From: Kai-Heng Feng kai.heng.feng@canonical.com

commit 36af2d5c4433fb40ee2af912c4ac0a30991aecfc upstream.

Commit 8765c5ba1949 ("ACPI / scan: Rework modalias creation when "compatible" is present") may create two "MODALIAS=" in one uevent file if specific conditions are met.

This breaks systemd-udevd, which assumes each "key" in one uevent file to be unique. The internal implementation of systemd-udevd overwrites the first MODALIAS with the second one, so its kmod rule doesn't load the driver for the first MODALIAS.

So if both the ACPI modalias and the OF modalias are present, use the latter to ensure that there will be only one MODALIAS.

Link: https://github.com/systemd/systemd/pull/18163 Suggested-by: Mika Westerberg mika.westerberg@linux.intel.com Fixes: 8765c5ba1949 ("ACPI / scan: Rework modalias creation when "compatible" is present") Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Reviewed-by: Mika Westerberg mika.westerberg@linux.intel.com Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: 4.1+ stable@vger.kernel.org # 4.1+ [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/acpi/device_sysfs.c | 20 ++++++-------------- 1 file changed, 6 insertions(+), 14 deletions(-)

--- a/drivers/acpi/device_sysfs.c +++ b/drivers/acpi/device_sysfs.c @@ -259,20 +259,12 @@ int __acpi_device_uevent_modalias(struct if (add_uevent_var(env, "MODALIAS=")) return -ENOMEM;

- len = create_pnp_modalias(adev, &env->buf[env->buflen - 1], - sizeof(env->buf) - env->buflen); - if (len < 0) - return len; - - env->buflen += len; - if (!adev->data.of_compatible) - return 0; - - if (len > 0 && add_uevent_var(env, "MODALIAS=")) - return -ENOMEM; - - len = create_of_modalias(adev, &env->buf[env->buflen - 1], - sizeof(env->buf) - env->buflen); + if (adev->data.of_compatible) + len = create_of_modalias(adev, &env->buf[env->buflen - 1], + sizeof(env->buf) - env->buflen); + else + len = create_pnp_modalias(adev, &env->buf[env->buflen - 1], + sizeof(env->buf) - env->buflen); if (len < 0) return len;

From: Giacinto Cifelli gciofono@gmail.com

commit 7e0e63d09516e96994c879f07c5a3c3269d7015e upstream.

Bus 003 Device 009: ID 1e2d:006f Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 239 Miscellaneous Device bDeviceSubClass 2 ? bDeviceProtocol 1 Interface Association bMaxPacketSize0 64 idVendor 0x1e2d idProduct 0x006f bcdDevice 0.00 iManufacturer 3 Cinterion Wireless Modules iProduct 2 PLSx3 iSerial 4 fa3c1419 bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 303 bNumInterfaces 9 bConfigurationValue 1 iConfiguration 1 Cinterion Configuration bmAttributes 0xe0 Self Powered Remote Wakeup MaxPower 500mA Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 0 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 2 Abstract (modem) bFunctionProtocol 1 AT-commands (v.25ter) iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 CDC Header: bcdCDC 1.10 CDC ACM: bmCapabilities 0x02 line coding and serial state CDC Call Management: bmCapabilities 0x03 call management use DataInterface bDataInterface 1 CDC Union: bMasterInterface 0 bSlaveInterface 1 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 Unused bInterfaceProtocol 0 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 2 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 2 Abstract (modem) bFunctionProtocol 1 AT-commands (v.25ter) iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 2 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 CDC Header: bcdCDC 1.10 CDC ACM: bmCapabilities 0x02 line coding and serial state CDC Call Management: bmCapabilities 0x03 call management use DataInterface bDataInterface 3 CDC Union: bMasterInterface 2 bSlaveInterface 3 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 3 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 Unused bInterfaceProtocol 0 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x84 EP 4 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 4 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 2 Abstract (modem) bFunctionProtocol 1 AT-commands (v.25ter) iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 4 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 CDC Header: bcdCDC 1.10 CDC ACM: bmCapabilities 0x02 line coding and serial state CDC Call Management: bmCapabilities 0x03 call management use DataInterface bDataInterface 5 CDC Union: bMasterInterface 4 bSlaveInterface 5 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 5 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 Unused bInterfaceProtocol 0 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x86 EP 6 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 6 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 2 Abstract (modem) bFunctionProtocol 1 AT-commands (v.25ter) iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 6 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 CDC Header: bcdCDC 1.10 CDC ACM: bmCapabilities 0x02 line coding and serial state CDC Call Management: bmCapabilities 0x03 call management use DataInterface bDataInterface 7 CDC Union: bMasterInterface 6 bSlaveInterface 7 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 7 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 Unused bInterfaceProtocol 0 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x88 EP 8 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 8 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x89 EP 9 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x8a EP 10 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x05 EP 5 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Device Qualifier (for other device speed): bLength 10 bDescriptorType 6 bcdUSB 2.00 bDeviceClass 239 Miscellaneous Device bDeviceSubClass 2 ? bDeviceProtocol 1 Interface Association bMaxPacketSize0 64 bNumConfigurations 1 Device Status: 0x0000 (Bus Powered)

Cc: stable@vger.kernel.org Signed-off-by: Giacinto Cifelli gciofono@gmail.com Acked-by: Bjørn Mork bjorn@mork.no Link: https://lore.kernel.org/r/20210120045650.10855-1-gciofono@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -934,6 +934,7 @@ static const struct usb_device_id produc {QMI_FIXED_INTF(0x0b3c, 0xc00a, 6)}, /* Olivetti Olicard 160 */ {QMI_FIXED_INTF(0x0b3c, 0xc00b, 4)}, /* Olivetti Olicard 500 */ {QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */ + {QMI_QUIRK_SET_DTR(0x1e2d, 0x006f, 8)}, /* Cinterion PLS83/PLS63 */ {QMI_FIXED_INTF(0x1e2d, 0x0053, 4)}, /* Cinterion PHxx,PXxx */ {QMI_FIXED_INTF(0x1e2d, 0x0082, 4)}, /* Cinterion PHxx,PXxx (2 RmNet) */ {QMI_FIXED_INTF(0x1e2d, 0x0082, 5)}, /* Cinterion PHxx,PXxx (2 RmNet) */

From: Lorenzo Bianconi lorenzo@kernel.org

commit 0acb20a5438c36e0cf2b8bf255f314b59fcca6ef upstream.

