S: Supported
W: https://github.com/linux-audit
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git
+Q: https://patchwork.kernel.org/project/audit/list
+P: https://github.com/linux-audit/audit-kernel/blob/main/README.md
+T: git https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git
F: include/asm-generic/audit_*.h
F: include/linux/audit.h
F: include/linux/audit_arch.h
F: include/uapi/linux/audit.h
F: kernel/audit*
F: lib/*audit.c
+K: \baudit_[a-z_0-9]\+\b
AUXILIARY BUS DRIVER
F: Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml
F: drivers/hwmon/axi-fan-control.c
+AXI SPI ENGINE
+S: Supported
+W: https://ez.analog.com/linux-software-drivers
+F: Documentation/devicetree/bindings/spi/adi,axi-spi-engine.yaml
+F: drivers/spi/spi-axi-spi-engine.c
+
AXXIA I2C CONTROLLER
BCACHE (BLOCK LAYER CACHE)
-M: Kent Overstreet <kent.overstreet@gmail.com>
+M: Kent Overstreet <kent.overstreet@linux.dev>
S: Maintained
W: http://bcache.evilpiepirate.org
S: Supported
F: drivers/net/wireless/broadcom/brcm80211/
S: Maintained
F: mm/memcontrol.c
F: mm/swap_cgroup.c
+F: samples/cgroup/*
F: tools/testing/selftests/cgroup/memcg_protection.m
F: tools/testing/selftests/cgroup/test_hugetlb_memcg.c
F: tools/testing/selftests/cgroup/test_kmem.c
F: include/linux/crypto*
F: lib/crypto/
+CRYPTO SPEED TEST COMPARE
+S: Maintained
+F: tools/crypto/tcrypt/tcrypt_speed_compare.py
+
CRYPTOGRAPHIC RANDOM NUMBER GENERATOR
F: drivers/gpu/drm/vboxvideo/
DRM DRIVER FOR VMWARE VIRTUAL GPU
-M: Zack Rusin <zackr@vmware.com>
-R: VMware Graphics Reviewers <linux-graphics-maintainer@vmware.com>
+M: Zack Rusin <zack.rusin@broadcom.com>
+R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
S: Supported
T: git git://anongit.freedesktop.org/drm/drm-misc
Extended Verification Module (EVM)
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity.git
FILESYSTEMS (VFS and infrastructure)
S: Maintained
F: fs/*
F: fs/fhandle.c
F: include/linux/exportfs.h
+FILESYSTEMS [IDMAPPED MOUNTS]
+S: Maintained
+F: Documentation/filesystems/idmappings.rst
+F: fs/mnt_idmapping.c
+F: include/linux/mnt_idmapping.*
+F: tools/testing/selftests/mount_setattr/
+
FILESYSTEMS [IOMAP]
F: fs/iomap/
F: include/linux/iomap.h
+FILESYSTEMS [STACKABLE]
+S: Maintained
+F: fs/backing-file.c
+F: include/linux/backing-file.h
+
FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER
F: tools/testing/selftests/gpio/
GPIO REGMAP
S: Maintained
F: drivers/gpio/gpio-regmap.c
F: include/linux/gpio/regmap.h
GPIO SUBSYSTEM
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git
-F: Documentation/ABI/obsolete/sysfs-gpio
-F: Documentation/ABI/testing/gpio-cdev
F: Documentation/admin-guide/gpio/
F: Documentation/devicetree/bindings/gpio/
F: Documentation/driver-api/gpio/
F: include/linux/gpio.h
F: include/linux/gpio/
F: include/linux/of_gpio.h
+
+GPIO UAPI
+S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git
+F: Documentation/ABI/obsolete/sysfs-gpio
+F: Documentation/ABI/testing/gpio-cdev
+F: drivers/gpio/gpiolib-cdev.c
F: include/uapi/linux/gpio.h
F: tools/gpio/
F: include/linux/hw_random.h
HARDWARE SPINLOCK CORE
F: drivers/gpio/gpio-hisi.c
HISILICON HIGH PERFORMANCE RSA ENGINE DRIVER (HPRE)
S: Maintained
F: drivers/scsi/hisi_sas/
HISILICON SECURITY ENGINE V2 DRIVER (SEC2)
S: Maintained
F: drivers/net/ethernet/huawei/hinic/
HUGETLB SUBSYSTEM
S: Maintained
F: drivers/media/platform/st/sti/hva
HWPOISON MEMORY FAILURE HANDLING
-M: Naoya Horiguchi <naoya.horiguchi@nec.com>
-R: Miaohe Lin <linmiaohe@huawei.com>
+M: Miaohe Lin <linmiaohe@huawei.com>
+R: Naoya Horiguchi <naoya.horiguchi@nec.com>
S: Maintained
F: mm/hwpoison-inject.c
W: https://github.com/o2genum/ideapad-slidebar
F: drivers/input/misc/ideapad_slidebar.c
-IDMAPPED MOUNTS
-S: Maintained
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping.git
-F: Documentation/filesystems/idmappings.rst
-F: include/linux/mnt_idmapping.*
-F: tools/testing/selftests/mount_setattr/
-
IDT VersaClock 5 CLOCK DRIVER
S: Maintained
INTEGRITY MEASUREMENT ARCHITECTURE (IMA)
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity.git
F: drivers/gpio/gpio-sch.c
F: drivers/gpio/gpio-sodaville.c
F: drivers/gpio/gpio-tangier.c
+F: drivers/gpio/gpio-tangier.h
INTEL GVT-g DRIVERS (Intel GPU Virtualization)
Q: https://patchwork.kernel.org/project/linux-dmaengine/list/
F: drivers/dma/ioat*
+INTEL IAA CRYPTO DRIVER
+S: Supported
+F: Documentation/driver-api/crypto/iaa/iaa-crypto.rst
+F: drivers/crypto/intel/iaa/*
+
INTEL IDLE DRIVER
F: scripts/Kbuild*
F: scripts/Makefile*
F: scripts/basic/
+F: scripts/clang-tools/
F: scripts/dummy-tools/
F: scripts/mk*
F: scripts/mod/
F: arch/powerpc/platforms/40x/
F: arch/powerpc/platforms/44x/
-LINUX FOR POWERPC EMBEDDED PPC83XX AND PPC85XX
+LINUX FOR POWERPC EMBEDDED PPC85XX
S: Odd fixes
T: git git://git.kernel.org/pub/scm/linux/kernel/git/scottwood/linux.git
F: Documentation/devicetree/bindings/cache/freescale-l2cache.txt
F: Documentation/devicetree/bindings/powerpc/fsl/
-F: arch/powerpc/platforms/83xx/
F: arch/powerpc/platforms/85xx/
-LINUX FOR POWERPC EMBEDDED PPC8XX
+LINUX FOR POWERPC EMBEDDED PPC8XX AND PPC83XX
S: Maintained
F: arch/powerpc/platforms/8xx/
+F: arch/powerpc/platforms/83xx/
LINUX KERNEL DUMP TEST MODULE (LKDTM)
F: Documentation/admin-guide/LSM/LoadPin.rst
F: security/loadpin/
+LOCKDOWN SECURITY MODULE
+S: Odd Fixes
+T: git https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm.git
+F: security/lockdown/
+
LOCKING PRIMITIVES
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
F: Documentation/locking/
F: arch/*/include/asm/spinlock*.h
-F: include/linux/lockdep.h
+F: include/linux/lockdep*.h
F: include/linux/mutex*.h
F: include/linux/rwlock*.h
F: include/linux/rwsem*.h
F: drivers/net/ethernet/marvell/mvneta.*
MARVELL MVPP2 ETHERNET DRIVER
-M: Marcin Wojtas <mw@semihalf.com>
+M: Marcin Wojtas <marcin.s.wojtas@gmail.com>
S: Maintained
NETWORKING [MPTCP]
S: Maintained
F: drivers/bluetooth/btnxpuart.c
NXP C45 TJA11XX PHY DRIVER
S: Maintained
