Merge tag 'loongarch-kvm-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.10

1. Add ParaVirt IPI support.
2. Add software breakpoint support.
3. Add mmio trace events support.

22 files changed, 279 insertions, 168 deletions

diff --git a/kernel/bounds.c b/kernel/bounds.c
index c5a9fcd2d622..29b2cd00df2c 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -19,7 +19,7 @@ int main(void)
 	DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
 	DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
 #ifdef CONFIG_SMP
-	DEFINE(NR_CPUS_BITS, bits_per(CONFIG_NR_CPUS));
+	DEFINE(NR_CPUS_BITS, order_base_2(CONFIG_NR_CPUS));
 #endif
 	DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
 #ifdef CONFIG_LRU_GEN
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 696bc55de8e8..1ea5ce5bb599 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2942,6 +2942,15 @@ bool __weak bpf_jit_supports_arena(void)
 	return false;
 }
 
+u64 __weak bpf_arch_uaddress_limit(void)
+{
+#if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE)
+	return TASK_SIZE;
+#else
+	return 0;
+#endif
+}
+
 /* Return TRUE if the JIT backend satisfies the following two conditions:
  * 1) JIT backend supports atomic_xchg() on pointer-sized words.
  * 2) Under the specific arch, the implementation of xchg() is the same
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 98188379d5c7..cb7ad1f795e1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -18289,8 +18289,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 			f = fdget(fd);
 			map = __bpf_map_get(f);
 			if (IS_ERR(map)) {
-				verbose(env, "fd %d is not pointing to valid bpf_map\n",
-					insn[0].imm);
+				verbose(env, "fd %d is not pointing to valid bpf_map\n", fd);
 				return PTR_ERR(map);
 			}
 
@@ -19676,6 +19675,36 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 			goto next_insn;
 		}
 
+		/* Make it impossible to de-reference a userspace address */
+		if (BPF_CLASS(insn->code) == BPF_LDX &&
+		    (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+		     BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) {
+			struct bpf_insn *patch = &insn_buf[0];
+			u64 uaddress_limit = bpf_arch_uaddress_limit();
+
+			if (!uaddress_limit)
+				goto next_insn;
+
+			*patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg);
+			if (insn->off)
+				*patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off);
+			*patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32);
+			*patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2);
+			*patch++ = *insn;
+			*patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+			*patch++ = BPF_MOV64_IMM(insn->dst_reg, 0);
+
+			cnt = patch - insn_buf;
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			goto next_insn;
+		}
+
 		/* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */
 		if (BPF_CLASS(insn->code) == BPF_LD &&
 		    (BPF_MODE(insn->code) == BPF_ABS ||
diff --git a/kernel/configs/hardening.config b/kernel/configs/hardening.config
index 7a5bbfc024b7..4b4cfcba3190 100644
--- a/kernel/configs/hardening.config
+++ b/kernel/configs/hardening.config
@@ -39,11 +39,12 @@ CONFIG_UBSAN=y
 CONFIG_UBSAN_TRAP=y
 CONFIG_UBSAN_BOUNDS=y
 # CONFIG_UBSAN_SHIFT is not set
-# CONFIG_UBSAN_DIV_ZERO
-# CONFIG_UBSAN_UNREACHABLE
-# CONFIG_UBSAN_BOOL
-# CONFIG_UBSAN_ENUM
-# CONFIG_UBSAN_ALIGNMENT
+# CONFIG_UBSAN_DIV_ZERO is not set
+# CONFIG_UBSAN_UNREACHABLE is not set
+# CONFIG_UBSAN_SIGNED_WRAP is not set
+# CONFIG_UBSAN_BOOL is not set
+# CONFIG_UBSAN_ENUM is not set
+# CONFIG_UBSAN_ALIGNMENT is not set
 
 # Sampling-based heap out-of-bounds and use-after-free detection.
 CONFIG_KFENCE=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8f6affd051f7..63447eb85dab 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3196,6 +3196,7 @@ void __init boot_cpu_hotplug_init(void)
 	this_cpu_write(cpuhp_state.target, CPUHP_ONLINE);
 }
 
+#ifdef CONFIG_CPU_MITIGATIONS
 /*
  * These are used for a global "mitigations=" cmdline option for toggling
  * optional CPU mitigations.
@@ -3206,8 +3207,7 @@ enum cpu_mitigations {
 	CPU_MITIGATIONS_AUTO_NOSMT,
 };
 
