Merge tag 'mm-nonmm-stable-2025-08-03-12-47' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-MM updates from Andrew Morton:
 "Significant patch series in this pull request:

   - "squashfs: Remove page->mapping references" (Matthew Wilcox) gets
     us closer to being able to remove page->mapping

   - "relayfs: misc changes" (Jason Xing) does some maintenance and
     minor feature addition work in relayfs

   - "kdump: crashkernel reservation from CMA" (Jiri Bohac) switches
     us from static preallocation of the kdump crashkernel's working
     memory over to dynamic allocation. So the difficulty of a-priori
     estimation of the second kernel's needs is removed and the first
     kernel obtains extra memory

   - "generalize panic_print's dump function to be used by other
     kernel parts" (Feng Tang) implements some consolidation and
     rationalization of the various ways in which a failing kernel
     splats information at the operator

* tag 'mm-nonmm-stable-2025-08-03-12-47' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (80 commits)
  tools/getdelays: add backward compatibility for taskstats version
  kho: add test for kexec handover
  delaytop: enhance error logging and add PSI feature description
  samples: Kconfig: fix spelling mistake "instancess" -> "instances"
  fat: fix too many log in fat_chain_add()
  scripts/spelling.txt: add notifer||notifier to spelling.txt
  xen/xenbus: fix typo "notifer"
  net: mvneta: fix typo "notifer"
  drm/xe: fix typo "notifer"
  cxl: mce: fix typo "notifer"
  KVM: x86: fix typo "notifer"
  MAINTAINERS: add maintainers for delaytop
  ucount: use atomic_long_try_cmpxchg() in atomic_long_inc_below()
  ucount: fix atomic_long_inc_below() argument type
  kexec: enable CMA based contiguous allocation
  stackdepot: make max number of pools boot-time configurable
  lib/xxhash: remove unused functions
  init/Kconfig: restore CONFIG_BROKEN help text
  lib/raid6: update recov_rvv.c zero page usage
  docs: update docs after introducing delaytop
  ...

17 files changed, 424 insertions, 171 deletions

diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 335b8425dd4b..a4ef79591eb2 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -21,6 +21,7 @@
 #include <linux/reboot.h>
 #include <linux/btf.h>
 #include <linux/objtool.h>
+#include <linux/delay.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -33,6 +34,11 @@
 /* Per cpu memory for storing cpu states in case of system crash. */
 note_buf_t __percpu *crash_notes;
 
+/* time to wait for possible DMA to finish before starting the kdump kernel
+ * when a CMA reservation is used
+ */
+#define CMA_DMA_TIMEOUT_SEC 10
+
 #ifdef CONFIG_CRASH_DUMP
 
 int kimage_crash_copy_vmcoreinfo(struct kimage *image)
@@ -97,6 +103,14 @@ int kexec_crash_loaded(void)
 }
 EXPORT_SYMBOL_GPL(kexec_crash_loaded);
 
+static void crash_cma_clear_pending_dma(void)
+{
+	if (!crashk_cma_cnt)
+		return;
+
+	mdelay(CMA_DMA_TIMEOUT_SEC * 1000);
+}
+
 /*
  * No panic_cpu check version of crash_kexec().  This function is called
  * only when panic_cpu holds the current CPU number; this is the only CPU
@@ -119,6 +133,7 @@ void __noclone __crash_kexec(struct pt_regs *regs)
 			crash_setup_regs(&fixed_regs, regs);
 			crash_save_vmcoreinfo();
 			machine_crash_shutdown(&fixed_regs);
+			crash_cma_clear_pending_dma();
 			machine_kexec(kexec_crash_image);
 		}
 		kexec_unlock();
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index acb6bf42e30d..87bf4d41eabb 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -14,6 +14,8 @@
 #include <linux/cpuhotplug.h>
 #include <linux/memblock.h>
 #include <linux/kmemleak.h>
+#include <linux/cma.h>
+#include <linux/crash_reserve.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -172,17 +174,19 @@ static int __init parse_crashkernel_simple(char *cmdline,
 
 #define SUFFIX_HIGH 0
 #define SUFFIX_LOW  1
-#define SUFFIX_NULL 2
+#define SUFFIX_CMA  2
+#define SUFFIX_NULL 3
 static __initdata char *suffix_tbl[] = {
 	[SUFFIX_HIGH] = ",high",
 	[SUFFIX_LOW]  = ",low",
+	[SUFFIX_CMA]  = ",cma",
 	[SUFFIX_NULL] = NULL,
 };
 
 /*
  * That function parses "suffix"  crashkernel command lines like
  *
- *	crashkernel=size,[high|low]
+ *	crashkernel=size,[high|low|cma]
  *
  * It returns 0 on success and -EINVAL on failure.
  */
@@ -298,9 +302,11 @@ int __init parse_crashkernel(char *cmdline,
 			     unsigned long long *crash_size,
 			     unsigned long long *crash_base,
 			     unsigned long long *low_size,
+			     unsigned long long *cma_size,
 			     bool *high)
 {
 	int ret;
+	unsigned long long __always_unused cma_base;
 
 	/* crashkernel=X[@offset] */
 	ret = __parse_crashkernel(cmdline, system_ram, crash_size,
@@ -331,6 +337,14 @@ int __init parse_crashkernel(char *cmdline,
 
 		*high = true;
 	}
+
+	/*
+	 * optional CMA reservation
+	 * cma_base is ignored
+	 */
+	if (cma_size)
+		__parse_crashkernel(cmdline, 0, cma_size,
+			&cma_base, suffix_tbl[SUFFIX_CMA]);
 #endif
 	if (!*crash_size)
 		ret = -EINVAL;
@@ -457,6 +471,56 @@ retry:
 #endif
 }
 
