20 files changed, 199 insertions, 111 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 8191a7db2777..66088a9e9b9e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -890,7 +890,8 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
 
 static int bpf_jit_blind_insn(const struct bpf_insn *from,
 			      const struct bpf_insn *aux,
-			      struct bpf_insn *to_buff)
+			      struct bpf_insn *to_buff,
+			      bool emit_zext)
 {
 	struct bpf_insn *to = to_buff;
 	u32 imm_rnd = get_random_int();
@@ -1005,6 +1006,8 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
 	case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */
 		*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm);
 		*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		if (emit_zext)
+			*to++ = BPF_ZEXT_REG(BPF_REG_AX);
 		*to++ = BPF_ALU64_REG(BPF_OR,  aux[0].dst_reg, BPF_REG_AX);
 		break;
 
@@ -1088,7 +1091,8 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
 		    insn[1].code == 0)
 			memcpy(aux, insn, sizeof(aux));
 
-		rewritten = bpf_jit_blind_insn(insn, aux, insn_buff);
+		rewritten = bpf_jit_blind_insn(insn, aux, insn_buff,
+						clone->aux->verifier_zext);
 		if (!rewritten)
 			continue;
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5d141f16f6fa..272071e9112f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1707,20 +1707,26 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	if (err)
 		goto free_used_maps;
 
-	err = bpf_prog_new_fd(prog);
-	if (err < 0) {
-		/* failed to allocate fd.
-		 * bpf_prog_put() is needed because the above
-		 * bpf_prog_alloc_id() has published the prog
-		 * to the userspace and the userspace may
-		 * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID.
-		 */
-		bpf_prog_put(prog);
-		return err;
-	}
-
+	/* Upon success of bpf_prog_alloc_id(), the BPF prog is
+	 * effectively publicly exposed. However, retrieving via
+	 * bpf_prog_get_fd_by_id() will take another reference,
+	 * therefore it cannot be gone underneath us.
+	 *
+	 * Only for the time /after/ successful bpf_prog_new_fd()
+	 * and before returning to userspace, we might just hold
+	 * one reference and any parallel close on that fd could
+	 * rip everything out. Hence, below notifications must
+	 * happen before bpf_prog_new_fd().
+	 *
+	 * Also, any failure handling from this point onwards must
+	 * be using bpf_prog_put() given the program is exposed.
+	 */
 	bpf_prog_kallsyms_add(prog);
 	perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0);
+
+	err = bpf_prog_new_fd(prog);
+	if (err < 0)
+		bpf_prog_put(prog);
 	return err;
 
 free_used_maps:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c84d83f86141..b5c14c9d7b98 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -985,9 +985,6 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg)
 	reg->smax_value = S64_MAX;
 	reg->umin_value = 0;
 	reg->umax_value = U64_MAX;
-
-	/* constant backtracking is enabled for root only for now */
-	reg->precise = capable(CAP_SYS_ADMIN) ? false : true;
 }
 
 /* Mark a register as having a completely unknown (scalar) value. */
@@ -1014,7 +1011,11 @@ static void mark_reg_unknown(struct bpf_verifier_env *env,
 			__mark_reg_not_init(regs + regno);
 		return;
 	}
-	__mark_reg_unknown(regs + regno);
+	regs += regno;
+	__mark_reg_unknown(regs);
+	/* constant backtracking is enabled for root without bpf2bpf calls */
+	regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
+			true : false;
 }
 
 static void __mark_reg_not_init(struct bpf_reg_state *reg)
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 2bd410f934b3..69cfb4345388 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -230,9 +230,7 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
  */
 struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 {
-	int node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
-	size_t count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	size_t align = get_order(PAGE_ALIGN(size));
+	size_t count = size >> PAGE_SHIFT;
 	struct page *page = NULL;
 	struct cma *cma = NULL;
 
@@ -243,14 +241,12 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 
 	/* CMA can be used only in the context which permits sleeping */
 	if (cma && gfpflags_allow_blocking(gfp)) {
+		size_t align = get_order(size);
 		size_t cma_align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
 
 		page = cma_alloc(cma, count, cma_align, gfp & __GFP_NOWARN);
 	}
 
-	/* Fallback allocation of normal pages */
-	if (!page)
-		page = alloc_pages_node(node, gfp, align);
 	return page;
 }
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 795c9b095d75..8402b29c280f 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -85,6 +85,8 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
+	size_t alloc_size = PAGE_ALIGN(size);
+	int node = dev_to_node(dev);
 	struct page *page = NULL;
 	u64 phys_mask;
 