-static enum cpu_mitigations cpu_mitigations __ro_after_init =
-	CPU_MITIGATIONS_AUTO;
+static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
 
 static int __init mitigations_parse_cmdline(char *arg)
 {
@@ -3223,7 +3223,6 @@ static int __init mitigations_parse_cmdline(char *arg)
 
 	return 0;
 }
-early_param("mitigations", mitigations_parse_cmdline);
 
 /* mitigations=off */
 bool cpu_mitigations_off(void)
@@ -3238,3 +3237,11 @@ bool cpu_mitigations_auto_nosmt(void)
 	return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
 }
 EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);
+#else
+static int __init mitigations_parse_cmdline(char *arg)
+{
+	pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n");
+	return 0;
+}
+#endif
+early_param("mitigations", mitigations_parse_cmdline);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 86fe172b5958..0de66f0ff43a 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -69,11 +69,14 @@
  * @alloc_size:	Size of the allocated buffer.
  * @list:	The free list describing the number of free entries available
  *		from each index.
+ * @pad_slots:	Number of preceding padding slots. Valid only in the first
+ *		allocated non-padding slot.
  */
 struct io_tlb_slot {
 	phys_addr_t orig_addr;
 	size_t alloc_size;
-	unsigned int list;
+	unsigned short list;
+	unsigned short pad_slots;
 };
 
 static bool swiotlb_force_bounce;
@@ -287,6 +290,7 @@ static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start,
 					 mem->nslabs - i);
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
 		mem->slots[i].alloc_size = 0;
+		mem->slots[i].pad_slots = 0;
 	}
 
 	memset(vaddr, 0, bytes);
@@ -821,12 +825,30 @@ void swiotlb_dev_init(struct device *dev)
 #endif
 }
 
-/*
- * Return the offset into a iotlb slot required to keep the device happy.
+/**
+ * swiotlb_align_offset() - Get required offset into an IO TLB allocation.
+ * @dev:         Owning device.
+ * @align_mask:  Allocation alignment mask.
+ * @addr:        DMA address.
+ *
+ * Return the minimum offset from the start of an IO TLB allocation which is
+ * required for a given buffer address and allocation alignment to keep the
+ * device happy.
+ *
+ * First, the address bits covered by min_align_mask must be identical in the
+ * original address and the bounce buffer address. High bits are preserved by
+ * choosing a suitable IO TLB slot, but bits below IO_TLB_SHIFT require extra
+ * padding bytes before the bounce buffer.
+ *
+ * Second, @align_mask specifies which bits of the first allocated slot must
+ * be zero. This may require allocating additional padding slots, and then the
+ * offset (in bytes) from the first such padding slot is returned.
  */
-static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
+static unsigned int swiotlb_align_offset(struct device *dev,
+					 unsigned int align_mask, u64 addr)
 {
-	return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
+	return addr & dma_get_min_align_mask(dev) &
+		(align_mask | (IO_TLB_SIZE - 1));
 }
 
 /*
@@ -841,27 +863,23 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	size_t alloc_size = mem->slots[index].alloc_size;
 	unsigned long pfn = PFN_DOWN(orig_addr);
 	unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
-	unsigned int tlb_offset, orig_addr_offset;
+	int tlb_offset;
 
 	if (orig_addr == INVALID_PHYS_ADDR)
 		return;
 
-	tlb_offset = tlb_addr & (IO_TLB_SIZE - 1);
-	orig_addr_offset = swiotlb_align_offset(dev, orig_addr);
-	if (tlb_offset < orig_addr_offset) {
-		dev_WARN_ONCE(dev, 1,
-			"Access before mapping start detected. orig offset %u, requested offset %u.\n",
-			orig_addr_offset, tlb_offset);
-		return;
-	}
-
-	tlb_offset -= orig_addr_offset;
-	if (tlb_offset > alloc_size) {
-		dev_WARN_ONCE(dev, 1,
-			"Buffer overflow detected. Allocation size: %zu. Mapping size: %zu+%u.\n",
-			alloc_size, size, tlb_offset);
-		return;
-	}
+	/*
+	 * It's valid for tlb_offset to be negative. This can happen when the
+	 * "offset" returned by swiotlb_align_offset() is non-zero, and the
+	 * tlb_addr is pointing within the first "offset" bytes of the second
+	 * or subsequent slots of the allocated swiotlb area. While it's not
+	 * valid for tlb_addr to be pointing within the first "offset" bytes
+	 * of the first slot, there's no way to check for such an error since
+	 * this function can't distinguish the first slot from the second and
+	 * subsequent slots.
+	 */
+	tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) -
+		     swiotlb_align_offset(dev, 0, orig_addr);
 