+struct range crashk_cma_ranges[CRASHKERNEL_CMA_RANGES_MAX];
+#ifdef CRASHKERNEL_CMA
+int crashk_cma_cnt;
+void __init reserve_crashkernel_cma(unsigned long long cma_size)
+{
+	unsigned long long request_size = roundup(cma_size, PAGE_SIZE);
+	unsigned long long reserved_size = 0;
+
+	if (!cma_size)
+		return;
+
+	while (cma_size > reserved_size &&
+	       crashk_cma_cnt < CRASHKERNEL_CMA_RANGES_MAX) {
+
+		struct cma *res;
+
+		if (cma_declare_contiguous(0, request_size, 0, 0, 0, false,
+				       "crashkernel", &res)) {
+			/* reservation failed, try half-sized blocks */
+			if (request_size <= PAGE_SIZE)
+				break;
+
+			request_size = roundup(request_size / 2, PAGE_SIZE);
+			continue;
+		}
+
+		crashk_cma_ranges[crashk_cma_cnt].start = cma_get_base(res);
+		crashk_cma_ranges[crashk_cma_cnt].end =
+			crashk_cma_ranges[crashk_cma_cnt].start +
+			cma_get_size(res) - 1;
+		++crashk_cma_cnt;
+		reserved_size += request_size;
+	}
+
+	if (cma_size > reserved_size)
+		pr_warn("crashkernel CMA reservation failed: %lld MB requested, %lld MB reserved in %d ranges\n",
+			cma_size >> 20, reserved_size >> 20, crashk_cma_cnt);
+	else
+		pr_info("crashkernel CMA reserved: %lld MB in %d ranges\n",
+			reserved_size >> 20, crashk_cma_cnt);
+}
+
+#else /* CRASHKERNEL_CMA */
+void __init reserve_crashkernel_cma(unsigned long long cma_size)
+{
+	if (cma_size)
+		pr_warn("crashkernel CMA reservation not supported\n");
+}
+#endif
+
 #ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
 static __init int insert_crashkernel_resources(void)
 {
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index f774367c8e71..7ca1940607bd 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -580,8 +580,8 @@ retry:
 
 out:
 	/* Revert back reference counter if instruction update failed. */
-	if (ret < 0 && is_register && ref_ctr_updated)
-		update_ref_ctr(uprobe, mm, -1);
+	if (ret < 0 && ref_ctr_updated)
+		update_ref_ctr(uprobe, mm, is_register ? -1 : 1);
 
 	/* try collapse pmd for compound page */
 	if (ret > 0)
diff --git a/kernel/exit.c b/kernel/exit.c
index 1d8c8ac33c4f..343eb97543d5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -693,12 +693,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 }
 
 /*
- * This does two things:
- *
- * A.  Make init inherit all the child processes
- * B.  Check to see if any process groups have become orphaned
- *	as a result of our exiting, and if they have any stopped
- *	jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
+ * Make init inherit all the child processes
  */
 static void forget_original_parent(struct task_struct *father,
 					struct list_head *dead)
diff --git a/kernel/fork.c b/kernel/fork.c
index e45354cc7cac..9ce93fd20f82 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -189,33 +189,33 @@ static inline void free_task_struct(struct task_struct *tsk)
 	kmem_cache_free(task_struct_cachep, tsk);
 }
 
-/*
- * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
- * kmemcache based allocator.
- */
-# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)
-
-#  ifdef CONFIG_VMAP_STACK
+#ifdef CONFIG_VMAP_STACK
 /*
  * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB
  * flush.  Try to minimize the number of calls by caching stacks.
  */
 #define NR_CACHED_STACKS 2
 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
+/*
+ * Allocated stacks are cached and later reused by new threads, so memcg
+ * accounting is performed by the code assigning/releasing stacks to tasks.
+ * We need a zeroed memory without __GFP_ACCOUNT.
+ */
+#define GFP_VMAP_STACK (GFP_KERNEL | __GFP_ZERO)
 
 struct vm_stack {
 	struct rcu_head rcu;
 	struct vm_struct *stack_vm_area;
 };
 
-static bool try_release_thread_stack_to_cache(struct vm_struct *vm)
+static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area)
 {
 	unsigned int i;
 
 	for (i = 0; i < NR_CACHED_STACKS; i++) {
 		struct vm_struct *tmp = NULL;
 
-		if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm))
+		if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area))
 			return true;
 	}
 	return false;
@@ -224,11 +224,12 @@ static bool try_release_thread_stack_to_cache(struct vm_struct *vm)
 static void thread_stack_free_rcu(struct rcu_head *rh)
 {
 	struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu);
+	struct vm_struct *vm_area = vm_stack->stack_vm_area;
 
 	if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area))
 		return;
 
-	vfree(vm_stack);
+	vfree(vm_area->addr);
 }
 
 static void thread_stack_delayed_free(struct task_struct *tsk)
@@ -241,32 +242,32 @@ static void thread_stack_delayed_free(struct task_struct *tsk)
 
 static int free_vm_stack_cache(unsigned int cpu)
 {
-	struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu);
+	struct vm_struct **cached_vm_stack_areas = per_cpu_ptr(cached_stacks, cpu);
 	int i;
 
 	for (i = 0; i < NR_CACHED_STACKS; i++) {
-		struct vm_struct *vm_stack = cached_vm_stacks[i];
+		struct vm_struct *vm_area = cached_vm_stack_areas[i];
 
-		if (!vm_stack)
+		if (!vm_area)
 			continue;
 
-		vfree(vm_stack->addr);
-		cached_vm_stacks[i] = NULL;
+		vfree(vm_area->addr);
+		cached_vm_stack_areas[i] = NULL;
 	}
 
 	return 0;
 }
 
-static int memcg_charge_kernel_stack(struct vm_struct *vm)
+static int memcg_charge_kernel_stack(struct vm_struct *vm_area)
 {
 	int i;
 	int ret;
 	int nr_charged = 0;
 
