Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Minor overlapping changes in the btusb and ixgbe drivers.

Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/bpf/verifier.c

@@ -1772,16 +1772,21 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 		bitmap_from_u64(mask, stack_mask);
 		for_each_set_bit(i, mask, 64) {
 			if (i >= func->allocated_stack / BPF_REG_SIZE) {
-				/* This can happen if backtracking
-				 * is propagating stack precision where
-				 * caller has larger stack frame
-				 * than callee, but backtrack_insn() should
-				 * have returned -ENOTSUPP.
+				/* the sequence of instructions:
+				 * 2: (bf) r3 = r10
+				 * 3: (7b) *(u64 *)(r3 -8) = r0
+				 * 4: (79) r4 = *(u64 *)(r10 -8)
+				 * doesn't contain jmps. It's backtracked
+				 * as a single block.
+				 * During backtracking insn 3 is not recognized as
+				 * stack access, so at the end of backtracking
+				 * stack slot fp-8 is still marked in stack_mask.
+				 * However the parent state may not have accessed
+				 * fp-8 and it's "unallocated" stack space.
+				 * In such case fallback to conservative.
 				 */
-				verbose(env, "BUG spi %d stack_size %d\n",
-					i, func->allocated_stack);
-				WARN_ONCE(1, "verifier backtracking bug");
-				return -EFAULT;
+				mark_all_scalars_precise(env, st);
+				return 0;
 			}
 
 			if (func->stack[i].slot_type[0] != STACK_SPILL) {

kernel/cgroup/cgroup.c

@@ -5255,8 +5255,16 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	 * if the parent has to be frozen, the child has too.
 	 */
 	cgrp->freezer.e_freeze = parent->freezer.e_freeze;
-	if (cgrp->freezer.e_freeze)
+	if (cgrp->freezer.e_freeze) {
+		/*
+		 * Set the CGRP_FREEZE flag, so when a process will be
+		 * attached to the child cgroup, it will become frozen.
+		 * At this point the new cgroup is unpopulated, so we can
+		 * consider it frozen immediately.
+		 */
+		set_bit(CGRP_FREEZE, &cgrp->flags);
 		set_bit(CGRP_FROZEN, &cgrp->flags);
+	}
 
 	spin_lock_irq(&css_set_lock);
 	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {

kernel/events/hw_breakpoint.c

@@ -413,7 +413,7 @@ static int hw_breakpoint_parse(struct perf_event *bp,
 
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
-	struct arch_hw_breakpoint hw;
+	struct arch_hw_breakpoint hw = { };
 	int err;
 
 	err = reserve_bp_slot(bp);
@@ -461,7 +461,7 @@ int
 modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
 			        bool check)
 {
-	struct arch_hw_breakpoint hw;
+	struct arch_hw_breakpoint hw = { };
 	int err;
 
 	err = hw_breakpoint_parse(bp, attr, &hw);

kernel/fork.c

@@ -2338,6 +2338,8 @@ struct mm_struct *copy_init_mm(void)
  *
  * It copies the process, and if successful kick-starts
  * it and waits for it to finish using the VM if required.
+ *
+ * args->exit_signal is expected to be checked for sanity by the caller.
  */
 long _do_fork(struct kernel_clone_args *args)
 {
@@ -2562,6 +2564,14 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 	if (copy_from_user(&args, uargs, size))
 		return -EFAULT;
 
+	/*
+	 * Verify that higher 32bits of exit_signal are unset and that
+	 * it is a valid signal
+	 */
+	if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) ||
+		     !valid_signal(args.exit_signal)))
+		return -EINVAL;
+
 	*kargs = (struct kernel_clone_args){
 		.flags		= args.flags,
 		.pidfd		= u64_to_user_ptr(args.pidfd),

kernel/irq/resend.c

@@ -36,6 +36,8 @@ static void resend_irqs(unsigned long arg)
 		irq = find_first_bit(irqs_resend, nr_irqs);
 		clear_bit(irq, irqs_resend);
 		desc = irq_to_desc(irq);
+		if (!desc)
+			continue;
 		local_irq_disable();
 		desc->handle_irq(desc);
 		local_irq_enable();

kernel/sched/core.c

@@ -5105,37 +5105,40 @@ out_unlock:
 	return retval;
 }
 
-static int sched_read_attr(struct sched_attr __user *uattr,
-			   struct sched_attr *attr,
-			   unsigned int usize)
+/*
+ * Copy the kernel size attribute structure (which might be larger
+ * than what user-space knows about) to user-space.
+ *
+ * Note that all cases are valid: user-space buffer can be larger or
+ * smaller than the kernel-space buffer. The usual case is that both
+ * have the same size.
+ */
+static int
+sched_attr_copy_to_user(struct sched_attr __user *uattr,
+			struct sched_attr *kattr,
+			unsigned int usize)
 {
-	int ret;
+	unsigned int ksize = sizeof(*kattr);
 
 	if (!access_ok(uattr, usize))
 		return -EFAULT;
 