The following crash log can occur unplugging the usb dongle since, after the urb poison in mt7601u_free_tx_queue(), usb_submit_urb() will always fail resulting in a skb kfree while the skb has been already queued.

Fix the issue enqueuing the skb only if usb_submit_urb() succeed.

Hardware name: Hewlett-Packard 500-539ng/2B2C, BIOS 80.06 04/01/2015 Workqueue: usb_hub_wq hub_event RIP: 0010:skb_trim+0x2c/0x30 RSP: 0000:ffffb4c88005bba8 EFLAGS: 00010206 RAX: 000000004ad483ee RBX: ffff9a236625dee0 RCX: 000000000000662f RDX: 000000000000000c RSI: 0000000000000000 RDI: ffff9a2343179300 RBP: ffff9a2343179300 R08: 0000000000000001 R09: 0000000000000000 R10: ffff9a23748f7840 R11: 0000000000000001 R12: ffff9a236625e4d4 R13: ffff9a236625dee0 R14: 0000000000001080 R15: 0000000000000008 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fd410a34ef8 CR3: 00000001416ee001 CR4: 00000000001706f0 Call Trace: mt7601u_tx_status+0x3e/0xa0 [mt7601u] mt7601u_dma_cleanup+0xca/0x110 [mt7601u] mt7601u_cleanup+0x22/0x30 [mt7601u] mt7601u_disconnect+0x22/0x60 [mt7601u] usb_unbind_interface+0x8a/0x270 ? kernfs_find_ns+0x35/0xd0 __device_release_driver+0x17a/0x230 device_release_driver+0x24/0x30 bus_remove_device+0xdb/0x140 device_del+0x18b/0x430 ? kobject_put+0x98/0x1d0 usb_disable_device+0xc6/0x1f0 usb_disconnect.cold+0x7e/0x20a hub_event+0xbf3/0x1870 process_one_work+0x1b6/0x350 worker_thread+0x53/0x3e0 ? process_one_work+0x350/0x350 kthread+0x11b/0x140 ? __kthread_bind_mask+0x60/0x60 ret_from_fork+0x22/0x30

Fixes: 23377c200b2eb ("mt7601u: fix possible memory leak when the device is disconnected") Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Acked-by: Jakub Kicinski kubakici@wp.pl Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/3b85219f669a63a8ced1f43686de05915a580489.161091924... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/wireless/mediatek/mt7601u/dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/wireless/mediatek/mt7601u/dma.c +++ b/drivers/net/wireless/mediatek/mt7601u/dma.c @@ -318,7 +318,6 @@ static int mt7601u_dma_submit_tx(struct }

e = &q->e[q->end]; - e->skb = skb; usb_fill_bulk_urb(e->urb, usb_dev, snd_pipe, skb->data, skb->len, mt7601u_complete_tx, q); ret = usb_submit_urb(e->urb, GFP_ATOMIC); @@ -336,6 +335,7 @@ static int mt7601u_dma_submit_tx(struct

q->end = (q->end + 1) % q->entries; q->used++; + e->skb = skb;

if (q->used >= q->entries) ieee80211_stop_queue(dev->hw, skb_get_queue_mapping(skb));

From: Arnd Bergmann arnd@arndb.de

commit 04e7712f4460585e5eed5b853fd8b82a9943958f upstream.

We are going to share the compat_sys_futex() handler between 64-bit architectures and 32-bit architectures that need to deal with both 32-bit and 64-bit time_t, and this is easier if both entry points are in the same file.

In fact, most other system call handlers do the same thing these days, so let's follow the trend here and merge all of futex_compat.c into futex.c.

In the process, a few minor changes have to be done to make sure everything still makes sense: handle_futex_death() and futex_cmpxchg_enabled() become local symbol, and the compat version of the fetch_robust_entry() function gets renamed to compat_fetch_robust_entry() to avoid a symbol clash.

This is intended as a purely cosmetic patch, no behavior should change.

Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [Lee: Back-ported to satisfy a build dependency] Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/futex.h | 8 - kernel/Makefile | 3 kernel/futex.c | 195 +++++++++++++++++++++++++++++++++++++++++++++++- kernel/futex_compat.c | 201 -------------------------------------------------- 4 files changed, 192 insertions(+), 215 deletions(-) delete mode 100644 kernel/futex_compat.c

--- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -11,9 +11,6 @@ union ktime; long do_futex(u32 __user *uaddr, int op, u32 val, union ktime *timeout, u32 __user *uaddr2, u32 val2, u32 val3);

-extern int -handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi); - /* * Futexes are matched on equal values of this key. * The key type depends on whether it's a shared or private mapping. @@ -58,11 +55,6 @@ union futex_key { #ifdef CONFIG_FUTEX extern void exit_robust_list(struct task_struct *curr); extern void exit_pi_state_list(struct task_struct *curr); -#ifdef CONFIG_HAVE_FUTEX_CMPXCHG -#define futex_cmpxchg_enabled 1 -#else -extern int futex_cmpxchg_enabled; -#endif #else static inline void exit_robust_list(struct task_struct *curr) { --- a/kernel/Makefile +++ b/kernel/Makefile @@ -36,9 +36,6 @@ obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ obj-$(CONFIG_FUTEX) += futex.o -ifeq ($(CONFIG_COMPAT),y) -obj-$(CONFIG_FUTEX) += futex_compat.o -endif obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o ifneq ($(CONFIG_SMP),y) --- a/kernel/futex.c +++ b/kernel/futex.c @@ -44,6 +44,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/compat.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/fs.h> @@ -171,8 +172,10 @@ * double_lock_hb() and double_unlock_hb(), respectively. */

