Merge tag 'v4.14-rc6' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 292 insertions, 172 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 98c0f00c3f5e..e2636737b69b 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -98,7 +98,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
 
 	if (array_size >= U32_MAX - PAGE_SIZE ||
-	    elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
+	    bpf_array_alloc_percpu(array)) {
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index e093d9a2c4dd..e745d6a88224 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -69,7 +69,7 @@ static LIST_HEAD(dev_map_list);
 
 static u64 dev_map_bitmap_size(const union bpf_attr *attr)
 {
-	return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+	return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long);
 }
 
 static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
@@ -78,6 +78,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	int err = -EINVAL;
 	u64 cost;
 
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
@@ -111,8 +114,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	err = -ENOMEM;
 
 	/* A per cpu bitfield with a bit per possible net device */
-	dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr),
-					    __alignof__(unsigned long));
+	dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr),
+						__alignof__(unsigned long),
+						GFP_KERNEL | __GFP_NOWARN);
 	if (!dtab->flush_needed)
 		goto free_dtab;
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 431126f31ea3..6533f08d1238 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -317,10 +317,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		 */
 		goto free_htab;
 
-	if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE)
-		/* make sure the size for pcpu_alloc() is reasonable */
-		goto free_htab;
-
 	htab->elem_size = sizeof(struct htab_elem) +
 			  round_up(htab->map.key_size, 8);
 	if (percpu)
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 6424ce0e4969..2b6eb35ae5d3 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -39,6 +39,7 @@
 #include <linux/workqueue.h>
 #include <linux/list.h>
 #include <net/strparser.h>
+#include <net/tcp.h>
 
 struct bpf_stab {
 	struct bpf_map map;
@@ -101,9 +102,16 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 		return SK_DROP;
 
 	skb_orphan(skb);
+	/* We need to ensure that BPF metadata for maps is also cleared
+	 * when we orphan the skb so that we don't have the possibility
+	 * to reference a stale map.
+	 */
+	TCP_SKB_CB(skb)->bpf.map = NULL;
 	skb->sk = psock->sock;
 	bpf_compute_data_end(skb);
+	preempt_disable();
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
+	preempt_enable();
 	skb->sk = NULL;
 
 	return rc;
@@ -114,17 +122,10 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
 	struct sock *sk;
 	int rc;
 
-	/* Because we use per cpu values to feed input from sock redirect
-	 * in BPF program to do_sk_redirect_map() call we need to ensure we
-	 * are not preempted. RCU read lock is not sufficient in this case
-	 * with CONFIG_PREEMPT_RCU enabled so we must be explicit here.
-	 */
-	preempt_disable();
 	rc = smap_verdict_func(psock, skb);
 	switch (rc) {
 	case SK_REDIRECT:
-		sk = do_sk_redirect_map();
-		preempt_enable();
+		sk = do_sk_redirect_map(skb);
 		if (likely(sk)) {
 			struct smap_psock *peer = smap_psock_sk(sk);
 
@@ -141,8 +142,6 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
 	/* Fall through and free skb otherwise */
 	case SK_DROP:
 	default:
-		if (rc != SK_REDIRECT)
-			preempt_enable();
 		kfree_skb(skb);
 	}
 }
@@ -487,6 +486,9 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	int err = -EINVAL;
 	u64 cost;
 
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
@@ -840,6 +842,12 @@ static int sock_map_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	if (skops.sk->sk_type != SOCK_STREAM ||
+	    skops.sk->sk_protocol != IPPROTO_TCP) {
+		fput(socket->file);
+		return -EOPNOTSUPP;
+	}
+
 	err = sock_map_ctx_update_elem(&skops, map, key, flags);
 	fput(socket->file);
 	return err;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8b8d6ba39e23..c48ca2a34b5e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1116,7 +1116,12 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		/* ctx accesses must be at a fixed offset, so that we can
 		 * determine what type of data were returned.
 		 */
-		if (!tnum_is_const(reg->var_off)) {
+		if (reg->off) {
+			verbose("dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
+				regno, reg->off, off - reg->off);
+			return -EACCES;
+		}
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
 			char tn_buf[48];
 
