struct list_head *pages)
}
EXPORT_SYMBOL(put_pages_list);
-/*
- * get_kernel_pages() - pin kernel pages in memory
- * @kiov: An array of struct kvec structures
- * @nr_segs: number of segments to pin
- * @write: pinning for read/write, currently ignored
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_segs long.
- *
- * Returns number of pages pinned. This may be fewer than the number requested.
- * If nr_segs is 0 or negative, returns 0. If no pages were pinned, returns 0.
- * Each page returned must be released with a put_page() call when it is
- * finished with.
- */
-int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
- struct page **pages)
-{
- int seg;
-
- for (seg = 0; seg < nr_segs; seg++) {
- if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE))
- return seg;
-
- pages[seg] = kmap_to_page(kiov[seg].iov_base);
- get_page(pages[seg]);
- }
-
- return seg;
-}
-EXPORT_SYMBOL_GPL(get_kernel_pages);
-
typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio);
static void lru_add_fn(struct lruvec *lruvec, struct folio *folio)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index eb9b0bf1fcdd..0ab52d16bde6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3651,7 +3651,7 @@ void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
* We've already scheduled a throttle, avoid taking the global swap
* lock.
*/
- if (current->throttle_queue)
+ if (current->throttle_disk)
return;
spin_lock(&swap_avail_lock);
generated by cgit v1.2.3 (git 2.39.0) at 2024-07-15 17:48:44 +0300