-#ifndef CONFIG_HAVE_FUTEX_CMPXCHG -int __read_mostly futex_cmpxchg_enabled; +#ifdef CONFIG_HAVE_FUTEX_CMPXCHG +#define futex_cmpxchg_enabled 1 +#else +static int __read_mostly futex_cmpxchg_enabled; #endif

/* @@ -3088,7 +3091,7 @@ err_unlock: * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ -int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) +static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) { u32 uval, uninitialized_var(nval), mval;

@@ -3318,6 +3321,192 @@ SYSCALL_DEFINE6(futex, u32 __user *, uad return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); }

+#ifdef CONFIG_COMPAT +/* + * Fetch a robust-list pointer. Bit 0 signals PI futexes: + */ +static inline int +compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, + compat_uptr_t __user *head, unsigned int *pi) +{ + if (get_user(*uentry, head)) + return -EFAULT; + + *entry = compat_ptr((*uentry) & ~1); + *pi = (unsigned int)(*uentry) & 1; + + return 0; +} + +static void __user *futex_uaddr(struct robust_list __user *entry, + compat_long_t futex_offset) +{ + compat_uptr_t base = ptr_to_compat(entry); + void __user *uaddr = compat_ptr(base + futex_offset); + + return uaddr; +} + +/* + * Walk curr->robust_list (very carefully, it's a userspace list!) + * and mark any locks found there dead, and notify any waiters. + * + * We silently return on any sign of list-walking problem. + */ +void compat_exit_robust_list(struct task_struct *curr) +{ + struct compat_robust_list_head __user *head = curr->compat_robust_list; + struct robust_list __user *entry, *next_entry, *pending; + unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; + unsigned int uninitialized_var(next_pi); + compat_uptr_t uentry, next_uentry, upending; + compat_long_t futex_offset; + int rc; + + if (!futex_cmpxchg_enabled) + return; + + /* + * Fetch the list head (which was registered earlier, via + * sys_set_robust_list()): + */ + if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) + return; + /* + * Fetch the relative futex offset: + */ + if (get_user(futex_offset, &head->futex_offset)) + return; + /* + * Fetch any possibly pending lock-add first, and handle it + * if it exists: + */ + if (compat_fetch_robust_entry(&upending, &pending, + &head->list_op_pending, &pip)) + return; + + next_entry = NULL; /* avoid warning with gcc */ + while (entry != (struct robust_list __user *) &head->list) { + /* + * Fetch the next entry in the list before calling + * handle_futex_death: + */ + rc = compat_fetch_robust_entry(&next_uentry, &next_entry, + (compat_uptr_t __user *)&entry->next, &next_pi); + /* + * A pending lock might already be on the list, so + * dont process it twice: + */ + if (entry != pending) { + void __user *uaddr = futex_uaddr(entry, futex_offset); + + if (handle_futex_death(uaddr, curr, pi)) + return; + } + if (rc) + return; + uentry = next_uentry; + entry = next_entry; + pi = next_pi; + /* + * Avoid excessively long or circular lists: + */ + if (!--limit) + break; + + cond_resched(); + } + if (pending) { + void __user *uaddr = futex_uaddr(pending, futex_offset); + + handle_futex_death(uaddr, curr, pip); + } +} + +COMPAT_SYSCALL_DEFINE2(set_robust_list, + struct compat_robust_list_head __user *, head, + compat_size_t, len) +{ + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + if (unlikely(len != sizeof(*head))) + return -EINVAL; + + current->compat_robust_list = head; + + return 0; +} + +COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, + compat_uptr_t __user *, head_ptr, + compat_size_t __user *, len_ptr) +{ + struct compat_robust_list_head __user *head; + unsigned long ret; + struct task_struct *p; + + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + rcu_read_lock(); + + ret = -ESRCH; + if (!pid) + p = current; + else { + p = find_task_by_vpid(pid); + if (!p) + goto err_unlock; + } + + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) + goto err_unlock; + + head = p->compat_robust_list; + rcu_read_unlock(); + + if (put_user(sizeof(*head), len_ptr)) + return -EFAULT; + return put_user(ptr_to_compat(head), head_ptr); + +err_unlock: + rcu_read_unlock(); + + return ret; +} + +COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, + struct compat_timespec __user *, utime, u32 __user *, uaddr2, + u32, val3) +{ + struct timespec ts; + ktime_t t, *tp = NULL; + int val2 = 0; + int cmd = op & FUTEX_CMD_MASK; + + if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || + cmd == FUTEX_WAIT_BITSET || + cmd == FUTEX_WAIT_REQUEUE_PI)) { + if (compat_get_timespec(&ts, utime)) + return -EFAULT; + if (!timespec_valid(&ts)) + return -EINVAL; + + t = timespec_to_ktime(ts); + if (cmd == FUTEX_WAIT) + t = ktime_add_safe(ktime_get(), t); + tp = &t; + } + if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || + cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) + val2 = (int) (unsigned long) utime; + + return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); +} +#endif /* CONFIG_COMPAT */ + static void __init futex_detect_cmpxchg(void) { #ifndef CONFIG_HAVE_FUTEX_CMPXCHG --- a/kernel/futex_compat.c +++ /dev/null @@ -1,201 +0,0 @@ -/* - * linux/kernel/futex_compat.c - * - * Futex compatibililty routines. - * - * Copyright 2006, Red Hat, Inc., Ingo Molnar - */ - -#include <linux/linkage.h> -#include <linux/compat.h> -#include <linux/nsproxy.h> -#include <linux/futex.h> -#include <linux/ptrace.h> -#include <linux/syscalls.h> - -#include <asm/uaccess.h> - - -/* - * Fetch a robust-list pointer. Bit 0 signals PI futexes: - */ -static inline int -fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, - compat_uptr_t __user *head, unsigned int *pi) -{ - if (get_user(*uentry, head)) - return -EFAULT; - - *entry = compat_ptr((*uentry) & ~1); - *pi = (unsigned int)(*uentry) & 1; - - return 0; -} - -static void __user *futex_uaddr(struct robust_list __user *entry, - compat_long_t futex_offset) -{ - compat_uptr_t base = ptr_to_compat(entry); - void __user *uaddr = compat_ptr(base + futex_offset); - - return uaddr; -} - -/* - * Walk curr->robust_list (very carefully, it's a userspace list!) - * and mark any locks found there dead, and notify any waiters. - * - * We silently return on any sign of list-walking problem. - */ -void compat_exit_robust_list(struct task_struct *curr) -{ - struct compat_robust_list_head __user *head = curr->compat_robust_list; - struct robust_list __user *entry, *next_entry, *pending; - unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; - unsigned int uninitialized_var(next_pi); - compat_uptr_t uentry, next_uentry, upending; - compat_long_t futex_offset; - int rc; - - if (!futex_cmpxchg_enabled) - return; - - /* - * Fetch the list head (which was registered earlier, via - * sys_set_robust_list()): - */ - if (fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) - return; - /* - * Fetch the relative futex offset: - */ - if (get_user(futex_offset, &head->futex_offset)) - return; - /* - * Fetch any possibly pending lock-add first, and handle it - * if it exists: - */ - if (fetch_robust_entry(&upending, &pending, - &head->list_op_pending, &pip)) - return; - - next_entry = NULL; /* avoid warning with gcc */ - while (entry != (struct robust_list __user *) &head->list) { - /* - * Fetch the next entry in the list before calling - * handle_futex_death: - */ - rc = fetch_robust_entry(&next_uentry, &next_entry, - (compat_uptr_t __user *)&entry->next, &next_pi); - /* - * A pending lock might already be on the list, so - * dont process it twice: - */ - if (entry != pending) { - void __user *uaddr = futex_uaddr(entry, futex_offset); - - if (handle_futex_death(uaddr, curr, pi)) - return; - } - if (rc) - return; - uentry = next_uentry; - entry = next_entry; - pi = next_pi; - /* - * Avoid excessively long or circular lists: - */ - if (!--limit) - break; - - cond_resched(); - } - if (pending) { - void __user *uaddr = futex_uaddr(pending, futex_offset); - - handle_futex_death(uaddr, curr, pip); - } -} - -COMPAT_SYSCALL_DEFINE2(set_robust_list, - struct compat_robust_list_head __user *, head, - compat_size_t, len) -{ - if (!futex_cmpxchg_enabled) - return -ENOSYS; - - if (unlikely(len != sizeof(*head))) - return -EINVAL; - - current->compat_robust_list = head; - - return 0; -} - -COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, - compat_uptr_t __user *, head_ptr, - compat_size_t __user *, len_ptr) -{ - struct compat_robust_list_head __user *head; - unsigned long ret; - struct task_struct *p; - - if (!futex_cmpxchg_enabled) - return -ENOSYS; - - rcu_read_lock(); - - ret = -ESRCH; - if (!pid) - p = current; - else { - p = find_task_by_vpid(pid); - if (!p) - goto err_unlock; - } - - ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) - goto err_unlock; - - head = p->compat_robust_list; - rcu_read_unlock(); - - if (put_user(sizeof(*head), len_ptr)) - return -EFAULT; - return put_user(ptr_to_compat(head), head_ptr); - -err_unlock: - rcu_read_unlock(); - - return ret; -} - -COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, - struct compat_timespec __user *, utime, u32 __user *, uaddr2, - u32, val3) -{ - struct timespec ts; - ktime_t t, *tp = NULL; - int val2 = 0; - int cmd = op & FUTEX_CMD_MASK; - - if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || - cmd == FUTEX_WAIT_BITSET || - cmd == FUTEX_WAIT_REQUEUE_PI)) { - if (compat_get_timespec(&ts, utime)) - return -EFAULT; - if (!timespec_valid(&ts)) - return -EINVAL; - - t = timespec_to_ktime(ts); - if (cmd == FUTEX_WAIT) - t = ktime_add_safe(ktime_get(), t); - tp = &t; - } - if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || - cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) - val2 = (int) (unsigned long) utime; - - return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); -}