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
@@ -1124,7 +1129,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				tn_buf, off, size);
 			return -EACCES;
 		}
-		off += reg->var_off.value;
 		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
 		if (!err && t == BPF_READ && value_regno >= 0) {
 			/* ctx access returns either a scalar, or a
@@ -2426,12 +2430,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 }
 
 static void find_good_pkt_pointers(struct bpf_verifier_state *state,
-				   struct bpf_reg_state *dst_reg)
+				   struct bpf_reg_state *dst_reg,
+				   bool range_right_open)
 {
 	struct bpf_reg_state *regs = state->regs, *reg;
+	u16 new_range;
 	int i;
 
-	if (dst_reg->off < 0)
+	if (dst_reg->off < 0 ||
+	    (dst_reg->off == 0 && range_right_open))
 		/* This doesn't give us any range */
 		return;
 
@@ -2442,9 +2449,13 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 		 */
 		return;
 
-	/* LLVM can generate four kind of checks:
+	new_range = dst_reg->off;
+	if (range_right_open)
+		new_range--;
+
+	/* Examples for register markings:
 	 *
-	 * Type 1/2:
+	 * pkt_data in dst register:
 	 *
 	 *   r2 = r3;
 	 *   r2 += 8;
@@ -2461,7 +2472,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	 *     r2=pkt(id=n,off=8,r=0)
 	 *     r3=pkt(id=n,off=0,r=0)
 	 *
-	 * Type 3/4:
+	 * pkt_data in src register:
 	 *
 	 *   r2 = r3;
 	 *   r2 += 8;
@@ -2479,7 +2490,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	 *     r3=pkt(id=n,off=0,r=0)
 	 *
 	 * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
-	 * so that range of bytes [r3, r3 + 8) is safe to access.
+	 * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8)
+	 * and [r3, r3 + 8-1) respectively is safe to access depending on
+	 * the check.
 	 */
 
 	/* If our ids match, then we must have the same max_value.  And we
@@ -2490,14 +2503,14 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
 			/* keep the maximum range already checked */
-			regs[i].range = max_t(u16, regs[i].range, dst_reg->off);
+			regs[i].range = max(regs[i].range, new_range);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
 		reg = &state->spilled_regs[i / BPF_REG_SIZE];
 		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
-			reg->range = max_t(u16, reg->range, dst_reg->off);
+			reg->range = max(reg->range, new_range);
 	}
 }
 
@@ -2861,19 +2874,43 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		find_good_pkt_pointers(this_branch, dst_reg);
+		/* pkt_data' > pkt_end */
+		find_good_pkt_pointers(this_branch, dst_reg, false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
+		   dst_reg->type == PTR_TO_PACKET_END &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET) {
+		/* pkt_end > pkt_data' */
+		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], true);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		find_good_pkt_pointers(other_branch, dst_reg);
+		/* pkt_data' < pkt_end */
+		find_good_pkt_pointers(other_branch, dst_reg, true);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
+		   dst_reg->type == PTR_TO_PACKET_END &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET) {
+		/* pkt_end < pkt_data' */
+		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
+		   dst_reg->type == PTR_TO_PACKET &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
+		/* pkt_data' >= pkt_end */
+		find_good_pkt_pointers(this_branch, dst_reg, true);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
 		   dst_reg->type == PTR_TO_PACKET_END &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		find_good_pkt_pointers(other_branch, &regs[insn->src_reg]);
+		/* pkt_end >= pkt_data' */
+		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
+		   dst_reg->type == PTR_TO_PACKET &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
+		/* pkt_data' <= pkt_end */
+		find_good_pkt_pointers(other_branch, dst_reg, false);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
 		   dst_reg->type == PTR_TO_PACKET_END &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		find_good_pkt_pointers(this_branch, &regs[insn->src_reg]);
+		/* pkt_end <= pkt_data' */
+		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], true);
 	} else if (is_pointer_value(env, insn->dst_reg)) {
 		verbose("R%d pointer comparison prohibited\n", insn->dst_reg);
 		return -EACCES;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index d851df22f5c5..04892a82f6ac 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -632,6 +632,11 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
 		__cpuhp_kick_ap(st);
 	}
 