F: drivers/net/phy/nxp-c45-tja11xx.c
F: drivers/gpio/gpio-omap.c
OMAP HARDWARE SPINLOCK SUPPORT
-S: Maintained
+S: Orphan
F: drivers/hwspinlock/omap_hwspinlock.c
OMAP HS MMC SUPPORT
F: drivers/pci/controller/dwc/pcie-armada8k.c
PCI DRIVER FOR CADENCE PCIE IP
-S: Maintained
+S: Orphan
F: Documentation/devicetree/bindings/pci/cdns,*
-F: drivers/pci/controller/cadence/
+F: drivers/pci/controller/cadence/*cadence*
PCI DRIVER FOR FREESCALE LAYERSCAPE
PROC SYSCTL
- M: Iurii Zaikin <yzaikin@google.com>
+ M: Joel Granados <j.granados@samsung.com>
S: Maintained
S: Supported
-W: http://kernsec.org/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm.git
+Q: https://patchwork.kernel.org/project/linux-security-module/list
+P: https://github.com/LinuxSecurityModule/kernel/blob/main/README.md
+T: git https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm.git
+F: include/uapi/linux/lsm.h
F: security/
+F: tools/testing/selftests/lsm/
X: security/selinux/
+K: \bsecurity_[a-z_0-9]\+\b
SELINUX SECURITY MODULE
S: Supported
-W: https://selinuxproject.org
W: https://github.com/SELinuxProject
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux.git
+Q: https://patchwork.kernel.org/project/selinux/list
+P: https://github.com/SELinuxProject/selinux-kernel/blob/main/README.md
+T: git https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux.git
F: Documentation/ABI/removed/sysfs-selinux-checkreqprot
F: Documentation/ABI/removed/sysfs-selinux-disable
F: Documentation/admin-guide/LSM/SELinux.rst
F: drivers/usb/misc/sisusbvga/
SL28 CPLD MFD DRIVER
S: Maintained
F: Documentation/devicetree/bindings/gpio/kontron,sl28cpld-gpio.yaml
F: Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml
F: drivers/watchdog/sl28cpld_wdt.c
SL28 VPD NVMEM LAYOUT DRIVER
S: Maintained
F: Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml
F: drivers/nvmem/layouts/sl28vpd.c
SPI NOR SUBSYSTEM
S: Maintained
W: http://www.linux-mtd.infradead.org/
S: Maintained
F: drivers/mmc/host/dw_mmc*
+SYNOPSYS DESIGNWARE PCIE PMU DRIVER
+S: Supported
+F: Documentation/admin-guide/perf/dwc_pcie_pmu.rst
+F: drivers/perf/dwc_pcie_pmu.c
+
SYNOPSYS HSDK RESET CONTROLLER DRIVER
S: Supported
F: include/linux/ulpi/
UNICODE SUBSYSTEM
-M: Gabriel Krisman Bertazi <krisman@collabora.com>
+M: Gabriel Krisman Bertazi <krisman@kernel.org>
S: Supported
F: fs/unicode/
F: include/linux/vmw_vmci*
VMWARE VMMOUSE SUBDRIVER
S: Supported
F: drivers/input/mouse/vmmouse.c
F: drivers/platform/x86/
F: include/linux/platform_data/x86/
-X86 PLATFORM DRIVERS - ARCH
-S: Maintained
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
-F: arch/x86/platform
-
X86 PLATFORM UV HPE SUPERDOME FLEX
W: http://xfs.org/
C: irc://irc.oftc.net/xfs
T: git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git
-P: Documentation/filesystems/xfs-maintainer-entry-profile.rst
+P: Documentation/filesystems/xfs/xfs-maintainer-entry-profile.rst
F: Documentation/ABI/testing/sysfs-fs-xfs
F: Documentation/admin-guide/xfs.rst
-F: Documentation/filesystems/xfs-*
+F: Documentation/filesystems/xfs/*
F: fs/xfs/
F: include/uapi/linux/dqblk_xfs.h
F: include/uapi/linux/fsmap.h
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
- {}
};
static void __init aio_sysctl_init(void)
return ERR_CAST(inode);
inode->i_mapping->a_ops = &aio_ctx_aops;
- inode->i_mapping->private_data = ctx;
+ inode->i_mapping->i_private_data = ctx;
inode->i_size = PAGE_SIZE * nr_pages;
file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
/* Prevent further access to the kioctx from migratepages */
i_mapping = aio_ring_file->f_mapping;
- spin_lock(&i_mapping->private_lock);
- i_mapping->private_data = NULL;
+ spin_lock(&i_mapping->i_private_lock);
+ i_mapping->i_private_data = NULL;
ctx->aio_ring_file = NULL;
- spin_unlock(&i_mapping->private_lock);
+ spin_unlock(&i_mapping->i_private_lock);
fput(aio_ring_file);
}
rc = 0;
- /* mapping->private_lock here protects against the kioctx teardown. */
- spin_lock(&mapping->private_lock);
- ctx = mapping->private_data;
+ /* mapping->i_private_lock here protects against the kioctx teardown. */
+ spin_lock(&mapping->i_private_lock);
+ ctx = mapping->i_private_data;
if (!ctx) {
rc = -EINVAL;
goto out;
out_unlock:
mutex_unlock(&ctx->ring_lock);
out:
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
return rc;
}
#else
kmem_cache_free(kiocb_cachep, iocb);
}
+struct aio_waiter {
+ struct wait_queue_entry w;
+ size_t min_nr;
+};
+
/* aio_complete
* Called when the io request on the given iocb is complete.
*/
struct kioctx *ctx = iocb->ki_ctx;
struct aio_ring *ring;
struct io_event *ev_page, *event;
- unsigned tail, pos, head;
+ unsigned tail, pos, head, avail;
unsigned long flags;
/*
ctx->completed_events++;
if (ctx->completed_events > 1)
refill_reqs_available(ctx, head, tail);
+
+ avail = tail > head
+ ? tail - head
+ : tail + ctx->nr_events - head;
spin_unlock_irqrestore(&ctx->completion_lock, flags);
pr_debug("added to ring %p at [%u]\n", iocb, tail);
* from IRQ context.
*/
if (iocb->ki_eventfd)
- eventfd_signal(iocb->ki_eventfd, 1);
+ eventfd_signal(iocb->ki_eventfd);
/*
* We have to order our ring_info tail store above and test
*/
smp_mb();
- if (waitqueue_active(&ctx->wait))
- wake_up(&ctx->wait);
+ if (waitqueue_active(&ctx->wait)) {
+ struct aio_waiter *curr, *next;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->wait.lock, flags);
+ list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry)
+ if (avail >= curr->min_nr) {
+ list_del_init_careful(&curr->w.entry);
+ wake_up_process(curr->w.private);
+ }
+ spin_unlock_irqrestore(&ctx->wait.lock, flags);
+ }
}
static inline void iocb_put(struct aio_kiocb *iocb)
struct io_event __user *event,
ktime_t until)
{
- long ret = 0;
+ struct hrtimer_sleeper t;
+ struct aio_waiter w;
+ long ret = 0, ret2 = 0;
/*
* Note that aio_read_events() is being called as the conditional - i.e.
* the ringbuffer empty. So in practice we should be ok, but it's
* something to be aware of when touching this code.