 	/*
-	 * If we're handed a smaller struct than we know of,
-	 * ensure all the unknown bits are 0 - i.e. old
-	 * user-space does not get uncomplete information.
+	 * sched_getattr() ABI forwards and backwards compatibility:
+	 *
+	 * If usize == ksize then we just copy everything to user-space and all is good.
+	 *
+	 * If usize < ksize then we only copy as much as user-space has space for,
+	 * this keeps ABI compatibility as well. We skip the rest.
+	 *
+	 * If usize > ksize then user-space is using a newer version of the ABI,
+	 * which part the kernel doesn't know about. Just ignore it - tooling can
+	 * detect the kernel's knowledge of attributes from the attr->size value
+	 * which is set to ksize in this case.
 	 */
-	if (usize < sizeof(*attr)) {
-		unsigned char *addr;
-		unsigned char *end;
+	kattr->size = min(usize, ksize);
 
-		addr = (void *)attr + usize;
-		end  = (void *)attr + sizeof(*attr);
-
-		for (; addr < end; addr++) {
-			if (*addr)
-				return -EFBIG;
-		}
-
-		attr->size = usize;
-	}
-
-	ret = copy_to_user(uattr, attr, attr->size);
-	if (ret)
+	if (copy_to_user(uattr, kattr, kattr->size))
 		return -EFAULT;
 
 	return 0;
@@ -5145,20 +5148,18 @@ static int sched_read_attr(struct sched_attr __user *uattr,
  * sys_sched_getattr - similar to sched_getparam, but with sched_attr
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
- * @size: sizeof(attr) for fwd/bwd comp.
+ * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility.
  * @flags: for future extension.
  */
 SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-		unsigned int, size, unsigned int, flags)
+		unsigned int, usize, unsigned int, flags)
 {
-	struct sched_attr attr = {
-		.size = sizeof(struct sched_attr),
-	};
+	struct sched_attr kattr = { };
 	struct task_struct *p;
 	int retval;
 
-	if (!uattr || pid < 0 || size > PAGE_SIZE ||
-	    size < SCHED_ATTR_SIZE_VER0 || flags)
+	if (!uattr || pid < 0 || usize > PAGE_SIZE ||
+	    usize < SCHED_ATTR_SIZE_VER0 || flags)
 		return -EINVAL;
 
 	rcu_read_lock();
@@ -5171,25 +5172,24 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	if (retval)
 		goto out_unlock;
 
-	attr.sched_policy = p->policy;
+	kattr.sched_policy = p->policy;
 	if (p->sched_reset_on_fork)
-		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+		kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
 	if (task_has_dl_policy(p))
-		__getparam_dl(p, &attr);
+		__getparam_dl(p, &kattr);
 	else if (task_has_rt_policy(p))
-		attr.sched_priority = p->rt_priority;
+		kattr.sched_priority = p->rt_priority;
 	else
-		attr.sched_nice = task_nice(p);
+		kattr.sched_nice = task_nice(p);
 
 #ifdef CONFIG_UCLAMP_TASK
-	attr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
-	attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+	kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+	kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
 #endif
 
 	rcu_read_unlock();
 
-	retval = sched_read_attr(uattr, &attr, size);
-	return retval;
+	return sched_attr_copy_to_user(uattr, &kattr, usize);
 
 out_unlock:
 	rcu_read_unlock();

kernel/sched/fair.c

@@ -4470,6 +4470,8 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 	if (likely(cfs_rq->runtime_remaining > 0))
 		return;
 
+	if (cfs_rq->throttled)
+		return;
 	/*
 	 * if we're unable to extend our runtime we resched so that the active
 	 * hierarchy can be throttled
@@ -4673,6 +4675,9 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
 		if (!cfs_rq_throttled(cfs_rq))
 			goto next;
 
+		/* By the above check, this should never be true */
+		SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
+
 		runtime = -cfs_rq->runtime_remaining + 1;
 		if (runtime > remaining)
 			runtime = remaining;