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

Fun set of conflict resolutions here...

For the mac80211 stuff, these were fortunately just parallel
adds.  Trivially resolved.

In drivers/net/phy/phy.c we had a bug fix in 'net' that moved the
function phy_disable_interrupts() earlier in the file, whilst in
'net-next' the phy_error() call from this function was removed.

In net/ipv4/xfrm4_policy.c, David Ahern's changes to remove the
'rt_table_id' member of rtable collided with a bug fix in 'net' that
added a new struct member "rt_mtu_locked" which needs to be copied
over here.

The mlxsw driver conflict consisted of net-next separating
the span code and definitions into separate files, whilst
a 'net' bug fix made some changes to that moved code.

The mlx5 infiniband conflict resolution was quite non-trivial,
the RDMA tree's merge commit was used as a guide here, and
here are their notes:

====================

    Due to bug fixes found by the syzkaller bot and taken into the for-rc
    branch after development for the 4.17 merge window had already started
    being taken into the for-next branch, there were fairly non-trivial
    merge issues that would need to be resolved between the for-rc branch
    and the for-next branch.  This merge resolves those conflicts and
    provides a unified base upon which ongoing development for 4.17 can
    be based.

    Conflicts:
            drivers/infiniband/hw/mlx5/main.c - Commit 42cea83f95
            (IB/mlx5: Fix cleanup order on unload) added to for-rc and
            commit b5ca15ad7e (IB/mlx5: Add proper representors support)
            add as part of the devel cycle both needed to modify the
            init/de-init functions used by mlx5.  To support the new
            representors, the new functions added by the cleanup patch
            needed to be made non-static, and the init/de-init list
            added by the representors patch needed to be modified to
            match the init/de-init list changes made by the cleanup
            patch.
    Updates:
            drivers/infiniband/hw/mlx5/mlx5_ib.h - Update function
            prototypes added by representors patch to reflect new function
            names as changed by cleanup patch
            drivers/infiniband/hw/mlx5/ib_rep.c - Update init/de-init
            stage list to match new order from cleanup patch
====================

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

kernel/bpf/syscall.c

@@ -1849,7 +1849,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	union bpf_attr attr = {};
 	int err;
 
-	if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled)
+	if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
 	err = check_uarg_tail_zero(uattr, sizeof(attr), size);

kernel/cgroup/cgroup.c

@@ -3183,6 +3183,16 @@ static int cgroup_enable_threaded(struct cgroup *cgrp)
 	if (cgroup_is_threaded(cgrp))
 		return 0;
 
+	/*
+	 * If @cgroup is populated or has domain controllers enabled, it
+	 * can't be switched.  While the below cgroup_can_be_thread_root()
+	 * test can catch the same conditions, that's only when @parent is
+	 * not mixable, so let's check it explicitly.
+	 */
+	if (cgroup_is_populated(cgrp) ||
+	    cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask)
+		return -EOPNOTSUPP;
+
 	/* we're joining the parent's domain, ensure its validity */
 	if (!cgroup_is_valid_domain(dom_cgrp) ||
 	    !cgroup_can_be_thread_root(dom_cgrp))

kernel/compat.c

@@ -488,25 +488,6 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat)
 }
 EXPORT_SYMBOL_GPL(get_compat_sigset);
 
-int
-put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set,
-		  unsigned int size)
-{
-	/* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */
-#ifdef __BIG_ENDIAN
-	compat_sigset_t v;
-	switch (_NSIG_WORDS) {
-	case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3];
-	case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2];
-	case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1];
-	case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0];
-	}
-	return copy_to_user(compat, &v, size) ? -EFAULT : 0;
-#else
-	return copy_to_user(compat, set, size) ? -EFAULT : 0;
-#endif
-}
-
 #ifdef CONFIG_NUMA
 COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
 		       compat_uptr_t __user *, pages32,

kernel/events/core.c

@@ -2246,7 +2246,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 			struct perf_event_context *task_ctx,
 			enum event_type_t event_type)
 {
-	enum event_type_t ctx_event_type = event_type & EVENT_ALL;
+	enum event_type_t ctx_event_type;
 	bool cpu_event = !!(event_type & EVENT_CPU);
 
 	/*
@@ -2256,6 +2256,8 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 	if (event_type & EVENT_PINNED)
 		event_type |= EVENT_FLEXIBLE;
 
+	ctx_event_type = event_type & EVENT_ALL;
+
 	perf_pmu_disable(cpuctx->ctx.pmu);
 	if (task_ctx)
 		task_ctx_sched_out(cpuctx, task_ctx, event_type);

kernel/fail_function.c

@@ -14,6 +14,15 @@
 
 static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs);
 
+static void fei_post_handler(struct kprobe *kp, struct pt_regs *regs,
+			     unsigned long flags)
+{
+	/*
+	 * A dummy post handler is required to prohibit optimizing, because
+	 * jump optimization does not support execution path overriding.
+	 */
+}
+
 struct fei_attr {
 	struct list_head list;
 	struct kprobe kp;
@@ -56,6 +65,7 @@ static struct fei_attr *fei_attr_new(const char *sym, unsigned long addr)
 			return NULL;
 		}
 		attr->kp.pre_handler = fei_kprobe_handler;
+		attr->kp.post_handler = fei_post_handler;
 		attr->retval = adjust_error_retval(addr, 0);
 		INIT_LIST_HEAD(&attr->list);
 	}

kernel/jump_label.c

@@ -373,7 +373,8 @@ static void __jump_label_update(struct static_key *key,
 			if (kernel_text_address(entry->code))
 				arch_jump_label_transform(entry, jump_label_type(entry));
 			else
-				WARN_ONCE(1, "can't patch jump_label at %pS", (void *)entry->code);
+				WARN_ONCE(1, "can't patch jump_label at %pS",
+					  (void *)(unsigned long)entry->code);
 		}
 	}
 }

kernel/locking/rtmutex.c

@@ -1616,11 +1616,12 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
 void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
 {
 	DEFINE_WAKE_Q(wake_q);
+	unsigned long flags;
 	bool postunlock;
 