+	/*
+	 * Clean up the leftovers so the next hotplug operation wont use stale
+	 * data.
+	 */
+	st->node = st->last = NULL;
 	return ret;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6bc21e202ae4..9d93db81fa36 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -662,7 +662,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	/*
 	 * Do not update time when cgroup is not active
 	 */
-	if (cgrp == event->cgrp)
+       if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 		__update_cgrp_time(event->cgrp);
 }
 
@@ -8955,6 +8955,14 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 
 static void free_pmu_context(struct pmu *pmu)
 {
+	/*
+	 * Static contexts such as perf_sw_context have a global lifetime
+	 * and may be shared between different PMUs. Avoid freeing them
+	 * when a single PMU is going away.
+	 */
+	if (pmu->task_ctx_nr > perf_invalid_context)
+		return;
+
 	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
 	mutex_unlock(&pmus_lock);
diff --git a/kernel/exit.c b/kernel/exit.c
index f2cd53e92147..f6cad39f35df 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1610,6 +1610,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	if (!infop)
 		return err;
 
+	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+		return -EFAULT;
+
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
@@ -1735,6 +1738,9 @@ COMPAT_SYSCALL_DEFINE5(waitid,
 	if (!infop)
 		return err;
 
+	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+		return -EFAULT;
+
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
diff --git a/kernel/fork.c b/kernel/fork.c
index e702cb9ffbd8..07cc743698d3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -215,6 +215,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 		if (!s)
 			continue;
 
+#ifdef CONFIG_DEBUG_KMEMLEAK
+		/* Clear stale pointers from reused stack. */
+		memset(s->addr, 0, THREAD_SIZE);
+#endif
 		tsk->stack_vm_area = s;
 		return s->addr;
 	}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 6fc89fd93824..5a2ef92c2782 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -265,8 +265,8 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
 			irq_setup_affinity(desc);
 			break;
 		case IRQ_STARTUP_MANAGED:
+			irq_do_set_affinity(d, aff, false);
 			ret = __irq_startup(desc);
-			irq_set_affinity_locked(d, aff, false);
 			break;
 		case IRQ_STARTUP_ABORT:
 			return 0;
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 638eb9c83d9f..9eb09aef0313 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -18,8 +18,34 @@
 static inline bool irq_needs_fixup(struct irq_data *d)
 {
 	const struct cpumask *m = irq_data_get_effective_affinity_mask(d);
+	unsigned int cpu = smp_processor_id();
 
-	return cpumask_test_cpu(smp_processor_id(), m);
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	/*
+	 * The cpumask_empty() check is a workaround for interrupt chips,
+	 * which do not implement effective affinity, but the architecture has
+	 * enabled the config switch. Use the general affinity mask instead.
+	 */
+	if (cpumask_empty(m))
+		m = irq_data_get_affinity_mask(d);
+
+	/*
+	 * Sanity check. If the mask is not empty when excluding the outgoing
+	 * CPU then it must contain at least one online CPU. The outgoing CPU
+	 * has been removed from the online mask already.
+	 */
+	if (cpumask_any_but(m, cpu) < nr_cpu_ids &&
+	    cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) {
+		/*
+		 * If this happens then there was a missed IRQ fixup at some
+		 * point. Warn about it and enforce fixup.
+		 */
+		pr_warn("Eff. affinity %*pbl of IRQ %u contains only offline CPUs after offlining CPU %u\n",
+			cpumask_pr_args(m), d->irq, cpu);
+		return true;
+	}
+#endif
+	return cpumask_test_cpu(cpu, m);
 }
 
 static bool migrate_one_irq(struct irq_desc *desc)
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index 5270a54b9fa4..c26c5bb6b491 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -135,17 +135,26 @@ void irq_gc_ack_clr_bit(struct irq_data *d)
 }
 