From: Thomas Gleixner tglx@linutronix.de

commit 3d4775df0a89240f671861c6ab6e8d59af8e9e41 upstream.

The futex exit handling relies on PF_ flags. That's suboptimal as it requires a smp_mb() and an ugly lock/unlock of the exiting tasks pi_lock in the middle of do_exit() to enforce the observability of PF_EXITING in the futex code.

Add a futex_state member to task_struct and convert the PF_EXITPIDONE logic over to the new state. The PF_EXITING dependency will be cleaned up in a later step.

This prepares for handling various futex exit issues later.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Ingo Molnar mingo@kernel.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20191106224556.149449274@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/futex.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/sched.h | 2 +- kernel/exit.c | 18 ++---------------- kernel/futex.c | 17 ++++++++--------- 4 files changed, 45 insertions(+), 26 deletions(-)

--- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -55,6 +55,11 @@ union futex_key { #define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = 0ULL } }

#ifdef CONFIG_FUTEX +enum { + FUTEX_STATE_OK, + FUTEX_STATE_DEAD, +}; + static inline void futex_init_task(struct task_struct *tsk) { tsk->robust_list = NULL; @@ -63,6 +68,34 @@ static inline void futex_init_task(struc #endif INIT_LIST_HEAD(&tsk->pi_state_list); tsk->pi_state_cache = NULL; + tsk->futex_state = FUTEX_STATE_OK; +} + +/** + * futex_exit_done - Sets the tasks futex state to FUTEX_STATE_DEAD + * @tsk: task to set the state on + * + * Set the futex exit state of the task lockless. The futex waiter code + * observes that state when a task is exiting and loops until the task has + * actually finished the futex cleanup. The worst case for this is that the + * waiter runs through the wait loop until the state becomes visible. + * + * This has two callers: + * + * - futex_mm_release() after the futex exit cleanup has been done + * + * - do_exit() from the recursive fault handling path. + * + * In case of a recursive fault this is best effort. Either the futex exit + * code has run already or not. If the OWNER_DIED bit has been set on the + * futex then the waiter can take it over. If not, the problem is pushed + * back to user space. If the futex exit code did not run yet, then an + * already queued waiter might block forever, but there is nothing which + * can be done about that. + */ +static inline void futex_exit_done(struct task_struct *tsk) +{ + tsk->futex_state = FUTEX_STATE_DEAD; }