-	BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
+	BUG_ON(vm_area->nr_pages != THREAD_SIZE / PAGE_SIZE);
 
 	for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
-		ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0);
+		ret = memcg_kmem_charge_page(vm_area->pages[i], GFP_KERNEL, 0);
 		if (ret)
 			goto err;
 		nr_charged++;
@@ -274,55 +275,47 @@ static int memcg_charge_kernel_stack(struct vm_struct *vm)
 	return 0;
 err:
 	for (i = 0; i < nr_charged; i++)
-		memcg_kmem_uncharge_page(vm->pages[i], 0);
+		memcg_kmem_uncharge_page(vm_area->pages[i], 0);
 	return ret;
 }
 
 static int alloc_thread_stack_node(struct task_struct *tsk, int node)
 {
-	struct vm_struct *vm;
+	struct vm_struct *vm_area;
 	void *stack;
 	int i;
 
 	for (i = 0; i < NR_CACHED_STACKS; i++) {
-		struct vm_struct *s;
-
-		s = this_cpu_xchg(cached_stacks[i], NULL);
-
-		if (!s)
+		vm_area = this_cpu_xchg(cached_stacks[i], NULL);
+		if (!vm_area)
 			continue;
 
 		/* Reset stack metadata. */
-		kasan_unpoison_range(s->addr, THREAD_SIZE);
+		kasan_unpoison_range(vm_area->addr, THREAD_SIZE);
 
-		stack = kasan_reset_tag(s->addr);
+		stack = kasan_reset_tag(vm_area->addr);
 
 		/* Clear stale pointers from reused stack. */
 		memset(stack, 0, THREAD_SIZE);
 
-		if (memcg_charge_kernel_stack(s)) {
-			vfree(s->addr);
+		if (memcg_charge_kernel_stack(vm_area)) {
+			vfree(vm_area->addr);
 			return -ENOMEM;
 		}
 
-		tsk->stack_vm_area = s;
+		tsk->stack_vm_area = vm_area;
 		tsk->stack = stack;
 		return 0;
 	}
 
-	/*
-	 * Allocated stacks are cached and later reused by new threads,
-	 * so memcg accounting is performed manually on assigning/releasing
-	 * stacks to tasks. Drop __GFP_ACCOUNT.
-	 */
 	stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN,
-				     THREADINFO_GFP & ~__GFP_ACCOUNT,
+				     GFP_VMAP_STACK,
 				     node, __builtin_return_address(0));
 	if (!stack)
 		return -ENOMEM;
 
-	vm = find_vm_area(stack);
-	if (memcg_charge_kernel_stack(vm)) {
+	vm_area = find_vm_area(stack);
+	if (memcg_charge_kernel_stack(vm_area)) {
 		vfree(stack);
 		return -ENOMEM;
 	}
@@ -331,7 +324,7 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node)
 	 * free_thread_stack() can be called in interrupt context,
 	 * so cache the vm_struct.
 	 */
-	tsk->stack_vm_area = vm;
+	tsk->stack_vm_area = vm_area;
 	stack = kasan_reset_tag(stack);
 	tsk->stack = stack;
 	return 0;
@@ -346,7 +339,13 @@ static void free_thread_stack(struct task_struct *tsk)
 	tsk->stack_vm_area = NULL;
 }
 
-#  else /* !CONFIG_VMAP_STACK */
+#else /* !CONFIG_VMAP_STACK */
+
+/*
+ * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
+ * kmemcache based allocator.
+ */
+#if THREAD_SIZE >= PAGE_SIZE
 
 static void thread_stack_free_rcu(struct rcu_head *rh)
 {
@@ -378,8 +377,7 @@ static void free_thread_stack(struct task_struct *tsk)
 	tsk->stack = NULL;
 }
 
-#  endif /* CONFIG_VMAP_STACK */
-# else /* !(THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)) */
+#else /* !(THREAD_SIZE >= PAGE_SIZE) */
 
 static struct kmem_cache *thread_stack_cache;
 
@@ -418,7 +416,8 @@ void thread_stack_cache_init(void)
 	BUG_ON(thread_stack_cache == NULL);
 }
 
-# endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */
+#endif /* THREAD_SIZE >= PAGE_SIZE */
+#endif /* CONFIG_VMAP_STACK */
 
 /* SLAB cache for signal_struct structures (tsk->signal) */
 static struct kmem_cache *signal_cachep;
@@ -438,11 +437,11 @@ static struct kmem_cache *mm_cachep;
 static void account_kernel_stack(struct task_struct *tsk, int account)
 {
 	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
-		struct vm_struct *vm = task_stack_vm_area(tsk);
+		struct vm_struct *vm_area = task_stack_vm_area(tsk);
 		int i;
 
 		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
-			mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB,
+			mod_lruvec_page_state(vm_area->pages[i], NR_KERNEL_STACK_KB,
 					      account * (PAGE_SIZE / 1024));
 	} else {
 		void *stack = task_stack_page(tsk);
@@ -458,12 +457,12 @@ void exit_task_stack_account(struct task_struct *tsk)
 	account_kernel_stack(tsk, -1);
 
 	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
-		struct vm_struct *vm;
+		struct vm_struct *vm_area;
 		int i;
 
-		vm = task_stack_vm_area(tsk);
+		vm_area = task_stack_vm_area(tsk);
 		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
-			memcg_kmem_uncharge_page(vm->pages[i], 0);
+			memcg_kmem_uncharge_page(vm_area->pages[i], 0);
 	}
 }
 
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index d2432df2b905..8708a1205f82 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -23,6 +23,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/sysctl.h>
 #include <linux/hung_task.h>
+#include <linux/rwsem.h>
 
 #include <trace/events/sched.h>
 
@@ -100,6 +101,7 @@ static void debug_show_blocker(struct task_struct *task)
 {
 	struct task_struct *g, *t;
 	unsigned long owner, blocker, blocker_type;
+	const char *rwsem_blocked_by, *rwsem_blocked_as;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held");
 