*/
- if (until == 0)
- aio_read_events(ctx, min_nr, nr, event, &ret);
- else
- wait_event_interruptible_hrtimeout(ctx->wait,
- aio_read_events(ctx, min_nr, nr, event, &ret),
- until);
+ aio_read_events(ctx, min_nr, nr, event, &ret);
+ if (until == 0 || ret < 0 || ret >= min_nr)
+ return ret;
+
+ hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ if (until != KTIME_MAX) {
+ hrtimer_set_expires_range_ns(&t.timer, until, current->timer_slack_ns);
+ hrtimer_sleeper_start_expires(&t, HRTIMER_MODE_REL);
+ }
+
+ init_wait(&w.w);
+
+ while (1) {
+ unsigned long nr_got = ret;
+
+ w.min_nr = min_nr - ret;
+
+ ret2 = prepare_to_wait_event(&ctx->wait, &w.w, TASK_INTERRUPTIBLE);
+ if (!ret2 && !t.task)
+ ret2 = -ETIME;
+
+ if (aio_read_events(ctx, min_nr, nr, event, &ret) || ret2)
+ break;
+
+ if (nr_got == ret)
+ schedule();
+ }
+
+ finish_wait(&ctx->wait, &w.w);
+ hrtimer_cancel(&t.timer);
+ destroy_hrtimer_on_stack(&t.timer);
+
return ret;
}
size_t len = iocb->aio_nbytes;
if (!vectored) {
- ssize_t ret = import_single_range(rw, buf, len, *iovec, iter);
+ ssize_t ret = import_ubuf(rw, buf, len, iter);
*iovec = NULL;
return ret;
}
.mode = 0444,
.proc_handler = proc_nr_dentry,
},
- { }
};
static int __init init_fs_dcache_sysctls(void)
this_cpu_inc(nr_dentry_unused);
if (d_is_negative(dentry))
this_cpu_inc(nr_dentry_negative);
- WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
+ WARN_ON_ONCE(!list_lru_add_obj(
+ &dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
static void d_lru_del(struct dentry *dentry)
this_cpu_dec(nr_dentry_unused);
if (d_is_negative(dentry))
this_cpu_dec(nr_dentry_negative);
- WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
+ WARN_ON_ONCE(!list_lru_del_obj(
+ &dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
static void d_shrink_del(struct dentry *dentry)
*
* This is guaranteed by the fact that all LRU management
* functions are intermediated by the LRU API calls like
- * list_lru_add and list_lru_del. List movement in this file
+ * list_lru_add_obj and list_lru_del_obj. List movement in this file
* only ever occur through this functions or through callbacks
* like this one, that are called from the LRU API.
*
#include <linux/coredump.h>
#include <linux/time_namespace.h>
#include <linux/user_events.h>
+#include <linux/rseq.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
* will be able to manipulate the current directory, etc.
* It would be nice to force an unshare instead...
*/
- t = p;
n_fs = 1;
spin_lock(&p->fs->lock);
rcu_read_lock();
- while_each_thread(p, t) {
+ for_other_threads(p, t) {
if (t->fs == p->fs)
n_fs++;
}
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
- { }
};
static int __init init_fs_exec_sysctls(void)
}
}
-void release_empty_file(struct file *f)
-{
- WARN_ON_ONCE(f->f_mode & (FMODE_BACKING | FMODE_OPENED));
- if (atomic_long_dec_and_test(&f->f_count)) {
- security_file_free(f);
- put_cred(f->f_cred);
- if (likely(!(f->f_mode & FMODE_NOACCOUNT)))
- percpu_counter_dec(&nr_files);
- kmem_cache_free(filp_cachep, f);
- }
-}
-
/*
* Return the total number of open files in the system
*/
.extra1 = &sysctl_nr_open_min,
.extra2 = &sysctl_nr_open_max,
},
- { }
};
static int __init init_fs_stat_sysctls(void)
static void ____fput(struct callback_head *work)
{
- __fput(container_of(work, struct file, f_rcuhead));
+ __fput(container_of(work, struct file, f_task_work));
}
/*
if (atomic_long_dec_and_test(&file->f_count)) {
struct task_struct *task = current;
+ if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) {
+ file_free(file);
+ return;
+ }
if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
- init_task_work(&file->f_rcuhead, ____fput);
- if (!task_work_add(task, &file->f_rcuhead, TWA_RESUME))
+ init_task_work(&file->f_task_work, ____fput);
+ if (!task_work_add(task, &file->f_task_work, TWA_RESUME))
return;
/*
* After this task has run exit_task_work(),
.mode = 0444,
.proc_handler = proc_nr_inodes,
},
- { }
};
static int __init init_fs_inode_sysctls(void)
atomic_set(&mapping->nr_thps, 0);
#endif
mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
- mapping->private_data = NULL;
+ mapping->i_private_data = NULL;
mapping->writeback_index = 0;
init_rwsem(&mapping->invalidate_lock);
lockdep_set_class_and_name(&mapping->invalidate_lock,
{
xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT);
init_rwsem(&mapping->i_mmap_rwsem);
- INIT_LIST_HEAD(&mapping->private_list);
- spin_lock_init(&mapping->private_lock);
+ INIT_LIST_HEAD(&mapping->i_private_list);
+ spin_lock_init(&mapping->i_private_lock);
mapping->i_mmap = RB_ROOT_CACHED;
}
if (!mapping_shrinkable(&inode->i_data))
return;
- if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
+ if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_inc(nr_unused);
else if (rotate)
inode->i_state |= I_REFERENCED;
static void inode_lru_list_del(struct inode *inode)
{
- if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
+ if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_dec(nr_unused);
}
* nor even WARN_ON(!mapping_empty).
*/
xa_unlock_irq(&inode->i_data.i_pages);
- BUG_ON(!list_empty(&inode->i_data.private_list));
+ BUG_ON(!list_empty(&inode->i_data.i_private_list));
BUG_ON(!(inode->i_state & I_FREEING));
BUG_ON(inode->i_state & I_CLEAR);
BUG_ON(!list_empty(&inode->i_wb_list));
* earlier than or equal to either the ctime or mtime,
* or if at least a day has passed since the last atime update.
*/
-static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
+static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode,
struct timespec64 now)
{
struct timespec64 atime, mtime, ctime;
if (!(mnt->mnt_flags & MNT_RELATIME))
- return 1;
+ return true;
/*
* Is mtime younger than or equal to atime? If yes, update atime:
*/
atime = inode_get_atime(inode);
mtime = inode_get_mtime(inode);
if (timespec64_compare(&mtime, &atime) >= 0)
- return 1;
+ return true;
/*
* Is ctime younger than or equal to atime? If yes, update atime:
*/
ctime = inode_get_ctime(inode);
if (timespec64_compare(&ctime, &atime) >= 0)
- return 1;
+ return true;
/*
* Is the previous atime value older than a day? If yes,
* update atime:
*/
if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60)
- return 1;
+ return true;
/*
* Good, we can skip the atime update:
*/
- return 0;
+ return false;
}
/**
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
bool inode_owner_or_capable(struct mnt_idmap *idmap,
const struct inode *inode)
serv->sv_maxconn = nlm_max_connections;
error = svc_set_num_threads(serv, NULL, 1);
- /* The thread now holds the only reference */
- svc_put(serv);
- if (error < 0)
+ if (error < 0) {
+ svc_destroy(&serv);
return error;
+ }
nlmsvc_serv = serv;
register_inetaddr_notifier(&lockd_inetaddr_notifier);
unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
#endif
- svc_get(nlmsvc_serv);
svc_set_num_threads(nlmsvc_serv, NULL, 0);
- svc_put(nlmsvc_serv);
timer_delete_sync(&nlmsvc_retry);
- nlmsvc_serv = NULL;
+ svc_destroy(&nlmsvc_serv);
dprintk("lockd_down: service destroyed\n");
}
.mode = 0644,
.proc_handler = proc_dointvec,
},
- { }
};
#endif /* CONFIG_SYSCTL */
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
static int check_acl(struct mnt_idmap *idmap,
struct inode *inode, int mask)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
static int acl_permission_check(struct mnt_idmap *idmap,
struct inode *inode, int mask)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int generic_permission(struct mnt_idmap *idmap, struct inode *inode,
int mask)
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
- { }
};
static int __init init_fs_namei_sysctls(void)
return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry));
}
-/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+/* Returns 0 and nd will be valid on success; Returns error, otherwise. */
static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
{
const char *s = path_init(nd, flags);
return retval;
}
-/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+/* Returns 0 and nd will be valid on success; Returns error, otherwise. */
static int path_parentat(struct nameidata *nd, unsigned flags,
struct path *parent)
{
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_create(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, bool want_excl)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
static int vfs_tmpfile(struct mnt_idmap *idmap,
const struct path *parentpath,
WARN_ON(1);
error = -EINVAL;
}
- if (unlikely(file->f_mode & FMODE_OPENED))
- fput(file);
- else
- release_empty_file(file);
+ fput(file);
if (error == -EOPENSTALE) {
if (flags & LOOKUP_RCU)
error = -ECHILD;
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t dev)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, struct inode **delegated_inode)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, const char *oldname)
* the vfsmount must be passed through @idmap. This function will then take
* care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs @nop_mnt_idmap.
