From: Pan Bian bianpan2016@163.com

commit cf3c46631e1637582f517a574c77cd6c05793817 upstream.

Put the device node dn before return error code on failure path.

Fixes: 461cd1b03e32 ("net: dsa: bcm_sf2: Register our slave MDIO bus") Signed-off-by: Pan Bian bianpan2016@163.com Link: https://lore.kernel.org/r/20210121123343.26330-1-bianpan2016@163.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/bcm_sf2.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -515,15 +515,19 @@ static int bcm_sf2_mdio_register(struct /* Find our integrated MDIO bus node */ dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio"); priv->master_mii_bus = of_mdio_find_bus(dn); - if (!priv->master_mii_bus) + if (!priv->master_mii_bus) { + of_node_put(dn); return -EPROBE_DEFER; + }

get_device(&priv->master_mii_bus->dev); priv->master_mii_dn = dn;

priv->slave_mii_bus = devm_mdiobus_alloc(ds->dev); - if (!priv->slave_mii_bus) + if (!priv->slave_mii_bus) { + of_node_put(dn); return -ENOMEM; + }

priv->slave_mii_bus->priv = priv; priv->slave_mii_bus->name = "sf2 slave mii";

From: Eric Dumazet edumazet@google.com

commit e4bedf48aaa5552bc1f49703abd17606e7e6e82a upstream

iproute2 probably never goes beyond 8 for the cell exponent, but stick to the max shift exponent for signed 32bit.

UBSAN reported: UBSAN: shift-out-of-bounds in net/sched/sch_api.c:389:22 shift exponent 130 is too large for 32-bit type 'int' CPU: 1 PID: 8450 Comm: syz-executor586 Not tainted 5.11.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x183/0x22e lib/dump_stack.c:120 ubsan_epilogue lib/ubsan.c:148 [inline] __ubsan_handle_shift_out_of_bounds+0x432/0x4d0 lib/ubsan.c:395 __detect_linklayer+0x2a9/0x330 net/sched/sch_api.c:389 qdisc_get_rtab+0x2b5/0x410 net/sched/sch_api.c:435 cbq_init+0x28f/0x12c0 net/sched/sch_cbq.c:1180 qdisc_create+0x801/0x1470 net/sched/sch_api.c:1246 tc_modify_qdisc+0x9e3/0x1fc0 net/sched/sch_api.c:1662 rtnetlink_rcv_msg+0xb1d/0xe60 net/core/rtnetlink.c:5564 netlink_rcv_skb+0x1f0/0x460 net/netlink/af_netlink.c:2494 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x7de/0x9b0 net/netlink/af_netlink.c:1330 netlink_sendmsg+0xaa6/0xe90 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg net/socket.c:672 [inline] ____sys_sendmsg+0x5a2/0x900 net/socket.c:2345 ___sys_sendmsg net/socket.c:2399 [inline] __sys_sendmsg+0x319/0x400 net/socket.c:2432 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Acked-by: Cong Wang cong.wang@bytedance.com Link: https://lore.kernel.org/r/20210114160637.1660597-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org [sudip: adjust context] Signed-off-by: Sudip Mukherjee sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_api.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -393,7 +393,8 @@ struct qdisc_rate_table *qdisc_get_rtab( { struct qdisc_rate_table *rtab;

- if (tab == NULL || r->rate == 0 || r->cell_log == 0 || + if (tab == NULL || r->rate == 0 || + r->cell_log == 0 || r->cell_log >= 32 || nla_len(tab) != TC_RTAB_SIZE) return NULL;

From: Peter Zijlstra peterz@infradead.org

These are unused and clutter up the code.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104151.652692478@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de [Lee: Back-ported to solve a dependency] Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/locking/rtmutex-debug.c | 9 -------- kernel/locking/rtmutex-debug.h | 3 -- kernel/locking/rtmutex.c | 42 +++++++++++++++-------------------------- kernel/locking/rtmutex.h | 2 - 4 files changed, 16 insertions(+), 40 deletions(-)

--- a/kernel/locking/rtmutex-debug.c +++ b/kernel/locking/rtmutex-debug.c @@ -173,12 +173,3 @@ void debug_rt_mutex_init(struct rt_mutex lock->name = name; }

-void -rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task) -{ -} - -void rt_mutex_deadlock_account_unlock(struct task_struct *task) -{ -} - --- a/kernel/locking/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h @@ -9,9 +9,6 @@ * This file contains macros used solely by rtmutex.c. Debug version. */

-extern void -rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task); -extern void rt_mutex_deadlock_account_unlock(struct task_struct *task); extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter); extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name); --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -956,8 +956,6 @@ takeit: */ rt_mutex_set_owner(lock, task);

- rt_mutex_deadlock_account_lock(lock, task); - return 1; }

@@ -1365,8 +1363,6 @@ static bool __sched rt_mutex_slowunlock(

debug_rt_mutex_unlock(lock);

- rt_mutex_deadlock_account_unlock(current); - /* * We must be careful here if the fast path is enabled. If we * have no waiters queued we cannot set owner to NULL here @@ -1432,11 +1428,10 @@ rt_mutex_fastlock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout, enum rtmutex_chainwalk chwalk)) { - if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { - rt_mutex_deadlock_account_lock(lock, current); + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 0; - } else - return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); + + return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); }

static inline int @@ -1448,21 +1443,19 @@ rt_mutex_timed_fastlock(struct rt_mutex enum rtmutex_chainwalk chwalk)) { if (chwalk == RT_MUTEX_MIN_CHAINWALK && - likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { - rt_mutex_deadlock_account_lock(lock, current); + likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 0; - } else - return slowfn(lock, state, timeout, chwalk); + + return slowfn(lock, state, timeout, chwalk); }

static inline int rt_mutex_fasttrylock(struct rt_mutex *lock, int (*slowfn)(struct rt_mutex *lock)) { - if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { - rt_mutex_deadlock_account_lock(lock, current); + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 1; - } + return slowfn(lock); }

@@ -1472,19 +1465,18 @@ rt_mutex_fastunlock(struct rt_mutex *loc struct wake_q_head *wqh)) { WAKE_Q(wake_q); + bool deboost;

- if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { - rt_mutex_deadlock_account_unlock(current); + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) + return;

- } else { - bool deboost = slowfn(lock, &wake_q); + deboost = slowfn(lock, &wake_q);

- wake_up_q(&wake_q); + wake_up_q(&wake_q);

- /* Undo pi boosting if necessary: */ - if (deboost) - rt_mutex_adjust_prio(current); - } + /* Undo pi boosting if necessary: */ + if (deboost) + rt_mutex_adjust_prio(current); }

/** @@ -1682,7 +1674,6 @@ void rt_mutex_init_proxy_locked(struct r __rt_mutex_init(lock, NULL); debug_rt_mutex_proxy_lock(lock, proxy_owner); rt_mutex_set_owner(lock, proxy_owner); - rt_mutex_deadlock_account_lock(lock, proxy_owner); }

/** @@ -1698,7 +1689,6 @@ void rt_mutex_proxy_unlock(struct rt_mut { debug_rt_mutex_proxy_unlock(lock); rt_mutex_set_owner(lock, NULL); - rt_mutex_deadlock_account_unlock(proxy_owner); }

/** --- a/kernel/locking/rtmutex.h +++ b/kernel/locking/rtmutex.h @@ -11,8 +11,6 @@ */

#define rt_mutex_deadlock_check(l) (0) -#define rt_mutex_deadlock_account_lock(m, t) do { } while (0) -#define rt_mutex_deadlock_account_unlock(l) do { } while (0) #define debug_rt_mutex_init_waiter(w) do { } while (0) #define debug_rt_mutex_free_waiter(w) do { } while (0) #define debug_rt_mutex_lock(l) do { } while (0)

From: Peter Zijlstra peterz@infradead.org

commit c1e2f0eaf015fb7076d51a339011f2383e6dd389 upstream.

