From c74aef2d06a9f59cece89093eecc552933cba72a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 17:48:06 +0200 Subject: futex: Fix pi_state->owner serialization There was a reported suspicion about a race between exit_pi_state_list() and put_pi_state(). The same report mentioned the comment with put_pi_state() said it should be called with hb->lock held, and it no longer is in all places. As it turns out, the pi_state->owner serialization is indeed broken. As per the new rules: 734009e96d19 ("futex: Change locking rules") pi_state->owner should be serialized by pi_state->pi_mutex.wait_lock. For the sites setting pi_state->owner we already hold wait_lock (where required) but exit_pi_state_list() and put_pi_state() were not and raced on clearing it. Fixes: 734009e96d19 ("futex: Change locking rules") Reported-by: Gratian Crisan Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: dvhart@infradead.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20170922154806.jd3ffltfk24m4o4y@hirez.programming.kicks-ass.net --- kernel/futex.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) (limited to 'kernel/futex.c') diff --git a/kernel/futex.c b/kernel/futex.c index 3d38eaf05492..0518a0bfc746 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -821,8 +821,6 @@ static void get_pi_state(struct futex_pi_state *pi_state) /* * Drops a reference to the pi_state object and frees or caches it * when the last reference is gone. - * - * Must be called with the hb lock held. */ static void put_pi_state(struct futex_pi_state *pi_state) { @@ -837,16 +835,22 @@ static void put_pi_state(struct futex_pi_state *pi_state) * 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); + struct task_struct *owner; - rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + owner = pi_state->owner; + if (owner) { + raw_spin_lock(&owner->pi_lock); + list_del_init(&pi_state->list); + raw_spin_unlock(&owner->pi_lock); + } + rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); } - if (current->pi_state_cache) + if (current->pi_state_cache) { kfree(pi_state); - else { + } else { /* * pi_state->list is already empty. * clear pi_state->owner. @@ -907,13 +911,14 @@ void exit_pi_state_list(struct task_struct *curr) raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); - - raw_spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); continue; } @@ -922,9 +927,10 @@ void exit_pi_state_list(struct task_struct *curr) WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; - raw_spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock(&curr->pi_lock); get_pi_state(pi_state); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); @@ -1208,6 +1214,10 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &p->pi_state_list); + /* + * Assignment without holding pi_state->pi_mutex.wait_lock is safe + * because there is no concurrency as the object is not published yet. + */ pi_state->owner = p; raw_spin_unlock_irq(&p->pi_lock); @@ -2878,6 +2888,7 @@ retry: raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + /* drops pi_state->pi_mutex.wait_lock */ ret = wake_futex_pi(uaddr, uval, pi_state); put_pi_state(pi_state); -- cgit v1.3-8-gc7d7 From 153fbd1226fb30b8630802aa5047b8af5ef53c9f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 31 Oct 2017 11:18:53 +0100 Subject: futex: Fix more put_pi_state() vs. exit_pi_state_list() races Dmitry (through syzbot) reported being able to trigger the WARN in get_pi_state() and a use-after-free on: raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); Both are due to this race: exit_pi_state_list() put_pi_state() lock(&curr->pi_lock) while() { pi_state = list_first_entry(head); hb = hash_futex(&pi_state->key); unlock(&curr->pi_lock); dec_and_test(&pi_state->refcount); lock(&hb->lock) lock(&pi_state->pi_mutex.wait_lock) // uaf if pi_state free'd lock(&curr->pi_lock); .... unlock(&curr->pi_lock); get_pi_state(); // WARN; refcount==0 The problem is we take the reference count too late, and don't allow it being 0. Fix it by using inc_not_zero() and simply retrying the loop when we fail to get a refcount. In that case put_pi_state() should remove the entry from the list. Reported-by: Dmitry Vyukov Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Cc: Gratian Crisan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: dvhart@infradead.org Cc: syzbot Cc: syzkaller-bugs@googlegroups.com Cc: Fixes: c74aef2d06a9 ("futex: Fix pi_state->owner serialization") Link: http://lkml.kernel.org/r/20171031101853.xpfh72y643kdfhjs@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/futex.