 /**
- * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt
+ * irq_gc_mask_disable_and_ack_set - Mask and ack pending interrupt
  * @d: irq_data
+ *
+ * This generic implementation of the irq_mask_ack method is for chips
+ * with separate enable/disable registers instead of a single mask
+ * register and where a pending interrupt is acknowledged by setting a
+ * bit.
+ *
+ * Note: This is the only permutation currently used.  Similar generic
+ * functions should be added here if other permutations are required.
  */
-void irq_gc_mask_disable_reg_and_ack(struct irq_data *d)
+void irq_gc_mask_disable_and_ack_set(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(gc, mask, ct->regs.mask);
+	irq_reg_writel(gc, mask, ct->regs.disable);
+	*ct->mask_cache &= ~mask;
 	irq_reg_writel(gc, mask, ct->regs.ack);
 	irq_gc_unlock(gc);
 }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d00132b5c325..4bff6a10ae8e 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -168,6 +168,19 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 			set_bit(IRQTF_AFFINITY, &action->thread_flags);
 }
 
+static void irq_validate_effective_affinity(struct irq_data *data)
+{
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	const struct cpumask *m = irq_data_get_effective_affinity_mask(data);
+	struct irq_chip *chip = irq_data_get_irq_chip(data);
+
+	if (!cpumask_empty(m))
+		return;
+	pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n",
+		     chip->name, data->irq);
+#endif
+}
+
 int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 			bool force)
 {
@@ -175,12 +188,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	int ret;
 
+	if (!chip || !chip->irq_set_affinity)
+		return -EINVAL;
+
 	ret = chip->irq_set_affinity(data, mask, force);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
 	case IRQ_SET_MASK_OK_DONE:
 		cpumask_copy(desc->irq_common_data.affinity, mask);
 	case IRQ_SET_MASK_OK_NOCOPY:
+		irq_validate_effective_affinity(data);
 		irq_set_thread_affinity(desc);
 		ret = 0;
 	}
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index b9628e43c78f..bf8c8fd72589 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -830,6 +830,41 @@ int klp_register_patch(struct klp_patch *patch)
 }
 EXPORT_SYMBOL_GPL(klp_register_patch);
 
+/*
+ * Remove parts of patches that touch a given kernel module. The list of
+ * patches processed might be limited. When limit is NULL, all patches
+ * will be handled.
+ */
+static void klp_cleanup_module_patches_limited(struct module *mod,
+					       struct klp_patch *limit)
+{
+	struct klp_patch *patch;
+	struct klp_object *obj;
+
+	list_for_each_entry(patch, &klp_patches, list) {
+		if (patch == limit)
+			break;
+
+		klp_for_each_object(patch, obj) {
+			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
+				continue;
+
+			/*
+			 * Only unpatch the module if the patch is enabled or
+			 * is in transition.
+			 */
+			if (patch->enabled || patch == klp_transition_patch) {
+				pr_notice("reverting patch '%s' on unloading module '%s'\n",
+					  patch->mod->name, obj->mod->name);
+				klp_unpatch_object(obj);
+			}
+
+			klp_free_object_loaded(obj);
+			break;
+		}
+	}
+}
+
 int klp_module_coming(struct module *mod)
 {
 	int ret;
@@ -894,7 +929,7 @@ err:
 	pr_warn("patch '%s' failed for module '%s', refusing to load module '%s'\n",
 		patch->mod->name, obj->mod->name, obj->mod->name);
 	mod->klp_alive = false;
-	klp_free_object_loaded(obj);
+	klp_cleanup_module_patches_limited(mod, patch);
 	mutex_unlock(&klp_mutex);
 
 	return ret;
@@ -902,9 +937,6 @@ err:
 
 void klp_module_going(struct module *mod)
 {
-	struct klp_patch *patch;
-	struct klp_object *obj;
-
 	if (WARN_ON(mod->state != MODULE_STATE_GOING &&
 		    mod->state != MODULE_STATE_COMING))
 		return;
@@ -917,25 +949,7 @@ void klp_module_going(struct module *mod)
 	 */
 	mod->klp_alive = false;
 