void futex_mm_release(struct task_struct *tsk); @@ -72,5 +105,6 @@ long do_futex(u32 __user *uaddr, int op, #else static inline void futex_init_task(struct task_struct *tsk) { } static inline void futex_mm_release(struct task_struct *tsk) { } +static inline void futex_exit_done(struct task_struct *tsk) { } #endif #endif --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1704,6 +1704,7 @@ struct task_struct { #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; + unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts]; @@ -2099,7 +2100,6 @@ extern void thread_group_cputime_adjuste * Per process flags */ #define PF_EXITING 0x00000004 /* getting shut down */ -#define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ --- a/kernel/exit.c +++ b/kernel/exit.c @@ -695,16 +695,7 @@ void do_exit(long code) */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); - /* - * We can do this unlocked here. The futex code uses - * this flag just to verify whether the pi state - * cleanup has been done or not. In the worst case it - * loops once more. We pretend that the cleanup was - * done as there is no way to return. Either the - * OWNER_DIED bit is set by now or we push the blocked - * task into the wait for ever nirwana as well. - */ - tsk->flags |= PF_EXITPIDONE; + futex_exit_done(tsk); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); } @@ -793,12 +784,7 @@ void do_exit(long code) * Make sure we are holding no locks: */ debug_check_no_locks_held(); - /* - * We can do this unlocked here. The futex code uses this flag - * just to verify whether the pi state cleanup has been done - * or not. In the worst case it loops once more. - */ - tsk->flags |= PF_EXITPIDONE; + futex_exit_done(tsk);

if (tsk->io_context) exit_io_context(tsk); --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1094,19 +1094,18 @@ static int attach_to_pi_owner(u32 uval, }

/* - * We need to look at the task state flags to figure out, - * whether the task is exiting. To protect against the do_exit - * change of the task flags, we do this protected by - * p->pi_lock: + * We need to look at the task state to figure out, whether the + * task is exiting. To protect against the change of the task state + * in futex_exit_release(), we do this protected by p->pi_lock: */ raw_spin_lock_irq(&p->pi_lock); - if (unlikely(p->flags & PF_EXITING)) { + if (unlikely(p->futex_state != FUTEX_STATE_OK)) { /* - * The task is on the way out. When PF_EXITPIDONE is - * set, we know that the task has finished the - * cleanup: + * The task is on the way out. When the futex state is + * FUTEX_STATE_DEAD, we know that the task has finished + * the cleanup: */ - int ret = (p->flags & PF_EXITPIDONE) ? -ESRCH : -EAGAIN; + int ret = (p->futex_state = FUTEX_STATE_DEAD) ? -ESRCH : -EAGAIN;

raw_spin_unlock_irq(&p->pi_lock); put_task_struct(p);

From: Thomas Gleixner tglx@linutronix.de

commit 150d71584b12809144b8145b817e83b81158ae5f upstream.

To allow separate handling of the futex exit state in the futex exit code for exit and exec, split futex_mm_release() into two functions and invoke them from the corresponding exit/exec_mm_release() callsites.

Preparatory only, no functional change.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Ingo Molnar mingo@kernel.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20191106224556.332094221@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/futex.h | 6 ++++-- kernel/fork.c | 5 ++--- kernel/futex.c | 7 ++++++- 3 files changed, 12 insertions(+), 6 deletions(-)

--- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -98,13 +98,15 @@ static inline void futex_exit_done(struc tsk->futex_state = FUTEX_STATE_DEAD; }

-void futex_mm_release(struct task_struct *tsk); +void futex_exit_release(struct task_struct *tsk); +void futex_exec_release(struct task_struct *tsk);

long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3); #else static inline void futex_init_task(struct task_struct *tsk) { } -static inline void futex_mm_release(struct task_struct *tsk) { } static inline void futex_exit_done(struct task_struct *tsk) { } +static inline void futex_exit_release(struct task_struct *tsk) { } +static inline void futex_exec_release(struct task_struct *tsk) { } #endif #endif --- a/kernel/fork.c +++ b/kernel/fork.c @@ -889,9 +889,6 @@ static int wait_for_vfork_done(struct ta */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { - /* Get rid of any futexes when releasing the mm */ - futex_mm_release(tsk); - uprobe_free_utask(tsk);

/* Get rid of any cached register state */ @@ -926,11 +923,13 @@ static void mm_release(struct task_struc

void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { + futex_exit_release(tsk); mm_release(tsk, mm); }

void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { + futex_exec_release(tsk); mm_release(tsk, mm); }

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -3234,7 +3234,7 @@ static void exit_robust_list(struct task curr, pip); }

-void futex_mm_release(struct task_struct *tsk) +void futex_exec_release(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); @@ -3252,6 +3252,11 @@ void futex_mm_release(struct task_struct exit_pi_state_list(tsk); }

+void futex_exit_release(struct task_struct *tsk) +{ + futex_exec_release(tsk); +} + long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) {

From: Thomas Gleixner tglx@linutronix.de

commit 18f694385c4fd77a09851fd301236746ca83f3cb upstream.

Instead of relying on PF_EXITING use an explicit state for the futex exit and set it in the futex exit function. This moves the smp barrier and the lock/unlock serialization into the futex code.

As with the DEAD state this is restricted to the exit path as exec continues to use the same task struct.