 	orig_addr += tlb_offset;
 	alloc_size -= tlb_offset;
@@ -1005,7 +1023,7 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
 	unsigned long max_slots = get_max_slots(boundary_mask);
 	unsigned int iotlb_align_mask = dma_get_min_align_mask(dev);
 	unsigned int nslots = nr_slots(alloc_size), stride;
-	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+	unsigned int offset = swiotlb_align_offset(dev, 0, orig_addr);
 	unsigned int index, slots_checked, count = 0, i;
 	unsigned long flags;
 	unsigned int slot_base;
@@ -1328,11 +1346,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		unsigned long attrs)
 {
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
-	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+	unsigned int offset;
 	struct io_tlb_pool *pool;
 	unsigned int i;
 	int index;
 	phys_addr_t tlb_addr;
+	unsigned short pad_slots;
 
 	if (!mem || !mem->nslabs) {
 		dev_warn_ratelimited(dev,
@@ -1349,6 +1368,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
+	offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr);
 	index = swiotlb_find_slots(dev, orig_addr,
 				   alloc_size + offset, alloc_align_mask, &pool);
 	if (index == -1) {
@@ -1364,6 +1384,10 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	 * This is needed when we sync the memory.  Then we sync the buffer if
 	 * needed.
 	 */
+	pad_slots = offset >> IO_TLB_SHIFT;
+	offset &= (IO_TLB_SIZE - 1);
+	index += pad_slots;
+	pool->slots[index].pad_slots = pad_slots;
 	for (i = 0; i < nr_slots(alloc_size + offset); i++)
 		pool->slots[index + i].orig_addr = slot_addr(orig_addr, i);
 	tlb_addr = slot_addr(pool->start, index) + offset;
@@ -1384,13 +1408,17 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 {
 	struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr);
 	unsigned long flags;
-	unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
-	int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
-	int nslots = nr_slots(mem->slots[index].alloc_size + offset);
-	int aindex = index / mem->area_nslabs;
-	struct io_tlb_area *area = &mem->areas[aindex];
+	unsigned int offset = swiotlb_align_offset(dev, 0, tlb_addr);
+	int index, nslots, aindex;
+	struct io_tlb_area *area;
 	int count, i;
 
+	index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
+	index -= mem->slots[index].pad_slots;
+	nslots = nr_slots(mem->slots[index].alloc_size + offset);
+	aindex = index / mem->area_nslabs;
+	area = &mem->areas[aindex];
+
 	/*
 	 * Return the buffer to the free list by setting the corresponding
 	 * entries to indicate the number of contiguous entries available.
@@ -1413,6 +1441,7 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 		mem->slots[i].list = ++count;
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
 		mem->slots[i].alloc_size = 0;
+		mem->slots[i].pad_slots = 0;
 	}
 
 	/*
@@ -1647,9 +1676,6 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get,
 static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 					 const char *dirname)
 {
-	atomic_long_set(&mem->total_used, 0);
-	atomic_long_set(&mem->used_hiwater, 0);
-
 	mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs);
 	if (!mem->nslabs)
 		return;
@@ -1660,7 +1686,6 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 	debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem,
 			&fops_io_tlb_hiwater);
 #ifdef CONFIG_SWIOTLB_DYNAMIC
-	atomic_long_set(&mem->transient_nslabs, 0);
 	debugfs_create_file("io_tlb_transient_nslabs", 0400, mem->debugfs,
 			    mem, &fops_io_tlb_transient_used);
 #endif
@@ -1773,6 +1798,7 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
 		mem->for_alloc = true;
 #ifdef CONFIG_SWIOTLB_DYNAMIC
 		spin_lock_init(&mem->lock);
+		INIT_LIST_HEAD_RCU(&mem->pools);
 #endif
 		add_mem_pool(mem, pool);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 39a5046c2f0b..aebb3e6c96dc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -714,6 +714,23 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		} else if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
 		vm_flags_clear(tmp, VM_LOCKED_MASK);
+		/*
+		 * Copy/update hugetlb private vma information.
+		 */
+		if (is_vm_hugetlb_page(tmp))
+			hugetlb_dup_vma_private(tmp);
+
+		/*
+		 * Link the vma into the MT. After using __mt_dup(), memory
+		 * allocation is not necessary here, so it cannot fail.
+		 */
+		vma_iter_bulk_store(&vmi, tmp);
+
+		mm->map_count++;
+
+		if (tmp->vm_ops && tmp->vm_ops->open)
+			tmp->vm_ops->open(tmp);
+
 		file = tmp->vm_file;
 		if (file) {
 			struct address_space *mapping = file->f_mapping;
@@ -730,25 +747,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 			i_mmap_unlock_write(mapping);
 		}
 