-	raw_spin_lock_irq(&lock->wait_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 	postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
-	raw_spin_unlock_irq(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	if (postunlock)
 		rt_mutex_postunlock(&wake_q);

kernel/memremap.c

@@ -427,7 +427,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
  err_pfn_remap:
  err_radix:
 	pgmap_radix_release(res, pgoff);
-	devres_free(pgmap);
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL(devm_memremap_pages);

kernel/module.c

@@ -4228,7 +4228,7 @@ static int modules_open(struct inode *inode, struct file *file)
 		m->private = kallsyms_show_value() ? NULL : (void *)8ul;
 	}
 
-	return 0;
+	return err;
 }
 
 static const struct file_operations proc_modules_operations = {

kernel/panic.c

@@ -640,7 +640,7 @@ device_initcall(register_warn_debugfs);
  */
 __visible void __stack_chk_fail(void)
 {
-	panic("stack-protector: Kernel stack is corrupted in: %p\n",
+	panic("stack-protector: Kernel stack is corrupted in: %pB\n",
 		__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__stack_chk_fail);

kernel/sched/core.c

@@ -6683,13 +6683,18 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
 		parent_quota = parent_b->hierarchical_quota;
 
 		/*
-		 * Ensure max(child_quota) <= parent_quota, inherit when no
+		 * Ensure max(child_quota) <= parent_quota.  On cgroup2,
+		 * always take the min.  On cgroup1, only inherit when no
 		 * limit is set:
 		 */
-		if (quota == RUNTIME_INF)
-			quota = parent_quota;
-		else if (parent_quota != RUNTIME_INF && quota > parent_quota)
-			return -EINVAL;
+		if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
+			quota = min(quota, parent_quota);
+		} else {
+			if (quota == RUNTIME_INF)
+				quota = parent_quota;
+			else if (parent_quota != RUNTIME_INF && quota > parent_quota)
+				return -EINVAL;
+		}
 	}
 	cfs_b->hierarchical_quota = quota;
 

kernel/trace/bpf_trace.c

@@ -661,32 +661,6 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx,
-	   struct bpf_perf_event_value *, buf, u32, size)
-{
-	int err = -EINVAL;
-
-	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
-		goto clear;
-	err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
-				    &buf->running);
-	if (unlikely(err))
-		goto clear;
-	return 0;
-clear:
-	memset(buf, 0, size);
-	return err;
-}
-
-static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
-         .func           = bpf_perf_prog_read_value_tp,
-         .gpl_only       = true,
-         .ret_type       = RET_INTEGER,
-         .arg1_type      = ARG_PTR_TO_CTX,
-         .arg2_type      = ARG_PTR_TO_UNINIT_MEM,
-         .arg3_type      = ARG_CONST_SIZE,
-};
-
 static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -694,8 +668,6 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 		return &bpf_perf_event_output_proto_tp;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto_tp;
-	case BPF_FUNC_perf_prog_read_value:
-		return &bpf_perf_prog_read_value_proto_tp;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -723,6 +695,46 @@ const struct bpf_verifier_ops tracepoint_verifier_ops = {
 const struct bpf_prog_ops tracepoint_prog_ops = {
 };
 
+BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx,
+	   struct bpf_perf_event_value *, buf, u32, size)
+{
+	int err = -EINVAL;
+
+	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+		goto clear;
+	err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
+				    &buf->running);
+	if (unlikely(err))
+		goto clear;
+	return 0;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
+         .func           = bpf_perf_prog_read_value,
+         .gpl_only       = true,
+         .ret_type       = RET_INTEGER,
+         .arg1_type      = ARG_PTR_TO_CTX,
+         .arg2_type      = ARG_PTR_TO_UNINIT_MEM,
+         .arg3_type      = ARG_CONST_SIZE,
+};
+
+static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_perf_event_output:
+		return &bpf_perf_event_output_proto_tp;
+	case BPF_FUNC_get_stackid:
+		return &bpf_get_stackid_proto_tp;
+	case BPF_FUNC_perf_prog_read_value:
+		return &bpf_perf_prog_read_value_proto;
+	default:
+		return tracing_func_proto(func_id);
+	}
+}
+
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    struct bpf_insn_access_aux *info)
 {
@@ -791,7 +803,7 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
 }
 
 const struct bpf_verifier_ops perf_event_verifier_ops = {
-	.get_func_proto		= tp_prog_func_proto,
+	.get_func_proto		= pe_prog_func_proto,
 	.is_valid_access	= pe_prog_is_valid_access,
 	.convert_ctx_access	= pe_prog_convert_ctx_access,
 };

kernel/workqueue.c

@@ -3018,14 +3018,6 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork)
 	return ret;
 }
 
-/*
- * See cancel_delayed_work()
- */
-bool cancel_work(struct work_struct *work)
-{
-	return __cancel_work(work, false);
-}
-
 /**
  * cancel_delayed_work - cancel a delayed work
  * @dwork: delayed_work to cancel
@@ -5337,7 +5329,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 
 	ret = device_register(&wq_dev->dev);
 	if (ret) {
-		kfree(wq_dev);
+		put_device(&wq_dev->dev);
 		wq->wq_dev = NULL;
 		return ret;
 	}