Julia reported futex state corruption in the following scenario:

waiter waker stealer (prio > waiter)

futex(WAIT_REQUEUE_PI, uaddr, uaddr2, timeout=[N ms]) futex_wait_requeue_pi() futex_wait_queue_me() freezable_schedule() <scheduled out> futex(LOCK_PI, uaddr2) futex(CMP_REQUEUE_PI, uaddr, uaddr2, 1, 0) /* requeues waiter to uaddr2 */ futex(UNLOCK_PI, uaddr2) wake_futex_pi() cmp_futex_value_locked(uaddr2, waiter) wake_up_q() <woken by waker> <hrtimer_wakeup() fires, clears sleeper->task> futex(LOCK_PI, uaddr2) __rt_mutex_start_proxy_lock() try_to_take_rt_mutex() /* steals lock */ rt_mutex_set_owner(lock, stealer) <preempted> <scheduled in> rt_mutex_wait_proxy_lock() __rt_mutex_slowlock() try_to_take_rt_mutex() /* fails, lock held by stealer */ if (timeout && !timeout->task) return -ETIMEDOUT; fixup_owner() /* lock wasn't acquired, so, fixup_pi_state_owner skipped */

return -ETIMEDOUT;

/* At this point, we've returned -ETIMEDOUT to userspace, but the * futex word shows waiter to be the owner, and the pi_mutex has * stealer as the owner */

futex_lock(LOCK_PI, uaddr2) -> bails with EDEADLK, futex word says we're owner.

And suggested that what commit:

73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state")

removes from fixup_owner() looks to be just what is needed. And indeed it is -- I completely missed that requeue_pi could also result in this case. So we need to restore that, except that subsequent patches, like commit:

16ffa12d7425 ("futex: Pull rt_mutex_futex_unlock() out from under hb->lock")

changed all the locking rules. Even without that, the sequence:

- if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) { - locked = 1; - goto out; - }

- raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock); - owner = rt_mutex_owner(&q->pi_state->pi_mutex); - if (!owner) - owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); - raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock); - ret = fixup_pi_state_owner(uaddr, q, owner);

already suggests there were races; otherwise we'd never have to look at next_owner.

So instead of doing 3 consecutive wait_lock sections with who knows what races, we do it all in a single section. Additionally, the usage of pi_state->owner in fixup_owner() was only safe because only the rt_mutex owner would modify it, which this additional case wrecks.

Luckily the values can only change away and not to the value we're testing, this means we can do a speculative test and double check once we have the wait_lock.

Fixes: 73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state") Reported-by: Julia Cartwright julia@ni.com Reported-by: Gratian Crisan gratian.crisan@ni.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Julia Cartwright julia@ni.com Tested-by: Gratian Crisan gratian.crisan@ni.com Cc: Darren Hart dvhart@infradead.org Link: https://lkml.kernel.org/r/20171208124939.7livp7no2ov65rrc@hirez.programming.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [Lee: Back-ported to solve a dependency] Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 80 +++++++++++++++++++++++++++++++++------- kernel/locking/rtmutex.c | 26 +++++++++---- kernel/locking/rtmutex_common.h | 1 3 files changed, 87 insertions(+), 20 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -2262,30 +2262,34 @@ static void unqueue_me_pi(struct futex_q spin_unlock(q->lock_ptr); }

-/* - * Fixup the pi_state owner with the new owner. - * - * Must be called with hash bucket lock held and mm->sem held for non - * private futexes. - */ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *newowner) + struct task_struct *argowner) { - u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; - struct task_struct *oldowner = pi_state->owner; u32 uval, uninitialized_var(curval), newval; + struct task_struct *oldowner, *newowner; + u32 newtid; int ret;

+ lockdep_assert_held(q->lock_ptr); + + oldowner = pi_state->owner; /* Owner died? */ if (!pi_state->owner) newtid |= FUTEX_OWNER_DIED;

/* - * We are here either because we stole the rtmutex from the - * previous highest priority waiter or we are the highest priority - * waiter but failed to get the rtmutex the first time. - * We have to replace the newowner TID in the user space variable. + * We are here because either: + * + * - we stole the lock and pi_state->owner needs updating to reflect + * that (@argowner == current), + * + * or: + * + * - someone stole our lock and we need to fix things to point to the + * new owner (@argowner == NULL). + * + * Either way, we have to replace the TID in the user space variable. * This must be atomic as we have to preserve the owner died bit here. * * Note: We write the user space value _before_ changing the pi_state @@ -2299,6 +2303,39 @@ static int fixup_pi_state_owner(u32 __us * in lookup_pi_state. */ retry: + if (!argowner) { + if (oldowner != current) { + /* + * We raced against a concurrent self; things are + * already fixed up. Nothing to do. + */ + return 0; + } + + if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) { + /* We got the lock after all, nothing to fix. */ + return 0; + } + + /* + * Since we just failed the trylock; there must be an owner. + */ + newowner = rt_mutex_owner(&pi_state->pi_mutex); + BUG_ON(!newowner); + } else { + WARN_ON_ONCE(argowner != current); + if (oldowner == current) { + /* + * We raced against a concurrent self; things are + * already fixed up. Nothing to do. + */ + return 0; + } + newowner = argowner; + } + + newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; + if (get_futex_value_locked(&uval, uaddr)) goto handle_fault;

@@ -2385,12 +2422,29 @@ static int fixup_owner(u32 __user *uaddr /* * Got the lock. We might not be the anticipated owner if we * did a lock-steal - fix up the PI-state in that case: + * + * Speculative pi_state->owner read (we don't hold wait_lock); + * since we own the lock pi_state->owner == current is the + * stable state, anything else needs more attention. */ if (q->pi_state->owner != current) ret = fixup_pi_state_owner(uaddr, q, current); goto out; }