@@ -111,12 +113,20 @@ static void debug_show_blocker(struct task_struct *task)
 
 	switch (blocker_type) {
 	case BLOCKER_TYPE_MUTEX:
-		owner = mutex_get_owner(
-			(struct mutex *)hung_task_blocker_to_lock(blocker));
+		owner = mutex_get_owner(hung_task_blocker_to_lock(blocker));
 		break;
 	case BLOCKER_TYPE_SEM:
-		owner = sem_last_holder(
-			(struct semaphore *)hung_task_blocker_to_lock(blocker));
+		owner = sem_last_holder(hung_task_blocker_to_lock(blocker));
+		break;
+	case BLOCKER_TYPE_RWSEM_READER:
+	case BLOCKER_TYPE_RWSEM_WRITER:
+		owner = (unsigned long)rwsem_owner(
+					hung_task_blocker_to_lock(blocker));
+		rwsem_blocked_as = (blocker_type == BLOCKER_TYPE_RWSEM_READER) ?
+					"reader" : "writer";
+		rwsem_blocked_by = is_rwsem_reader_owned(
+					hung_task_blocker_to_lock(blocker)) ?
+					"reader" : "writer";
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -134,6 +144,11 @@ static void debug_show_blocker(struct task_struct *task)
 			pr_err("INFO: task %s:%d is blocked on a semaphore, but the last holder is not found.\n",
 			       task->comm, task->pid);
 			break;
+		case BLOCKER_TYPE_RWSEM_READER:
+		case BLOCKER_TYPE_RWSEM_WRITER:
+			pr_err("INFO: task %s:%d is blocked on an rw-semaphore, but the owner is not found.\n",
+			       task->comm, task->pid);
+			break;
 		}
 		return;
 	}
@@ -152,6 +167,12 @@ static void debug_show_blocker(struct task_struct *task)
 			pr_err("INFO: task %s:%d blocked on a semaphore likely last held by task %s:%d\n",
 			       task->comm, task->pid, t->comm, t->pid);
 			break;
+		case BLOCKER_TYPE_RWSEM_READER:
+		case BLOCKER_TYPE_RWSEM_WRITER:
+			pr_err("INFO: task %s:%d <%s> blocked on an rw-semaphore likely owned by task %s:%d <%s>\n",
+			       task->comm, task->pid, rwsem_blocked_as, t->comm,
+			       t->pid, rwsem_blocked_by);
+			break;
 		}
 		sched_show_task(t);
 		return;
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 187ba1b80bda..1d85597057e1 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -552,7 +552,7 @@ static int kcov_get_mode(unsigned long arg)
 
 /*
  * Fault in a lazily-faulted vmalloc area before it can be used by
- * __santizer_cov_trace_pc(), to avoid recursion issues if any code on the
+ * __sanitizer_cov_trace_pc(), to avoid recursion issues if any code on the
  * vmalloc fault handling path is instrumented.
  */
 static void kcov_fault_in_area(struct kcov *kcov)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index a6b3f96bb50c..28008e3d462e 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -152,7 +152,7 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
 		goto out;
 
 	for (i = 0; i < nr_segments; i++) {
-		ret = kimage_load_segment(image, &image->segment[i]);
+		ret = kimage_load_segment(image, i);
 		if (ret)
 			goto out;
 	}
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 351cd7d76dfa..31203f0bacaf 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -40,6 +40,7 @@
 #include <linux/hugetlb.h>
 #include <linux/objtool.h>
 #include <linux/kmsg_dump.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -553,6 +554,24 @@ static void kimage_free_entry(kimage_entry_t entry)
 	kimage_free_pages(page);
 }
 
+static void kimage_free_cma(struct kimage *image)
+{
+	unsigned long i;
+
+	for (i = 0; i < image->nr_segments; i++) {
+		struct page *cma = image->segment_cma[i];
+		u32 nr_pages = image->segment[i].memsz >> PAGE_SHIFT;
+
+		if (!cma)
+			continue;
+
+		arch_kexec_pre_free_pages(page_address(cma), nr_pages);
+		dma_release_from_contiguous(NULL, cma, nr_pages);
+		image->segment_cma[i] = NULL;
+	}
+
+}
+
 void kimage_free(struct kimage *image)
 {
 	kimage_entry_t *ptr, entry;
@@ -591,6 +610,9 @@ void kimage_free(struct kimage *image)
 	/* Free the kexec control pages... */
 	kimage_free_page_list(&image->control_pages);
 
+	/* Free CMA allocations */
+	kimage_free_cma(image);
+
 	/*
 	 * Free up any temporary buffers allocated. This might hit if
 	 * error occurred much later after buffer allocation.
@@ -716,9 +738,69 @@ static struct page *kimage_alloc_page(struct kimage *image,
 	return page;
 }
 
-static int kimage_load_normal_segment(struct kimage *image,
-					 struct kexec_segment *segment)
+static int kimage_load_cma_segment(struct kimage *image, int idx)
+{
+	struct kexec_segment *segment = &image->segment[idx];
+	struct page *cma = image->segment_cma[idx];
+	char *ptr = page_address(cma);
+	unsigned long maddr;
+	size_t ubytes, mbytes;
+	int result = 0;
+	unsigned char __user *buf = NULL;
+	unsigned char *kbuf = NULL;
+
+	if (image->file_mode)
+		kbuf = segment->kbuf;
+	else
+		buf = segment->buf;
+	ubytes = segment->bufsz;
+	mbytes = segment->memsz;
+	maddr = segment->mem;
+
+	/* Then copy from source buffer to the CMA one */
+	while (mbytes) {
+		size_t uchunk, mchunk;
+
+		ptr += maddr & ~PAGE_MASK;
+		mchunk = min_t(size_t, mbytes,
+				PAGE_SIZE - (maddr & ~PAGE_MASK));
+		uchunk = min(ubytes, mchunk);
+
+		if (uchunk) {
+			/* For file based kexec, source pages are in kernel memory */
+			if (image->file_mode)
+				memcpy(ptr, kbuf, uchunk);
+			else
+				result = copy_from_user(ptr, buf, uchunk);
+			ubytes -= uchunk;
+			if (image->file_mode)
+				kbuf += uchunk;
+			else
+				buf += uchunk;
+		}
+
+		if (result) {
+			result = -EFAULT;
+			goto out;
+		}
+
+		ptr    += mchunk;
+		maddr  += mchunk;
+		mbytes -= mchunk;
+
+		cond_resched();
+	}
+
+	/* Clear any remainder */
+	memset(ptr, 0, mbytes);
+
+out:
+	return result;
+}
+
+static int kimage_load_normal_segment(struct kimage *image, int idx)
 {
+	struct kexec_segment *segment = &image->segment[idx];
 	unsigned long maddr;
 	size_t ubytes, mbytes;
 	int result;
@@ -733,6 +815,9 @@ static int kimage_load_normal_segment(struct kimage *image,
 	mbytes = segment->memsz;
 	maddr = segment->mem;
 