+ * raw inode simply pass @nop_mnt_idmap.
*/
int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap,
struct inode *dir, struct dentry *new_dentry,
#include <linux/fs_context.h>
#include <linux/shmem_fs.h>
#include <linux/mnt_idmapping.h>
+#include <linux/nospec.h>
#include "pnode.h"
#include "internal.h"
static DEFINE_IDA(mnt_id_ida);
static DEFINE_IDA(mnt_group_ida);
+/* Don't allow confusion with old 32bit mount ID */
+static atomic64_t mnt_id_ctr = ATOMIC64_INIT(1ULL << 32);
+
static struct hlist_head *mount_hashtable __ro_after_init;
static struct hlist_head *mountpoint_hashtable __ro_after_init;
static struct kmem_cache *mnt_cache __ro_after_init;
if (res < 0)
return res;
mnt->mnt_id = res;
+ mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr);
return 0;
}
return m;
}
-static inline void lock_ns_list(struct mnt_namespace *ns)
-{
- spin_lock(&ns->ns_lock);
-}
-
-static inline void unlock_ns_list(struct mnt_namespace *ns)
-{
- spin_unlock(&ns->ns_lock);
-}
-
-static inline bool mnt_is_cursor(struct mount *mnt)
-{
- return mnt->mnt.mnt_flags & MNT_CURSOR;
-}
-
/*
* __is_local_mountpoint - Test to see if dentry is a mountpoint in the
* current mount namespace.
bool __is_local_mountpoint(struct dentry *dentry)
{
struct mnt_namespace *ns = current->nsproxy->mnt_ns;
- struct mount *mnt;
+ struct mount *mnt, *n;
bool is_covered = false;
down_read(&namespace_sem);
- lock_ns_list(ns);
- list_for_each_entry(mnt, &ns->list, mnt_list) {
- if (mnt_is_cursor(mnt))
- continue;
+ rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) {
is_covered = (mnt->mnt_mountpoint == dentry);
if (is_covered)
break;
}
- unlock_ns_list(ns);
up_read(&namespace_sem);
return is_covered;
mnt_add_count(old_parent, -1);
}
+static inline struct mount *node_to_mount(struct rb_node *node)
+{
+ return node ? rb_entry(node, struct mount, mnt_node) : NULL;
+}
+
+static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)
+{
+ struct rb_node **link = &ns->mounts.rb_node;
+ struct rb_node *parent = NULL;
+
+ WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB);
+ mnt->mnt_ns = ns;
+ while (*link) {
+ parent = *link;
+ if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique)
+ link = &parent->rb_left;
+ else
+ link = &parent->rb_right;
+ }
+ rb_link_node(&mnt->mnt_node, parent, link);
+ rb_insert_color(&mnt->mnt_node, &ns->mounts);
+ mnt->mnt.mnt_flags |= MNT_ONRB;
+}
+
/*
* vfsmount lock must be held for write
*/
BUG_ON(parent == mnt);
list_add_tail(&head, &mnt->mnt_list);
- list_for_each_entry(m, &head, mnt_list)
- m->mnt_ns = n;
+ while (!list_empty(&head)) {
+ m = list_first_entry(&head, typeof(*m), mnt_list);
+ list_del(&m->mnt_list);
- list_splice(&head, n->list.prev);
-
- n->mounts += n->pending_mounts;
+ mnt_add_to_ns(n, m);
+ }
+ n->nr_mounts += n->pending_mounts;
n->pending_mounts = 0;
__attach_mnt(mnt, parent);
}
mnt->mnt.mnt_flags = old->mnt.mnt_flags;
- mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
+ mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB);
atomic_inc(&sb->s_active);
mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt));
return &p->mnt;
}
-#ifdef CONFIG_PROC_FS
-static struct mount *mnt_list_next(struct mnt_namespace *ns,
- struct list_head *p)
+/*
+ * Returns the mount which either has the specified mnt_id, or has the next
+ * smallest id afer the specified one.
+ */
+static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id)
{
- struct mount *mnt, *ret = NULL;
+ struct rb_node *node = ns->mounts.rb_node;
+ struct mount *ret = NULL;
- lock_ns_list(ns);
- list_for_each_continue(p, &ns->list) {
- mnt = list_entry(p, typeof(*mnt), mnt_list);
- if (!mnt_is_cursor(mnt)) {
- ret = mnt;
- break;
+ while (node) {
+ struct mount *m = node_to_mount(node);
+
+ if (mnt_id <= m->mnt_id_unique) {
+ ret = node_to_mount(node);
+ if (mnt_id == m->mnt_id_unique)
+ break;
+ node = node->rb_left;
+ } else {
+ node = node->rb_right;
}
}
- unlock_ns_list(ns);
-
return ret;
}
+#ifdef CONFIG_PROC_FS
+
/* iterator; we want it to have access to namespace_sem, thus here... */
static void *m_start(struct seq_file *m, loff_t *pos)
{
struct proc_mounts *p = m->private;
- struct list_head *prev;
down_read(&namespace_sem);
- if (!*pos) {
- prev = &p->ns->list;
- } else {
- prev = &p->cursor.mnt_list;
-
- /* Read after we'd reached the end? */
- if (list_empty(prev))
- return NULL;
- }
- return mnt_list_next(p->ns, prev);
+ return mnt_find_id_at(p->ns, *pos);
}
static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct proc_mounts *p = m->private;
- struct mount *mnt = v;
+ struct mount *next = NULL, *mnt = v;
+ struct rb_node *node = rb_next(&mnt->mnt_node);
++*pos;
- return mnt_list_next(p->ns, &mnt->mnt_list);
+ if (node) {
+ next = node_to_mount(node);
+ *pos = next->mnt_id_unique;
+ }
+ return next;
}
static void m_stop(struct seq_file *m, void *v)
{
- struct proc_mounts *p = m->private;
- struct mount *mnt = v;
-
- lock_ns_list(p->ns);
- if (mnt)
- list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list);
- else
- list_del_init(&p->cursor.mnt_list);
- unlock_ns_list(p->ns);
up_read(&namespace_sem);
}
.show = m_show,
};
-void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor)
-{
- down_read(&namespace_sem);
- lock_ns_list(ns);
- list_del(&cursor->mnt_list);
- unlock_ns_list(ns);
- up_read(&namespace_sem);
-}
#endif /* CONFIG_PROC_FS */
/**
/* Gather the mounts to umount */
for (p = mnt; p; p = next_mnt(p, mnt)) {
p->mnt.mnt_flags |= MNT_UMOUNT;
- list_move(&p->mnt_list, &tmp_list);
+ if (p->mnt.mnt_flags & MNT_ONRB)
+ move_from_ns(p, &tmp_list);
+ else
+ list_move(&p->mnt_list, &tmp_list);
}
/* Hide the mounts from mnt_mounts */
list_del_init(&p->mnt_list);
ns = p->mnt_ns;
if (ns) {
- ns->mounts--;
+ ns->nr_mounts--;
__touch_mnt_namespace(ns);
}
p->mnt_ns = NULL;
event++;
if (flags & MNT_DETACH) {
- if (!list_empty(&mnt->mnt_list))
+ if (mnt->mnt.mnt_flags & MNT_ONRB ||
+ !list_empty(&mnt->mnt_list))
umount_tree(mnt, UMOUNT_PROPAGATE);
retval = 0;
} else {
shrink_submounts(mnt);
retval = -EBUSY;
if (!propagate_mount_busy(mnt, 2)) {
- if (!list_empty(&mnt->mnt_list))
+ if (mnt->mnt.mnt_flags & MNT_ONRB ||
+ !list_empty(&mnt->mnt_list))
umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
retval = 0;
}
unsigned int mounts = 0;
struct mount *p;
- if (ns->mounts >= max)
+ if (ns->nr_mounts >= max)
return -ENOSPC;
- max -= ns->mounts;
+ max -= ns->nr_mounts;
if (ns->pending_mounts >= max)
return -ENOSPC;
max -= ns->pending_mounts;
touch_mnt_namespace(source_mnt->mnt_ns);
} else {
if (source_mnt->mnt_ns) {
+ LIST_HEAD(head);
+
/* move from anon - the caller will destroy */
- list_del_init(&source_mnt->mnt_ns->list);
+ for (p = source_mnt; p; p = next_mnt(p, source_mnt))
+ move_from_ns(p, &head);
+ list_del_init(&head);
}
if (beneath)
mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp);
lock_mount_hash();
for (p = mnt; p; p = next_mnt(p, mnt)) {
- p->mnt_ns = ns;
- ns->mounts++;
+ mnt_add_to_ns(ns, p);
+ ns->nr_mounts++;
}
ns->root = mnt;
- list_add_tail(&ns->list, &mnt->mnt_list);
mntget(&mnt->mnt);
unlock_mount_hash();
namespace_unlock();
if (IS_ERR(fc))
return PTR_ERR(fc);
+ /*
+ * Indicate to the filesystem that the remount request is coming
+ * from the legacy mount system call.