-	list_for_each_entry(patch, &klp_patches, list) {
-		klp_for_each_object(patch, obj) {
-			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
-				continue;
-
-			/*
-			 * Only unpatch the module if the patch is enabled or
-			 * is in transition.
-			 */
-			if (patch->enabled || patch == klp_transition_patch) {
-				pr_notice("reverting patch '%s' on unloading module '%s'\n",
-					  patch->mod->name, obj->mod->name);
-				klp_unpatch_object(obj);
-			}
-
-			klp_free_object_loaded(obj);
-			break;
-		}
-	}
+	klp_cleanup_module_patches_limited(mod, NULL);
 
 	mutex_unlock(&klp_mutex);
 }
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 729a8706751d..6d5880089ff6 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -854,7 +854,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
  * @sp: srcu_struct in queue the callback
- * @head: structure to be used for queueing the SRCU callback.
+ * @rhp: structure to be used for queueing the SRCU callback.
  * @func: function to be invoked after the SRCU grace period
  *
  * The callback function will be invoked some time after a full SRCU
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index 50d1861f7759..3f943efcf61c 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -85,6 +85,9 @@ void rcu_sync_init(struct rcu_sync *rsp, enum rcu_sync_type type)
 }
 
 /**
+ * rcu_sync_enter_start - Force readers onto slow path for multiple updates
+ * @rsp: Pointer to rcu_sync structure to use for synchronization
+ *
  * Must be called after rcu_sync_init() and before first use.
  *
  * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}()
@@ -142,7 +145,7 @@ void rcu_sync_enter(struct rcu_sync *rsp)
 
 /**
  * rcu_sync_func() - Callback function managing reader access to fastpath
- * @rsp: Pointer to rcu_sync structure to use for synchronization
+ * @rhp: Pointer to rcu_head in rcu_sync structure to use for synchronization
  *
  * This function is passed to one of the call_rcu() functions by
  * rcu_sync_exit(), so that it is invoked after a grace period following the
@@ -158,9 +161,9 @@ void rcu_sync_enter(struct rcu_sync *rsp)
  * rcu_sync_exit().  Otherwise, set all state back to idle so that readers
  * can again use their fastpaths.
  */
-static void rcu_sync_func(struct rcu_head *rcu)
+static void rcu_sync_func(struct rcu_head *rhp)
 {
-	struct rcu_sync *rsp = container_of(rcu, struct rcu_sync, cb_head);
+	struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head);
 	unsigned long flags;
 
 	BUG_ON(rsp->gp_state != GP_PASSED);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b0ad62b0e7b8..3e3650e94ae6 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3097,9 +3097,10 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func,
  * read-side critical sections have completed. call_rcu_sched() assumes
  * that the read-side critical sections end on enabling of preemption
  * or on voluntary preemption.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR
- *  - anything that disables preemption.
+ * RCU read-side critical sections are delimited by:
+ *
+ * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR
+ * - anything that disables preemption.
  *
  *  These may be nested.
  *
@@ -3124,11 +3125,12 @@ EXPORT_SYMBOL_GPL(call_rcu_sched);
  * handler. This means that read-side critical sections in process
  * context must not be interrupted by softirqs. This interface is to be
  * used when most of the read-side critical sections are in softirq context.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context.
- *  OR
- *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
- *  These may be nested.
+ * RCU read-side critical sections are delimited by:
+ *
+ * - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context, OR
+ * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
+ *
+ * These may be nested.
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 70ba32e08a23..d3f3094856fe 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5356,91 +5356,62 @@ static int wake_wide(struct task_struct *p)
 	return 1;
 }
 
-struct llc_stats {
-	unsigned long	nr_running;
-	unsigned long	load;
-	unsigned long	capacity;
-	int		has_capacity;
-};
+/*
+ * The purpose of wake_affine() is to quickly determine on which CPU we can run
+ * soonest. For the purpose of speed we only consider the waking and previous
+ * CPU.
+ *
+ * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or
+ *			will be) idle.
+ *
+ * wake_affine_weight() - considers the weight to reflect the average
+ *			  scheduling latency of the CPUs. This seems to work
+ *			  for the overloaded case.
+ */
 
-static bool get_llc_stats(struct llc_stats *stats, int cpu)
+static bool
+wake_affine_idle(struct sched_domain *sd, struct task_struct *p,
+		 int this_cpu, int prev_cpu, int sync)
 {
-	struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
-
-	if (!sds)
-		return false;
+	if (idle_cpu(this_cpu))
+		return true;
 