-		/*
-		 * Copy/update hugetlb private vma information.
-		 */
-		if (is_vm_hugetlb_page(tmp))
-			hugetlb_dup_vma_private(tmp);
-
-		/*
-		 * Link the vma into the MT. After using __mt_dup(), memory
-		 * allocation is not necessary here, so it cannot fail.
-		 */
-		vma_iter_bulk_store(&vmi, tmp);
-
-		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
 			retval = copy_page_range(tmp, mpnt);
 
-		if (tmp->vm_ops && tmp->vm_ops->open)
-			tmp->vm_ops->open(tmp);
-
 		if (retval) {
 			mpnt = vma_next(&vmi);
 			goto loop_out;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9d9095e81792..65adc815fc6e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1567,10 +1567,17 @@ static int check_kprobe_address_safe(struct kprobe *p,
 	jump_label_lock();
 	preempt_disable();
 
-	/* Ensure it is not in reserved area nor out of text */
-	if (!(core_kernel_text((unsigned long) p->addr) ||
-	    is_module_text_address((unsigned long) p->addr)) ||
-	    in_gate_area_no_mm((unsigned long) p->addr) ||
+	/* Ensure the address is in a text area, and find a module if exists. */
+	*probed_mod = NULL;
+	if (!core_kernel_text((unsigned long) p->addr)) {
+		*probed_mod = __module_text_address((unsigned long) p->addr);
+		if (!(*probed_mod)) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+	/* Ensure it is not in reserved area. */
+	if (in_gate_area_no_mm((unsigned long) p->addr) ||
 	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr) ||
 	    static_call_text_reserved(p->addr, p->addr) ||
@@ -1580,8 +1587,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
 		goto out;
 	}
 
-	/* Check if 'p' is probing a module. */
-	*probed_mod = __module_text_address((unsigned long) p->addr);
+	/* Get module refcount and reject __init functions for loaded modules. */
 	if (*probed_mod) {
 		/*
 		 * We must hold a refcount of the probed module while updating
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index e3ae93bbcb9b..09f8397bae15 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -106,6 +106,12 @@ static void s2idle_enter(void)
 	swait_event_exclusive(s2idle_wait_head,
 		    s2idle_state == S2IDLE_STATE_WAKE);
 
+	/*
+	 * Kick all CPUs to ensure that they resume their timers and restore
+	 * consistent system state.
+	 */
+	wake_up_all_idle_cpus();
+
 	cpus_read_unlock();
 
 	raw_spin_lock_irq(&s2idle_lock);
diff --git a/kernel/profile.c b/kernel/profile.c
index 8a77769bc4b4..2b775cc5c28f 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -344,49 +344,6 @@ void profile_tick(int type)
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 
-static int prof_cpu_mask_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask));
-	return 0;
-}
-
-static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, prof_cpu_mask_proc_show, NULL);
-}
-
-static ssize_t prof_cpu_mask_proc_write(struct file *file,
-	const char __user *buffer, size_t count, loff_t *pos)
-{
-	cpumask_var_t new_value;
-	int err;
-
-	if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
-		return -ENOMEM;
-
-	err = cpumask_parse_user(buffer, count, new_value);
-	if (!err) {
-		cpumask_copy(prof_cpu_mask, new_value);
-		err = count;
-	}
-	free_cpumask_var(new_value);
-	return err;
-}
-
-static const struct proc_ops prof_cpu_mask_proc_ops = {
-	.proc_open	= prof_cpu_mask_proc_open,
-	.proc_read	= seq_read,
-	.proc_lseek	= seq_lseek,
-	.proc_release	= single_release,
-	.proc_write	= prof_cpu_mask_proc_write,
-};
-
-void create_prof_cpu_mask(void)
-{
-	/* create /proc/irq/prof_cpu_mask */
-	proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops);
-}
-
 /*
  * This function accesses profiling information. The returned data is
  * binary: the sampling step and the actual contents of the profile
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 03be0d1330a6..c62805dbd608 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -696,15 +696,21 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
  *
  * XXX could add max_slice to the augmented data to track this.
  */
-static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static s64 entity_lag(u64 avruntime, struct sched_entity *se)
 {
-	s64 lag, limit;
+	s64 vlag, limit;
+
+	vlag = avruntime - se->vruntime;
+	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
 