+ /* + * If we didn't get the lock; check if anybody stole it from us. In + * that case, we need to fix up the uval to point to them instead of + * us, otherwise bad things happen. [10] + * + * Another speculative read; pi_state->owner == current is unstable + * but needs our attention. + */ + if (q->pi_state->owner == current) { + ret = fixup_pi_state_owner(uaddr, q, NULL); + goto out; + } + /* * Paranoia check. If we did not take the lock, then we should not be * the owner of the rt_mutex. --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1314,6 +1314,19 @@ rt_mutex_slowlock(struct rt_mutex *lock, return ret; }

+static inline int __rt_mutex_slowtrylock(struct rt_mutex *lock) +{ + int ret = try_to_take_rt_mutex(lock, current, NULL); + + /* + * try_to_take_rt_mutex() sets the lock waiters bit + * unconditionally. Clean this up. + */ + fixup_rt_mutex_waiters(lock); + + return ret; +} + /* * Slow path try-lock function: */ @@ -1336,13 +1349,7 @@ static inline int rt_mutex_slowtrylock(s */ raw_spin_lock_irqsave(&lock->wait_lock, flags);

- ret = try_to_take_rt_mutex(lock, current, NULL); - - /* - * try_to_take_rt_mutex() sets the lock waiters bit - * unconditionally. Clean this up. - */ - fixup_rt_mutex_waiters(lock); + ret = __rt_mutex_slowtrylock(lock);

raw_spin_unlock_irqrestore(&lock->wait_lock, flags);

@@ -1530,6 +1537,11 @@ int __sched rt_mutex_futex_trylock(struc return rt_mutex_slowtrylock(lock); }

+int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return __rt_mutex_slowtrylock(lock); +} + /** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -114,6 +114,7 @@ extern bool rt_mutex_cleanup_proxy_lock( struct rt_mutex_waiter *waiter); extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); extern int rt_mutex_futex_trylock(struct rt_mutex *l); +extern int __rt_mutex_futex_trylock(struct rt_mutex *l);

extern void rt_mutex_futex_unlock(struct rt_mutex *lock); extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,

From: Thomas Gleixner tglx@linutronix.de

[ Upstream commit c5cade200ab9a2a3be9e7f32a752c8d86b502ec7 ]

Updating pi_state::owner is done at several places with the same code. Provide a function for it and use that at the obvious places.

This is also a preparation for a bug fix to avoid yet another copy of the same code or alternatively introducing a completely unpenetratable mess of gotos.

Originally-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 64 +++++++++++++++++++++++++++++---------------------------- 1 file changed, 33 insertions(+), 31 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -837,6 +837,29 @@ static struct futex_pi_state * alloc_pi_ return pi_state; }

+static void pi_state_update_owner(struct futex_pi_state *pi_state, + struct task_struct *new_owner) +{ + struct task_struct *old_owner = pi_state->owner; + + lockdep_assert_held(&pi_state->pi_mutex.wait_lock); + + if (old_owner) { + raw_spin_lock(&old_owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + raw_spin_unlock(&old_owner->pi_lock); + } + + if (new_owner) { + raw_spin_lock(&new_owner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &new_owner->pi_state_list); + pi_state->owner = new_owner; + raw_spin_unlock(&new_owner->pi_lock); + } +} + /* * Drops a reference to the pi_state object and frees or caches it * when the last reference is gone. @@ -1432,26 +1455,16 @@ static int wake_futex_pi(u32 __user *uad else ret = -EINVAL; } - if (ret) { - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); - return ret; - } - - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock);

- raw_spin_lock(&new_owner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &new_owner->pi_state_list); - pi_state->owner = new_owner; - raw_spin_unlock(&new_owner->pi_lock); - - /* - * We've updated the uservalue, this unlock cannot fail. - */ - deboost = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + if (!ret) { + /* + * This is a point of no return; once we modified the uval + * there is no going back and subsequent operations must + * not fail. + */ + pi_state_update_owner(pi_state, new_owner); + deboost = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + }

raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); @@ -2353,19 +2366,8 @@ retry: * We fixed up user space. Now we need to fix the pi_state * itself. */ - if (pi_state->owner != NULL) { - raw_spin_lock_irq(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); - } - - pi_state->owner = newowner; + pi_state_update_owner(pi_state, newowner);

- raw_spin_lock_irq(&newowner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &newowner->pi_state_list); - raw_spin_unlock_irq(&newowner->pi_lock); return 0;

/*

From: Thomas Gleixner tglx@linutronix.de

[ Upstream commit 6ccc84f917d33312eb2846bd7b567639f585ad6d ]

No point in open coding it. This way it gains the extra sanity checks.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Lee Jones lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/futex.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -879,10 +879,7 @@ static void put_pi_state(struct futex_pi * and has cleaned up the pi_state already */ if (pi_state->owner) { - raw_spin_lock_irq(&pi_state->owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); - + pi_state_update_owner(pi_state, NULL); rt_mutex_proxy_unlock(&pi_state->pi_mutex); }

From: Thomas Gleixner tglx@linutronix.de

fixup_pi_state_owner() tries to ensure that the state of the rtmutex, pi_state and the user space value related to the PI futex are consistent before returning to user space. In case that the user space value update faults and the fault cannot be resolved by faulting the page in via fault_in_user_writeable() the function returns with -EFAULT and leaves the rtmutex and pi_state owner state inconsistent.

A subsequent futex_unlock_pi() operates on the inconsistent pi_state and releases the rtmutex despite not owning it which can corrupt the RB tree of the rtmutex and cause a subsequent kernel stack use after free.

It was suggested to loop forever in fixup_pi_state_owner() if the fault cannot be resolved, but that results in runaway tasks which is especially undesired when the problem happens due to a programming error and not due to malice.

As the user space value cannot be fixed up, the proper solution is to make the rtmutex and the pi_state consistent so both have the same owner. This leaves the user space value out of sync. Any subsequent operation on the futex will fail because the 10th rule of PI futexes (pi_state owner and user space value are consistent) has been violated.

As a consequence this removes the inept attempts of 'fixing' the situation in case that the current task owns the rtmutex when returning with an unresolvable fault by unlocking the rtmutex which left pi_state::owner and rtmutex::owner out of sync in a different and only slightly less dangerous way.