-	stats->nr_running	= READ_ONCE(sds->nr_running);
-	stats->load		= READ_ONCE(sds->load);
-	stats->capacity		= READ_ONCE(sds->capacity);
-	stats->has_capacity	= stats->nr_running < per_cpu(sd_llc_size, cpu);
+	if (sync && cpu_rq(this_cpu)->nr_running == 1)
+		return true;
 
-	return true;
+	return false;
 }
 
-/*
- * Can a task be moved from prev_cpu to this_cpu without causing a load
- * imbalance that would trigger the load balancer?
- *
- * Since we're running on 'stale' values, we might in fact create an imbalance
- * but recomputing these values is expensive, as that'd mean iteration 2 cache
- * domains worth of CPUs.
- */
 static bool
-wake_affine_llc(struct sched_domain *sd, struct task_struct *p,
-		int this_cpu, int prev_cpu, int sync)
+wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
+		   int this_cpu, int prev_cpu, int sync)
 {
-	struct llc_stats prev_stats, this_stats;
 	s64 this_eff_load, prev_eff_load;
 	unsigned long task_load;
 
-	if (!get_llc_stats(&prev_stats, prev_cpu) ||
-	    !get_llc_stats(&this_stats, this_cpu))
-		return false;
+	this_eff_load = target_load(this_cpu, sd->wake_idx);
+	prev_eff_load = source_load(prev_cpu, sd->wake_idx);
 
-	/*
-	 * If sync wakeup then subtract the (maximum possible)
-	 * effect of the currently running task from the load
-	 * of the current LLC.
-	 */
 	if (sync) {
 		unsigned long current_load = task_h_load(current);
 
-		/* in this case load hits 0 and this LLC is considered 'idle' */
-		if (current_load > this_stats.load)
+		if (current_load > this_eff_load)
 			return true;
 
-		this_stats.load -= current_load;
+		this_eff_load -= current_load;
 	}
 
-	/*
-	 * The has_capacity stuff is not SMT aware, but by trying to balance
-	 * the nr_running on both ends we try and fill the domain at equal
-	 * rates, thereby first consuming cores before siblings.
-	 */
-
-	/* if the old cache has capacity, stay there */
-	if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1)
-		return false;
-
-	/* if this cache has capacity, come here */
-	if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running)
-		return true;
-
-	/*
-	 * Check to see if we can move the load without causing too much
-	 * imbalance.
-	 */
 	task_load = task_h_load(p);
 
-	this_eff_load = 100;
-	this_eff_load *= prev_stats.capacity;
-
-	prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
-	prev_eff_load *= this_stats.capacity;
+	this_eff_load += task_load;
+	if (sched_feat(WA_BIAS))
+		this_eff_load *= 100;
+	this_eff_load *= capacity_of(prev_cpu);
 
-	this_eff_load *= this_stats.load + task_load;
-	prev_eff_load *= prev_stats.load - task_load;
+	prev_eff_load -= task_load;
+	if (sched_feat(WA_BIAS))
+		prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
+	prev_eff_load *= capacity_of(this_cpu);
 
 	return this_eff_load <= prev_eff_load;
 }
@@ -5449,22 +5420,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		       int prev_cpu, int sync)
 {
 	int this_cpu = smp_processor_id();
-	bool affine;
+	bool affine = false;
 
-	/*
-	 * Default to no affine wakeups; wake_affine() should not effect a task
-	 * placement the load-balancer feels inclined to undo. The conservative
-	 * option is therefore to not move tasks when they wake up.
-	 */
-	affine = false;
+	if (sched_feat(WA_IDLE) && !affine)
+		affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync);
 
-	/*
-	 * If the wakeup is across cache domains, try to evaluate if movement
-	 * makes sense, otherwise rely on select_idle_siblings() to do
-	 * placement inside the cache domain.
-	 */
-	if (!cpus_share_cache(prev_cpu, this_cpu))
-		affine = wake_affine_llc(sd, p, this_cpu, prev_cpu, sync);
+	if (sched_feat(WA_WEIGHT) && !affine)
+		affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync);
 