+	return clamp(vlag, -limit, limit);
+}
+
+static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
 	SCHED_WARN_ON(!se->on_rq);
-	lag = avg_vruntime(cfs_rq) - se->vruntime;
 
-	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
-	se->vlag = clamp(lag, -limit, limit);
+	se->vlag = entity_lag(avg_vruntime(cfs_rq), se);
 }
 
 /*
@@ -3676,11 +3682,10 @@ static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 #endif
 
-static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se,
+static void reweight_eevdf(struct sched_entity *se, u64 avruntime,
 			   unsigned long weight)
 {
 	unsigned long old_weight = se->load.weight;
-	u64 avruntime = avg_vruntime(cfs_rq);
 	s64 vlag, vslice;
 
 	/*
@@ -3761,7 +3766,7 @@ static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	 *	   = V  - vl'
 	 */
 	if (avruntime != se->vruntime) {
-		vlag = (s64)(avruntime - se->vruntime);
+		vlag = entity_lag(avruntime, se);
 		vlag = div_s64(vlag * old_weight, weight);
 		se->vruntime = avruntime - vlag;
 	}
@@ -3787,25 +3792,26 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
 	bool curr = cfs_rq->curr == se;
+	u64 avruntime;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
-		if (curr)
-			update_curr(cfs_rq);
-		else
+		update_curr(cfs_rq);
+		avruntime = avg_vruntime(cfs_rq);
+		if (!curr)
 			__dequeue_entity(cfs_rq, se);
 		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	if (!se->on_rq) {
+	if (se->on_rq) {
+		reweight_eevdf(se, avruntime, weight);
+	} else {
 		/*
 		 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
 		 * we need to scale se->vlag when w_i changes.
 		 */
 		se->vlag = div_s64(se->vlag * se->load.weight, weight);
-	} else {
-		reweight_eevdf(cfs_rq, se, weight);
 	}
 
 	update_load_set(&se->load, weight);
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 373d42c707bc..5891e715f00d 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -46,7 +46,16 @@ int housekeeping_any_cpu(enum hk_type type)
 			if (cpu < nr_cpu_ids)
 				return cpu;
 
-			return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+			cpu = cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+			if (likely(cpu < nr_cpu_ids))
+				return cpu;
+			/*
+			 * Unless we have another problem this can only happen
+			 * at boot time before start_secondary() brings the 1st
+			 * housekeeping CPU up.
+			 */
+			WARN_ON_ONCE(system_state == SYSTEM_RUNNING ||
+				     type != HK_TYPE_TIMER);
 		}
 	}
 	return smp_processor_id();
@@ -109,6 +118,7 @@ static void __init housekeeping_setup_type(enum hk_type type,
 static int __init housekeeping_setup(char *str, unsigned long flags)
 {
 	cpumask_var_t non_housekeeping_mask, housekeeping_staging;
+	unsigned int first_cpu;
 	int err = 0;
 
 	if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) {
@@ -129,7 +139,8 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
 	cpumask_andnot(housekeeping_staging,
 		       cpu_possible_mask, non_housekeeping_mask);
 
-	if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) {
+	first_cpu = cpumask_first_and(cpu_present_mask, housekeeping_staging);
+	if (first_cpu >= nr_cpu_ids || first_cpu >= setup_max_cpus) {
 		__cpumask_set_cpu(smp_processor_id(), housekeeping_staging);
 		__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
 		if (!housekeeping.flags) {
@@ -138,6 +149,9 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
 		}
 	}
 
+	if (cpumask_empty(non_housekeeping_mask))
+		goto free_housekeeping_staging;
+
 	if (!housekeeping.flags) {
 		/* First setup call ("nohz_full=" or "isolcpus=") */
 		enum hk_type type;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d2242679239e..ae50f212775e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -79,6 +79,8 @@
 # include <asm/paravirt_api_clock.h>
 #endif
 
+#include <asm/barrier.h>
+
 #include "cpupri.h"
 #include "cpudeadline.h"
 