+	if (image->segment_cma[idx])
+		return kimage_load_cma_segment(image, idx);
+
 	result = kimage_set_destination(image, maddr);
 	if (result < 0)
 		goto out;
@@ -787,13 +872,13 @@ out:
 }
 
 #ifdef CONFIG_CRASH_DUMP
-static int kimage_load_crash_segment(struct kimage *image,
-					struct kexec_segment *segment)
+static int kimage_load_crash_segment(struct kimage *image, int idx)
 {
 	/* For crash dumps kernels we simply copy the data from
 	 * user space to it's destination.
 	 * We do things a page at a time for the sake of kmap.
 	 */
+	struct kexec_segment *segment = &image->segment[idx];
 	unsigned long maddr;
 	size_t ubytes, mbytes;
 	int result;
@@ -858,18 +943,17 @@ out:
 }
 #endif
 
-int kimage_load_segment(struct kimage *image,
-				struct kexec_segment *segment)
+int kimage_load_segment(struct kimage *image, int idx)
 {
 	int result = -ENOMEM;
 
 	switch (image->type) {
 	case KEXEC_TYPE_DEFAULT:
-		result = kimage_load_normal_segment(image, segment);
+		result = kimage_load_normal_segment(image, idx);
 		break;
 #ifdef CONFIG_CRASH_DUMP
 	case KEXEC_TYPE_CRASH:
-		result = kimage_load_crash_segment(image, segment);
+		result = kimage_load_crash_segment(image, idx);
 		break;
 #endif
 	}
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b835033c65eb..91d46502a817 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -26,6 +26,7 @@
 #include <linux/kernel_read_file.h>
 #include <linux/syscalls.h>
 #include <linux/vmalloc.h>
+#include <linux/dma-map-ops.h>
 #include "kexec_internal.h"
 
 #ifdef CONFIG_KEXEC_SIG
@@ -253,6 +254,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 		ret = 0;
 	}
 
+	image->no_cma = !!(flags & KEXEC_FILE_NO_CMA);
+
 	if (cmdline_len) {
 		image->cmdline_buf = memdup_user(cmdline_ptr, cmdline_len);
 		if (IS_ERR(image->cmdline_buf)) {
@@ -434,7 +437,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 			      i, ksegment->buf, ksegment->bufsz, ksegment->mem,
 			      ksegment->memsz);
 
-		ret = kimage_load_segment(image, &image->segment[i]);
+		ret = kimage_load_segment(image, i);
 		if (ret)
 			goto out;
 	}
@@ -663,6 +666,43 @@ static int kexec_walk_resources(struct kexec_buf *kbuf,
 		return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
 }
 
+static int kexec_alloc_contig(struct kexec_buf *kbuf)
+{
+	size_t nr_pages = kbuf->memsz >> PAGE_SHIFT;
+	unsigned long mem;
+	struct page *p;
+
+	/* User space disabled CMA allocations, bail out. */
+	if (kbuf->image->no_cma)
+		return -EPERM;
+
+	/* Skip CMA logic for crash kernel */
+	if (kbuf->image->type == KEXEC_TYPE_CRASH)
+		return -EPERM;
+
+	p = dma_alloc_from_contiguous(NULL, nr_pages, get_order(kbuf->buf_align), true);
+	if (!p)
+		return -ENOMEM;
+
+	pr_debug("allocated %zu DMA pages at 0x%lx", nr_pages, page_to_boot_pfn(p));
+
+	mem = page_to_boot_pfn(p) << PAGE_SHIFT;
+
+	if (kimage_is_destination_range(kbuf->image, mem, mem + kbuf->memsz)) {
+		/* Our region is already in use by a statically defined one. Bail out. */
+		pr_debug("CMA overlaps existing mem: 0x%lx+0x%lx\n", mem, kbuf->memsz);
+		dma_release_from_contiguous(NULL, p, nr_pages);
+		return -EBUSY;
+	}
+
+	kbuf->mem = page_to_boot_pfn(p) << PAGE_SHIFT;
+	kbuf->cma = p;
+
+	arch_kexec_post_alloc_pages(page_address(p), (int)nr_pages, 0);
+
+	return 0;
+}
+
 /**
  * kexec_locate_mem_hole - find free memory for the purgatory or the next kernel
  * @kbuf:	Parameters for the memory search.
@@ -687,6 +727,13 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
 	if (ret <= 0)
 		return ret;
 
