summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/userspace-api/seccomp_filter.rst2
-rw-r--r--MAINTAINERS2
-rw-r--r--arch/arc/Kconfig2
-rw-r--r--arch/arc/include/asm/checksum.h2
-rw-r--r--arch/arc/include/asm/perf_event.h2
-rw-r--r--arch/arc/kernel/fpu.c9
-rw-r--r--arch/arc/kernel/unwind.c10
-rw-r--r--arch/arc/kernel/vmlinux.lds.S2
-rw-r--r--block/blk-cgroup.c14
-rw-r--r--drivers/platform/x86/Kconfig3
-rw-r--r--drivers/platform/x86/dual_accel_detect.h76
-rw-r--r--drivers/platform/x86/intel-hid.c21
-rw-r--r--drivers/platform/x86/intel-vbtn.c18
-rw-r--r--drivers/platform/x86/pcengines-apuv2.c2
-rw-r--r--drivers/platform/x86/thinkpad_acpi.c3
-rw-r--r--fs/namespace.c42
-rw-r--r--fs/overlayfs/export.c2
-rw-r--r--fs/overlayfs/file.c47
-rw-r--r--fs/overlayfs/readdir.c5
-rw-r--r--kernel/cgroup/rstat.c19
-rw-r--r--kernel/seccomp.c2
21 files changed, 222 insertions, 63 deletions
diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst
index d61219889e49..539e9d4a4860 100644
--- a/Documentation/userspace-api/seccomp_filter.rst
+++ b/Documentation/userspace-api/seccomp_filter.rst
@@ -263,7 +263,7 @@ Userspace can also add file descriptors to the notifying process via
``ioctl(SECCOMP_IOCTL_NOTIF_ADDFD)``. The ``id`` member of
``struct seccomp_notif_addfd`` should be the same ``id`` as in
``struct seccomp_notif``. The ``newfd_flags`` flag may be used to set flags
-like O_EXEC on the file descriptor in the notifying process. If the supervisor
+like O_CLOEXEC on the file descriptor in the notifying process. If the supervisor
wants to inject the file descriptor with a specific number, the
``SECCOMP_ADDFD_FLAG_SETFD`` flag can be used, and set the ``newfd`` member to
the specific number to use. If that file descriptor is already open in the
diff --git a/MAINTAINERS b/MAINTAINERS
index c9467d2839f5..bbaecde94aa0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17815,7 +17815,7 @@ F: include/linux/sync_file.h
F: include/uapi/linux/sync_file.h
SYNOPSYS ARC ARCHITECTURE
-M: Vineet Gupta <vgupta@synopsys.com>
+M: Vineet Gupta <vgupta@kernel.org>
L: linux-snps-arc@lists.infradead.org
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc.git
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index d8f51eb8963b..b5bf68e74732 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -409,7 +409,7 @@ choice
help
Depending on the configuration, CPU can contain DSP registers
(ACC0_GLO, ACC0_GHI, DSP_BFLY0, DSP_CTRL, DSP_FFT_CTRL).
- Bellow is options describing how to handle these registers in
+ Below are options describing how to handle these registers in
interrupt entry / exit and in context switch.