Fixes: 1b7558e457ed ("futexes: fix fault handling in futex_lock_pi") Reported-by: gzobqq@gmail.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.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, 20 insertions(+), 18 deletions(-)

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -1017,7 +1017,8 @@ static void exit_pi_state_list(struct ta * FUTEX_OWNER_DIED bit. See [4] * * [10] There is no transient state which leaves owner and user space - * TID out of sync. + * TID out of sync. Except one error case where the kernel is denied + * write access to the user address, see fixup_pi_state_owner(). */

/* @@ -2392,6 +2393,24 @@ handle_fault: if (!err) goto retry;

+ /* + * fault_in_user_writeable() failed so user state is immutable. At + * best we can make the kernel state consistent but user state will + * be most likely hosed and any subsequent unlock operation will be + * rejected due to PI futex rule [10]. + * + * Ensure that the rtmutex owner is also the pi_state owner despite + * the user space value claiming something different. There is no + * point in unlocking the rtmutex if current is the owner as it + * would need to wait until the next waiter has taken the rtmutex + * to guarantee consistent state. Keep it simple. Userspace asked + * for this wreckaged state. + * + * The rtmutex has an owner - either current or some other + * task. See the EAGAIN loop above. + */ + pi_state_update_owner(pi_state, rt_mutex_owner(&pi_state->pi_mutex)); + return err; }

@@ -2777,13 +2796,6 @@ retry_private: if (res) ret = (res < 0) ? res : 0;

- /* - * If fixup_owner() faulted and was unable to handle the fault, unlock - * it and return the fault to userspace. - */ - if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) - rt_mutex_futex_unlock(&q.pi_state->pi_mutex); - /* Unqueue and drop the lock */ unqueue_me_pi(&q);

@@ -3088,8 +3100,6 @@ static int futex_wait_requeue_pi(u32 __u if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); - if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) - rt_mutex_futex_unlock(&q.pi_state->pi_mutex); /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. @@ -3126,14 +3136,6 @@ static int futex_wait_requeue_pi(u32 __u if (res) ret = (res < 0) ? res : 0;

- /* - * If fixup_pi_state_owner() faulted and was unable to handle - * the fault, unlock the rt_mutex and return the fault to - * userspace. - */ - if (ret && rt_mutex_owner(pi_mutex) == current) - rt_mutex_futex_unlock(pi_mutex); - /* Unqueue and drop the lock. */ unqueue_me_pi(&q); }

From: Felix Fietkau nbd@nbd.name

[ Upstream commit 622d3b4e39381262da7b18ca1ed1311df227de86 ]

When using WEP, the default unicast key needs to be selected, instead of the STA PTK.

Signed-off-by: Felix Fietkau nbd@nbd.name Link: https://lore.kernel.org/r/20201218184718.93650-5-nbd@nbd.name Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/rx.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 9be82ed02e0e5..c38d68131d02e 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3802,6 +3802,8 @@ void ieee80211_check_fast_rx(struct sta_info *sta)

rcu_read_lock(); key = rcu_dereference(sta->ptk[sta->ptk_idx]); + if (!key) + key = rcu_dereference(sdata->default_unicast_key); if (key) { switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP:

From: Josh Poimboeuf jpoimboe@redhat.com

[ Upstream commit 1d489151e9f9d1647110277ff77282fe4d96d09b ]

Thanks to a recent binutils change which doesn't generate unused symbols, it's now possible for thunk_64.o be completely empty without CONFIG_PREEMPTION: no text, no data, no symbols.

We could edit the Makefile to only build that file when CONFIG_PREEMPTION is enabled, but that will likely create confusion if/when the thunks end up getting used by some other code again.

Just ignore it and move on.

Reported-by: Nathan Chancellor natechancellor@gmail.com Reviewed-by: Nathan Chancellor natechancellor@gmail.com Reviewed-by: Miroslav Benes mbenes@suse.cz Tested-by: Nathan Chancellor natechancellor@gmail.com Link: https://github.com/ClangBuiltLinux/linux/issues/1254 Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/objtool/elf.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index d84c28eac262d..0ba5bb51bd93c 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -226,8 +226,11 @@ static int read_symbols(struct elf *elf)

symtab = find_section_by_name(elf, ".symtab"); if (!symtab) { - WARN("missing symbol table"); - return -1; + /* + * A missing symbol table is actually possible if it's an empty + * .o file. This can happen for thunk_64.o. + */ + return 0; }

symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize;

From: Pho Tran Pho.Tran@silabs.com

commit 3c4f6ecd93442f4376a58b38bb40ee0b8c46e0e6 upstream.

Information pid/vid of WSDA-200-USB, Lord corporation company: vid: 199b pid: ba30

Signed-off-by: Pho Tran pho.tran@silabs.com [ johan: amend comment with product name ] Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -198,6 +198,7 @@ static const struct usb_device_id id_tab { USB_DEVICE(0x1901, 0x0194) }, /* GE Healthcare Remote Alarm Box */ { USB_DEVICE(0x1901, 0x0195) }, /* GE B850/B650/B450 CP2104 DP UART interface */ { USB_DEVICE(0x1901, 0x0196) }, /* GE B850 CP2105 DP UART interface */ + { USB_DEVICE(0x199B, 0xBA30) }, /* LORD WSDA-200-USB */ { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */

From: Christoph Schemmel christoph.schemmel@gmail.com

commit e478d6029dca9d8462f426aee0d32896ef64f10f upstream.

Adding support for Cinterion device MV31 for enumeration with PID 0x00B3 and 0x00B7.

usb-devices output for 0x00B3 T: Bus=04 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 6 Spd=5000 MxCh= 0 D: Ver= 3.20 Cls=ef(misc ) Sub=02 Prot=01 MxPS= 9 #Cfgs= 1 P: Vendor=1e2d ProdID=00b3 Rev=04.14 S: Manufacturer=Cinterion S: Product=Cinterion PID 0x00B3 USB Mobile Broadband S: SerialNumber=b3246eed C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=896mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=cdc_wdm I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option

usb-devices output for 0x00B7 T: Bus=04 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 5 Spd=5000 MxCh= 0 D: Ver= 3.20 Cls=ef(misc ) Sub=02 Prot=01 MxPS= 9 #Cfgs= 1 P: Vendor=1e2d ProdID=00b7 Rev=04.14 S: Manufacturer=Cinterion S: Product=Cinterion PID 0x00B3 USB Mobile Broadband S: SerialNumber=b3246eed C: #Ifs= 4 Cfg#= 1 Atr=a0 MxPwr=896mA I: If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#=0x1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option

Signed-off-by: Christoph Schemmel christoph.schemmel@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/serial/option.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -425,6 +425,8 @@ static void option_instat_callback(struc #define CINTERION_PRODUCT_AHXX_2RMNET 0x0084 #define CINTERION_PRODUCT_AHXX_AUDIO 0x0085 #define CINTERION_PRODUCT_CLS8 0x00b0 +#define CINTERION_PRODUCT_MV31_MBIM 0x00b3 +#define CINTERION_PRODUCT_MV31_RMNET 0x00b7

/* Olivetti products */ #define OLIVETTI_VENDOR_ID 0x0b3c @@ -1896,6 +1898,10 @@ static const struct usb_device_id option { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) }, { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, /* HC28 enumerates with Siemens or Cinterion VID depending on FW revision */ { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV31_MBIM, 0xff), + .driver_info = RSVD(3)}, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV31_RMNET, 0xff), + .driver_info = RSVD(0)}, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100), .driver_info = RSVD(4) }, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120),

From: Xie He xie.he.0141@gmail.com

[ Upstream commit 88c7a9fd9bdd3e453f04018920964c6f848a591a ]

When sending a packet, we will prepend it with an LAPB header. This modifies the shared parts of a cloned skb, so we should copy the skb rather than just clone it, before we prepend the header.