This allows to simplify that logic in a next step.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Ingo Molnar mingo@kernel.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20191106224556.539409004@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/futex.h | 31 +++---------------------------- kernel/exit.c | 8 +------- kernel/futex.c | 37 ++++++++++++++++++++++++++++++++++++- 3 files changed, 40 insertions(+), 36 deletions(-)

--- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -57,6 +57,7 @@ union futex_key { #ifdef CONFIG_FUTEX enum { FUTEX_STATE_OK, + FUTEX_STATE_EXITING, FUTEX_STATE_DEAD, };

@@ -71,33 +72,7 @@ static inline void futex_init_task(struc tsk->futex_state = FUTEX_STATE_OK; }

-/** - * futex_exit_done - Sets the tasks futex state to FUTEX_STATE_DEAD - * @tsk: task to set the state on - * - * Set the futex exit state of the task lockless. The futex waiter code - * observes that state when a task is exiting and loops until the task has - * actually finished the futex cleanup. The worst case for this is that the - * waiter runs through the wait loop until the state becomes visible. - * - * This has two callers: - * - * - futex_mm_release() after the futex exit cleanup has been done - * - * - do_exit() from the recursive fault handling path. - * - * In case of a recursive fault this is best effort. Either the futex exit - * code has run already or not. If the OWNER_DIED bit has been set on the - * futex then the waiter can take it over. If not, the problem is pushed - * back to user space. If the futex exit code did not run yet, then an - * already queued waiter might block forever, but there is nothing which - * can be done about that. - */ -static inline void futex_exit_done(struct task_struct *tsk) -{ - tsk->futex_state = FUTEX_STATE_DEAD; -} - +void futex_exit_recursive(struct task_struct *tsk); void futex_exit_release(struct task_struct *tsk); void futex_exec_release(struct task_struct *tsk);

@@ -105,7 +80,7 @@ long do_futex(u32 __user *uaddr, int op, u32 __user *uaddr2, u32 val2, u32 val3); #else static inline void futex_init_task(struct task_struct *tsk) { } -static inline void futex_exit_done(struct task_struct *tsk) { } +static inline void futex_exit_recursive(struct task_struct *tsk) { } static inline void futex_exit_release(struct task_struct *tsk) { } static inline void futex_exec_release(struct task_struct *tsk) { } #endif --- a/kernel/exit.c +++ b/kernel/exit.c @@ -695,18 +695,12 @@ void do_exit(long code) */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); - futex_exit_done(tsk); + futex_exit_recursive(tsk); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); }

exit_signals(tsk); /* sets PF_EXITING */ - /* - * tsk->flags are checked in the futex code to protect against - * an exiting task cleaning up the robust pi futexes. - */ - smp_mb(); - raw_spin_unlock_wait(&tsk->pi_lock);

if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3252,10 +3252,45 @@ void futex_exec_release(struct task_stru exit_pi_state_list(tsk); }

+/** + * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD + * @tsk: task to set the state on + * + * Set the futex exit state of the task lockless. The futex waiter code + * observes that state when a task is exiting and loops until the task has + * actually finished the futex cleanup. The worst case for this is that the + * waiter runs through the wait loop until the state becomes visible. + * + * This is called from the recursive fault handling path in do_exit(). + * + * This is best effort. Either the futex exit code has run already or + * not. If the OWNER_DIED bit has been set on the futex then the waiter can + * take it over. If not, the problem is pushed back to user space. If the + * futex exit code did not run yet, then an already queued waiter might + * block forever, but there is nothing which can be done about that. + */ +void futex_exit_recursive(struct task_struct *tsk) +{ + tsk->futex_state = FUTEX_STATE_DEAD; +} + void futex_exit_release(struct task_struct *tsk) { + tsk->futex_state = FUTEX_STATE_EXITING; + /* + * Ensure that all new tsk->pi_lock acquisitions must observe + * FUTEX_STATE_EXITING. Serializes against attach_to_pi_owner(). + */ + smp_mb(); + /* + * Ensure that we must observe the pi_state in exit_pi_state_list(). + */ + raw_spin_lock_irq(&tsk->pi_lock); + raw_spin_unlock_irq(&tsk->pi_lock); + futex_exec_release(tsk); - futex_exit_done(tsk); + + tsk->futex_state = FUTEX_STATE_DEAD; }

long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,

From: Thomas Gleixner tglx@linutronix.de

commit af8cbda2cfcaa5515d61ec500498d46e9a8247e2 upstream.

exec() attempts to handle potentially held futexes gracefully by running the futex exit handling code like exit() does.

The current implementation has no protection against concurrent incoming waiters. The reason is that the futex state cannot be set to FUTEX_STATE_DEAD after the cleanup because the task struct is still active and just about to execute the new binary.

While its arguably buggy when a task holds a futex over exec(), for consistency sake the state handling can at least cover the actual futex exit cleanup section. This provides state consistency protection accross the cleanup. As the futex state of the task becomes FUTEX_STATE_OK after the cleanup has been finished, this cannot prevent subsequent attempts to attach to the task in case that the cleanup was not successfull in mopping up all leftovers.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Ingo Molnar mingo@kernel.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20191106224556.753355618@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 38 ++++++++++++++++++++++++++++++++++---- 1 file changed, 34 insertions(+), 4 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -3234,7 +3234,7 @@ static void exit_robust_list(struct task curr, pip); }

-void futex_exec_release(struct task_struct *tsk) +static void futex_cleanup(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); @@ -3274,7 +3274,7 @@ void futex_exit_recursive(struct task_st tsk->futex_state = FUTEX_STATE_DEAD; }

-void futex_exit_release(struct task_struct *tsk) +static void futex_cleanup_begin(struct task_struct *tsk) { /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. @@ -3290,10 +3290,40 @@ void futex_exit_release(struct task_stru raw_spin_lock_irq(&tsk->pi_lock); tsk->futex_state = FUTEX_STATE_EXITING; raw_spin_unlock_irq(&tsk->pi_lock); +}

- futex_exec_release(tsk); +static void futex_cleanup_end(struct task_struct *tsk, int state) +{ + /* + * Lockless store. The only side effect is that an observer might + * take another loop until it becomes visible. + */ + tsk->futex_state = state; +}