@@ -3445,13 +3447,19 @@ static inline void switch_mm_cid(struct rq *rq,
 		 * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
 		 * Provide it here.
 		 */
-		if (!prev->mm)                          // from kernel
+		if (!prev->mm) {                        // from kernel
 			smp_mb();
-		/*
-		 * user -> user transition guarantees a memory barrier through
-		 * switch_mm() when current->mm changes. If current->mm is
-		 * unchanged, no barrier is needed.
-		 */
+		} else {				// from user
+			/*
+			 * user->user transition relies on an implicit
+			 * memory barrier in switch_mm() when
+			 * current->mm changes. If the architecture
+			 * switch_mm() does not have an implicit memory
+			 * barrier, it is emitted here.  If current->mm
+			 * is unchanged, no barrier is needed.
+			 */
+			smp_mb__after_switch_mm();
+		}
 	}
 	if (prev->mm_cid_active) {
 		mm_cid_snapshot_time(rq, prev->mm);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b315b21fb28c..02582017759a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -508,7 +508,7 @@ static inline bool lockdep_softirq_start(void) { return false; }
 static inline void lockdep_softirq_end(bool in_hardirq) { }
 #endif
 
-asmlinkage __visible void __softirq_entry __do_softirq(void)
+static void handle_softirqs(bool ksirqd)
 {
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
 	unsigned long old_flags = current->flags;
@@ -563,8 +563,7 @@ restart:
 		pending >>= softirq_bit;
 	}
 
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
-	    __this_cpu_read(ksoftirqd) == current)
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && ksirqd)
 		rcu_softirq_qs();
 
 	local_irq_disable();
@@ -584,6 +583,11 @@ restart:
 	current_restore_flags(old_flags, PF_MEMALLOC);
 }
 
+asmlinkage __visible void __softirq_entry __do_softirq(void)
+{
+	handle_softirqs(false);
+}
+
 /**
  * irq_enter_rcu - Enter an interrupt context with RCU watching
  */
@@ -921,7 +925,7 @@ static void run_ksoftirqd(unsigned int cpu)
 		 * We can safely run softirq on inline stack, as we are not deep
 		 * in the task stack here.
 		 */
-		__do_softirq();
+		handle_softirqs(true);
 		ksoftirqd_run_end();
 		cond_resched();
 		return;
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index fb0fdec8719a..d88b13076b79 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -7,6 +7,7 @@
  * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
  * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
  */
+#include <linux/compiler.h>
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/hrtimer.h>
@@ -84,7 +85,7 @@ int tick_is_oneshot_available(void)
  */
 static void tick_periodic(int cpu)
 {
-	if (tick_do_timer_cpu == cpu) {
+	if (READ_ONCE(tick_do_timer_cpu) == cpu) {
 		raw_spin_lock(&jiffies_lock);
 		write_seqcount_begin(&jiffies_seq);
 
@@ -215,8 +216,8 @@ static void tick_setup_device(struct tick_device *td,
 		 * If no cpu took the do_timer update, assign it to
 		 * this cpu:
 		 */
-		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
-			tick_do_timer_cpu = cpu;
+		if (READ_ONCE(tick_do_timer_cpu) == TICK_DO_TIMER_BOOT) {
+			WRITE_ONCE(tick_do_timer_cpu, cpu);
 			tick_next_period = ktime_get();
 #ifdef CONFIG_NO_HZ_FULL
 			/*
@@ -232,7 +233,7 @@ static void tick_setup_device(struct tick_device *td,
 						!tick_nohz_full_cpu(cpu)) {
 			tick_take_do_timer_from_boot();
 			tick_do_timer_boot_cpu = -1;
-			WARN_ON(tick_do_timer_cpu != cpu);
+			WARN_ON(READ_ONCE(tick_do_timer_cpu) != cpu);
 #endif
 		}
 
@@ -406,10 +407,10 @@ void tick_assert_timekeeping_handover(void)
 int tick_cpu_dying(unsigned int dying_cpu)
 {
 	/*
-	 * If the current CPU is the timekeeper, it's the only one that
-	 * can safely hand over its duty. Also all online CPUs are in
-	 * stop machine, guaranteed not to be idle, therefore it's safe
-	 * to pick any online successor.
+	 * If the current CPU is the timekeeper, it's the only one that can
+	 * safely hand over its duty. Also all online CPUs are in stop
+	 * machine, guaranteed not to be idle, therefore there is no
+	 * concurrency and it's safe to pick any online successor.
 	 */
 	if (tick_do_timer_cpu == dying_cpu)
 		tick_do_timer_cpu = cpumask_first(cpu_online_mask);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1331216a9cae..71a792cd8936 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -8,6 +8,7 @@
  *
  *  Started by: Thomas Gleixner and Ingo Molnar
  */
+#include <linux/compiler.h>
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/hrtimer.h>
@@ -204,7 +205,7 @@ static inline void tick_sched_flag_clear(struct tick_sched *ts,
 