In "Documentation/networking/driver.rst" (the 2nd point), it states that drivers shouldn't modify the shared parts of a cloned skb when transmitting.

The "dev_queue_xmit_nit" function in "net/core/dev.c", which is called when an skb is being sent, clones the skb and sents the clone to AF_PACKET sockets. Because the LAPB drivers first remove a 1-byte pseudo-header before handing over the skb to us, if we don't copy the skb before prepending the LAPB header, the first byte of the packets received on AF_PACKET sockets can be corrupted.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Xie He xie.he.0141@gmail.com Acked-by: Martin Schiller ms@dev.tdt.de Link: https://lore.kernel.org/r/20210201055706.415842-1-xie.he.0141@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/lapb/lapb_out.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c index 482c94d9d958a..d1c7dcc234486 100644 --- a/net/lapb/lapb_out.c +++ b/net/lapb/lapb_out.c @@ -87,7 +87,8 @@ void lapb_kick(struct lapb_cb *lapb) skb = skb_dequeue(&lapb->write_queue);

do { - if ((skbn = skb_clone(skb, GFP_ATOMIC)) == NULL) { + skbn = skb_copy(skb, GFP_ATOMIC); + if (!skbn) { skb_queue_head(&lapb->write_queue, skb); break; }

From: Dan Carpenter dan.carpenter@oracle.com

commit 3e1f4a2e1184ae6ad7f4caf682ced9554141a0f4 upstream.

This code should return -ENOMEM if the allocation fails but it currently returns success.

Fixes: 9b95236eebdb ("usb: gadget: ether: allocate and init otg descriptor by otg capabilities") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Link: https://lore.kernel.org/r/YBKE9rqVuJEOUWpW@mwanda Cc: stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/gadget/legacy/ether.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/usb/gadget/legacy/ether.c +++ b/drivers/usb/gadget/legacy/ether.c @@ -407,8 +407,10 @@ static int eth_bind(struct usb_composite struct usb_descriptor_header *usb_desc;

usb_desc = usb_otg_descriptor_alloc(gadget); - if (!usb_desc) + if (!usb_desc) { + status = -ENOMEM; goto fail1; + } usb_otg_descriptor_init(gadget, usb_desc); otg_desc[0] = usb_desc; otg_desc[1] = NULL;

From: Heiko Stuebner heiko.stuebner@theobroma-systems.com

commit f670e9f9c8cac716c3506c6bac9e997b27ad441a upstream.

dwc2_hsotg_process_req_status uses ep_from_windex() to retrieve the endpoint for the index provided in the wIndex request param.

In a test-case with a rndis gadget running and sending a malformed packet to it like: dev.ctrl_transfer( 0x82, # bmRequestType 0x00, # bRequest 0x0000, # wValue 0x0001, # wIndex 0x00 # wLength ) it is possible to cause a crash:

[ 217.533022] dwc2 ff300000.usb: dwc2_hsotg_process_req_status: USB_REQ_GET_STATUS [ 217.559003] Unable to handle kernel read from unreadable memory at virtual address 0000000000000088 ... [ 218.313189] Call trace: [ 218.330217] ep_from_windex+0x3c/0x54 [ 218.348565] usb_gadget_giveback_request+0x10/0x20 [ 218.368056] dwc2_hsotg_complete_request+0x144/0x184

This happens because ep_from_windex wants to compare the endpoint direction even if index_to_ep() didn't return an endpoint due to the direction not matching.

The fix is easy insofar that the actual direction check is already happening when calling index_to_ep() which will return NULL if there is no endpoint for the targeted direction, so the offending check can go away completely.

Fixes: c6f5c050e2a7 ("usb: dwc2: gadget: add bi-directional endpoint support") Cc: stable@vger.kernel.org Reported-by: Gerhard Klostermeier gerhard.klostermeier@syss.de Signed-off-by: Heiko Stuebner heiko.stuebner@theobroma-systems.com Link: https://lore.kernel.org/r/20210127103919.58215-1-heiko@sntech.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/dwc2/gadget.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-)

--- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -942,7 +942,6 @@ static void dwc2_hsotg_complete_oursetup static struct dwc2_hsotg_ep *ep_from_windex(struct dwc2_hsotg *hsotg, u32 windex) { - struct dwc2_hsotg_ep *ep; int dir = (windex & USB_DIR_IN) ? 1 : 0; int idx = windex & 0x7F;

@@ -952,12 +951,7 @@ static struct dwc2_hsotg_ep *ep_from_win if (idx > hsotg->num_of_eps) return NULL;

- ep = index_to_ep(hsotg, idx, dir); - - if (idx && ep->dir_in != dir) - return NULL; - - return ep; + return index_to_ep(hsotg, idx, dir); }

/**

From: Wang ShaoBo bobo.shaobowang@huawei.com

commit 0188b87899ffc4a1d36a0badbe77d56c92fd91dc upstream.

Our system encountered a re-init error when re-registering same kretprobe, where the kretprobe_instance in rp->free_instances is illegally accessed after re-init.

Implementation to avoid re-registration has been introduced for kprobe before, but lags for register_kretprobe(). We must check if kprobe has been re-registered before re-initializing kretprobe, otherwise it will destroy the data struct of kretprobe registered, which can lead to memory leak, system crash, also some unexpected behaviors.

We use check_kprobe_rereg() to check if kprobe has been re-registered before running register_kretprobe()'s body, for giving a warning message and terminate registration process.

Link: https://lkml.kernel.org/r/20210128124427.2031088-1-bobo.shaobowang@huawei.co...

Cc: stable@vger.kernel.org Fixes: 1f0ab40976460 ("kprobes: Prevent re-registration of the same kprobe") [ The above commit should have been done for kretprobes too ] Acked-by: Naveen N. Rao naveen.n.rao@linux.vnet.ibm.com Acked-by: Ananth N Mavinakayanahalli ananth@linux.ibm.com Acked-by: Masami Hiramatsu mhiramat@kernel.org Signed-off-by: Wang ShaoBo bobo.shaobowang@huawei.com Signed-off-by: Cheng Jian cj.chengjian@huawei.com Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/kprobes.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1884,6 +1884,10 @@ int register_kretprobe(struct kretprobe int i; void *addr;

+ /* If only rp->kp.addr is specified, check reregistering kprobes */ + if (rp->kp.addr && check_kprobe_rereg(&rp->kp)) + return -EINVAL; + if (kretprobe_blacklist_size) { addr = kprobe_addr(&rp->kp); if (IS_ERR(addr))

From: Aurelien Aptel aaptel@suse.com

commit 21b200d091826a83aafc95d847139b2b0582f6d1 upstream.