 	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
 	if (affine) {
@@ -7600,7 +7562,6 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq)
  */
 static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
 {
-	struct sched_domain_shared *shared = env->sd->shared;
 	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
@@ -7672,22 +7633,6 @@ next_group:
 		if (env->dst_rq->rd->overload != overload)
 			env->dst_rq->rd->overload = overload;
 	}
-
-	if (!shared)
-		return;
-
-	/*
-	 * Since these are sums over groups they can contain some CPUs
-	 * multiple times for the NUMA domains.
-	 *
-	 * Currently only wake_affine_llc() and find_busiest_group()
-	 * uses these numbers, only the last is affected by this problem.
-	 *
-	 * XXX fix that.
-	 */
-	WRITE_ONCE(shared->nr_running,	sds->total_running);
-	WRITE_ONCE(shared->load,	sds->total_load);
-	WRITE_ONCE(shared->capacity,	sds->total_capacity);
 }
 
 /**
@@ -8098,6 +8043,13 @@ static int should_we_balance(struct lb_env *env)
 	int cpu, balance_cpu = -1;
 
 	/*
+	 * Ensure the balancing environment is consistent; can happen
+	 * when the softirq triggers 'during' hotplug.
+	 */
+	if (!cpumask_test_cpu(env->dst_cpu, env->cpus))
+		return 0;
+
+	/*
 	 * In the newly idle case, we will allow all the cpu's
 	 * to do the newly idle load balance.
 	 */
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index d3fb15555291..319ed0e8a347 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -81,3 +81,6 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)
 
+SCHED_FEAT(WA_IDLE, true)
+SCHED_FEAT(WA_WEIGHT, true)
+SCHED_FEAT(WA_BIAS, true)
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index a92fddc22747..dd7908743dab 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -18,6 +18,7 @@
 #include <linux/membarrier.h>
 #include <linux/tick.h>
 #include <linux/cpumask.h>
+#include <linux/atomic.h>
 
 #include "sched.h"	/* for cpu_rq(). */
 
@@ -26,21 +27,26 @@
  * except MEMBARRIER_CMD_QUERY.
  */
 #define MEMBARRIER_CMD_BITMASK	\
-	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
+	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED	\
+	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)
 
 static void ipi_mb(void *info)
 {
 	smp_mb();	/* IPIs should be serializing but paranoid. */
 }
 
-static void membarrier_private_expedited(void)
+static int membarrier_private_expedited(void)
 {
 	int cpu;
 	bool fallback = false;
 	cpumask_var_t tmpmask;
 
+	if (!(atomic_read(&current->mm->membarrier_state)
+			& MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
+		return -EPERM;
+
 	if (num_online_cpus() == 1)
-		return;
+		return 0;
 
 	/*
 	 * Matches memory barriers around rq->curr modification in
@@ -94,6 +100,24 @@ static void membarrier_private_expedited(void)
 	 * rq->curr modification in scheduler.
 	 */
 	smp_mb();	/* exit from system call is not a mb */
+	return 0;
+}
+
+static void membarrier_register_private_expedited(void)
+{
+	struct task_struct *p = current;
+	struct mm_struct *mm = p->mm;
+
+	/*
+	 * We need to consider threads belonging to different thread
+	 * groups, which use the same mm. (CLONE_VM but not
+	 * CLONE_THREAD).
+	 */
+	if (atomic_read(&mm->membarrier_state)
+			& MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)
+		return;
+	atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY,
+			&mm->membarrier_state);
 }
 
 /**
@@ -144,7 +168,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
 			synchronize_sched();
 		return 0;
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-		membarrier_private_expedited();
+		return membarrier_private_expedited();
+	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+		membarrier_register_private_expedited();
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index bb3a38005b9c..0ae832e13b97 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -473,7 +473,7 @@ static long seccomp_attach_filter(unsigned int flags,
 	return 0;
 }
 
-void __get_seccomp_filter(struct seccomp_filter *filter)
+static void __get_seccomp_filter(struct seccomp_filter *filter)
 {
 	/* Reference count is bounded by the number of total processes. */
 	refcount_inc(&filter->usage);