@@ -95,8 +97,14 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	gfp &= ~__GFP_ZERO;
 	gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
 			&phys_mask);
+	page = dma_alloc_contiguous(dev, alloc_size, gfp);
+	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+		dma_free_contiguous(dev, page, alloc_size);
+		page = NULL;
+	}
 again:
-	page = dma_alloc_contiguous(dev, size, gfp);
+	if (!page)
+		page = alloc_pages_node(node, gfp, get_order(alloc_size));
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
 		dma_free_contiguous(dev, page, size);
 		page = NULL;
@@ -297,7 +305,7 @@ void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
 
 	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
 }
 EXPORT_SYMBOL(dma_direct_unmap_page);
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 9de232229063..796a44f8ef5a 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -444,7 +444,9 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 				   dma_addr_t tbl_dma_addr,
-				   phys_addr_t orig_addr, size_t size,
+				   phys_addr_t orig_addr,
+				   size_t mapping_size,
+				   size_t alloc_size,
 				   enum dma_data_direction dir,
 				   unsigned long attrs)
 {
@@ -464,6 +466,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 		pr_warn_once("%s is active and system is using DMA bounce buffers\n",
 			     sme_active() ? "SME" : "SEV");
 
+	if (mapping_size > alloc_size) {
+		dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+			      mapping_size, alloc_size);
+		return (phys_addr_t)DMA_MAPPING_ERROR;
+	}
+
 	mask = dma_get_seg_boundary(hwdev);
 
 	tbl_dma_addr &= mask;
@@ -471,8 +479,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 
 	/*
- 	 * Carefully handle integer overflow which can occur when mask == ~0UL.
- 	 */
+	 * Carefully handle integer overflow which can occur when mask == ~0UL.
+	 */
 	max_slots = mask + 1
 		    ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
 		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
@@ -481,8 +489,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	 * For mappings greater than or equal to a page, we limit the stride
 	 * (and hence alignment) to a page size.
 	 */
-	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	if (size >= PAGE_SIZE)
+	nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	if (alloc_size >= PAGE_SIZE)
 		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
 	else
 		stride = 1;
@@ -547,7 +555,7 @@ not_found:
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 	if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
 		dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
-			 size, io_tlb_nslabs, tmp_io_tlb_used);
+			 alloc_size, io_tlb_nslabs, tmp_io_tlb_used);
 	return (phys_addr_t)DMA_MAPPING_ERROR;
 found:
 	io_tlb_used += nslots;
@@ -562,7 +570,7 @@ found:
 		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+		swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
 
 	return tlb_addr;
 }
@@ -571,11 +579,11 @@ found:
  * tlb_addr is the physical address of the bounce buffer to unmap.
  */
 void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
-			      size_t size, enum dma_data_direction dir,
-			      unsigned long attrs)
+			      size_t mapping_size, size_t alloc_size,
+			      enum dma_data_direction dir, unsigned long attrs)
 {
 	unsigned long flags;
-	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	phys_addr_t orig_addr = io_tlb_orig_addr[index];
 
@@ -585,7 +593,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	if (orig_addr != INVALID_PHYS_ADDR &&
 	    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
-		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+		swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_FROM_DEVICE);
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -665,14 +673,14 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
 
 	/* Oh well, have to allocate and map a bounce buffer. */
 	*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
-			*phys, size, dir, attrs);
+			*phys, size, size, dir, attrs);
 	if (*phys == (phys_addr_t)DMA_MAPPING_ERROR)
 		return false;
 
 	/* Ensure that the address returned is DMA'ble */
 	*dma_addr = __phys_to_dma(dev, *phys);
 	if (unlikely(!dma_capable(dev, *dma_addr, size))) {
-		swiotlb_tbl_unmap_single(dev, *phys, size, dir,
+		swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
 		return false;
 	}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 9484e88dabc2..9be995fc3c5a 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -295,6 +295,18 @@ static void irq_sysfs_add(int irq, struct irq_desc *desc)
 	}
 }
 
+static void irq_sysfs_del(struct irq_desc *desc)
+{
+	/*
+	 * If irq_sysfs_init() has not yet been invoked (early boot), then
+	 * irq_kobj_base is NULL and the descriptor was never added.
+	 * kobject_del() complains about a object with no parent, so make
+	 * it conditional.
+	 */
+	if (irq_kobj_base)
+		kobject_del(&desc->kobj);
+}
+
 static int __init irq_sysfs_init(void)
 {
 	struct irq_desc *desc;
@@ -325,6 +337,7 @@ static struct kobj_type irq_kobj_type = {
 };
 
 static void irq_sysfs_add(int irq, struct irq_desc *desc) {}
+static void irq_sysfs_del(struct irq_desc *desc) {}
 
 #endif /* CONFIG_SYSFS */
 
@@ -438,7 +451,7 @@ static void free_desc(unsigned int irq)
 	 * The sysfs entry must be serialized against a concurrent
 	 * irq_sysfs_init() as well.
 	 */
-	kobject_del(&desc->kobj);
+	irq_sysfs_del(desc);
 	delete_irq_desc(irq);
 
 	/*
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 95a260f9214b..136ce049c4ad 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -263,8 +263,10 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
 {
 	char namebuf[KSYM_NAME_LEN];
 
-	if (is_ksym_addr(addr))
-		return !!get_symbol_pos(addr, symbolsize, offset);
+	if (is_ksym_addr(addr)) {
+		get_symbol_pos(addr, symbolsize, offset);
+		return 1;
+	}
 	return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf) ||
 	       !!__bpf_address_lookup(addr, symbolsize, offset, namebuf);
 }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9873fc627d61..d9770a5393c8 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -470,6 +470,7 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
  */
 static void do_optimize_kprobes(void)
 {
+	lockdep_assert_held(&text_mutex);
 	/*
 	 * The optimization/unoptimization refers online_cpus via
 	 * stop_machine() and cpu-hotplug modifies online_cpus.
@@ -487,9 +488,7 @@ static void do_optimize_kprobes(void)
 	    list_empty(&optimizing_list))
 		return;
 
-	mutex_lock(&text_mutex);
 	arch_optimize_kprobes(&optimizing_list);
-	mutex_unlock(&text_mutex);
 }
 
 /*
@@ -500,6 +499,7 @@ static void do_unoptimize_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
+	lockdep_assert_held(&text_mutex);
 	/* See comment in do_optimize_kprobes() */
 	lockdep_assert_cpus_held();
 
@@ -507,7 +507,6 @@ static void do_unoptimize_kprobes(void)
 	if (list_empty(&unoptimizing_list))
 		return;
 
-	mutex_lock(&text_mutex);
 	arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
 	/* Loop free_list for disarming */
 	list_for_each_entry_safe(op, tmp, &freeing_list, list) {
@@ -524,7 +523,6 @@ static void do_unoptimize_kprobes(void)
 		} else
 			list_del_init(&op->list);
 	}
-	mutex_unlock(&text_mutex);
 }
 
 /* Reclaim all kprobes on the free_list */
@@ -556,6 +554,7 @@ static void kprobe_optimizer(struct work_struct *work)
 {
 	mutex_lock(&kprobe_mutex);
 	cpus_read_lock();
+	mutex_lock(&text_mutex);
 	/* Lock modules while optimizing kprobes */
 	mutex_lock(&module_mutex);
 
@@ -583,6 +582,7 @@ static void kprobe_optimizer(struct work_struct *work)
 	do_free_cleaned_kprobes();
 
 	mutex_unlock(&module_mutex);
+	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
 	mutex_unlock(&kprobe_mutex);
 
diff --git a/kernel/module.c b/kernel/module.c
index 5933395af9a0..9ee93421269c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -65,9 +65,9 @@
 /*
  * Modules' sections will be aligned on page boundaries
  * to ensure complete separation of code and data, but
- * only when CONFIG_STRICT_MODULE_RWX=y
+ * only when CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y
  */
-#ifdef CONFIG_STRICT_MODULE_RWX
+#ifdef CONFIG_ARCH_HAS_STRICT_MODULE_RWX
 # define debug_align(X) ALIGN(X, PAGE_SIZE)
 #else
 # define debug_align(X) (X)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2b037f195473..df9f1fe5689b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3904,7 +3904,7 @@ void __noreturn do_task_dead(void)
 
 static inline void sched_submit_work(struct task_struct *tsk)
 {
-	if (!tsk->state || tsk_is_pi_blocked(tsk))
+	if (!tsk->state)
 		return;
 
 	/*
@@ -3920,6 +3920,9 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		preempt_enable_no_resched();
 	}
 
+	if (tsk_is_pi_blocked(tsk))
+		return;
+
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
 	 * make sure to submit it to avoid deadlocks.
@@ -5102,37 +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;
-
-		addr = (void *)attr + usize;
-		end  = (void *)attr + sizeof(*attr);
+	kattr->size = min(usize, ksize);
 
-		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;
@@ -5142,20 +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();
@@ -5168,25 +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();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bc9cfeaac8bd..500f5db0de0b 100644
--- a/kernel/sched/fair.c
+++ b/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;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 23fbbcc414d5..6e52b67b420e 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1131,7 +1131,15 @@ static void psi_trigger_destroy(struct kref *ref)
 	 * deadlock while waiting for psi_poll_work to acquire trigger_lock
 	 */
 	if (kworker_to_destroy) {
+		/*
+		 * After the RCU grace period has expired, the worker
+		 * can no longer be found through group->poll_kworker.
+		 * But it might have been already scheduled before
+		 * that - deschedule it cleanly before destroying it.
+		 */
 		kthread_cancel_delayed_work_sync(&group->poll_work);
+		atomic_set(&group->poll_scheduled, 0);
+
 		kthread_destroy_worker(kworker_to_destroy);
 	}
 	kfree(t);
diff --git a/kernel/signal.c b/kernel/signal.c
index e667be6907d7..534fec266a33 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -90,6 +90,11 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force)
 	    handler == SIG_DFL && !(force && sig_kernel_only(sig)))
 		return true;
 
+	/* Only allow kernel generated signals to this kthread */
+	if (unlikely((t->flags & PF_KTHREAD) &&
+		     (handler == SIG_KTHREAD_KERNEL) && !force))
+		return true;
+
 	return sig_handler_ignored(handler, sig);
 }
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d911c8470149..ca69290bee2a 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -146,6 +146,11 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
 static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 {
 	tk->offs_boot = ktime_add(tk->offs_boot, delta);
+	/*
+	 * Timespec representation for VDSO update to avoid 64bit division
+	 * on every update.
+	 */
+	tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot);
 }
 
 /*
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 8cf3596a4ce6..4bc37ac3bb05 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -17,7 +17,7 @@ static inline void update_vdso_data(struct vdso_data *vdata,
 				    struct timekeeper *tk)
 {
 	struct vdso_timestamp *vdso_ts;
-	u64 nsec;
+	u64 nsec, sec;
 
 	vdata[CS_HRES_COARSE].cycle_last	= tk->tkr_mono.cycle_last;
 	vdata[CS_HRES_COARSE].mask		= tk->tkr_mono.mask;
@@ -45,23 +45,27 @@ static inline void update_vdso_data(struct vdso_data *vdata,
 	}
 	vdso_ts->nsec	= nsec;
 
-	/* CLOCK_MONOTONIC_RAW */
-	vdso_ts		= &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
-	vdso_ts->sec	= tk->raw_sec;
-	vdso_ts->nsec	= tk->tkr_raw.xtime_nsec;
+	/* Copy MONOTONIC time for BOOTTIME */
+	sec	= vdso_ts->sec;
+	/* Add the boot offset */
+	sec	+= tk->monotonic_to_boot.tv_sec;
+	nsec	+= (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift;
 
 	/* CLOCK_BOOTTIME */
 	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME];
-	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
-	nsec = tk->tkr_mono.xtime_nsec;
-	nsec += ((u64)(tk->wall_to_monotonic.tv_nsec +
-		       ktime_to_ns(tk->offs_boot)) << tk->tkr_mono.shift);
+	vdso_ts->sec	= sec;
+
 	while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
 		nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift);
 		vdso_ts->sec++;
 	}
 	vdso_ts->nsec	= nsec;
 