Assuming - //HOST/a is mounted on /mnt - //HOST/b is mounted on /mnt/b

On a slow connection, running 'df' and killing it while it's processing /mnt/b can make cifs_get_inode_info() returns -ERESTARTSYS.

This triggers the following chain of events: => the dentry revalidation fail => dentry is put and released => superblock associated with the dentry is put => /mnt/b is unmounted

This patch makes cifs_d_revalidate() return the error instead of 0 (invalid) when cifs_revalidate_dentry() fails, except for ENOENT (file deleted) and ESTALE (file recreated).

Signed-off-by: Aurelien Aptel aaptel@suse.com Suggested-by: Shyam Prasad N nspmangalore@gmail.com Reviewed-by: Shyam Prasad N nspmangalore@gmail.com CC: stable@vger.kernel.org Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/dir.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-)

--- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -830,6 +830,7 @@ static int cifs_d_revalidate(struct dentry *direntry, unsigned int flags) { struct inode *inode; + int rc;

if (flags & LOOKUP_RCU) return -ECHILD; @@ -839,8 +840,25 @@ cifs_d_revalidate(struct dentry *direntr if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode))) CIFS_I(inode)->time = 0; /* force reval */

- if (cifs_revalidate_dentry(direntry)) - return 0; + rc = cifs_revalidate_dentry(direntry); + if (rc) { + cifs_dbg(FYI, "cifs_revalidate_dentry failed with rc=%d", rc); + switch (rc) { + case -ENOENT: + case -ESTALE: + /* + * Those errors mean the dentry is invalid + * (file was deleted or recreated) + */ + return 0; + default: + /* + * Otherwise some unexpected error happened + * report it as-is to VFS layer + */ + return rc; + } + } else { /* * If the inode wasn't known to be a dfs entry when

From: Russell King rmk+kernel@armlinux.org.uk

commit 39d3454c3513840eb123b3913fda6903e45ce671 upstream.

Building with gcc 4.9.2 reveals a latent bug in the PCI accessors for Footbridge platforms, which causes a fatal alignment fault while accessing IO memory. Fix this by making the assembly volatile.

Cc: stable@vger.kernel.org Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/mach-footbridge/dc21285.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

--- a/arch/arm/mach-footbridge/dc21285.c +++ b/arch/arm/mach-footbridge/dc21285.c @@ -69,15 +69,15 @@ dc21285_read_config(struct pci_bus *bus, if (addr) switch (size) { case 1: - asm("ldrb %0, [%1, %2]" + asm volatile("ldrb %0, [%1, %2]" : "=r" (v) : "r" (addr), "r" (where) : "cc"); break; case 2: - asm("ldrh %0, [%1, %2]" + asm volatile("ldrh %0, [%1, %2]" : "=r" (v) : "r" (addr), "r" (where) : "cc"); break; case 4: - asm("ldr %0, [%1, %2]" + asm volatile("ldr %0, [%1, %2]" : "=r" (v) : "r" (addr), "r" (where) : "cc"); break; } @@ -103,17 +103,17 @@ dc21285_write_config(struct pci_bus *bus if (addr) switch (size) { case 1: - asm("strb %0, [%1, %2]" + asm volatile("strb %0, [%1, %2]" : : "r" (value), "r" (addr), "r" (where) : "cc"); break; case 2: - asm("strh %0, [%1, %2]" + asm volatile("strh %0, [%1, %2]" : : "r" (value), "r" (addr), "r" (where) : "cc"); break; case 4: - asm("str %0, [%1, %2]" + asm volatile("str %0, [%1, %2]" : : "r" (value), "r" (addr), "r" (where) : "cc"); break;

From: Muchun Song songmuchun@bytedance.com

commit 0eb2df2b5629794020f75e94655e1994af63f0d4 upstream.

There is a race between isolate_huge_page() and __free_huge_page().

CPU0: CPU1:

if (PageHuge(page)) put_page(page) __free_huge_page(page) spin_lock(&hugetlb_lock) update_and_free_page(page) set_compound_page_dtor(page, NULL_COMPOUND_DTOR) spin_unlock(&hugetlb_lock) isolate_huge_page(page) // trigger BUG_ON VM_BUG_ON_PAGE(!PageHead(page), page) spin_lock(&hugetlb_lock) page_huge_active(page) // trigger BUG_ON VM_BUG_ON_PAGE(!PageHuge(page), page) spin_unlock(&hugetlb_lock)

When we isolate a HugeTLB page on CPU0. Meanwhile, we free it to the buddy allocator on CPU1. Then, we can trigger a BUG_ON on CPU0, because it is already freed to the buddy allocator.

Link: https://lkml.kernel.org/r/20210115124942.46403-5-songmuchun@bytedance.com Fixes: c8721bbbdd36 ("mm: memory-hotplug: enable memory hotplug to handle hugepage") Signed-off-by: Muchun Song songmuchun@bytedance.com Reviewed-by: Mike Kravetz mike.kravetz@oracle.com Acked-by: Michal Hocko mhocko@suse.com Reviewed-by: Oscar Salvador osalvador@suse.de Cc: David Hildenbrand david@redhat.com Cc: Yang Shi shy828301@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/hugetlb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4657,9 +4657,9 @@ bool isolate_huge_page(struct page *page { bool ret = true;

- VM_BUG_ON_PAGE(!PageHead(page), page); spin_lock(&hugetlb_lock); - if (!page_huge_active(page) || !get_page_unless_zero(page)) { + if (!PageHeadHuge(page) || !page_huge_active(page) || + !get_page_unless_zero(page)) { ret = false; goto unlock; }

From: Hugh Dickins hughd@google.com

commit 1c2f67308af4c102b4e1e6cd6f69819ae59408e0 upstream.

Sergey reported deadlock between kswapd correctly doing its usual lock_page(page) followed by down_read(page->mapping->i_mmap_rwsem), and madvise(MADV_REMOVE) on an madvise(MADV_HUGEPAGE) area doing down_write(page->mapping->i_mmap_rwsem) followed by lock_page(page).

This happened when shmem_fallocate(punch hole)'s unmap_mapping_range() reaches zap_pmd_range()'s call to __split_huge_pmd(). The same deadlock could occur when partially truncating a mapped huge tmpfs file, or using fallocate(FALLOC_FL_PUNCH_HOLE) on it.

__split_huge_pmd()'s page lock was added in 5.8, to make sure that any concurrent use of reuse_swap_page() (holding page lock) could not catch the anon THP's mapcounts and swapcounts while they were being split.

Fortunately, reuse_swap_page() is never applied to a shmem or file THP (not even by khugepaged, which checks PageSwapCache before calling), and anonymous THPs are never created in shmem or file areas: so that __split_huge_pmd()'s page lock can only be necessary for anonymous THPs, on which there is no risk of deadlock with i_mmap_rwsem.

Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2101161409470.2022@eggly.anvils Fixes: c444eb564fb1 ("mm: thp: make the THP mapcount atomic against __split_huge_pmd_locked()") Signed-off-by: Hugh Dickins hughd@google.com Reported-by: Sergey Senozhatsky sergey.senozhatsky.work@gmail.com Reviewed-by: Andrea Arcangeli aarcange@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/huge_memory.c | 37 +++++++++++++++++++++++-------------- 1 file changed, 23 insertions(+), 14 deletions(-)

--- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1753,7 +1753,7 @@ void __split_huge_pmd(struct vm_area_str spinlock_t *ptl; struct mm_struct *mm = vma->vm_mm; unsigned long haddr = address & HPAGE_PMD_MASK; - bool was_locked = false; + bool do_unlock_page = false; pmd_t _pmd;

mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); @@ -1766,7 +1766,6 @@ void __split_huge_pmd(struct vm_area_str VM_BUG_ON(freeze && !page); if (page) { VM_WARN_ON_ONCE(!PageLocked(page)); - was_locked = true; if (page != pmd_page(*pmd)) goto out; } @@ -1775,19 +1774,29 @@ repeat: if (pmd_trans_huge(*pmd)) { if (!page) { page = pmd_page(*pmd); - if (unlikely(!trylock_page(page))) { - get_page(page); - _pmd = *pmd; - spin_unlock(ptl); - lock_page(page); - spin_lock(ptl); - if (unlikely(!pmd_same(*pmd, _pmd))) { - unlock_page(page); + /* + * An anonymous page must be locked, to ensure that a + * concurrent reuse_swap_page() sees stable mapcount; + * but reuse_swap_page() is not used on shmem or file, + * and page lock must not be taken when zap_pmd_range() + * calls __split_huge_pmd() while i_mmap_lock is held. + */ + if (PageAnon(page)) { + if (unlikely(!trylock_page(page))) { + get_page(page); + _pmd = *pmd; + spin_unlock(ptl); + lock_page(page); + spin_lock(ptl); + if (unlikely(!pmd_same(*pmd, _pmd))) { + unlock_page(page); + put_page(page); + page = NULL; + goto repeat; + } put_page(page); - page = NULL; - goto repeat; } - put_page(page); + do_unlock_page = true; } } if (PageMlocked(page)) @@ -1797,7 +1806,7 @@ repeat: __split_huge_pmd_locked(vma, pmd, haddr, freeze); out: spin_unlock(ptl); - if (!was_locked && page) + if (do_unlock_page) unlock_page(page); mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE); }

From: Dave Hansen dave.hansen@linux.intel.com

commit 25a068b8e9a4eb193d755d58efcb3c98928636e0 upstream.

Jan Kiszka reported that the x2apic_wrmsr_fence() function uses a plain MFENCE while the Intel SDM (10.12.3 MSR Access in x2APIC Mode) calls for MFENCE; LFENCE.

Short summary: we have special MSRs that have weaker ordering than all the rest. Add fencing consistent with current SDM recommendations.

This is not known to cause any issues in practice, only in theory.

Longer story below:

The reason the kernel uses a different semantic is that the SDM changed (roughly in late 2017). The SDM changed because folks at Intel were auditing all of the recommended fences in the SDM and realized that the x2apic fences were insufficient.

Why was the pain MFENCE judged insufficient?

WRMSR itself is normally a serializing instruction. No fences are needed because the instruction itself serializes everything.

But, there are explicit exceptions for this serializing behavior written into the WRMSR instruction documentation for two classes of MSRs: IA32_TSC_DEADLINE and the X2APIC MSRs.

Back to x2apic: WRMSR is *not* serializing in this specific case. But why is MFENCE insufficient? MFENCE makes writes visible, but only affects load/store instructions. WRMSR is unfortunately not a load/store instruction and is unaffected by MFENCE. This means that a non-serializing WRMSR could be reordered by the CPU to execute before the writes made visible by the MFENCE have even occurred in the first place.

This means that an x2apic IPI could theoretically be triggered before there is any (visible) data to process.

Does this affect anything in practice? I honestly don't know. It seems quite possible that by the time an interrupt gets to consume the (not yet) MFENCE'd data, it has become visible, mostly by accident.

To be safe, add the SDM-recommended fences for all x2apic WRMSRs.

This also leaves open the question of the _other_ weakly-ordered WRMSR: MSR_IA32_TSC_DEADLINE. While it has the same ordering architecture as the x2APIC MSRs, it seems substantially less likely to be a problem in practice. While writes to the in-memory Local Vector Table (LVT) might theoretically be reordered with respect to a weakly-ordered WRMSR like TSC_DEADLINE, the SDM has this to say:

In x2APIC mode, the WRMSR instruction is used to write to the LVT entry. The processor ensures the ordering of this write and any subsequent WRMSR to the deadline; no fencing is required.

But, that might still leave xAPIC exposed. The safest thing to do for now is to add the extra, recommended LFENCE.

[ bp: Massage commit message, fix typos, drop accidentally added newline to tools/arch/x86/include/asm/barrier.h. ]

Reported-by: Jan Kiszka jan.kiszka@siemens.com Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200305174708.F77040DD@viggo.jf.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/apic.h | 10 ---------- arch/x86/include/asm/barrier.h | 18 ++++++++++++++++++ arch/x86/kernel/apic/apic.c | 4 ++++ arch/x86/kernel/apic/x2apic_cluster.c | 6 ++++-- arch/x86/kernel/apic/x2apic_phys.c | 6 ++++-- 5 files changed, 30 insertions(+), 14 deletions(-)

--- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -176,16 +176,6 @@ static inline void lapic_update_tsc_freq #endif /* !CONFIG_X86_LOCAL_APIC */

#ifdef CONFIG_X86_X2APIC -/* - * Make previous memory operations globally visible before - * sending the IPI through x2apic wrmsr. We need a serializing instruction or - * mfence for this. - */ -static inline void x2apic_wrmsr_fence(void) -{ - asm volatile("mfence" : : : "memory"); -} - static inline void native_apic_msr_write(u32 reg, u32 v) { if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR || --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -110,4 +110,22 @@ do { \

#include <asm-generic/barrier.h>

+/* + * Make previous memory operations globally visible before + * a WRMSR. + * + * MFENCE makes writes visible, but only affects load/store + * instructions. WRMSR is unfortunately not a load/store + * instruction and is unaffected by MFENCE. The LFENCE ensures + * that the WRMSR is not reordered. + * + * Most WRMSRs are full serializing instructions themselves and + * do not require this barrier. This is only required for the + * IA32_TSC_DEADLINE and X2APIC MSRs. + */ +static inline void weak_wrmsr_fence(void) +{ + asm volatile("mfence; lfence" : : : "memory"); +} + #endif /* _ASM_X86_BARRIER_H */ --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -42,6 +42,7 @@ #include <asm/x86_init.h> #include <asm/pgalloc.h> #include <linux/atomic.h> +#include <asm/barrier.h> #include <asm/mpspec.h> #include <asm/i8259.h> #include <asm/proto.h> @@ -476,6 +477,9 @@ static int lapic_next_deadline(unsigned { u64 tsc;

+ /* This MSR is special and need a special fence: */ + weak_wrmsr_fence(); + tsc = rdtsc(); wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); return 0; --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -27,7 +27,8 @@ static void x2apic_send_IPI(int cpu, int { u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu);

- x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); }

@@ -40,7 +41,8 @@ __x2apic_send_IPI_mask(const struct cpum unsigned long flags; u32 dest;

- x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence();

local_irq_save(flags);

--- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -40,7 +40,8 @@ static void x2apic_send_IPI(int cpu, int { u32 dest = per_cpu(x86_cpu_to_apicid, cpu);

- x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); __x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL); }

@@ -51,7 +52,8 @@ __x2apic_send_IPI_mask(const struct cpum unsigned long this_cpu; unsigned long flags;

- x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence();

local_irq_save(flags);

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

commit 81b704d3e4674e09781d331df73d76675d5ad8cb upstream.