config ARC_DSP_NONE
diff --git a/arch/arc/include/asm/checksum.h b/arch/arc/include/asm/checksum.h
index 69debd77cd04..0b485800a392 100644
--- a/arch/arc/include/asm/checksum.h
+++ b/arch/arc/include/asm/checksum.h
@@ -24,7 +24,7 @@
*/
static inline __sum16 csum_fold(__wsum s)
{
- unsigned r = s << 16 | s >> 16; /* ror */
+ unsigned int r = s << 16 | s >> 16; /* ror */
s = ~s;
s -= r;
return s >> 16;
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 30b9ae511ea9..e1971d34ef30 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -123,7 +123,7 @@ static const char * const arc_pmu_ev_hw_map[] = {
#define C(_x) PERF_COUNT_HW_CACHE_##_x
#define CACHE_OP_UNSUPPORTED 0xffff
-static const unsigned arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC,
diff --git a/arch/arc/kernel/fpu.c b/arch/arc/kernel/fpu.c
index c67c0f0f5f77..ec640219d989 100644
--- a/arch/arc/kernel/fpu.c
+++ b/arch/arc/kernel/fpu.c
@@ -57,23 +57,26 @@ void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
void fpu_init_task(struct pt_regs *regs)
{
+ const unsigned int fwe = 0x80000000;
+
/* default rounding mode */
write_aux_reg(ARC_REG_FPU_CTRL, 0x100);
- /* set "Write enable" to allow explicit write to exception flags */
- write_aux_reg(ARC_REG_FPU_STATUS, 0x80000000);
+ /* Initialize to zero: setting requires FWE be set */
+ write_aux_reg(ARC_REG_FPU_STATUS, fwe);
}
void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
{
struct arc_fpu *save = &prev->thread.fpu;
struct arc_fpu *restore = &next->thread.fpu;
+ const unsigned int fwe = 0x80000000;
save->ctrl = read_aux_reg(ARC_REG_FPU_CTRL);
save->status = read_aux_reg(ARC_REG_FPU_STATUS);
write_aux_reg(ARC_REG_FPU_CTRL, restore->ctrl);
- write_aux_reg(ARC_REG_FPU_STATUS, restore->status);
+ write_aux_reg(ARC_REG_FPU_STATUS, (fwe | restore->status));
}
#endif
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 47bab67f8649..9e28058cdba8 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -260,7 +260,7 @@ static void init_unwind_hdr(struct unwind_table *table,
{
const u8 *ptr;
unsigned long tableSize = table->size, hdrSize;
- unsigned n;
+ unsigned int n;
const u32 *fde;
struct {
u8 version;
@@ -462,7 +462,7 @@ static uleb128_t get_uleb128(const u8 **pcur, const u8 *end)
{
const u8 *cur = *pcur;
uleb128_t value;
- unsigned shift;
+ unsigned int shift;
for (shift = 0, value = 0; cur < end; shift += 7) {
if (shift + 7 > 8 * sizeof(value)
@@ -483,7 +483,7 @@ static sleb128_t get_sleb128(const u8 **pcur, const u8 *end)
{
const u8 *cur = *pcur;
sleb128_t value;
- unsigned shift;
+ unsigned int shift;
for (shift = 0, value = 0; cur < end; shift += 7) {
if (shift + 7 > 8 * sizeof(value)
@@ -609,7 +609,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end,
static signed fde_pointer_type(const u32 *cie)
{
const u8 *ptr = (const u8 *)(cie + 2);
- unsigned version = *ptr;
+ unsigned int version = *ptr;
if (*++ptr) {
const char *aug;
@@ -904,7 +904,7 @@ int arc_unwind(struct unwind_frame_info *frame)
const u8 *ptr = NULL, *end = NULL;
unsigned long pc = UNW_PC(frame) - frame->call_frame;
unsigned long startLoc = 0, endLoc = 0, cfa;
- unsigned i;
+ unsigned int i;
signed ptrType = -1;
uleb128_t retAddrReg = 0;
const struct unwind_table *table;
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index e2146a8da195..529ae50f9fe2 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -88,6 +88,8 @@ SECTIONS
CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
+ IRQENTRY_TEXT
+ SOFTIRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
}
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 575d7a2e7203..31fe9be179d9 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -790,6 +790,7 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
struct blkcg_gq *parent = blkg->parent;
struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu);
struct blkg_iostat cur, delta;
+ unsigned long flags;
unsigned int seq;
/* fetch the current per-cpu values */
@@ -799,21 +800,21 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
} while (u64_stats_fetch_retry(&bisc->sync, seq));
/* propagate percpu delta to global */
- u64_stats_update_begin(&blkg->iostat.sync);
+ flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
blkg_iostat_set(&delta, &cur);
blkg_iostat_sub(&delta, &bisc->last);
blkg_iostat_add(&blkg->iostat.cur, &delta);
blkg_iostat_add(&bisc->last, &delta);
- u64_stats_update_end(&blkg->iostat.sync);
+ u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
/* propagate global delta to parent (unless that's root) */
if (parent && parent->parent) {
- u64_stats_update_begin(&parent->iostat.sync);
+ flags = u64_stats_update_begin_irqsave(&parent->iostat.sync);
blkg_iostat_set(&delta, &blkg->iostat.cur);
blkg_iostat_sub(&delta, &blkg->iostat.last);
blkg_iostat_add(&parent->iostat.cur, &delta);
blkg_iostat_add(&blkg->iostat.last, &delta);
- u64_stats_update_end(&parent->iostat.sync);
+ u64_stats_update_end_irqrestore(&parent->iostat.sync, flags);
}
}
@@ -848,6 +849,7 @@ static void blkcg_fill_root_iostats(void)
memset(&tmp, 0, sizeof(tmp));
for_each_possible_cpu(cpu) {
struct disk_stats *cpu_dkstats;
+ unsigned long flags;
cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu);
tmp.ios[BLKG_IOSTAT_READ] +=
@@ -864,9 +866,9 @@ static void blkcg_fill_root_iostats(void)
tmp.bytes[BLKG_IOSTAT_DISCARD] +=
cpu_dkstats->sectors[STAT_DISCARD] << 9;
- u64_stats_update_begin(&blkg->iostat.sync);
+ flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
blkg_iostat_set(&blkg->iostat.cur, &tmp);
- u64_stats_update_end(&blkg->iostat.sync);
+ u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
}
}
}
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 7d385c3b2239..d12db6c316ea 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -508,6 +508,7 @@ config THINKPAD_ACPI
depends on RFKILL || RFKILL = n
depends on ACPI_VIDEO || ACPI_VIDEO = n
depends on BACKLIGHT_CLASS_DEVICE
+ depends on I2C
select ACPI_PLATFORM_PROFILE
select HWMON
select NVRAM
@@ -691,6 +692,7 @@ config INTEL_HID_EVENT
tristate "INTEL HID Event"
depends on ACPI
depends on INPUT
+ depends on I2C
select INPUT_SPARSEKMAP
help
This driver provides support for the Intel HID Event hotkey interface.
@@ -742,6 +744,7 @@ config INTEL_VBTN
tristate "INTEL VIRTUAL BUTTON"
depends on ACPI
depends on INPUT
+ depends on I2C
select INPUT_SPARSEKMAP
help
This driver provides support for the Intel Virtual Button interface.
diff --git a/drivers/platform/x86/dual_accel_detect.h b/drivers/platform/x86/dual_accel_detect.h
new file mode 100644
index 000000000000..a9eae17cc43d
--- /dev/null
+++ b/drivers/platform/x86/dual_accel_detect.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Helper code to detect 360 degree hinges (yoga) style 2-in-1 devices using 2 accelerometers
+ * to allow the OS to determine the angle between the display and the base of the device.
+ *
+ * On Windows these are read by a special HingeAngleService process which calls undocumented
+ * ACPI methods, to let the firmware know if the 2-in-1 is in tablet- or laptop-mode.
+ * The firmware may use this to disable the kbd and touchpad to avoid spurious input in
+ * tablet-mode as well as to report SW_TABLET_MODE info to the OS.
+ *
+ * Since Linux does not call these undocumented methods, the SW_TABLET_MODE info reported
+ * by various drivers/platform/x86 drivers is incorrect. These drivers use the detection
+ * code in this file to disable SW_TABLET_MODE reporting to avoid reporting broken info
+ * (instead userspace can derive the status itself by directly reading the 2 accels).
+ */
+
+#include <linux/acpi.h>
+#include <linux/i2c.h>
+
+static int dual_accel_i2c_resource_count(struct acpi_resource *ares, void *data)
+{
+ struct acpi_resource_i2c_serialbus *sb;
+ int *count = data;
+
+ if (i2c_acpi_get_i2c_resource(ares, &sb))
+ *count = *count + 1;
+
+ return 1;
+}
+
+static int dual_accel_i2c_client_count(struct acpi_device *adev)
+{
+ int ret, count = 0;
+ LIST_HEAD(r);
+
+ ret = acpi_dev_get_resources(adev, &r, dual_accel_i2c_resource_count, &count);
+ if (ret < 0)
+ return ret;
+
+ acpi_dev_free_resource_list(&r);
+ return count;
+}
+
+static bool dual_accel_detect_bosc0200(void)
+{
+ struct acpi_device *adev;
+ int count;
+
+ adev = acpi_dev_get_first_match_dev("BOSC0200", NULL, -1);
+ if (!adev)
+ return false;
+
+ count = dual_accel_i2c_client_count(adev);
+
+ acpi_dev_put(adev);
+
+ return count == 2;
+}
+
+static bool dual_accel_detect(void)
+{
+ /* Systems which use a pair of accels with KIOX010A / KIOX020A ACPI ids */
+ if (acpi_dev_present("KIOX010A", NULL, -1) &&
+ acpi_dev_present("KIOX020A", NULL, -1))
+ return true;
+
+ /* Systems which use a single DUAL250E ACPI device to model 2 accels */
+ if (acpi_dev_present("DUAL250E", NULL, -1))
+ return true;
+
+ /* Systems which use a single BOSC0200 ACPI device to model 2 accels */
+ if (dual_accel_detect_bosc0200())
+ return true;
+
+ return false;
+}
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index e5fbe017f8e1..2e4e97a626a5 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -14,6 +14,7 @@
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/suspend.h>
+#include "dual_accel_detect.h"
/* When NOT in tablet mode, VGBS returns with the flag 0x40 */
#define TABLET_MODE_FLAG BIT(6)
@@ -122,6 +123,7 @@ struct intel_hid_priv {
struct input_dev *array;
struct input_dev *switches;
bool wakeup_mode;
+ bool dual_accel;
};
#define HID_EVENT_FILTER_UUID "eeec56b3-4442-408f-a792-4edd4d758054"
@@ -451,22 +453,9 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
* SW_TABLET_MODE report, in these cases we enable support when receiving
* the first event instead of during driver setup.
*
- * Some 360 degree hinges (yoga) style 2-in-1 devices use 2 accelerometers
- * to allow the OS to determine the angle between the display and the base
- * of the device. On Windows these are read by a special HingeAngleService
- * process which calls an ACPI DSM (Device Specific Method) on the
- * ACPI KIOX010A device node for the sensor in the display, to let the
- * firmware know if the 2-in-1 is in tablet- or laptop-mode so that it can
- * disable the kbd and touchpad to avoid spurious input in tablet-mode.
- *
- * The linux kxcjk1013 driver calls the DSM for this once at probe time
- * to ensure that the builtin kbd and touchpad work. On some devices this
- * causes a "spurious" 0xcd event on the intel-hid ACPI dev. In this case
- * there is not a functional tablet-mode switch, so we should not register
- * the tablet-mode switch device.
+ * See dual_accel_detect.h for more info on the dual_accel check.
*/
- if (!priv->switches && (event == 0xcc || event == 0xcd) &&
- !acpi_dev_present("KIOX010A", NULL, -1)) {
+ if (!priv->switches && !priv->dual_accel && (event == 0xcc || event == 0xcd)) {
dev_info(&device->dev, "switch event received, enable switches supports\n");
err = intel_hid_switches_setup(device);
if (err)
@@ -607,6 +596,8 @@ static int intel_hid_probe(struct platform_device *device)
return -ENOMEM;
dev_set_drvdata(&device->dev, priv);
+ priv->dual_accel = dual_accel_detect();
+
err = intel_hid_input_setup(device);
if (err) {
pr_err("Failed to setup Intel HID hotkeys\n");
diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c
index 888a764efad1..309166431063 100644
--- a/drivers/platform/x86/intel-vbtn.c
+++ b/drivers/platform/x86/intel-vbtn.c
@@ -14,6 +14,7 @@
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/suspend.h>
+#include "dual_accel_detect.h"
/* Returned when NOT in tablet mode on some HP Stream x360 11 models */
#define VGBS_TABLET_MODE_FLAG_ALT 0x10
@@ -66,6 +67,7 @@ static const struct key_entry intel_vbtn_switchmap[] = {
struct intel_vbtn_priv {
struct input_dev *buttons_dev;
struct input_dev *switches_dev;
+ bool dual_accel;
bool has_buttons;
bool has_switches;
bool wakeup_mode;
@@ -160,6 +162,10 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
input_dev = priv->buttons_dev;
} else if ((ke = sparse_keymap_entry_from_scancode(priv->switches_dev, event))) {
if (!priv->has_switches) {
+ /* See dual_accel_detect.h for more info */
+ if (priv->dual_accel)
+ return;
+
dev_info(&device->dev, "Registering Intel Virtual Switches input-dev after receiving a switch event\n");
ret = input_register_device(priv->switches_dev);
if (ret)
@@ -248,11 +254,15 @@ static const struct dmi_system_id dmi_switches_allow_list[] = {
{} /* Array terminator */
};
-static bool intel_vbtn_has_switches(acpi_handle handle)
+static bool intel_vbtn_has_switches(acpi_handle handle, bool dual_accel)
{
unsigned long long vgbs;
acpi_status status;
+ /* See dual_accel_detect.h for more info */
+ if (dual_accel)
+ return false;
+
if (!dmi_check_system(dmi_switches_allow_list))
return false;
@@ -263,13 +273,14 @@ static bool intel_vbtn_has_switches(acpi_handle handle)
static int intel_vbtn_probe(struct platform_device *device)
{
acpi_handle handle = ACPI_HANDLE(&device->dev);
- bool has_buttons, has_switches;
+ bool dual_accel, has_buttons, has_switches;
struct intel_vbtn_priv *priv;
acpi_status status;
int err;
+ dual_accel = dual_accel_detect();
has_buttons = acpi_has_method(handle, "VBDL");
- has_switches = intel_vbtn_has_switches(handle);
+ has_switches = intel_vbtn_has_switches(handle, dual_accel);
if (!has_buttons && !has_switches) {
dev_warn(&device->dev, "failed to read Intel Virtual Button driver\n");
@@ -281,6 +292,7 @@ static int intel_vbtn_probe(struct platform_device *device)
return -ENOMEM;
dev_set_drvdata(&device->dev, priv);
+ priv->dual_accel = dual_accel;
priv->has_buttons = has_buttons;
priv->has_switches = has_switches;
diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c
index c37349f97bb8..d063d91db9bc 100644
--- a/drivers/platform/x86/pcengines-apuv2.c
+++ b/drivers/platform/x86/pcengines-apuv2.c
@@ -94,6 +94,7 @@ static struct gpiod_lookup_table gpios_led_table = {
NULL, 1, GPIO_ACTIVE_LOW),
GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_LINE_LED3,
NULL, 2, GPIO_ACTIVE_LOW),
+ {} /* Terminating entry */
}
};
@@ -123,6 +124,7 @@ static struct gpiod_lookup_table gpios_key_table = {
.table = {
GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_LINE_MODESW,
NULL, 0, GPIO_ACTIVE_LOW),
+ {} /* Terminating entry */
}
};
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 603156a6e3ed..50ff04c84650 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -73,6 +73,7 @@
#include <linux/uaccess.h>
#include <acpi/battery.h>
#include <acpi/video.h>
+#include "dual_accel_detect.h"
/* ThinkPad CMOS commands */
#define TP_CMOS_VOLUME_DOWN 0
@@ -3232,7 +3233,7 @@ static int hotkey_init_tablet_mode(void)
* the laptop/tent/tablet mode to the EC. The bmc150 iio driver
* does not support this, so skip the hotkey on these models.
*/
- if (has_tablet_mode && !acpi_dev_present("BOSC0200", "1", -1))
+ if (has_tablet_mode && !dual_accel_detect())
tp_features.hotkey_tablet = TP_HOTKEY_TABLET_USES_GMMS;
type = "GMMS";
} else if (acpi_evalf(hkey_handle, &res, "MHKG", "qd")) {
diff --git a/fs/namespace.c b/fs/namespace.c
index ab4174a3c802..f79d9471cb76 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1938,6 +1938,20 @@ void drop_collected_mounts(struct vfsmount *mnt)
namespace_unlock();
}
+static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+{
+ struct mount *child;
+
+ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+ if (!is_subdir(child->mnt_mountpoint, dentry))
+ continue;
+
+ if (child->mnt.mnt_flags & MNT_LOCKED)
+ return true;
+ }
+ return false;
+}
+
/**
* clone_private_mount - create a private clone of a path
* @path: path to clone
@@ -1953,10 +1967,19 @@ struct vfsmount *clone_private_mount(const struct path *path)
struct mount *old_mnt = real_mount(path->mnt);
struct mount *new_mnt;
+ down_read(&namespace_sem);
if (IS_MNT_UNBINDABLE(old_mnt))
- return ERR_PTR(-EINVAL);
+ goto invalid;
+
+ if (!check_mnt(old_mnt))
+ goto invalid;
+
+ if (has_locked_children(old_mnt, path->dentry))
+ goto invalid;
new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
+ up_read(&namespace_sem);
+
if (IS_ERR(new_mnt))
return ERR_CAST(new_mnt);
@@ -1964,6 +1987,10 @@ struct vfsmount *clone_private_mount(const struct path *path)
new_mnt->mnt_ns = MNT_NS_INTERNAL;
return &new_mnt->mnt;
+
+invalid:
+ up_read(&namespace_sem);
+ return ERR_PTR(-EINVAL);
}
EXPORT_SYMBOL_GPL(clone_private_mount);
@@ -2315,19 +2342,6 @@ static int do_change_type(struct path *path, int ms_flags)
return err;
}
-static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
-{
- struct mount *child;
- list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
- if (!is_subdir(child->mnt_mountpoint, dentry))
- continue;
-
- if (child->mnt.mnt_flags & MNT_LOCKED)
- return true;
- }
- return false;
-}
-
static struct mount *__do_loopback(struct path *old_path, int recurse)
{
struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt);
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index 41ebf52f1bbc..ebde05c9cf62 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -392,6 +392,7 @@ static struct dentry *ovl_lookup_real_one(struct dentry *connected,
*/
take_dentry_name_snapshot(&name, real);
this = lookup_one_len(name.name.name, connected, name.name.len);
+ release_dentry_name_snapshot(&name);
err = PTR_ERR(this);
if (IS_ERR(this)) {
goto fail;
@@ -406,7 +407,6 @@ static struct dentry *ovl_lookup_real_one(struct dentry *connected,
}
out:
- release_dentry_name_snapshot(&name);
dput(parent);
inode_unlock(dir);
return this;
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 4d53d3b7e5fe..d081faa55e83 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -392,6 +392,51 @@ out_unlock:
return ret;
}
+/*
+ * Calling iter_file_splice_write() directly from overlay's f_op may deadlock
+ * due to lock order inversion between pipe->mutex in iter_file_splice_write()
+ * and file_start_write(real.file) in ovl_write_iter().
+ *
+ * So do everything ovl_write_iter() does and call iter_file_splice_write() on
+ * the real file.
+ */
+static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags)
+{
+ struct fd real;
+ const struct cred *old_cred;
+ struct inode *inode = file_inode(out);
+ struct inode *realinode = ovl_inode_real(inode);
+ ssize_t ret;
+
+ inode_lock(inode);
+ /* Update mode */
+ ovl_copyattr(realinode, inode);
+ ret = file_remove_privs(out);
+ if (ret)
+ goto out_unlock;
+
+ ret = ovl_real_fdget(out, &real);
+ if (ret)
+ goto out_unlock;
+
+ old_cred = ovl_override_creds(inode->i_sb);
+ file_start_write(real.file);
+
+ ret = iter_file_splice_write(pipe, real.file, ppos, len, flags);
+
+ file_end_write(real.file);
+ /* Update size */
+ ovl_copyattr(realinode, inode);
+ revert_creds(old_cred);
+ fdput(real);
+
+out_unlock:
+ inode_unlock(inode);
+
+ return ret;
+}
+
static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
struct fd real;
@@ -603,7 +648,7 @@ const struct file_operations ovl_file_operations = {
.fadvise = ovl_fadvise,
.flush = ovl_flush,
.splice_read = generic_file_splice_read,
- .splice_write = iter_file_splice_write,
+ .splice_write = ovl_splice_write,
.copy_file_range = ovl_copy_file_range,
.remap_file_range = ovl_remap_file_range,
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index e8ad2c2c77dd..150fdf3bc68d 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -481,6 +481,8 @@ static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p)
}
this = lookup_one_len(p->name, dir, p->len);
if (IS_ERR_OR_NULL(this) || !this->d_inode) {
+ /* Mark a stale entry */
+ p->is_whiteout = true;
if (IS_ERR(this)) {
err = PTR_ERR(this);
this = NULL;
@@ -776,6 +778,9 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
if (err)
goto out;
}
+ }
+ /* ovl_cache_update_ino() sets is_whiteout on stale entry */
+ if (!p->is_whiteout) {
if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
break;
}
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 7f0e58917432..b264ab5652ba 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -347,19 +347,20 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
}
static struct cgroup_rstat_cpu *
-cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp)
+cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags)
{
struct cgroup_rstat_cpu *rstatc;
rstatc = get_cpu_ptr(cgrp->rstat_cpu);
- u64_stats_update_begin(&rstatc->bsync);
+ *flags = u64_stats_update_begin_irqsave(&rstatc->bsync);
return rstatc;
}
static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp,
- struct cgroup_rstat_cpu *rstatc)
+ struct cgroup_rstat_cpu *rstatc,
+ unsigned long flags)
{
- u64_stats_update_end(&rstatc->bsync);
+ u64_stats_update_end_irqrestore(&rstatc->bsync, flags);
cgroup_rstat_updated(cgrp, smp_processor_id());
put_cpu_ptr(rstatc);
}
@@ -367,18 +368,20 @@ static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp,
void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec)
{
struct cgroup_rstat_cpu *rstatc;
+ unsigned long flags;
- rstatc = cgroup_base_stat_cputime_account_begin(cgrp);
+ rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
rstatc->bstat.cputime.sum_exec_runtime += delta_exec;
- cgroup_base_stat_cputime_account_end(cgrp, rstatc);
+ cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags);
}
void __cgroup_account_cputime_field(struct cgroup *cgrp,
enum cpu_usage_stat index, u64 delta_exec)
{
struct cgroup_rstat_cpu *rstatc;
+ unsigned long flags;
- rstatc = cgroup_base_stat_cputime_account_begin(cgrp);
+ rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
switch (index) {
case CPUTIME_USER:
@@ -394,7 +397,7 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp,
break;
}
- cgroup_base_stat_cputime_account_end(cgrp, rstatc);
+ cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags);
}
/*
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 057e17f3215d..6469eca8078c 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -602,7 +602,7 @@ static inline void seccomp_sync_threads(unsigned long flags)
smp_store_release(&thread->seccomp.filter,
caller->seccomp.filter);
atomic_set(&thread->seccomp.filter_count,
- atomic_read(&thread->seccomp.filter_count));
+ atomic_read(&caller->seccomp.filter_count));
/*
* Don't let an unprivileged task work around
generated by cgit (git 2.34.1) at 2024-06-27 04:24:44 +0000