 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 {
-	int cpu = smp_processor_id();
+	int tick_cpu, cpu = smp_processor_id();
 
 	/*
 	 * Check if the do_timer duty was dropped. We don't care about
@@ -216,16 +217,18 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 	 * If nohz_full is enabled, this should not happen because the
 	 * 'tick_do_timer_cpu' CPU never relinquishes.
 	 */
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) &&
-	    unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
+	tick_cpu = READ_ONCE(tick_do_timer_cpu);
+
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) {
 #ifdef CONFIG_NO_HZ_FULL
 		WARN_ON_ONCE(tick_nohz_full_running);
 #endif
-		tick_do_timer_cpu = cpu;
+		WRITE_ONCE(tick_do_timer_cpu, cpu);
+		tick_cpu = cpu;
 	}
 
 	/* Check if jiffies need an update */
-	if (tick_do_timer_cpu == cpu)
+	if (tick_cpu == cpu)
 		tick_do_update_jiffies64(now);
 
 	/*
@@ -610,7 +613,7 @@ bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
 	 * timers, workqueues, timekeeping, ...) on behalf of full dynticks
 	 * CPUs. It must remain online when nohz full is enabled.
 	 */
-	if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
+	if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu)
 		return false;
 	return true;
 }
@@ -891,6 +894,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 {
 	u64 basemono, next_tick, delta, expires;
 	unsigned long basejiff;
+	int tick_cpu;
 
 	basemono = get_jiffies_update(&basejiff);
 	ts->last_jiffies = basejiff;
@@ -947,9 +951,9 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 	 * Otherwise we can sleep as long as we want.
 	 */
 	delta = timekeeping_max_deferment();
-	if (cpu != tick_do_timer_cpu &&
-	    (tick_do_timer_cpu != TICK_DO_TIMER_NONE ||
-	     !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST)))
+	tick_cpu = READ_ONCE(tick_do_timer_cpu);
+	if (tick_cpu != cpu &&
+	    (tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST)))
 		delta = KTIME_MAX;
 
 	/* Calculate the next expiry time */
@@ -970,6 +974,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	unsigned long basejiff = ts->last_jiffies;
 	u64 basemono = ts->timer_expires_base;
 	bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
+	int tick_cpu;
 	u64 expires;
 
 	/* Make sure we won't be trying to stop it twice in a row. */
@@ -1007,10 +1012,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	 * do_timer() never gets invoked. Keep track of the fact that it
 	 * was the one which had the do_timer() duty last.
 	 */
-	if (cpu == tick_do_timer_cpu) {
-		tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+	tick_cpu = READ_ONCE(tick_do_timer_cpu);
+	if (tick_cpu == cpu) {
+		WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE);
 		tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST);
-	} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+	} else if (tick_cpu != TICK_DO_TIMER_NONE) {
 		tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST);
 	}
 
@@ -1173,15 +1179,17 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		return false;
 
 	if (tick_nohz_full_enabled()) {
+		int tick_cpu = READ_ONCE(tick_do_timer_cpu);
+
 		/*
 		 * Keep the tick alive to guarantee timekeeping progression
 		 * if there are full dynticks CPUs around
 		 */
-		if (tick_do_timer_cpu == cpu)
+		if (tick_cpu == cpu)
 			return false;
 
 		/* Should not happen for nohz-full */
-		if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
+		if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE))
 			return false;
 	}
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61c541c36596..47345bf1d4a9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -965,7 +965,7 @@ config FTRACE_RECORD_RECURSION
 
 config FTRACE_RECORD_RECURSION_SIZE
 	int "Max number of recursed functions to record"
-	default	128
+	default 128
 	depends on FTRACE_RECORD_RECURSION
 	help
 	  This defines the limit of number of functions that can be
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 25476ead681b..6511dc3a00da 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1393,7 +1393,6 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 	old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
 	old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
 