- tsk->futex_state = FUTEX_STATE_DEAD; +void futex_exec_release(struct task_struct *tsk) +{ + /* + * The state handling is done for consistency, but in the case of + * exec() there is no way to prevent futher damage as the PID stays + * the same. But for the unlikely and arguably buggy case that a + * futex is held on exec(), this provides at least as much state + * consistency protection which is possible. + */ + futex_cleanup_begin(tsk); + futex_cleanup(tsk); + /* + * Reset the state to FUTEX_STATE_OK. The task is alive and about + * exec a new binary. + */ + futex_cleanup_end(tsk, FUTEX_STATE_OK); +} + +void futex_exit_release(struct task_struct *tsk) +{ + futex_cleanup_begin(tsk); + futex_cleanup(tsk); + futex_cleanup_end(tsk, FUTEX_STATE_DEAD); }

long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,

From: Thomas Gleixner tglx@linutronix.de

commit ac31c7ff8624409ba3c4901df9237a616c187a5d upstream.

attach_to_pi_owner() returns -EAGAIN for various cases:

- Owner task is exiting - Futex value has changed

The caller drops the held locks (hash bucket, mmap_sem) and retries the operation. In case of the owner task exiting this can result in a live lock.

As a preparatory step for seperating those cases, provide a distinct return value (EBUSY) for the owner exiting case.

No functional change.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Ingo Molnar mingo@kernel.org Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20191106224556.935606117@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -1909,12 +1909,13 @@ retry_private: if (!ret) goto retry; goto out; + case -EBUSY: case -EAGAIN: /* * Two reasons for this: - * - Owner is exiting and we just wait for the + * - EBUSY: Owner is exiting and we just wait for the * exit to complete. - * - The user space value changed. + * - EAGAIN: The user space value changed. */ free_pi_state(pi_state); pi_state = NULL; @@ -2580,12 +2581,13 @@ retry_private: goto out_unlock_put_key; case -EFAULT: goto uaddr_faulted; + case -EBUSY: case -EAGAIN: /* * Two reasons for this: - * - Task is exiting and we just wait for the + * - EBUSY: Task is exiting and we just wait for the * exit to complete. - * - The user space value changed. + * - EAGAIN: The user space value changed. */ queue_unlock(hb); put_futex_key(&q.key);

From: Max Krummenacher max.oss.09@gmail.com

commit a88afa46b86ff461c89cc33fc3a45267fff053e8 upstream.

When the kernel is configured to use the Thumb-2 instruction set "suspend-to-memory" fails to resume. Observed on a Colibri iMX6ULL (i.MX 6ULL) and Apalis iMX6 (i.MX 6Q).

It looks like the CPU resumes unconditionally in ARM instruction mode and then chokes on the presented Thumb-2 code it should execute.

Fix this by using the arm instruction set for all code in suspend-imx6.S.

Signed-off-by: Max Krummenacher max.krummenacher@toradex.com Fixes: df595746fa69 ("ARM: imx: add suspend in ocram support for i.mx6q") Acked-by: Oleksandr Suvorov oleksandr.suvorov@toradex.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm/mach-imx/suspend-imx6.S | 1 + 1 file changed, 1 insertion(+)

--- a/arch/arm/mach-imx/suspend-imx6.S +++ b/arch/arm/mach-imx/suspend-imx6.S @@ -73,6 +73,7 @@ #define MX6Q_CCM_CCR 0x0

.align 3 + .arm

.macro sync_l2_cache

From: Shmulik Ladkani shmulik@metanetworks.com

[ Upstream commit 56ce7c25ae1525d83cf80a880cf506ead1914250 ]

When setting xfrm replay_window to values higher than 32, a rare page-fault occurs in xfrm_replay_advance_bmp:

BUG: unable to handle page fault for address: ffff8af350ad7920 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD ad001067 P4D ad001067 PUD 0 Oops: 0002 [#1] SMP PTI CPU: 3 PID: 30 Comm: ksoftirqd/3 Kdump: loaded Not tainted 5.4.52-050452-generic #202007160732 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 RIP: 0010:xfrm_replay_advance_bmp+0xbb/0x130 RSP: 0018:ffffa1304013ba40 EFLAGS: 00010206 RAX: 000000000000010d RBX: 0000000000000002 RCX: 00000000ffffff4b RDX: 0000000000000018 RSI: 00000000004c234c RDI: 00000000ffb3dbff RBP: ffffa1304013ba50 R08: ffff8af330ad7920 R09: 0000000007fffffa R10: 0000000000000800 R11: 0000000000000010 R12: ffff8af29d6258c0 R13: ffff8af28b95c700 R14: 0000000000000000 R15: ffff8af29d6258fc FS: 0000000000000000(0000) GS:ffff8af339ac0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff8af350ad7920 CR3: 0000000015ee4000 CR4: 00000000001406e0 Call Trace: xfrm_input+0x4e5/0xa10 xfrm4_rcv_encap+0xb5/0xe0 xfrm4_udp_encap_rcv+0x140/0x1c0

Analysis revealed offending code is when accessing:

replay_esn->bmp[nr] |= (1U << bitnr);

with 'nr' being 0x07fffffa.

This happened in an SMP system when reordering of packets was present; A packet arrived with a "too old" sequence number (outside the window, i.e 'diff > replay_window'), and therefore the following calculation:

bitnr = replay_esn->replay_window - (diff - pos);

yields a negative result, but since bitnr is u32 we get a large unsigned quantity (in crash dump above: 0xffffff4b seen in ecx).

This was supposed to be protected by xfrm_input()'s former call to:

if (x->repl->check(x, skb, seq)) {

However, the state's spinlock x->lock is *released* after '->check()' is performed, and gets re-acquired before '->advance()' - which gives a chance for a different core to update the xfrm state, e.g. by advancing 'replay_esn->seq' when it encounters more packets - leading to a 'diff > replay_window' situation when original core continues to xfrm_replay_advance_bmp().

An attempt to fix this issue was suggested in commit bcf66bf54aab ("xfrm: Perform a replay check after return from async codepaths"), by calling 'x->repl->recheck()' after lock is re-acquired, but fix applied only to asyncronous crypto algorithms.