+ */
fc->oldapi = true;
+
err = parse_monolithic_mount_data(fc, data);
if (!err) {
down_write(&sb->s_umount);
* can_move_mount_beneath - check that we can mount beneath the top mount
* @from: mount to mount beneath
* @to: mount under which to mount
+ * @mp: mountpoint of @to
*
* - Make sure that @to->dentry is actually the root of a mount under
* which we can mount another mount.
if (IS_ERR(fc))
return PTR_ERR(fc);
+ /*
+ * Indicate to the filesystem that the mount request is coming
+ * from the legacy mount system call.
+ */
+ fc->oldapi = true;
+
if (subtype)
err = vfs_parse_fs_string(fc, "subtype",
subtype, strlen(subtype));
if (!anon)
new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
refcount_set(&new_ns->ns.count, 1);
- INIT_LIST_HEAD(&new_ns->list);
+ new_ns->mounts = RB_ROOT;
init_waitqueue_head(&new_ns->poll);
- spin_lock_init(&new_ns->ns_lock);
new_ns->user_ns = get_user_ns(user_ns);
new_ns->ucounts = ucounts;
return new_ns;
unlock_mount_hash();
}
new_ns->root = new;
- list_add_tail(&new_ns->list, &new->mnt_list);
/*
* Second pass: switch the tsk->fs->* elements and mark new vfsmounts
p = old;
q = new;
while (p) {
- q->mnt_ns = new_ns;
- new_ns->mounts++;
+ mnt_add_to_ns(new_ns, q);
+ new_ns->nr_mounts++;
if (new_fs) {
if (&p->mnt == new_fs->root.mnt) {
new_fs->root.mnt = mntget(&q->mnt);
mntput(m);
return ERR_CAST(ns);
}
- mnt->mnt_ns = ns;
ns->root = mnt;
- ns->mounts++;
- list_add(&mnt->mnt_list, &ns->list);
+ ns->nr_mounts++;
+ mnt_add_to_ns(ns, mnt);
err = vfs_path_lookup(m->mnt_root, m,
name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
goto err_path;
}
mnt = real_mount(newmount.mnt);
- mnt->mnt_ns = ns;
ns->root = mnt;
- ns->mounts = 1;
- list_add(&mnt->mnt_list, &ns->list);
+ ns->nr_mounts = 1;
+ mnt_add_to_ns(ns, mnt);
mntget(newmount.mnt);
/* Attach to an apparent O_PATH fd with a note that we need to unmount
* Creating an idmapped mount with the filesystem wide idmapping
* doesn't make sense so block that. We don't allow mushy semantics.
*/
- if (!check_fsmapping(kattr->mnt_idmap, m->mnt_sb))
+ if (kattr->mnt_userns == m->mnt_sb->s_user_ns)
return -EINVAL;
/*
return err;
}
+int show_path(struct seq_file *m, struct dentry *root)
+{
+ if (root->d_sb->s_op->show_path)
+ return root->d_sb->s_op->show_path(m, root);
+
+ seq_dentry(m, root, " \t\n\\");
+ return 0;
+}
+
+static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns)
+{
+ struct mount *mnt = mnt_find_id_at(ns, id);
+
+ if (!mnt || mnt->mnt_id_unique != id)
+ return NULL;
+
+ return &mnt->mnt;
+}
+
+struct kstatmount {
+ struct statmount __user *buf;
+ size_t bufsize;
+ struct vfsmount *mnt;
+ u64 mask;
+ struct path root;
+ struct statmount sm;
+ struct seq_file seq;
+};
+
+static u64 mnt_to_attr_flags(struct vfsmount *mnt)
+{
+ unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags);
+ u64 attr_flags = 0;
+
+ if (mnt_flags & MNT_READONLY)
+ attr_flags |= MOUNT_ATTR_RDONLY;
+ if (mnt_flags & MNT_NOSUID)
+ attr_flags |= MOUNT_ATTR_NOSUID;
+ if (mnt_flags & MNT_NODEV)
+ attr_flags |= MOUNT_ATTR_NODEV;
+ if (mnt_flags & MNT_NOEXEC)
+ attr_flags |= MOUNT_ATTR_NOEXEC;
+ if (mnt_flags & MNT_NODIRATIME)
+ attr_flags |= MOUNT_ATTR_NODIRATIME;
+ if (mnt_flags & MNT_NOSYMFOLLOW)
+ attr_flags |= MOUNT_ATTR_NOSYMFOLLOW;
+
+ if (mnt_flags & MNT_NOATIME)
+ attr_flags |= MOUNT_ATTR_NOATIME;
+ else if (mnt_flags & MNT_RELATIME)
+ attr_flags |= MOUNT_ATTR_RELATIME;
+ else
+ attr_flags |= MOUNT_ATTR_STRICTATIME;
+
+ if (is_idmapped_mnt(mnt))
+ attr_flags |= MOUNT_ATTR_IDMAP;
+
+ return attr_flags;
+}
+
+static u64 mnt_to_propagation_flags(struct mount *m)
+{
+ u64 propagation = 0;
+
+ if (IS_MNT_SHARED(m))
+ propagation |= MS_SHARED;
+ if (IS_MNT_SLAVE(m))
+ propagation |= MS_SLAVE;
+ if (IS_MNT_UNBINDABLE(m))
+ propagation |= MS_UNBINDABLE;
+ if (!propagation)
+ propagation |= MS_PRIVATE;
+
+ return propagation;
+}
+
+static void statmount_sb_basic(struct kstatmount *s)
+{
+ struct super_block *sb = s->mnt->mnt_sb;
+
+ s->sm.mask |= STATMOUNT_SB_BASIC;
+ s->sm.sb_dev_major = MAJOR(sb->s_dev);
+ s->sm.sb_dev_minor = MINOR(sb->s_dev);
+ s->sm.sb_magic = sb->s_magic;
+ s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME);
+}
+
+static void statmount_mnt_basic(struct kstatmount *s)
+{
+ struct mount *m = real_mount(s->mnt);
+
+ s->sm.mask |= STATMOUNT_MNT_BASIC;
+ s->sm.mnt_id = m->mnt_id_unique;
+ s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique;
+ s->sm.mnt_id_old = m->mnt_id;
+ s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id;
+ s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt);
+ s->sm.mnt_propagation = mnt_to_propagation_flags(m);
+ s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0;
+ s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0;
+}
+
+static void statmount_propagate_from(struct kstatmount *s)
+{
+ struct mount *m = real_mount(s->mnt);
+
+ s->sm.mask |= STATMOUNT_PROPAGATE_FROM;
+ if (IS_MNT_SLAVE(m))
+ s->sm.propagate_from = get_dominating_id(m, ¤t->fs->root);
+}
+
+static int statmount_mnt_root(struct kstatmount *s, struct seq_file *seq)
+{
+ int ret;
+ size_t start = seq->count;
+
+ ret = show_path(seq, s->mnt->mnt_root);
+ if (ret)
+ return ret;
+
+ if (unlikely(seq_has_overflowed(seq)))
+ return -EAGAIN;
+
+ /*
+ * Unescape the result. It would be better if supplied string was not
+ * escaped in the first place, but that's a pretty invasive change.
+ */
+ seq->buf[seq->count] = '\0';
+ seq->count = start;
+ seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL));
+ return 0;
+}
+
+static int statmount_mnt_point(struct kstatmount *s, struct seq_file *seq)
+{
+ struct vfsmount *mnt = s->mnt;
+ struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
+ int err;
+
+ err = seq_path_root(seq, &mnt_path, &s->root, "");
+ return err == SEQ_SKIP ? 0 : err;
+}
+
+static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq)
+{
+ struct super_block *sb = s->mnt->mnt_sb;
+
+ seq_puts(seq, sb->s_type->name);
+ return 0;
+}
+
+static int statmount_string(struct kstatmount *s, u64 flag)
+{
+ int ret;
+ size_t kbufsize;
+ struct seq_file *seq = &s->seq;
+ struct statmount *sm = &s->sm;
+
+ switch (flag) {
+ case STATMOUNT_FS_TYPE:
+ sm->fs_type = seq->count;
+ ret = statmount_fs_type(s, seq);
+ break;
+ case STATMOUNT_MNT_ROOT:
+ sm->mnt_root = seq->count;
+ ret = statmount_mnt_root(s, seq);
+ break;
+ case STATMOUNT_MNT_POINT:
+ sm->mnt_point = seq->count;
+ ret = statmount_mnt_point(s, seq);
+ break;
+ default:
+ WARN_ON_ONCE(true);
+ return -EINVAL;
+ }
+
+ if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize)))
+ return -EOVERFLOW;
+ if (kbufsize >= s->bufsize)
+ return -EOVERFLOW;
+
+ /* signal a retry */
+ if (unlikely(seq_has_overflowed(seq)))
+ return -EAGAIN;
+
+ if (ret)
+ return ret;
+
+ seq->buf[seq->count++] = '\0';
+ sm->mask |= flag;
+ return 0;
+}
+
+static int copy_statmount_to_user(struct kstatmount *s)
+{
+ struct statmount *sm = &s->sm;
+ struct seq_file *seq = &s->seq;
+ char __user *str = ((char __user *)s->buf) + sizeof(*sm);
+ size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm));
+
+ if (seq->count && copy_to_user(str, seq->buf, seq->count))
+ return -EFAULT;
+
+ /* Return the number of bytes copied to the buffer */
+ sm->size = copysize + seq->count;
+ if (copy_to_user(s->buf, sm, copysize))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int do_statmount(struct kstatmount *s)
+{
+ struct mount *m = real_mount(s->mnt);
+ int err;
+
+ /*
+ * Don't trigger audit denials. We just want to determine what
+ * mounts to show users.
+ */
+ if (!is_path_reachable(m, m->mnt.mnt_root, &s->root) &&
+ !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ err = security_sb_statfs(s->mnt->mnt_root);
+ if (err)
+ return err;
+
+ if (s->mask & STATMOUNT_SB_BASIC)
+ statmount_sb_basic(s);
+
+ if (s->mask & STATMOUNT_MNT_BASIC)
+ statmount_mnt_basic(s);
+
+ if (s->mask & STATMOUNT_PROPAGATE_FROM)
+ statmount_propagate_from(s);
+
+ if (s->mask & STATMOUNT_FS_TYPE)
+ err = statmount_string(s, STATMOUNT_FS_TYPE);
+
+ if (!err && s->mask & STATMOUNT_MNT_ROOT)
+ err = statmount_string(s, STATMOUNT_MNT_ROOT);
+
+ if (!err && s->mask & STATMOUNT_MNT_POINT)
+ err = statmount_string(s, STATMOUNT_MNT_POINT);
+
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static inline bool retry_statmount(const long ret, size_t *seq_size)
+{
+ if (likely(ret != -EAGAIN))
+ return false;
+ if (unlikely(check_mul_overflow(*seq_size, 2, seq_size)))
+ return false;
+ if (unlikely(*seq_size > MAX_RW_COUNT))
+ return false;
+ return true;
+}
+
+static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq,
+ struct statmount __user *buf, size_t bufsize,
+ size_t seq_size)
+{
+ if (!access_ok(buf, bufsize))
+ return -EFAULT;
+
+ memset(ks, 0, sizeof(*ks));
+ ks->mask = kreq->param;
+ ks->buf = buf;
+ ks->bufsize = bufsize;
+ ks->seq.size = seq_size;
+ ks->seq.buf = kvmalloc(seq_size, GFP_KERNEL_ACCOUNT);
+ if (!ks->seq.buf)
+ return -ENOMEM;
+ return 0;
+}
+
+static int copy_mnt_id_req(const struct mnt_id_req __user *req,
+ struct mnt_id_req *kreq)
+{
+ int ret;
+ size_t usize;
+
+ BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER0);
+
+ ret = get_user(usize, &req->size);
+ if (ret)
+ return -EFAULT;
+ if (unlikely(usize > PAGE_SIZE))
+ return -E2BIG;
+ if (unlikely(usize < MNT_ID_REQ_SIZE_VER0))
+ return -EINVAL;
+ memset(kreq, 0, sizeof(*kreq));
+ ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize);
+ if (ret)
+ return ret;
+ if (kreq->spare != 0)
+ return -EINVAL;
+ return 0;
+}
+
+SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req,
+ struct statmount __user *, buf, size_t, bufsize,
+ unsigned int, flags)
+{
+ struct vfsmount *mnt;
+ struct mnt_id_req kreq;
+ struct kstatmount ks;
+ /* We currently support retrieval of 3 strings. */
+ size_t seq_size = 3 * PATH_MAX;
+ int ret;
+
+ if (flags)
+ return -EINVAL;
+
+ ret = copy_mnt_id_req(req, &kreq);
+ if (ret)
+ return ret;
+
+retry:
+ ret = prepare_kstatmount(&ks, &kreq, buf, bufsize, seq_size);
+ if (ret)
+ return ret;
+
+ down_read(&namespace_sem);
+ mnt = lookup_mnt_in_ns(kreq.mnt_id, current->nsproxy->mnt_ns);
+ if (!mnt) {
+ up_read(&namespace_sem);
+ kvfree(ks.seq.buf);
+ return -ENOENT;
+ }
+
+ ks.mnt = mnt;
+ get_fs_root(current->fs, &ks.root);
+ ret = do_statmount(&ks);
+ path_put(&ks.root);
+ up_read(&namespace_sem);
+
+ if (!ret)
+ ret = copy_statmount_to_user(&ks);
+ kvfree(ks.seq.buf);
+ if (retry_statmount(ret, &seq_size))
+ goto retry;
+ return ret;
+}
+
+static struct mount *listmnt_next(struct mount *curr)
+{
+ return node_to_mount(rb_next(&curr->mnt_node));
+}
+
+static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id,
+ u64 __user *buf, size_t bufsize,
+ const struct path *root)
+{
+ struct mount *r;
+ ssize_t ctr;
+ int err;
+
+ /*
+ * Don't trigger audit denials. We just want to determine what
+ * mounts to show users.
+ */
+ if (!is_path_reachable(real_mount(orig->mnt), orig->dentry, root) &&
+ !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ err = security_sb_statfs(orig->dentry);
+ if (err)
+ return err;
+
+ for (ctr = 0, r = first; r && ctr < bufsize; r = listmnt_next(r)) {
+ if (r->mnt_id_unique == mnt_id)
+ continue;
+ if (!is_path_reachable(r, r->mnt.mnt_root, orig))
+ continue;
+ ctr = array_index_nospec(ctr, bufsize);
+ if (put_user(r->mnt_id_unique, buf + ctr))
+ return -EFAULT;
+ if (check_add_overflow(ctr, 1, &ctr))
+ return -ERANGE;
+ }
+ return ctr;
+}
+
+SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
+ u64 __user *, buf, size_t, bufsize, unsigned int, flags)
+{
+ struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+ struct mnt_id_req kreq;
+ struct mount *first;
+ struct path root, orig;
+ u64 mnt_id, last_mnt_id;
+ ssize_t ret;
+
+ if (flags)
+ return -EINVAL;
+
+ ret = copy_mnt_id_req(req, &kreq);
+ if (ret)
+ return ret;
+ mnt_id = kreq.mnt_id;
+ last_mnt_id = kreq.param;
+
+ down_read(&namespace_sem);
+ get_fs_root(current->fs, &root);
+ if (mnt_id == LSMT_ROOT) {
+ orig = root;
+ } else {
+ ret = -ENOENT;
+ orig.mnt = lookup_mnt_in_ns(mnt_id, ns);
+ if (!orig.mnt)
+ goto err;
+ orig.dentry = orig.mnt->mnt_root;
+ }
+ if (!last_mnt_id)
+ first = node_to_mount(rb_first(&ns->mounts));
+ else
+ first = mnt_find_id_at(ns, last_mnt_id + 1);
+
+ ret = do_listmount(first, &orig, mnt_id, buf, bufsize, &root);
+err:
+ path_put(&root);
+ up_read(&namespace_sem);
+ return ret;
+}
+
+
static void __init init_mount_tree(void)
{
struct vfsmount *mnt;
if (IS_ERR(ns))
panic("Can't allocate initial namespace");
m = real_mount(mnt);
- m->mnt_ns = ns;
ns->root = m;
- ns->mounts = 1;
- list_add(&m->mnt_list, &ns->list);
+ ns->nr_mounts = 1;
+ mnt_add_to_ns(ns, m);
init_task.nsproxy->mnt_ns = ns;
get_mnt_ns(ns);
int *new_mnt_flags)
{
int new_flags = *new_mnt_flags;
- struct mount *mnt;
+ struct mount *mnt, *n;
bool visible = false;
down_read(&namespace_sem);
- lock_ns_list(ns);
- list_for_each_entry(mnt, &ns->list, mnt_list) {
+ rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) {
struct mount *child;
int mnt_flags;
- if (mnt_is_cursor(mnt))
- continue;
-
if (mnt->mnt.mnt_sb->s_type != sb->s_type)
continue;
next: ;
}
found:
- unlock_ns_list(ns);
up_read(&namespace_sem);
return visible;
}
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
},
- { }
};
static int __init init_fs_namespace_sysctls(void)
#include <asm/ioctls.h>
-#include "../../mount.h"
+#include "../fsnotify.h"
#include "../fdinfo.h"
#include "fanotify.h"
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO
},
- { }
};
static void __init fanotify_sysctls_init(void)
return recalc;
}
+struct fan_fsid {
+ struct super_block *sb;
+ __kernel_fsid_t id;
+ bool weak;
+};
+
+static int fanotify_set_mark_fsid(struct fsnotify_group *group,
+ struct fsnotify_mark *mark,
+ struct fan_fsid *fsid)
+{
+ struct fsnotify_mark_connector *conn;
+ struct fsnotify_mark *old;
+ struct super_block *old_sb = NULL;
+
+ FANOTIFY_MARK(mark)->fsid = fsid->id;
+ mark->flags |= FSNOTIFY_MARK_FLAG_HAS_FSID;
+ if (fsid->weak)
+ mark->flags |= FSNOTIFY_MARK_FLAG_WEAK_FSID;
+
+ /* First mark added will determine if group is single or multi fsid */
+ if (list_empty(&group->marks_list))
+ return 0;
+
+ /* Find sb of an existing mark */
+ list_for_each_entry(old, &group->marks_list, g_list) {
+ conn = READ_ONCE(old->connector);
+ if (!conn)
+ continue;
+ old_sb = fsnotify_connector_sb(conn);
+ if (old_sb)
+ break;
+ }
+
+ /* Only detached marks left? */
+ if (!old_sb)
+ return 0;
+
+ /* Do not allow mixing of marks with weak and strong fsid */
+ if ((mark->flags ^ old->flags) & FSNOTIFY_MARK_FLAG_WEAK_FSID)
+ return -EXDEV;
+
+ /* Allow mixing of marks with strong fsid from different fs */
+ if (!fsid->weak)
+ return 0;
+
+ /* Do not allow mixing marks with weak fsid from different fs */
+ if (old_sb != fsid->sb)
+ return -EXDEV;
+
+ /* Do not allow mixing marks from different btrfs sub-volumes */
+ if (!fanotify_fsid_equal(&FANOTIFY_MARK(old)->fsid,
+ &FANOTIFY_MARK(mark)->fsid))
+ return -EXDEV;
+
+ return 0;
+}
+
static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
fsnotify_connp_t *connp,
unsigned int obj_type,
unsigned int fan_flags,
- __kernel_fsid_t *fsid)
+ struct fan_fsid *fsid)
{
struct ucounts *ucounts = group->fanotify_data.ucounts;
+ struct fanotify_mark *fan_mark;
struct fsnotify_mark *mark;
int ret;
!inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS))
return ERR_PTR(-ENOSPC);
- mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
- if (!mark) {
+ fan_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
+ if (!fan_mark) {
ret = -ENOMEM;
goto out_dec_ucounts;
}
+ mark = &fan_mark->fsn_mark;
fsnotify_init_mark(mark, group);
if (fan_flags & FAN_MARK_EVICTABLE)
mark->flags |= FSNOTIFY_MARK_FLAG_NO_IREF;
- ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0, fsid);
- if (ret) {
- fsnotify_put_mark(mark);
- goto out_dec_ucounts;
+ /* Cache fsid of filesystem containing the marked object */
+ if (fsid) {
+ ret = fanotify_set_mark_fsid(group, mark, fsid);
+ if (ret)
+ goto out_put_mark;
+ } else {
+ fan_mark->fsid.val[0] = fan_mark->fsid.val[1] = 0;
}
+ ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0);
+ if (ret)
+ goto out_put_mark;
+
return mark;
+out_put_mark:
+ fsnotify_put_mark(mark);
out_dec_ucounts:
if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
dec_ucount(ucounts, UCOUNT_FANOTIFY_MARKS);
static int fanotify_add_mark(struct fsnotify_group *group,
fsnotify_connp_t *connp, unsigned int obj_type,
__u32 mask, unsigned int fan_flags,
- __kernel_fsid_t *fsid)
+ struct fan_fsid *fsid)
{
struct fsnotify_mark *fsn_mark;
bool recalc;
static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
struct vfsmount *mnt, __u32 mask,
- unsigned int flags, __kernel_fsid_t *fsid)
+ unsigned int flags, struct fan_fsid *fsid)
{
return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags, fsid);
static int fanotify_add_sb_mark(struct fsnotify_group *group,
struct super_block *sb, __u32 mask,
- unsigned int flags, __kernel_fsid_t *fsid)
+ unsigned int flags, struct fan_fsid *fsid)
{
return fanotify_add_mark(group, &sb->s_fsnotify_marks,
FSNOTIFY_OBJ_TYPE_SB, mask, flags, fsid);
static int fanotify_add_inode_mark(struct fsnotify_group *group,
struct inode *inode, __u32 mask,
- unsigned int flags, __kernel_fsid_t *fsid)
+ unsigned int flags, struct fan_fsid *fsid)
{
pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
return fd;
}
-static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
+static int fanotify_test_fsid(struct dentry *dentry, unsigned int flags,
+ struct fan_fsid *fsid)
{
+ unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
__kernel_fsid_t root_fsid;
int err;
/*
* Make sure dentry is not of a filesystem with zero fsid (e.g. fuse).
*/
- err = vfs_get_fsid(dentry, fsid);
+ err = vfs_get_fsid(dentry, &fsid->id);
if (err)
return err;
- if (!fsid->val[0] && !fsid->val[1])
- return -ENODEV;
+ fsid->sb = dentry->d_sb;
+ if (!fsid->id.val[0] && !fsid->id.val[1]) {
+ err = -ENODEV;
+ goto weak;
+ }
/*
* Make sure dentry is not of a filesystem subvolume (e.g. btrfs)
if (err)
return err;
- if (root_fsid.val[0] != fsid->val[0] ||
- root_fsid.val[1] != fsid->val[1])
- return -EXDEV;
+ if (!fanotify_fsid_equal(&root_fsid, &fsid->id)) {
+ err = -EXDEV;
+ goto weak;
+ }
+ fsid->weak = false;
return 0;
+
+weak:
+ /* Allow weak fsid when marking inodes */
+ fsid->weak = true;
+ return (mark_type == FAN_MARK_INODE) ? 0 : err;
}
/* Check if filesystem can encode a unique fid */
struct fsnotify_group *group;
struct fd f;
struct path path;
- __kernel_fsid_t __fsid, *fsid = NULL;
+ struct fan_fsid __fsid, *fsid = NULL;
u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS;
}
if (fid_mode) {
- ret = fanotify_test_fsid(path.dentry, &__fsid);
+ ret = fanotify_test_fsid(path.dentry, flags, &__fsid);
if (ret)
goto path_put_and_out;
BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12);
BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11);
- fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
+ fanotify_mark_cache = KMEM_CACHE(fanotify_mark,
SLAB_PANIC|SLAB_ACCOUNT);
fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event,
SLAB_PANIC);
bool was_empty = false;
bool wake_next_writer = false;
+ /*
+ * Reject writing to watch queue pipes before the point where we lock
+ * the pipe.
+ * Otherwise, lockdep would be unhappy if the caller already has another
+ * pipe locked.
+ * If we had to support locking a normal pipe and a notification pipe at
+ * the same time, we could set up lockdep annotations for that, but
+ * since we don't actually need that, it's simpler to just bail here.
+ */
+ if (pipe_has_watch_queue(pipe))
+ return -EXDEV;
+
/* Null write succeeds. */
if (unlikely(total_len == 0))
return 0;
goto out;
}
- if (pipe_has_watch_queue(pipe)) {
- ret = -EXDEV;
- goto out;
- }
-
/*
* If it wasn't empty we try to merge new data into
* the last buffer.
pipe->tail = tail;
pipe->head = head;
+ if (!pipe_has_watch_queue(pipe)) {
+ pipe->max_usage = nr_slots;
+ pipe->nr_accounted = nr_slots;
+ }
+
spin_unlock_irq(&pipe->rd_wait.lock);
/* This might have made more room for writers */
if (ret < 0)
goto out_revert_acct;
- pipe->max_usage = nr_slots;
- pipe->nr_accounted = nr_slots;
return pipe->max_usage * PAGE_SIZE;
out_revert_acct:
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
- { }
};
#endif
/*
* Convert in-memory reserved quotas to real consumed quotas
*/
-int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
+void dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
{
struct dquot **dquots;
int cnt, index;
*inode_reserved_space(inode) -= number;
__inode_add_bytes(inode, number);
spin_unlock(&inode->i_lock);
- return 0;
+ return;
}
dquots = i_dquot(inode);
spin_unlock(&inode->i_lock);
mark_all_dquot_dirty(dquots);
srcu_read_unlock(&dquot_srcu, index);
- return 0;
+ return;
}
EXPORT_SYMBOL(dquot_claim_space_nodirty);
.proc_handler = proc_dointvec,
},
#endif
- { },
};
static int __init dquot_init(void)
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
- { }
};
#endif
return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED;
}
+static int userfaultfd_move(struct userfaultfd_ctx *ctx,
+ unsigned long arg)
+{
+ __s64 ret;
+ struct uffdio_move uffdio_move;
+ struct uffdio_move __user *user_uffdio_move;
+ struct userfaultfd_wake_range range;
+ struct mm_struct *mm = ctx->mm;
+
+ user_uffdio_move = (struct uffdio_move __user *) arg;
+
+ if (atomic_read(&ctx->mmap_changing))
+ return -EAGAIN;
+
+ if (copy_from_user(&uffdio_move, user_uffdio_move,
+ /* don't copy "move" last field */
+ sizeof(uffdio_move)-sizeof(__s64)))
+ return -EFAULT;
+
+ /* Do not allow cross-mm moves. */
+ if (mm != current->mm)
+ return -EINVAL;
+
+ ret = validate_range(mm, uffdio_move.dst, uffdio_move.len);
+ if (ret)
+ return ret;
+
+ ret = validate_range(mm, uffdio_move.src, uffdio_move.len);
+ if (ret)
+ return ret;
+
+ if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES|
+ UFFDIO_MOVE_MODE_DONTWAKE))
+ return -EINVAL;
+
+ if (mmget_not_zero(mm)) {
+ mmap_read_lock(mm);
+
+ /* Re-check after taking mmap_lock */
+ if (likely(!atomic_read(&ctx->mmap_changing)))
+ ret = move_pages(ctx, mm, uffdio_move.dst, uffdio_move.src,
+ uffdio_move.len, uffdio_move.mode);
+ else
+ ret = -EINVAL;
+
+ mmap_read_unlock(mm);
+ mmput(mm);
+ } else {
+ return -ESRCH;
+ }
+
+ if (unlikely(put_user(ret, &user_uffdio_move->move)))
+ return -EFAULT;
+ if (ret < 0)
+ goto out;
+
+ /* len == 0 would wake all */
+ VM_WARN_ON(!ret);
+ range.len = ret;
+ if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) {
+ range.start = uffdio_move.dst;
+ wake_userfault(ctx, &range);
+ }
+ ret = range.len == uffdio_move.len ? 0 : -EAGAIN;
+
+out:
+ return ret;
+}
+
/*
* userland asks for a certain API version and we return which bits
* and ioctl commands are implemented in this kernel for such API
case UFFDIO_ZEROPAGE:
ret = userfaultfd_zeropage(ctx, arg);
break;
+ case UFFDIO_MOVE:
+ ret = userfaultfd_move(ctx, arg);
+ break;
case UFFDIO_WRITEPROTECT:
ret = userfaultfd_writeprotect(ctx, arg);
break;