Calling acpi_thermal_check() from acpi_thermal_notify() directly is problematic if _TMP triggers Notify () on the thermal zone for which it has been evaluated (which happens on some systems), because it causes a new acpi_thermal_notify() invocation to be queued up every time and if that takes place too often, an indefinite number of pending work items may accumulate in kacpi_notify_wq over time.

Besides, it is not really useful to queue up a new invocation of acpi_thermal_check() if one of them is pending already.

For these reasons, rework acpi_thermal_notify() to queue up a thermal check instead of calling acpi_thermal_check() directly and only allow one thermal check to be pending at a time. Moreover, only allow one acpi_thermal_check_fn() instance at a time to run thermal_zone_device_update() for one thermal zone and make it return early if it sees other instances running for the same thermal zone.

While at it, fold acpi_thermal_check() into acpi_thermal_check_fn(), as it is only called from there after the other changes made here.

[This issue appears to have been exposed by commit 6d25be5782e4 ("sched/core, workqueues: Distangle worker accounting from rq lock"), but it is unclear why it was not visible earlier.]

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208877 Reported-by: Stephen Berman stephen.berman@gmx.net Diagnosed-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Tested-by: Stephen Berman stephen.berman@gmx.net Cc: All applicable stable@vger.kernel.org [bigeasy: Backported to v4.9.y, use atomic_t instead of refcount_t] Signed-off-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/acpi/thermal.c | 55 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 38 insertions(+), 17 deletions(-)

--- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -188,6 +188,8 @@ struct acpi_thermal { int tz_enabled; int kelvin_offset; struct work_struct thermal_check_work; + struct mutex thermal_check_lock; + atomic_t thermal_check_count; };

/* -------------------------------------------------------------------------- @@ -513,17 +515,6 @@ static int acpi_thermal_get_trip_points( return 0; }

-static void acpi_thermal_check(void *data) -{ - struct acpi_thermal *tz = data; - - if (!tz->tz_enabled) - return; - - thermal_zone_device_update(tz->thermal_zone, - THERMAL_EVENT_UNSPECIFIED); -} - /* sys I/F for generic thermal sysfs support */

static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp) @@ -557,6 +548,8 @@ static int thermal_get_mode(struct therm return 0; }

+static void acpi_thermal_check_fn(struct work_struct *work); + static int thermal_set_mode(struct thermal_zone_device *thermal, enum thermal_device_mode mode) { @@ -582,7 +575,7 @@ static int thermal_set_mode(struct therm ACPI_DEBUG_PRINT((ACPI_DB_INFO, "%s kernel ACPI thermal control\n", tz->tz_enabled ? "Enable" : "Disable")); - acpi_thermal_check(tz); + acpi_thermal_check_fn(&tz->thermal_check_work); } return 0; } @@ -951,6 +944,12 @@ static void acpi_thermal_unregister_ther Driver Interface -------------------------------------------------------------------------- */

+static void acpi_queue_thermal_check(struct acpi_thermal *tz) +{ + if (!work_pending(&tz->thermal_check_work)) + queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work); +} + static void acpi_thermal_notify(struct acpi_device *device, u32 event) { struct acpi_thermal *tz = acpi_driver_data(device); @@ -961,17 +960,17 @@ static void acpi_thermal_notify(struct a

switch (event) { case ACPI_THERMAL_NOTIFY_TEMPERATURE: - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); break; case ACPI_THERMAL_NOTIFY_THRESHOLDS: acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_THRESHOLDS); - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); acpi_bus_generate_netlink_event(device->pnp.device_class, dev_name(&device->dev), event, 0); break; case ACPI_THERMAL_NOTIFY_DEVICES: acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_DEVICES); - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); acpi_bus_generate_netlink_event(device->pnp.device_class, dev_name(&device->dev), event, 0); break; @@ -1071,7 +1070,27 @@ static void acpi_thermal_check_fn(struct { struct acpi_thermal *tz = container_of(work, struct acpi_thermal, thermal_check_work); - acpi_thermal_check(tz); + + if (!tz->tz_enabled) + return; + /* + * In general, it is not sufficient to check the pending bit, because + * subsequent instances of this function may be queued after one of them + * has started running (e.g. if _TMP sleeps). Avoid bailing out if just + * one of them is running, though, because it may have done the actual + * check some time ago, so allow at least one of them to block on the + * mutex while another one is running the update. + */ + if (!atomic_add_unless(&tz->thermal_check_count, -1, 1)) + return; + + mutex_lock(&tz->thermal_check_lock); + + thermal_zone_device_update(tz->thermal_zone, THERMAL_EVENT_UNSPECIFIED); + + atomic_inc(&tz->thermal_check_count); + + mutex_unlock(&tz->thermal_check_lock); }

static int acpi_thermal_add(struct acpi_device *device) @@ -1103,6 +1122,8 @@ static int acpi_thermal_add(struct acpi_ if (result) goto free_memory;

+ atomic_set(&tz->thermal_check_count, 3); + mutex_init(&tz->thermal_check_lock); INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn);

pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device), @@ -1168,7 +1189,7 @@ static int acpi_thermal_resume(struct de tz->state.active |= tz->trips.active[i].flags.enabled; }

- queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work); + acpi_queue_thermal_check(tz);

return AE_OK; }

From: Shih-Yuan Lee (FourDollars) sylee@canonical.com

commit b4576de87243c32fab50dda9f8eba1e3cf13a7e2 upstream.

The PIN number for Dell headset mode of ALC3271 is wrong.

Fixes: fcc6c877a01f ("ALSA: hda/realtek - Support Dell headset mode for ALC3271") Signed-off-by: Shih-Yuan Lee (FourDollars) sylee@canonical.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6284,7 +6284,7 @@ static const struct snd_hda_pin_quirk al SND_HDA_PIN_QUIRK(0x10ec0299, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, {0x12, 0xb7a60130}, - {0x13, 0xb8a60140}, + {0x13, 0xb8a61140}, {0x17, 0x90170110}), {} };