Augment the fix, by *always* calling 'recheck()' - irrespective if we're using async crypto.

Fixes: 0ebea8ef3559 ("[IPSEC]: Move state lock into x->type->input") Signed-off-by: Shmulik Ladkani shmulik.ladkani@gmail.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 1e87639f2c270..d613bf77cc0f9 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -315,7 +315,7 @@ resume: /* only the first xfrm gets the encap type */ encap_type = 0;

- if (async && x->repl->recheck(x, skb, seq)) { + if (x->repl->recheck(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; }

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 054c9939b4800a91475d8d89905827bf9e1ad97a ]

syzbot reported a crash that happened when changing the interface type around a lot, and while it might have been easy to fix just the symptom there, a little deeper investigation found that really the reason is that we allowed packets to be transmitted while in the middle of changing the interface type.

Disallow TX by stopping the queues while changing the type.

Fixes: 34d4bc4d41d2 ("mac80211: support runtime interface type changes") Reported-by: syzbot+d7a3b15976bf7de2238a@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20210122171115.b321f98f4d4f.I6997841933c17b093535c... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/ieee80211_i.h | 1 + net/mac80211/iface.c | 6 ++++++ 2 files changed, 7 insertions(+)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a991d1df6774d..1046520d726d8 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1027,6 +1027,7 @@ enum queue_stop_reason { IEEE80211_QUEUE_STOP_REASON_FLUSH, IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN, IEEE80211_QUEUE_STOP_REASON_RESERVE_TID, + IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE,

IEEE80211_QUEUE_STOP_REASONS, }; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 519def0e15f17..6d12a893eb11c 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1507,6 +1507,10 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, if (ret) return ret;

+ ieee80211_stop_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE); + synchronize_net(); + ieee80211_do_stop(sdata, false);

ieee80211_teardown_sdata(sdata); @@ -1527,6 +1531,8 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, err = ieee80211_do_open(&sdata->wdev, false); WARN(err, "type change: do_open returned %d", err);

+ ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE); return ret; }

From: David Woodhouse dwmw@amazon.co.uk

commit c40aaaac1018ff1382f2d35df5129a6bcea3df6b upstream.

Instead of bailing out completely, such a unit can still be used for interrupt remapping.

Signed-off-by: David Woodhouse dwmw@amazon.co.uk Reviewed-by: Lu Baolu baolu.lu@linux.intel.com Link: https://lore.kernel.org/linux-iommu/549928db2de6532117f36c9c810373c14cf76f51... Signed-off-by: Joerg Roedel jroedel@suse.de [ - context change due to moving drivers/iommu/dmar.c to drivers/iommu/intel/dmar.c - remove the unused err_unmap label - use iommu->iommu_dev instead of iommu->iommu.ops to decide whether when freeing ] Signed-off-by: Filippo Sironi sironi@amazon.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iommu/dmar.c | 44 +++++++++++++++++++++++++++----------------- 1 file changed, 27 insertions(+), 17 deletions(-)

--- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -1012,8 +1012,8 @@ static int alloc_iommu(struct dmar_drhd_ { struct intel_iommu *iommu; u32 ver, sts; - int agaw = 0; - int msagaw = 0; + int agaw = -1; + int msagaw = -1; int err;

if (!drhd->reg_base_addr) { @@ -1038,17 +1038,28 @@ static int alloc_iommu(struct dmar_drhd_ }

err = -EINVAL; - agaw = iommu_calculate_agaw(iommu); - if (agaw < 0) { - pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n", - iommu->seq_id); - goto err_unmap; - } - msagaw = iommu_calculate_max_sagaw(iommu); - if (msagaw < 0) { - pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n", - iommu->seq_id); - goto err_unmap; + if (cap_sagaw(iommu->cap) == 0) { + pr_info("%s: No supported address widths. Not attempting DMA translation.\n", + iommu->name); + drhd->ignored = 1; + } + + if (!drhd->ignored) { + agaw = iommu_calculate_agaw(iommu); + if (agaw < 0) { + pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n", + iommu->seq_id); + drhd->ignored = 1; + } + } + if (!drhd->ignored) { + msagaw = iommu_calculate_max_sagaw(iommu); + if (msagaw < 0) { + pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n", + iommu->seq_id); + drhd->ignored = 1; + agaw = -1; + } } iommu->agaw = agaw; iommu->msagaw = msagaw; @@ -1077,15 +1088,13 @@ static int alloc_iommu(struct dmar_drhd_

drhd->iommu = iommu;

- if (intel_iommu_enabled) + if (intel_iommu_enabled && !drhd->ignored) iommu->iommu_dev = iommu_device_create(NULL, iommu, intel_iommu_groups, "%s", iommu->name);

return 0;

-err_unmap: - unmap_iommu(iommu); error_free_seq_id: dmar_free_seq_id(iommu); error: @@ -1095,7 +1104,8 @@ error:

static void free_iommu(struct intel_iommu *iommu) { - iommu_device_destroy(iommu->iommu_dev); + if (intel_iommu_enabled && iommu->iommu_dev) + iommu_device_destroy(iommu->iommu_dev);

if (iommu->irq) { if (iommu->pr_irq) {

From: Pan Bian bianpan2016@163.com

commit 3a30537cee233fb7da302491b28c832247d89bbe upstream.

Goto to the label put_dev instead of the label error to fix potential resource leak on path that the target index is invalid.

Fixes: c4fbb6515a4d ("NFC: The core part should generate the target index") Signed-off-by: Pan Bian bianpan2016@163.com Link: https://lore.kernel.org/r/20210121152748.98409-1-bianpan2016@163.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/nfc/rawsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -117,7 +117,7 @@ static int rawsock_connect(struct socket if (addr->target_idx > dev->target_next_idx - 1 || addr->target_idx < dev->target_next_idx - dev->n_targets) { rc = -EINVAL; - goto error; + goto put_dev; }

rc = nfc_activate_target(dev, addr->target_idx, addr->nfc_protocol);