-	local_inc(&cpu_buffer->pages_touched);
 	/*
 	 * Just make sure we have seen our old_write and synchronize
 	 * with any interrupts that come in.
@@ -1430,8 +1429,9 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 		 */
 		local_set(&next_page->page->commit, 0);
 
-		/* Again, either we update tail_page or an interrupt does */
-		(void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page);
+		/* Either we update tail_page or an interrupt does */
+		if (try_cmpxchg(&cpu_buffer->tail_page, &tail_page, next_page))
+			local_inc(&cpu_buffer->pages_touched);
 	}
 }
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7c364b87352e..6ef29eba90ce 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1670,6 +1670,7 @@ static int trace_format_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
+#ifdef CONFIG_PERF_EVENTS
 static ssize_t
 event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 {
@@ -1684,6 +1685,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
 }
+#endif
 
 static ssize_t
 event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
@@ -2152,10 +2154,12 @@ static const struct file_operations ftrace_event_format_fops = {
 	.release = seq_release,
 };
 
+#ifdef CONFIG_PERF_EVENTS
 static const struct file_operations ftrace_event_id_fops = {
 	.read = event_id_read,
 	.llseek = default_llseek,
 };
+#endif
 
 static const struct file_operations ftrace_event_filter_fops = {
 	.open = tracing_open_file_tr,
@@ -2548,6 +2552,14 @@ static int event_callback(const char *name, umode_t *mode, void **data,
 	return 0;
 }
 
+/* The file is incremented on creation and freeing the enable file decrements it */
+static void event_release(const char *name, void *data)
+{
+	struct trace_event_file *file = data;
+
+	event_file_put(file);
+}
+
 static int
 event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file)
 {
@@ -2562,6 +2574,7 @@ event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file)
 		{
 			.name		= "enable",
 			.callback	= event_callback,
+			.release	= event_release,
 		},
 		{
 			.name		= "filter",
@@ -2630,6 +2643,9 @@ event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file)
 		return ret;
 	}
 
+	/* Gets decremented on freeing of the "enable" file */
+	event_file_get(file);
+
 	return 0;
 }
 
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index dfe3ee6035ec..42bc0f362226 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1466,7 +1466,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 		parg->fmt = kmalloc(len, GFP_KERNEL);
 		if (!parg->fmt) {
 			ret = -ENOMEM;
-			goto out;
+			goto fail;
 		}
 		snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
 			 parg->count);
diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c
index f95516cd45bb..23c125c2e243 100644
--- a/kernel/vmcore_info.c
+++ b/kernel/vmcore_info.c
@@ -205,11 +205,10 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_NUMBER(PG_head_mask);
 #define PAGE_BUDDY_MAPCOUNT_VALUE	(~PG_buddy)
 	VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
-#ifdef CONFIG_HUGETLB_PAGE
-	VMCOREINFO_NUMBER(PG_hugetlb);
+#define PAGE_HUGETLB_MAPCOUNT_VALUE	(~PG_hugetlb)
+	VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE);
 #define PAGE_OFFLINE_MAPCOUNT_VALUE	(~PG_offline)
 	VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE);
-#endif
 
 #ifdef CONFIG_KALLSYMS
 	VMCOREINFO_SYMBOL(kallsyms_names);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0066c8f6c154..d2dbe099286b 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1277,8 +1277,12 @@ static bool kick_pool(struct worker_pool *pool)
 	    !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) {
 		struct work_struct *work = list_first_entry(&pool->worklist,
 						struct work_struct, entry);
-		p->wake_cpu = cpumask_any_distribute(pool->attrs->__pod_cpumask);
-		get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++;
+		int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask,
+							  cpu_online_mask);
+		if (wake_cpu < nr_cpu_ids) {
+			p->wake_cpu = wake_cpu;
+			get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++;
+		}
 	}
 #endif
 	wake_up_process(p);
@@ -1594,6 +1598,15 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu)
 	if (off_cpu >= 0)
 		total_cpus--;
 
+	/* If all CPUs of the wq get offline, use the default values */
+	if (unlikely(!total_cpus)) {
+		for_each_node(node)
+			wq_node_nr_active(wq, node)->max = min_active;
+
+		wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active;
+		return;
+	}
+
 	for_each_node(node) {
 		int node_cpus;
 
@@ -1606,7 +1619,7 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu)
 			      min_active, max_active);
 	}
 
-	wq_node_nr_active(wq, NUMA_NO_NODE)->max = min_active;
+	wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active;
 }
 
 /**