+	/*
+	 * Try to find a free physically contiguous block of memory first. With that, we
+	 * can avoid any copying at kexec time.
+	 */
+	if (!kexec_alloc_contig(kbuf))
+		return 0;
+
 	if (!IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
 		ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
 	else
@@ -732,6 +779,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 	/* Ensure minimum alignment needed for segments. */
 	kbuf->memsz = ALIGN(kbuf->memsz, PAGE_SIZE);
 	kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE);
+	kbuf->cma = NULL;
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
 	ret = arch_kexec_locate_mem_hole(kbuf);
@@ -744,6 +792,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 	ksegment->bufsz = kbuf->bufsz;
 	ksegment->mem = kbuf->mem;
 	ksegment->memsz = kbuf->memsz;
+	kbuf->image->segment_cma[kbuf->image->nr_segments] = kbuf->cma;
 	kbuf->image->nr_segments++;
 	return 0;
 }
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 30a733a55a67..228bb88c018b 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -10,7 +10,7 @@ struct kimage *do_kimage_alloc_init(void);
 int sanity_check_segment_list(struct kimage *image);
 void kimage_free_page_list(struct list_head *list);
 void kimage_free(struct kimage *image);
-int kimage_load_segment(struct kimage *image, struct kexec_segment *segment);
+int kimage_load_segment(struct kimage *image, int idx);
 void kimage_terminate(struct kimage *image);
 int kimage_is_destination_range(struct kimage *image,
 				unsigned long start, unsigned long end);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 85fc068f0083..0e98b228a8ef 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -88,13 +88,12 @@ static inline struct kthread *to_kthread(struct task_struct *k)
 /*
  * Variant of to_kthread() that doesn't assume @p is a kthread.
  *
- * Per construction; when:
+ * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will
+ * always remain a kthread.  For kthreads p->worker_private always
+ * points to a struct kthread.  For tasks that are not kthreads
+ * p->worker_private is used to point to other things.
  *
- *   (p->flags & PF_KTHREAD) && p->worker_private
- *
- * the task is both a kthread and struct kthread is persistent. However
- * PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and
- * begin_new_exec()).
+ * Return NULL for any task that is not a kthread.
  */
 static inline struct kthread *__to_kthread(struct task_struct *p)
 {
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 8572dba95af4..24df4d98f7d2 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -27,6 +27,7 @@
 #include <linux/export.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
+#include <linux/hung_task.h>
 #include <trace/events/lock.h>
 
 #ifndef CONFIG_PREEMPT_RT
@@ -181,11 +182,11 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
 	__rwsem_set_reader_owned(sem, current);
 }
 
-#ifdef CONFIG_DEBUG_RWSEMS
+#if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER)
 /*
  * Return just the real task structure pointer of the owner
  */
-static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
+struct task_struct *rwsem_owner(struct rw_semaphore *sem)
 {
 	return (struct task_struct *)
 		(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
@@ -194,7 +195,7 @@ static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
 /*
  * Return true if the rwsem is owned by a reader.
  */
-static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
+bool is_rwsem_reader_owned(struct rw_semaphore *sem)
 {
 	/*
 	 * Check the count to see if it is write-locked.
@@ -207,10 +208,10 @@ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
 }
 
 /*
- * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
- * is a task pointer in owner of a reader-owned rwsem, it will be the
- * real owner or one of the real owners. The only exception is when the
- * unlock is done by up_read_non_owner().
+ * With CONFIG_DEBUG_RWSEMS or CONFIG_DETECT_HUNG_TASK_BLOCKER configured,
+ * it will make sure that the owner field of a reader-owned rwsem either
+ * points to a real reader-owner(s) or gets cleared. The only exception is
+ * when the unlock is done by up_read_non_owner().
  */
 static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
 {
@@ -1063,10 +1064,13 @@ queue:
 		wake_up_q(&wake_q);
 
 	trace_contention_begin(sem, LCB_F_READ);
+	set_current_state(state);
+
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_READER);
 
 	/* wait to be given the lock */
 	for (;;) {
-		set_current_state(state);
 		if (!smp_load_acquire(&waiter.task)) {
 			/* Matches rwsem_mark_wake()'s smp_store_release(). */
 			break;
@@ -1081,8 +1085,12 @@ queue:
 		}
 		schedule_preempt_disabled();
 		lockevent_inc(rwsem_sleep_reader);
+		set_current_state(state);
 	}
 
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_clear_blocker();
+
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock);
 	trace_contention_end(sem, 0);
@@ -1144,6 +1152,9 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 	set_current_state(state);
 	trace_contention_begin(sem, LCB_F_WRITE);
 
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_WRITER);
+
 	for (;;) {
 		if (rwsem_try_write_lock(sem, &waiter)) {
 			/* rwsem_try_write_lock() implies ACQUIRE on success */
@@ -1177,6 +1188,10 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 trylock_again:
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
+
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_clear_blocker();
+
 	__set_current_state(TASK_RUNNING);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	lockevent_inc(rwsem_wlock);
diff --git a/kernel/panic.c b/kernel/panic.c
index 43817111c979..72fcbb5a071b 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -36,6 +36,7 @@
 #include <linux/sysfs.h>
 #include <linux/context_tracking.h>
 #include <linux/seq_buf.h>
+#include <linux/sys_info.h>
 #include <trace/events/error_report.h>
 #include <asm/sections.h>
 
@@ -63,20 +64,13 @@ int panic_on_warn __read_mostly;
 unsigned long panic_on_taint;
 bool panic_on_taint_nousertaint = false;
 static unsigned int warn_limit __read_mostly;
+static bool panic_console_replay;
 
 bool panic_triggering_all_cpu_backtrace;
 
 int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
 
-#define PANIC_PRINT_TASK_INFO		0x00000001
-#define PANIC_PRINT_MEM_INFO		0x00000002
-#define PANIC_PRINT_TIMER_INFO		0x00000004
-#define PANIC_PRINT_LOCK_INFO		0x00000008
-#define PANIC_PRINT_FTRACE_INFO		0x00000010
-#define PANIC_PRINT_ALL_PRINTK_MSG	0x00000020
-#define PANIC_PRINT_ALL_CPU_BT		0x00000040
-#define PANIC_PRINT_BLOCKED_TASKS	0x00000080
 unsigned long panic_print;
 
 ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
@@ -128,6 +122,13 @@ static int proc_taint(const struct ctl_table *table, int write,
 	return err;
 }
 