+	/* CLOCK_MONOTONIC_RAW */
+	vdso_ts		= &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
+	vdso_ts->sec	= tk->raw_sec;
+	vdso_ts->nsec	= tk->tkr_raw.xtime_nsec;
+
 	/* CLOCK_TAI */
 	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI];
 	vdso_ts->sec	= tk->xtime_sec + (s64)tk->tai_offset;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index eca34503f178..f9821a3374e9 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3095,6 +3095,14 @@ t_probe_next(struct seq_file *m, loff_t *pos)
 		hnd = &iter->probe_entry->hlist;
 
 	hash = iter->probe->ops.func_hash->filter_hash;
+
+	/*
+	 * A probe being registered may temporarily have an empty hash
+	 * and it's at the end of the func_probes list.
+	 */
+	if (!hash || hash == EMPTY_HASH)
+		return NULL;
+
 	size = 1 << hash->size_bits;
 
  retry:
@@ -4320,12 +4328,21 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr,
 
 	mutex_unlock(&ftrace_lock);
 
+	/*
+	 * Note, there's a small window here that the func_hash->filter_hash
+	 * may be NULL or empty. Need to be carefule when reading the loop.
+	 */
 	mutex_lock(&probe->ops.func_hash->regex_lock);
 
 	orig_hash = &probe->ops.func_hash->filter_hash;
 	old_hash = *orig_hash;
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
 
+	if (!hash) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	ret = ftrace_match_records(hash, glob, strlen(glob));
 
 	/* Nothing found? */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 525a97fbbc60..563e80f9006a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1567,9 +1567,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu,
 
 /**
  * update_max_tr_single - only copy one trace over, and reset the rest
- * @tr - tracer
- * @tsk - task with the latency
- * @cpu - the cpu of the buffer to copy.
+ * @tr: tracer
+ * @tsk: task with the latency
+ * @cpu: the cpu of the buffer to copy.
  *
  * Flip the trace of a single CPU buffer between the @tr and the max_tr.
  */
@@ -1767,7 +1767,7 @@ static void __init apply_trace_boot_options(void);
 
 /**
  * register_tracer - register a tracer with the ftrace system.
- * @type - the plugin for the tracer
+ * @type: the plugin for the tracer
  *
  * Register a new plugin tracer.
  */
@@ -2230,9 +2230,9 @@ static bool tracing_record_taskinfo_skip(int flags)
 /**
  * tracing_record_taskinfo - record the task info of a task
  *
- * @task  - task to record
- * @flags - TRACE_RECORD_CMDLINE for recording comm
- *        - TRACE_RECORD_TGID for recording tgid
+ * @task:  task to record
+ * @flags: TRACE_RECORD_CMDLINE for recording comm
+ *         TRACE_RECORD_TGID for recording tgid
  */
 void tracing_record_taskinfo(struct task_struct *task, int flags)
 {
@@ -2258,10 +2258,10 @@ void tracing_record_taskinfo(struct task_struct *task, int flags)
 /**
  * tracing_record_taskinfo_sched_switch - record task info for sched_switch
  *
- * @prev - previous task during sched_switch
- * @next - next task during sched_switch
- * @flags - TRACE_RECORD_CMDLINE for recording comm
- *          TRACE_RECORD_TGID for recording tgid
+ * @prev: previous task during sched_switch
+ * @next: next task during sched_switch
+ * @flags: TRACE_RECORD_CMDLINE for recording comm
+ *         TRACE_RECORD_TGID for recording tgid
  */
 void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
 					  struct task_struct *next, int flags)
@@ -3072,7 +3072,9 @@ static void trace_printk_start_stop_comm(int enabled)
 
 /**
  * trace_vbprintk - write binary msg to tracing buffer
- *
+ * @ip:    The address of the caller
+ * @fmt:   The string format to write to the buffer
+ * @args:  Arguments for @fmt
  */
 int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 {
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c7506bc81b75..648930823b57 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -787,7 +787,7 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
 	return ret;
 }
 
-static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
+int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
 {
 	char *event = NULL, *sub = NULL, *match;
 	int ret;
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index dbef0d135075..fb6bfbc5bf86 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -895,7 +895,8 @@ void trace_probe_cleanup(struct trace_probe *tp)
 	for (i = 0; i < tp->nr_args; i++)
 		traceprobe_free_probe_arg(&tp->args[i]);
 
-	kfree(call->class->system);
+	if (call->class)
+		kfree(call->class->system);
 	kfree(call->name);
 	kfree(call->print_fmt);
 }