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) (limited to 'kernel/futex.c') diff --git a/kernel/futex.c b/kernel/futex.c index 0518a0bfc746..ca5bb9cba5cf 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -903,11 +903,27 @@ void exit_pi_state_list(struct task_struct *curr) */ raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { - next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; hb = hash_futex(&key); + + /* + * We can race against put_pi_state() removing itself from the + * list (a waiter going away). put_pi_state() will first + * decrement the reference count and then modify the list, so + * its possible to see the list entry but fail this reference + * acquire. + * + * In that case; drop the locks to let put_pi_state() make + * progress and retry the loop. + */ + if (!atomic_inc_not_zero(&pi_state->refcount)) { + raw_spin_unlock_irq(&curr->pi_lock); + cpu_relax(); + raw_spin_lock_irq(&curr->pi_lock); + continue; + } raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); @@ -918,8 +934,10 @@ void exit_pi_state_list(struct task_struct *curr) * task still owns the PI-state: */ if (head->next != next) { + /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + put_pi_state(pi_state); continue; } @@ -927,9 +945,8 @@ void exit_pi_state_list(struct task_struct *curr) WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; - raw_spin_unlock(&curr->pi_lock); - get_pi_state(pi_state); + raw_spin_unlock(&curr->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); -- cgit v1.3-8-gc7d7 From e78c38f6bdd900b2ad9ac9df8eff58b745dc5b3c Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 23 Oct 2017 13:41:51 +0200 Subject: futex: futex_wake_op, do not fail on invalid op In commit 30d6e0a4190d ("futex: Remove duplicated code and fix undefined behaviour"), I let FUTEX_WAKE_OP to fail on invalid op. Namely when op should be considered as shift and the shift is out of range (< 0 or > 31). But strace's test suite does this madness: futex(0x7fabd78bcffc, 0x5, 0xfacefeed, 0xb, 0x7fabd78bcffc, 0xa0caffee); futex(0x7fabd78bcffc, 0x5, 0xfacefeed, 0xb, 0x7fabd78bcffc, 0xbadfaced); futex(0x7fabd78bcffc, 0x5, 0xfacefeed, 0xb, 0x7fabd78bcffc, 0xffffffff); When I pick the first 0xa0caffee, it decodes as: 0x80000000 & 0xa0caffee: oparg is shift 0x70000000 & 0xa0caffee: op is FUTEX_OP_OR 0x0f000000 & 0xa0caffee: cmp is FUTEX_OP_CMP_EQ 0x00fff000 & 0xa0caffee: oparg is sign-extended 0xcaf = -849 0x00000fff & 0xa0caffee: cmparg is sign-extended 0xfee = -18 That means the op tries to do this: (futex |= (1 << (-849))) == -18 which is completely bogus. The new check of op in the code is: if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { if (oparg < 0 || oparg > 31) return -EINVAL; oparg = 1 << oparg; } which results obviously in the "Invalid argument" errno: FAIL: futex =========== futex(0x7fabd78bcffc, 0x5, 0xfacefeed, 0xb, 0x7fabd78bcffc, 0xa0caffee) = -1: Invalid argument futex.test: failed test: ../futex failed with code 1 So let us soften the failure to print only a (ratelimited) message, crop the value and continue as if it were right. When userspace keeps up, we can switch this to return -EINVAL again. [v2] Do not return 0 immediatelly, proceed with the cropped value. Fixes: 30d6e0a4190d ("futex: Remove duplicated code and fix undefined behaviour") Signed-off-by: Jiri Slaby Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Darren Hart Signed-off-by: Linus Torvalds --- kernel/futex.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'kernel/futex.c') diff --git a/kernel/futex.c b/kernel/futex.c index 0518a0bfc746..0d638f008bb1 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1570,8 +1570,16 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) int oldval, ret; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { - if (oparg < 0 || oparg > 31) - return -EINVAL; + if (oparg < 0 || oparg > 31) { + char comm[sizeof(current->comm)]; + /* + * kill this print and return -EINVAL when userspace + * is sane again + */ + pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n", + get_task_comm(comm, current), oparg); + oparg &= 31; + } oparg = 1 << oparg; } -- cgit v1.3-8-gc7d7