+static int sysctl_panic_print_handler(const struct ctl_table *table, int write,
+			   void *buffer, size_t *lenp, loff_t *ppos)
+{
+	pr_info_once("Kernel: 'panic_print' sysctl interface will be obsoleted by both 'panic_sys_info' and 'panic_console_replay'\n");
+	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+}
+
 static const struct ctl_table kern_panic_table[] = {
 #ifdef CONFIG_SMP
 	{
@@ -165,7 +166,7 @@ static const struct ctl_table kern_panic_table[] = {
 		.data		= &panic_print,
 		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax,
+		.proc_handler	= sysctl_panic_print_handler,
 	},
 	{
 		.procname	= "panic_on_warn",
@@ -193,6 +194,13 @@ static const struct ctl_table kern_panic_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+	{
+		.procname	= "panic_sys_info",
+		.data		= &panic_print,
+		.maxlen         = sizeof(panic_print),
+		.mode		= 0644,
+		.proc_handler	= sysctl_sys_info_handler,
+	},
 };
 
 static __init int kernel_panic_sysctls_init(void)
@@ -203,6 +211,15 @@ static __init int kernel_panic_sysctls_init(void)
 late_initcall(kernel_panic_sysctls_init);
 #endif
 
+/* The format is "panic_sys_info=tasks,mem,locks,ftrace,..." */
+static int __init setup_panic_sys_info(char *buf)
+{
+	/* There is no risk of race in kernel boot phase */
+	panic_print = sys_info_parse_param(buf);
+	return 1;
+}
+__setup("panic_sys_info=", setup_panic_sys_info);
+
 static atomic_t warn_count = ATOMIC_INIT(0);
 
 #ifdef CONFIG_SYSFS
@@ -298,33 +315,6 @@ void nmi_panic(struct pt_regs *regs, const char *msg)
 }
 EXPORT_SYMBOL(nmi_panic);
 
-static void panic_print_sys_info(bool console_flush)
-{
-	if (console_flush) {
-		if (panic_print & PANIC_PRINT_ALL_PRINTK_MSG)
-			console_flush_on_panic(CONSOLE_REPLAY_ALL);
-		return;
-	}
-
-	if (panic_print & PANIC_PRINT_TASK_INFO)
-		show_state();
-
-	if (panic_print & PANIC_PRINT_MEM_INFO)
-		show_mem();
-
-	if (panic_print & PANIC_PRINT_TIMER_INFO)
-		sysrq_timer_list_show();
-
-	if (panic_print & PANIC_PRINT_LOCK_INFO)
-		debug_show_all_locks();
-
-	if (panic_print & PANIC_PRINT_FTRACE_INFO)
-		ftrace_dump(DUMP_ALL);
-
-	if (panic_print & PANIC_PRINT_BLOCKED_TASKS)
-		show_state_filter(TASK_UNINTERRUPTIBLE);
-}
-
 void check_panic_on_warn(const char *origin)
 {
 	unsigned int limit;
@@ -345,7 +335,7 @@ void check_panic_on_warn(const char *origin)
  */
 static void panic_other_cpus_shutdown(bool crash_kexec)
 {
-	if (panic_print & PANIC_PRINT_ALL_CPU_BT) {
+	if (panic_print & SYS_INFO_ALL_CPU_BT) {
 		/* Temporary allow non-panic CPUs to write their backtraces. */
 		panic_triggering_all_cpu_backtrace = true;
 		trigger_all_cpu_backtrace();
@@ -468,7 +458,7 @@ void vpanic(const char *fmt, va_list args)
 	 */
 	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
 
-	panic_print_sys_info(false);
+	sys_info(panic_print);
 
 	kmsg_dump_desc(KMSG_DUMP_PANIC, buf);
 
@@ -497,7 +487,9 @@ void vpanic(const char *fmt, va_list args)
 	debug_locks_off();
 	console_flush_on_panic(CONSOLE_FLUSH_PENDING);
 
-	panic_print_sys_info(true);
+	if ((panic_print & SYS_INFO_PANIC_CONSOLE_REPLAY) ||
+		panic_console_replay)
+		console_flush_on_panic(CONSOLE_REPLAY_ALL);
 
 	if (!panic_blink)
 		panic_blink = no_blink;
@@ -949,6 +941,7 @@ core_param(panic_print, panic_print, ulong, 0644);
 core_param(pause_on_oops, pause_on_oops, int, 0644);
 core_param(panic_on_warn, panic_on_warn, int, 0644);
 core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644);
+core_param(panic_console_replay, panic_console_replay, bool, 0644);
 
 static int __init oops_setup(char *s)
 {
diff --git a/kernel/relay.c b/kernel/relay.c
index c0c93a04d4ce..8d915fe98198 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -118,7 +118,7 @@ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size)
 		return NULL;
 
 	for (i = 0; i < n_pages; i++) {
-		buf->page_array[i] = alloc_page(GFP_KERNEL);
+		buf->page_array[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
 		if (unlikely(!buf->page_array[i]))
 			goto depopulate;
 		set_page_private(buf->page_array[i], (unsigned long)buf);
@@ -127,7 +127,6 @@ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size)
 	if (!mem)
 		goto depopulate;
 
-	memset(mem, 0, *size);
 	buf->page_count = n_pages;
 	return mem;
 
@@ -250,13 +249,18 @@ EXPORT_SYMBOL_GPL(relay_buf_full);
  */
 
 static int relay_subbuf_start(struct rchan_buf *buf, void *subbuf,
-			      void *prev_subbuf, size_t prev_padding)
+			      void *prev_subbuf)
 {
+	int full = relay_buf_full(buf);
+
+	if (full)
+		buf->stats.full_count++;
+
 	if (!buf->chan->cb->subbuf_start)
-		return !relay_buf_full(buf);
+		return !full;
 
 	return buf->chan->cb->subbuf_start(buf, subbuf,
-					   prev_subbuf, prev_padding);
+					   prev_subbuf);
 }
 
 /**
@@ -298,11 +302,13 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init)
 	buf->finalized = 0;
 	buf->data = buf->start;
 	buf->offset = 0;
+	buf->stats.full_count = 0;
+	buf->stats.big_count = 0;
 
 	for (i = 0; i < buf->chan->n_subbufs; i++)
 		buf->padding[i] = 0;
 
-	relay_subbuf_start(buf, buf->data, NULL, 0);
+	relay_subbuf_start(buf, buf->data, NULL);
 }
 
 /**
@@ -555,9 +561,11 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 		goto toobig;
 
 	if (buf->offset != buf->chan->subbuf_size + 1) {
-		buf->prev_padding = buf->chan->subbuf_size - buf->offset;
+		size_t prev_padding;
+
+		prev_padding = buf->chan->subbuf_size - buf->offset;
 		old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs;
-		buf->padding[old_subbuf] = buf->prev_padding;
+		buf->padding[old_subbuf] = prev_padding;
 		buf->subbufs_produced++;
 		if (buf->dentry)
 			d_inode(buf->dentry)->i_size +=
@@ -582,7 +590,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 	new_subbuf = buf->subbufs_produced % buf->chan->n_subbufs;
 	new = buf->start + new_subbuf * buf->chan->subbuf_size;
 	buf->offset = 0;
-	if (!relay_subbuf_start(buf, new, old, buf->prev_padding)) {
+	if (!relay_subbuf_start(buf, new, old)) {
 		buf->offset = buf->chan->subbuf_size + 1;
 		return 0;
 	}
@@ -595,7 +603,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 	return length;
 
 toobig:
-	buf->chan->last_toobig = length;
+	buf->stats.big_count++;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(relay_switch_subbuf);
@@ -655,11 +663,6 @@ void relay_close(struct rchan *chan)
 			if ((buf = *per_cpu_ptr(chan->buf, i)))
 				relay_close_buf(buf);
 
-	if (chan->last_toobig)
-		printk(KERN_WARNING "relay: one or more items not logged "
-		       "[item size (%zd) > sub-buffer size (%zd)]\n",
-		       chan->last_toobig, chan->subbuf_size);
-
 	list_del(&chan->list);
 	kref_put(&chan->kref, relay_destroy_channel);
 	mutex_unlock(&relay_channels_mutex);
@@ -694,6 +697,42 @@ void relay_flush(struct rchan *chan)
 EXPORT_SYMBOL_GPL(relay_flush);
 
 /**
+ *	relay_stats - get channel buffer statistics
+ *	@chan: the channel
+ *	@flags: select particular information to get
+ *
+ *	Returns the count of certain field that caller specifies.
+ */
+size_t relay_stats(struct rchan *chan, int flags)
+{
+	unsigned int i, count = 0;
+	struct rchan_buf *rbuf;
+
+	if (!chan || flags > RELAY_STATS_LAST)
+		return 0;
+
+	if (chan->is_global) {
+		rbuf = *per_cpu_ptr(chan->buf, 0);
+		if (flags & RELAY_STATS_BUF_FULL)
+			count = rbuf->stats.full_count;
+		else if (flags & RELAY_STATS_WRT_BIG)
+			count = rbuf->stats.big_count;
+	} else {
+		for_each_online_cpu(i) {
+			rbuf = *per_cpu_ptr(chan->buf, i);
+			if (rbuf) {
+				if (flags & RELAY_STATS_BUF_FULL)
+					count += rbuf->stats.full_count;
+				else if (flags & RELAY_STATS_WRT_BIG)
+					count += rbuf->stats.big_count;
+			}
+		}
+	}
+
+	return count;
+}
+
+/**
  *	relay_file_open - open file op for relay files
  *	@inode: the inode
  *	@filp: the file
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 47168d2afbf1..6941145b5058 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -415,9 +415,10 @@ static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
 				size_t count, loff_t *ppos)
 {
 	struct blk_trace *bt = filp->private_data;
+	size_t dropped = relay_stats(bt->rchan, RELAY_STATS_BUF_FULL);
 	char buf[16];
 
-	snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped));
+	snprintf(buf, sizeof(buf), "%zu\n", dropped);
 
 	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
 }
@@ -456,23 +457,6 @@ static const struct file_operations blk_msg_fops = {
 	.llseek =	noop_llseek,
 };
 
-/*
- * Keep track of how many times we encountered a full subbuffer, to aid
- * the user space app in telling how many lost events there were.
- */
-static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
-				     void *prev_subbuf, size_t prev_padding)
-{
-	struct blk_trace *bt;
-
-	if (!relay_buf_full(buf))
-		return 1;
-
-	bt = buf->chan->private_data;
-	atomic_inc(&bt->dropped);
-	return 0;
-}
-
 static int blk_remove_buf_file_callback(struct dentry *dentry)
 {
 	debugfs_remove(dentry);
@@ -491,7 +475,6 @@ static struct dentry *blk_create_buf_file_callback(const char *filename,
 }
 
 static const struct rchan_callbacks blk_relay_callbacks = {
-	.subbuf_start		= blk_subbuf_start_callback,
 	.create_buf_file	= blk_create_buf_file_callback,
 	.remove_buf_file	= blk_remove_buf_file_callback,
 };
@@ -580,7 +563,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	}
 
 	bt->dev = dev;
-	atomic_set(&bt->dropped, 0);
 	INIT_LIST_HEAD(&bt->running_list);
 
 	ret = -EIO;
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 8686e329b8f2..586af49fc03e 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -199,18 +199,16 @@ void put_ucounts(struct ucounts *ucounts)
 	}
 }
 
-static inline bool atomic_long_inc_below(atomic_long_t *v, int u)
+static inline bool atomic_long_inc_below(atomic_long_t *v, long u)
 {
-	long c, old;
-	c = atomic_long_read(v);
-	for (;;) {
+	long c = atomic_long_read(v);
+
+	do {
 		if (unlikely(c >= u))
 			return false;
-		old = atomic_long_cmpxchg(v, c, c+1);
-		if (likely(old == c))
-			return true;
-		c = old;
-	}
+	} while (!atomic_long_try_cmpxchg(v, &c, c+1));
+
+	return true;
 }
 
 struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid,