Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Cross merge bpf/master after 6.17-rc1. No conflict. Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
2025-08-12 12:14:02 -07:00
parent fa47913284 8f5ae30d69
commit 9e293d47bf
1195 changed files with 33452 additions and 11564 deletions
@@ -1,3 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 /config_data
 /kheaders.md5
+/kheaders-objlist
+/kheaders-srclist
@@ -159,11 +159,48 @@ filechk_cat = cat $<
 $(obj)/config_data: $(KCONFIG_CONFIG) FORCE
 	$(call filechk,cat)

+# kheaders_data.tar.xz
 $(obj)/kheaders.o: $(obj)/kheaders_data.tar.xz

-quiet_cmd_genikh = CHK     $(obj)/kheaders_data.tar.xz
-      cmd_genikh = $(CONFIG_SHELL) $(srctree)/kernel/gen_kheaders.sh $@
-$(obj)/kheaders_data.tar.xz: FORCE
-	$(call cmd,genikh)
+quiet_cmd_kheaders_data = GEN     $@
+      cmd_kheaders_data = "$<" "$@" "$(obj)/kheaders-srclist" "$(obj)/kheaders-objlist" "$(KBUILD_BUILD_TIMESTAMP)"
+      cmd_kheaders_data_dep = cat $(depfile) >> $(dot-target).cmd; rm -f $(depfile)

-clean-files := kheaders_data.tar.xz kheaders.md5
+define rule_kheaders_data
+	$(call cmd_and_savecmd,kheaders_data)
+	$(call cmd,kheaders_data_dep)
+endef
+
+targets += kheaders_data.tar.xz
+$(obj)/kheaders_data.tar.xz: $(src)/gen_kheaders.sh $(obj)/kheaders-srclist $(obj)/kheaders-objlist $(obj)/kheaders.md5 FORCE
+	$(call if_changed_rule,kheaders_data)
+
+# generated headers in objtree
+#
+# include/generated/utsversion.h is ignored because it is generated
+# after gen_kheaders.sh is executed. (utsversion.h is unneeded for kheaders)
+filechk_kheaders_objlist = \
+	for d in include "arch/$(SRCARCH)/include"; do \
+		find "$${d}/generated" ! -path "include/generated/utsversion.h" -a -name "*.h" -print; \
+	done
+
+$(obj)/kheaders-objlist: FORCE
+	$(call filechk,kheaders_objlist)
+
+# non-generated headers in srctree
+filechk_kheaders_srclist = \
+	for d in include "arch/$(SRCARCH)/include"; do \
+		find "$(srctree)/$${d}" -path "$(srctree)/$${d}/generated" -prune -o -name "*.h" -print; \
+	done
+
+$(obj)/kheaders-srclist: FORCE
+	$(call filechk,kheaders_srclist)
+
+# Some files are symlinks. If symlinks are changed, kheaders_data.tar.xz should
+# be rebuilt.
+filechk_kheaders_md5sum = xargs -r -a $< stat -c %N | md5sum
+
+$(obj)/kheaders.md5: $(obj)/kheaders-srclist FORCE
+	$(call filechk,kheaders_md5sum)
+
+clean-files := kheaders.md5 kheaders-srclist kheaders-objlist
@@ -23115,6 +23115,8 @@ static void free_states(struct bpf_verifier_env *env)

 	for (i = 0; i < env->scc_cnt; ++i) {
 		info = env->scc_info[i];
+		if (!info)
+			continue;
 		for (j = 0; j < info->num_visits; j++)
 			free_backedges(&info->visits[j]);
 		kvfree(info);
@@ -24555,6 +24557,7 @@ dfs_continue:
 		err = -ENOMEM;
 		goto exit;
 	}
+	env->scc_cnt = next_scc_id;
 exit:
 	kvfree(stack);
 	kvfree(pre);
@@ -1309,9 +1309,6 @@ static int takedown_cpu(unsigned int cpu)
 	 */
 	irq_lock_sparse();

-	/*
-	 * So now all preempt/rcu users must observe !cpu_active().
-	 */
 	err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu));
 	if (err) {
 		/* CPU refused to die */
@@ -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();
@@ -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)
 {
@@ -6842,10 +6842,20 @@ static vm_fault_t perf_mmap_pfn_mkwrite(struct vm_fault *vmf)
 	return vmf->pgoff == 0 ? 0 : VM_FAULT_SIGBUS;
 }

+static int perf_mmap_may_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	/*
+	 * Forbid splitting perf mappings to prevent refcount leaks due to
+	 * the resulting non-matching offsets and sizes. See open()/close().
+	 */
+	return -EINVAL;
+}
+
 static const struct vm_operations_struct perf_mmap_vmops = {
 	.open		= perf_mmap_open,
 	.close		= perf_mmap_close, /* non mergeable */
 	.pfn_mkwrite	= perf_mmap_pfn_mkwrite,
+	.may_split	= perf_mmap_may_split,
 };

 static int map_range(struct perf_buffer *rb, struct vm_area_struct *vma)
@@ -7051,8 +7061,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			ret = 0;
 			goto unlock;
 		}
-
-		atomic_set(&rb->aux_mmap_count, 1);
 	}

 	user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10);
@@ -7115,15 +7123,16 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		perf_event_update_time(event);
 		perf_event_init_userpage(event);
 		perf_event_update_userpage(event);
+		ret = 0;
 	} else {
 		ret = rb_alloc_aux(rb, event, vma->vm_pgoff, nr_pages,
 				   event->attr.aux_watermark, flags);
-		if (!ret)
+		if (!ret) {
+			atomic_set(&rb->aux_mmap_count, 1);
 			rb->aux_mmap_locked = extra;
+		}
 	}

-	ret = 0;
-
 unlock:
 	if (!ret) {
 		atomic_long_add(user_extra, &user->locked_vm);
@@ -7131,6 +7140,7 @@ unlock:

 		atomic_inc(&event->mmap_count);
 	} else if (rb) {
+		/* AUX allocation failed */
 		atomic_dec(&rb->mmap_count);
 	}
 aux_unlock:
@@ -7138,6 +7148,9 @@ aux_unlock:
 		mutex_unlock(aux_mutex);
 	mutex_unlock(&event->mmap_mutex);

+	if (ret)
+		return ret;
+
 	/*
 	 * Since pinned accounting is per vm we cannot allow fork() to copy our
 	 * vma.
@@ -7145,13 +7158,20 @@ aux_unlock:
 	vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
 	vma->vm_ops = &perf_mmap_vmops;

-	if (!ret)
-		ret = map_range(rb, vma);
-
 	mapped = get_mapped(event, event_mapped);
 	if (mapped)
 		mapped(event, vma->vm_mm);

+	/*
+	 * Try to map it into the page table. On fail, invoke
+	 * perf_mmap_close() to undo the above, as the callsite expects
+	 * full cleanup in this case and therefore does not invoke
+	 * vmops::close().
+	 */
+	ret = map_range(rb, vma);
+	if (ret)
+		perf_mmap_close(vma);
+
 	return ret;
 }

@@ -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)
@@ -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)
@@ -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);
 	}
 }

@@ -586,9 +585,12 @@ static void check_mm(struct mm_struct *mm)
 	for (i = 0; i < NR_MM_COUNTERS; i++) {
 		long x = percpu_counter_sum(&mm->rss_stat[i]);

-		if (unlikely(x))
-			pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n",
-				 mm, resident_page_types[i], x);
+		if (unlikely(x)) {
+			pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld Comm:%s Pid:%d\n",
+				 mm, resident_page_types[i], x,
+				 current->comm,
+				 task_pid_nr(current));
+		}
 	}

 	if (mm_pgtables_bytes(mm))
@@ -687,6 +689,7 @@ void __mmdrop(struct mm_struct *mm)
 	mm_pasid_drop(mm);
 	mm_destroy_cid(mm);
 	percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS);
+	futex_hash_free(mm);

 	free_mm(mm);
 }
@@ -1135,7 +1138,6 @@ static inline void __mmput(struct mm_struct *mm)
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
 	lru_gen_del_mm(mm);
-	futex_hash_free(mm);
 	mmdrop(mm);
 }

@@ -4,79 +4,34 @@
 # This script generates an archive consisting of kernel headers
 # for CONFIG_IKHEADERS.
 set -e
-sfile="$(readlink -f "$0")"
-outdir="$(pwd)"
 tarfile=$1
-tmpdir=$outdir/${tarfile%/*}/.tmp_dir
+srclist=$2
+objlist=$3
+timestamp=$4

-dir_list="
-include/
-arch/$SRCARCH/include/
-"
+dir=$(dirname "${tarfile}")
+tmpdir=${dir}/.tmp_dir
+depfile=${dir}/.$(basename "${tarfile}").d

-# Support incremental builds by skipping archive generation
-# if timestamps of files being archived are not changed.
+# generate dependency list.
+{
+	echo
+	echo "deps_${tarfile} := \\"
+	sed 's:\(.*\):  \1 \\:' "${srclist}"
+	sed -n '/^include\/generated\/autoconf\.h$/!s:\(.*\):  \1 \\:p' "${objlist}"
+	echo
+	echo "${tarfile}: \$(deps_${tarfile})"
+	echo
+	echo "\$(deps_${tarfile}):"

-# This block is useful for debugging the incremental builds.
-# Uncomment it for debugging.
-# if [ ! -f /tmp/iter ]; then iter=1; echo 1 > /tmp/iter;
-# else iter=$(($(cat /tmp/iter) + 1)); echo $iter > /tmp/iter; fi
-# find $all_dirs -name "*.h" | xargs ls -l > /tmp/ls-$iter
-
-all_dirs=
-if [ "$building_out_of_srctree" ]; then
-	for d in $dir_list; do
-		all_dirs="$all_dirs $srctree/$d"
-	done
-fi
-all_dirs="$all_dirs $dir_list"
-
-# include/generated/utsversion.h is ignored because it is generated after this
-# script is executed. (utsversion.h is unneeded for kheaders)
-#
-# When Kconfig regenerates include/generated/autoconf.h, its timestamp is
-# updated, but the contents might be still the same. When any CONFIG option is
-# changed, Kconfig touches the corresponding timestamp file include/config/*.
-# Hence, the md5sum detects the configuration change anyway. We do not need to
-# check include/generated/autoconf.h explicitly.
-#
-# Ignore them for md5 calculation to avoid pointless regeneration.
-headers_md5="$(find $all_dirs -name "*.h" -a			\
-		! -path include/generated/utsversion.h -a	\
-		! -path include/generated/autoconf.h		|
-		xargs ls -l | md5sum | cut -d ' ' -f1)"
-
-# Any changes to this script will also cause a rebuild of the archive.
-this_file_md5="$(ls -l $sfile | md5sum | cut -d ' ' -f1)"
-if [ -f $tarfile ]; then tarfile_md5="$(md5sum $tarfile | cut -d ' ' -f1)"; fi
-if [ -f kernel/kheaders.md5 ] &&
-	[ "$(head -n 1 kernel/kheaders.md5)" = "$headers_md5" ] &&
-	[ "$(head -n 2 kernel/kheaders.md5 | tail -n 1)" = "$this_file_md5" ] &&
-	[ "$(tail -n 1 kernel/kheaders.md5)" = "$tarfile_md5" ]; then
-		exit
-fi
-
-echo "  GEN     $tarfile"
+} > "${depfile}"

 rm -rf "${tmpdir}"
 mkdir "${tmpdir}"

-if [ "$building_out_of_srctree" ]; then
-	(
-		cd $srctree
-		for f in $dir_list
-			do find "$f" -name "*.h";
-		done | tar -c -f - -T - | tar -xf - -C "${tmpdir}"
-	)
-fi
-
-for f in $dir_list;
-	do find "$f" -name "*.h";
-done | tar -c -f - -T - | tar -xf - -C "${tmpdir}"
-
-# Always exclude include/generated/utsversion.h
-# Otherwise, the contents of the tarball may vary depending on the build steps.
-rm -f "${tmpdir}/include/generated/utsversion.h"
+# shellcheck disable=SC2154 # srctree is passed as an env variable
+sed "s:^${srctree}/::" "${srclist}" | ${TAR} -c -f - -C "${srctree}" -T - | ${TAR} -xf - -C "${tmpdir}"
+${TAR} -c -f - -T "${objlist}" | ${TAR} -xf - -C "${tmpdir}"

 # Remove comments except SDPX lines
 # Use a temporary file to store directory contents to prevent find/xargs from
@@ -88,12 +43,8 @@ xargs -0 -P8 -n1 \
 rm -f "${tmpdir}.contents.txt"

 # Create archive and try to normalize metadata for reproducibility.
-tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
+${TAR} "${timestamp:+--mtime=$timestamp}" \
    --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \
-    -I $XZ -cf $tarfile -C "${tmpdir}/" . > /dev/null
-
-echo $headers_md5 > kernel/kheaders.md5
-echo "$this_file_md5" >> kernel/kheaders.md5
-echo "$(md5sum $tarfile | cut -d ' ' -f1)" >> kernel/kheaders.md5
+    -I "${XZ}" -cf "${tarfile}" -C "${tmpdir}/" . > /dev/null

 rm -rf "${tmpdir}"
@@ -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;
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: LGPL-2.1+

+#include <linux/cleanup.h>
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
@@ -134,7 +135,8 @@ static void irq_shutdown_depth_test(struct kunit *test)
 	disable_irq(virq);
 	KUNIT_EXPECT_EQ(test, desc->depth, 1);

-	irq_shutdown_and_deactivate(desc);
+	scoped_guard(raw_spinlock_irqsave, &desc->lock)
+		irq_shutdown_and_deactivate(desc);

 	KUNIT_EXPECT_FALSE(test, irqd_is_activated(data));
 	KUNIT_EXPECT_FALSE(test, irqd_is_started(data));
@@ -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)
@@ -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;
 	}
@@ -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
 	}
@@ -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;
 }
@@ -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);
@@ -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)
 {
@@ -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);
@@ -112,6 +112,13 @@ struct find_symbol_arg {
 	enum mod_license license;
 };

+/* modules using other modules */
+struct module_use {
+	struct list_head source_list;
+	struct list_head target_list;
+	struct module *source, *target;
+};
+
 int mod_verify_sig(const void *mod, struct load_info *info);
 int try_to_force_load(struct module *mod, const char *reason);
 bool find_symbol(struct find_symbol_arg *fsa);
@@ -608,7 +608,7 @@ MODINFO_ATTR(version);
 MODINFO_ATTR(srcversion);

 static struct {
-	char name[MODULE_NAME_LEN + 1];
+	char name[MODULE_NAME_LEN];
 	char taints[MODULE_FLAGS_BUF_SIZE];
 } last_unloaded_module;

@@ -779,14 +779,16 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 	struct module *mod;
 	char name[MODULE_NAME_LEN];
 	char buf[MODULE_FLAGS_BUF_SIZE];
-	int ret, forced = 0;
+	int ret, len, forced = 0;

 	if (!capable(CAP_SYS_MODULE) || modules_disabled)
 		return -EPERM;

-	if (strncpy_from_user(name, name_user, MODULE_NAME_LEN-1) < 0)
-		return -EFAULT;
-	name[MODULE_NAME_LEN-1] = '\0';
+	len = strncpy_from_user(name, name_user, MODULE_NAME_LEN);
+	if (len == 0 || len == MODULE_NAME_LEN)
+		return -ENOENT;
+	if (len < 0)
+		return len;

 	audit_log_kern_module(name);

@@ -1320,20 +1322,11 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 	else
 		execmem_type = EXECMEM_MODULE_TEXT;

-	ptr = execmem_alloc(execmem_type, size);
+	ptr = execmem_alloc_rw(execmem_type, size);
 	if (!ptr)
 		return -ENOMEM;

-	if (execmem_is_rox(execmem_type)) {
-		int err = execmem_make_temp_rw(ptr, size);
-
-		if (err) {
-			execmem_free(ptr);
-			return -ENOMEM;
-		}
-
-		mod->mem[type].is_rox = true;
-	}
+	mod->mem[type].is_rox = execmem_is_rox(execmem_type);

 	/*
 	 * The pointer to these blocks of memory are stored on the module
@@ -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)
 {
@@ -64,6 +64,7 @@ struct dev_printk_info;

 extern struct printk_ringbuffer *prb;
 extern bool printk_kthreads_running;
+extern bool printk_kthreads_ready;
 extern bool debug_non_panic_cpus;

 __printf(4, 0)
@@ -179,6 +180,7 @@ static inline void nbcon_kthread_wake(struct console *con)
 #define PRINTKRB_RECORD_MAX	0

 #define printk_kthreads_running (false)
+#define printk_kthreads_ready (false)

 /*
 * In !PRINTK builds we still export console_sem
@@ -214,8 +214,9 @@ static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq)

 /**
 * nbcon_context_try_acquire_direct - Try to acquire directly
- * @ctxt:	The context of the caller
- * @cur:	The current console state
+ * @ctxt:		The context of the caller
+ * @cur:		The current console state
+ * @is_reacquire:	This acquire is a reacquire
 *
 * Acquire the console when it is released. Also acquire the console when
 * the current owner has a lower priority and the console is in a safe state.
@@ -225,17 +226,17 @@ static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq)
 *
 * Errors:
 *
- *	-EPERM:		A panic is in progress and this is not the panic CPU.
- *			Or the current owner or waiter has the same or higher
- *			priority. No acquire method can be successful in
- *			this case.
+ *	-EPERM:		A panic is in progress and this is neither the panic
+ *			CPU nor is this a reacquire. Or the current owner or
+ *			waiter has the same or higher priority. No acquire
+ *			method can be successful in these cases.
 *
 *	-EBUSY:		The current owner has a lower priority but the console
 *			in an unsafe state. The caller should try using
 *			the handover acquire method.
 */
 static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt,
-					    struct nbcon_state *cur)
+					    struct nbcon_state *cur, bool is_reacquire)
 {
 	unsigned int cpu = smp_processor_id();
 	struct console *con = ctxt->console;
@@ -243,14 +244,20 @@ static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt,

 	do {
 		/*
-		 * Panic does not imply that the console is owned. However, it
-		 * is critical that non-panic CPUs during panic are unable to
-		 * acquire ownership in order to satisfy the assumptions of
-		 * nbcon_waiter_matches(). In particular, the assumption that
-		 * lower priorities are ignored during panic.
+		 * Panic does not imply that the console is owned. However,
+		 * since all non-panic CPUs are stopped during panic(), it
+		 * is safer to have them avoid gaining console ownership.
+		 *
+		 * If this acquire is a reacquire (and an unsafe takeover
+		 * has not previously occurred) then it is allowed to attempt
+		 * a direct acquire in panic. This gives console drivers an
+		 * opportunity to perform any necessary cleanup if they were
+		 * interrupted by the panic CPU while printing.
 		 */
-		if (other_cpu_in_panic())
+		if (other_cpu_in_panic() &&
+		    (!is_reacquire || cur->unsafe_takeover)) {
 			return -EPERM;
+		}

 		if (ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio)
 			return -EPERM;
@@ -301,8 +308,9 @@ static bool nbcon_waiter_matches(struct nbcon_state *cur, int expected_prio)
 	 * Event #1 implies this context is EMERGENCY.
 	 * Event #2 implies the new context is PANIC.
 	 * Event #3 occurs when panic() has flushed the console.
-	 * Events #4 and #5 are not possible due to the other_cpu_in_panic()
-	 * check in nbcon_context_try_acquire_direct().
+	 * Event #4 occurs when a non-panic CPU reacquires.
+	 * Event #5 is not possible due to the other_cpu_in_panic() check
+	 *          in nbcon_context_try_acquire_handover().
 	 */

 	return (cur->req_prio == expected_prio);
@@ -431,6 +439,16 @@ static int nbcon_context_try_acquire_handover(struct nbcon_context *ctxt,
 	WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio);
 	WARN_ON_ONCE(!cur->unsafe);

+	/*
+	 * Panic does not imply that the console is owned. However, it
+	 * is critical that non-panic CPUs during panic are unable to
+	 * wait for a handover in order to satisfy the assumptions of
+	 * nbcon_waiter_matches(). In particular, the assumption that
+	 * lower priorities are ignored during panic.
+	 */
+	if (other_cpu_in_panic())
+		return -EPERM;
+
 	/* Handover is not possible on the same CPU. */
 	if (cur->cpu == cpu)
 		return -EBUSY;
@@ -558,7 +576,8 @@ static struct printk_buffers panic_nbcon_pbufs;

 /**
 * nbcon_context_try_acquire - Try to acquire nbcon console
- * @ctxt:	The context of the caller
+ * @ctxt:		The context of the caller
+ * @is_reacquire:	This acquire is a reacquire
 *
 * Context:	Under @ctxt->con->device_lock() or local_irq_save().
 * Return:	True if the console was acquired. False otherwise.
@@ -568,7 +587,7 @@ static struct printk_buffers panic_nbcon_pbufs;
 * in an unsafe state. Otherwise, on success the caller may assume
 * the console is not in an unsafe state.
 */
-static bool nbcon_context_try_acquire(struct nbcon_context *ctxt)
+static bool nbcon_context_try_acquire(struct nbcon_context *ctxt, bool is_reacquire)
 {
 	unsigned int cpu = smp_processor_id();
 	struct console *con = ctxt->console;
@@ -577,7 +596,7 @@ static bool nbcon_context_try_acquire(struct nbcon_context *ctxt)

 	nbcon_state_read(con, &cur);
 try_again:
-	err = nbcon_context_try_acquire_direct(ctxt, &cur);
+	err = nbcon_context_try_acquire_direct(ctxt, &cur, is_reacquire);
 	if (err != -EBUSY)
 		goto out;

@@ -913,7 +932,7 @@ void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt)
 {
 	struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);

-	while (!nbcon_context_try_acquire(ctxt))
+	while (!nbcon_context_try_acquire(ctxt, true))
 		cpu_relax();

 	nbcon_write_context_set_buf(wctxt, NULL, 0);
@@ -1101,7 +1120,7 @@ static bool nbcon_emit_one(struct nbcon_write_context *wctxt, bool use_atomic)
 		cant_migrate();
 	}

-	if (!nbcon_context_try_acquire(ctxt))
+	if (!nbcon_context_try_acquire(ctxt, false))
 		goto out;

 	/*
@@ -1486,7 +1505,7 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq,
 	ctxt->prio			= nbcon_get_default_prio();
 	ctxt->allow_unsafe_takeover	= allow_unsafe_takeover;

-	if (!nbcon_context_try_acquire(ctxt))
+	if (!nbcon_context_try_acquire(ctxt, false))
 		return -EPERM;

 	while (nbcon_seq_read(con) < stop_seq) {
@@ -1671,6 +1690,9 @@ bool nbcon_alloc(struct console *con)
 {
 	struct nbcon_state state = { };

+	/* Synchronize the kthread start. */
+	lockdep_assert_console_list_lock_held();
+
 	/* The write_thread() callback is mandatory. */
 	if (WARN_ON(!con->write_thread))
 		return false;
@@ -1701,12 +1723,15 @@ bool nbcon_alloc(struct console *con)
 			return false;
 		}

-		if (printk_kthreads_running) {
+		if (printk_kthreads_ready && !have_boot_console) {
 			if (!nbcon_kthread_create(con)) {
 				kfree(con->pbufs);
 				con->pbufs = NULL;
 				return false;
 			}
+
+			/* Might be the first kthread. */
+			printk_kthreads_running = true;
 		}
 	}

@@ -1716,14 +1741,30 @@ bool nbcon_alloc(struct console *con)
 /**
 * nbcon_free - Free and cleanup the nbcon console specific data
 * @con:	Console to free/cleanup nbcon data
+ *
+ * Important: @have_nbcon_console must be updated before calling
+ *	this function. In particular, it can be set only when there
+ *	is still another nbcon console registered.
 */
 void nbcon_free(struct console *con)
 {
 	struct nbcon_state state = { };

-	if (printk_kthreads_running)
+	/* Synchronize the kthread stop. */
+	lockdep_assert_console_list_lock_held();
+
+	if (printk_kthreads_running) {
 		nbcon_kthread_stop(con);

+		/* Might be the last nbcon console.
+		 *
+		 * Do not rely on printk_kthreads_check_locked(). It is not
+		 * called in some code paths, see nbcon_free() callers.
+		 */
+		if (!have_nbcon_console)
+			printk_kthreads_running = false;
+	}
+
 	nbcon_state_set(con, &state);

 	/* Boot consoles share global printk buffers. */
@@ -1762,7 +1803,7 @@ bool nbcon_device_try_acquire(struct console *con)
 	ctxt->console	= con;
 	ctxt->prio	= NBCON_PRIO_NORMAL;

-	if (!nbcon_context_try_acquire(ctxt))
+	if (!nbcon_context_try_acquire(ctxt, false))
 		return false;

 	if (!nbcon_context_enter_unsafe(ctxt))
@@ -3574,7 +3574,7 @@ EXPORT_SYMBOL(console_resume);
 static int unregister_console_locked(struct console *console);

 /* True when system boot is far enough to create printer threads. */
-static bool printk_kthreads_ready __ro_after_init;
+bool printk_kthreads_ready __ro_after_init;

 static struct task_struct *printk_legacy_kthread;

@@ -3713,6 +3713,7 @@ static void printk_kthreads_check_locked(void)
 	if (!printk_kthreads_ready)
 		return;

+	/* Start or stop the legacy kthread when needed. */
 	if (have_legacy_console || have_boot_console) {
 		if (!printk_legacy_kthread &&
 		    force_legacy_kthread() &&
@@ -4204,14 +4205,6 @@ static int unregister_console_locked(struct console *console)
 	 */
 	synchronize_srcu(&console_srcu);

-	if (console->flags & CON_NBCON)
-		nbcon_free(console);
-
-	console_sysfs_notify();
-
-	if (console->exit)
-		res = console->exit(console);
-
 	/*
 	 * With this console gone, the global flags tracking registered
 	 * console types may have changed. Update them.
@@ -4232,6 +4225,15 @@ static int unregister_console_locked(struct console *console)
 	if (!found_nbcon_con)
 		have_nbcon_console = found_nbcon_con;

+	/* @have_nbcon_console must be updated before calling nbcon_free(). */
+	if (console->flags & CON_NBCON)
+		nbcon_free(console);
+
+	console_sysfs_notify();
+
+	if (console->exit)
+		res = console->exit(console);
+
 	/* Changed console list, may require printer threads to start/stop. */
 	printk_kthreads_check_locked();

@@ -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);
@@ -693,6 +696,42 @@ 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
@@ -176,7 +176,7 @@ struct psi_group psi_system = {
 	.pcpu = &system_group_pcpu,
 };

-static DEFINE_PER_CPU(seqcount_t, psi_seq);
+static DEFINE_PER_CPU(seqcount_t, psi_seq) = SEQCNT_ZERO(psi_seq);

 static inline void psi_write_begin(int cpu)
 {
@@ -204,11 +204,7 @@ static void poll_timer_fn(struct timer_list *t);

 static void group_init(struct psi_group *group)
 {
-	int cpu;
-
 	group->enabled = true;
-	for_each_possible_cpu(cpu)
-		seqcount_init(per_cpu_ptr(&psi_seq, cpu));
 	group->avg_last_update = sched_clock();
 	group->avg_next_update = group->avg_last_update + psi_period;
 	mutex_init(&group->avgs_lock);
@@ -1018,7 +1018,7 @@ void __init smp_init(void)
 * @cond_func:	A callback function that is passed a cpu id and
 *		the info parameter. The function is called
 *		with preemption disabled. The function should
- *		return a blooean value indicating whether to IPI
+ *		return a boolean value indicating whether to IPI
 *		the specified CPU.
 * @func:	The function to run on all applicable CPUs.
 *		This must be fast and non-blocking.
@@ -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;
@@ -4812,26 +4812,26 @@ int ring_buffer_write(struct trace_buffer *buffer,
 	int ret = -EBUSY;
 	int cpu;

-	preempt_disable_notrace();
+	guard(preempt_notrace)();

 	if (atomic_read(&buffer->record_disabled))
-		goto out;
+		return -EBUSY;

 	cpu = raw_smp_processor_id();

 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
-		goto out;
+		return -EBUSY;

 	cpu_buffer = buffer->buffers[cpu];

 	if (atomic_read(&cpu_buffer->record_disabled))
-		goto out;
+		return -EBUSY;

 	if (length > buffer->max_data_size)
-		goto out;
+		return -EBUSY;

 	if (unlikely(trace_recursive_lock(cpu_buffer)))
-		goto out;
+		return -EBUSY;

 	event = rb_reserve_next_event(buffer, cpu_buffer, length);
 	if (!event)
@@ -4849,10 +4849,6 @@ int ring_buffer_write(struct trace_buffer *buffer,

 out_unlock:
 	trace_recursive_unlock(cpu_buffer);
-
- out:
-	preempt_enable_notrace();
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_write);
@@ -432,15 +432,13 @@ static void ftrace_exports(struct ring_buffer_event *event, int flag)
 {
 	struct trace_export *export;

-	preempt_disable_notrace();
+	guard(preempt_notrace)();

 	export = rcu_dereference_raw_check(ftrace_exports_list);
 	while (export) {
 		trace_process_export(export, event, flag);
 		export = rcu_dereference_raw_check(export->next);
 	}
-
-	preempt_enable_notrace();
 }

 static inline void
@@ -497,27 +495,18 @@ int register_ftrace_export(struct trace_export *export)
 	if (WARN_ON_ONCE(!export->write))
 		return -1;

-	mutex_lock(&ftrace_export_lock);
+	guard(mutex)(&ftrace_export_lock);

 	add_ftrace_export(&ftrace_exports_list, export);

-	mutex_unlock(&ftrace_export_lock);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(register_ftrace_export);

 int unregister_ftrace_export(struct trace_export *export)
 {
-	int ret;
-
-	mutex_lock(&ftrace_export_lock);
-
-	ret = rm_ftrace_export(&ftrace_exports_list, export);
-
-	mutex_unlock(&ftrace_export_lock);
-
-	return ret;
+	guard(mutex)(&ftrace_export_lock);
+	return rm_ftrace_export(&ftrace_exports_list, export);
 }
 EXPORT_SYMBOL_GPL(unregister_ftrace_export);

@@ -640,9 +629,8 @@ void trace_array_put(struct trace_array *this_tr)
 	if (!this_tr)
 		return;

-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);
 	__trace_array_put(this_tr);
-	mutex_unlock(&trace_types_lock);
 }
 EXPORT_SYMBOL_GPL(trace_array_put);

@@ -1160,13 +1148,11 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip,

 	trace_ctx = tracing_gen_ctx();
 	buffer = tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
+	guard(ring_buffer_nest)(buffer);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
 					    trace_ctx);
-	if (!event) {
-		size = 0;
-		goto out;
-	}
+	if (!event)
+		return 0;

 	entry = ring_buffer_event_data(event);
 	entry->ip = ip;
@@ -1182,8 +1168,6 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip,

 	__buffer_unlock_commit(buffer, event);
 	ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL);
- out:
-	ring_buffer_nest_end(buffer);
 	return size;
 }
 EXPORT_SYMBOL_GPL(__trace_array_puts);
@@ -1213,7 +1197,6 @@ int __trace_bputs(unsigned long ip, const char *str)
 	struct bputs_entry *entry;
 	unsigned int trace_ctx;
 	int size = sizeof(struct bputs_entry);
-	int ret = 0;

 	if (!printk_binsafe(tr))
 		return __trace_puts(ip, str, strlen(str));
@@ -1227,11 +1210,11 @@ int __trace_bputs(unsigned long ip, const char *str)
 	trace_ctx = tracing_gen_ctx();
 	buffer = tr->array_buffer.buffer;

-	ring_buffer_nest_start(buffer);
+	guard(ring_buffer_nest)(buffer);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
 					    trace_ctx);
 	if (!event)
-		goto out;
+		return 0;

 	entry = ring_buffer_event_data(event);
 	entry->ip			= ip;
@@ -1240,10 +1223,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	__buffer_unlock_commit(buffer, event);
 	ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL);

-	ret = 1;
- out:
-	ring_buffer_nest_end(buffer);
-	return ret;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(__trace_bputs);

@@ -1432,13 +1412,8 @@ static int tracing_arm_snapshot_locked(struct trace_array *tr)

 int tracing_arm_snapshot(struct trace_array *tr)
 {
-	int ret;
-
-	mutex_lock(&trace_types_lock);
-	ret = tracing_arm_snapshot_locked(tr);
-	mutex_unlock(&trace_types_lock);
-
-	return ret;
+	guard(mutex)(&trace_types_lock);
+	return tracing_arm_snapshot_locked(tr);
 }

 void tracing_disarm_snapshot(struct trace_array *tr)
@@ -1841,7 +1816,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,

 	ret = get_user(ch, ubuf++);
 	if (ret)
-		goto out;
+		return ret;

 	read++;
 	cnt--;
@@ -1855,7 +1830,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		while (cnt && isspace(ch)) {
 			ret = get_user(ch, ubuf++);
 			if (ret)
-				goto out;
+				return ret;
 			read++;
 			cnt--;
 		}
@@ -1865,8 +1840,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		/* only spaces were written */
 		if (isspace(ch) || !ch) {
 			*ppos += read;
-			ret = read;
-			goto out;
+			return read;
 		}
 	}

@@ -1874,13 +1848,12 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 	while (cnt && !isspace(ch) && ch) {
 		if (parser->idx < parser->size - 1)
 			parser->buffer[parser->idx++] = ch;
-		else {
-			ret = -EINVAL;
-			goto out;
-		}
+		else
+			return -EINVAL;
+
 		ret = get_user(ch, ubuf++);
 		if (ret)
-			goto out;
+			return ret;
 		read++;
 		cnt--;
 	}
@@ -1895,15 +1868,11 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		/* Make sure the parsed string always terminates with '\0'. */
 		parser->buffer[parser->idx] = 0;
 	} else {
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}

 	*ppos += read;
-	ret = read;
-
-out:
-	return ret;
+	return read;
 }

 /* TODO add a seq_buf_to_buffer() */
@@ -2405,10 +2374,10 @@ int __init register_tracer(struct tracer *type)
 	mutex_unlock(&trace_types_lock);

 	if (ret || !default_bootup_tracer)
-		goto out_unlock;
+		return ret;

 	if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE))
-		goto out_unlock;
+		return 0;

 	printk(KERN_INFO "Starting tracer '%s'\n", type->name);
 	/* Do we want this tracer to start on bootup? */
@@ -2420,8 +2389,7 @@ int __init register_tracer(struct tracer *type)
 	/* disable other selftests, since this will break it. */
 	disable_tracing_selftest("running a tracer");

- out_unlock:
-	return ret;
+	return 0;
 }

 static void tracing_reset_cpu(struct array_buffer *buf, int cpu)
@@ -2498,9 +2466,8 @@ void tracing_reset_all_online_cpus_unlocked(void)

 void tracing_reset_all_online_cpus(void)
 {
-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);
 	tracing_reset_all_online_cpus_unlocked();
-	mutex_unlock(&trace_types_lock);
 }

 int is_tracing_stopped(void)
@@ -2511,18 +2478,17 @@ int is_tracing_stopped(void)
 static void tracing_start_tr(struct trace_array *tr)
 {
 	struct trace_buffer *buffer;
-	unsigned long flags;

 	if (tracing_disabled)
 		return;

-	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	guard(raw_spinlock_irqsave)(&tr->start_lock);
 	if (--tr->stop_count) {
 		if (WARN_ON_ONCE(tr->stop_count < 0)) {
 			/* Someone screwed up their debugging */
 			tr->stop_count = 0;
 		}
-		goto out;
+		return;
 	}

 	/* Prevent the buffers from switching */
@@ -2539,9 +2505,6 @@ static void tracing_start_tr(struct trace_array *tr)
 #endif

 	arch_spin_unlock(&tr->max_lock);
-
- out:
-	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }

 /**
@@ -2559,11 +2522,10 @@ void tracing_start(void)
 static void tracing_stop_tr(struct trace_array *tr)
 {
 	struct trace_buffer *buffer;
-	unsigned long flags;

-	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	guard(raw_spinlock_irqsave)(&tr->start_lock);
 	if (tr->stop_count++)
-		goto out;
+		return;

 	/* Prevent the buffers from switching */
 	arch_spin_lock(&tr->max_lock);
@@ -2579,9 +2541,6 @@ static void tracing_stop_tr(struct trace_array *tr)
 #endif

 	arch_spin_unlock(&tr->max_lock);
-
- out:
-	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }

 /**
@@ -2694,12 +2653,12 @@ void trace_buffered_event_enable(void)

 		per_cpu(trace_buffered_event, cpu) = event;

-		preempt_disable();
-		if (cpu == smp_processor_id() &&
-		    __this_cpu_read(trace_buffered_event) !=
-		    per_cpu(trace_buffered_event, cpu))
-			WARN_ON_ONCE(1);
-		preempt_enable();
+		scoped_guard(preempt,) {
+			if (cpu == smp_processor_id() &&
+			    __this_cpu_read(trace_buffered_event) !=
+			    per_cpu(trace_buffered_event, cpu))
+				WARN_ON_ONCE(1);
+		}
 	}
 }

@@ -3044,7 +3003,7 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 		skip++;
 #endif

-	preempt_disable_notrace();
+	guard(preempt_notrace)();

 	stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;

@@ -3102,8 +3061,6 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 	/* Again, don't let gcc optimize things here */
 	barrier();
 	__this_cpu_dec(ftrace_stack_reserve);
-	preempt_enable_notrace();
-
 }

 static inline void ftrace_trace_stack(struct trace_array *tr,
@@ -3186,9 +3143,9 @@ ftrace_trace_userstack(struct trace_array *tr,
 	 * prevent recursion, since the user stack tracing may
 	 * trigger other kernel events.
 	 */
-	preempt_disable();
+	guard(preempt)();
 	if (__this_cpu_read(user_stack_count))
-		goto out;
+		return;

 	__this_cpu_inc(user_stack_count);

@@ -3206,8 +3163,6 @@ ftrace_trace_userstack(struct trace_array *tr,

 out_drop_count:
 	__this_cpu_dec(user_stack_count);
- out:
-	preempt_enable();
 }
 #else /* CONFIG_USER_STACKTRACE_SUPPORT */
 static void ftrace_trace_userstack(struct trace_array *tr,
@@ -3389,7 +3344,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	pause_graph_tracing();

 	trace_ctx = tracing_gen_ctx();
-	preempt_disable_notrace();
+	guard(preempt_notrace)();

 	tbuffer = get_trace_buf();
 	if (!tbuffer) {
@@ -3404,26 +3359,23 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)

 	size = sizeof(*entry) + sizeof(u32) * len;
 	buffer = tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
-	event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
-					    trace_ctx);
-	if (!event)
-		goto out;
-	entry = ring_buffer_event_data(event);
-	entry->ip			= ip;
-	entry->fmt			= fmt;
+	scoped_guard(ring_buffer_nest, buffer) {
+		event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
+						    trace_ctx);
+		if (!event)
+			goto out_put;
+		entry = ring_buffer_event_data(event);
+		entry->ip			= ip;
+		entry->fmt			= fmt;

-	memcpy(entry->buf, tbuffer, sizeof(u32) * len);
-	__buffer_unlock_commit(buffer, event);
-	ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
-
-out:
-	ring_buffer_nest_end(buffer);
+		memcpy(entry->buf, tbuffer, sizeof(u32) * len);
+		__buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
+	}
 out_put:
 	put_trace_buf();

 out_nobuffer:
-	preempt_enable_notrace();
 	unpause_graph_tracing();

 	return len;
@@ -3447,7 +3399,7 @@ int __trace_array_vprintk(struct trace_buffer *buffer,
 	pause_graph_tracing();

 	trace_ctx = tracing_gen_ctx();
-	preempt_disable_notrace();
+	guard(preempt_notrace)();


 	tbuffer = get_trace_buf();
@@ -3459,24 +3411,22 @@ int __trace_array_vprintk(struct trace_buffer *buffer,
 	len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);

 	size = sizeof(*entry) + len + 1;
-	ring_buffer_nest_start(buffer);
-	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
-					    trace_ctx);
-	if (!event)
-		goto out;
-	entry = ring_buffer_event_data(event);
-	entry->ip = ip;
-
-	memcpy(&entry->buf, tbuffer, len + 1);
-	__buffer_unlock_commit(buffer, event);
-	ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL);
+	scoped_guard(ring_buffer_nest, buffer) {
+		event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+						    trace_ctx);
+		if (!event)
+			goto out;
+		entry = ring_buffer_event_data(event);
+		entry->ip = ip;

+		memcpy(&entry->buf, tbuffer, len + 1);
+		__buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL);
+	}
 out:
-	ring_buffer_nest_end(buffer);
 	put_trace_buf();

 out_nobuffer:
-	preempt_enable_notrace();
 	unpause_graph_tracing();

 	return len;
@@ -4800,20 +4750,16 @@ int tracing_open_file_tr(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;

-	mutex_lock(&event_mutex);
+	guard(mutex)(&event_mutex);

 	/* Fail if the file is marked for removal */
 	if (file->flags & EVENT_FILE_FL_FREED) {
 		trace_array_put(file->tr);
-		ret = -ENODEV;
+		return -ENODEV;
 	} else {
 		event_file_get(file);
 	}

-	mutex_unlock(&event_mutex);
-	if (ret)
-		return ret;
-
 	filp->private_data = inode->i_private;

 	return 0;
@@ -5090,7 +5036,7 @@ tracing_cpumask_read(struct file *filp, char __user *ubuf,
 		     size_t count, loff_t *ppos)
 {
 	struct trace_array *tr = file_inode(filp)->i_private;
-	char *mask_str;
+	char *mask_str __free(kfree) = NULL;
 	int len;

 	len = snprintf(NULL, 0, "%*pb\n",
@@ -5101,16 +5047,10 @@ tracing_cpumask_read(struct file *filp, char __user *ubuf,

 	len = snprintf(mask_str, len, "%*pb\n",
 		       cpumask_pr_args(tr->tracing_cpumask));
-	if (len >= count) {
-		count = -EINVAL;
-		goto out_err;
-	}
-	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
+	if (len >= count)
+		return -EINVAL;

-out_err:
-	kfree(mask_str);
-
-	return count;
+	return simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
 }

 int tracing_set_cpumask(struct trace_array *tr,
@@ -5957,9 +5897,9 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf,
 	char buf[MAX_TRACER_SIZE+2];
 	int r;

-	mutex_lock(&trace_types_lock);
-	r = sprintf(buf, "%s\n", tr->current_trace->name);
-	mutex_unlock(&trace_types_lock);
+	scoped_guard(mutex, &trace_types_lock) {
+		r = sprintf(buf, "%s\n", tr->current_trace->name);
+	}

 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
@@ -6261,15 +6201,13 @@ int tracing_update_buffers(struct trace_array *tr)
 {
 	int ret = 0;

-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);

 	update_last_data(tr);

 	if (!tr->ring_buffer_expanded)
 		ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
 						RING_BUFFER_ALL_CPUS);
-	mutex_unlock(&trace_types_lock);
-
 	return ret;
 }

@@ -6566,7 +6504,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;

-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);
 	cpu = tracing_get_cpu(inode);
 	ret = open_pipe_on_cpu(tr, cpu);
 	if (ret)
@@ -6610,7 +6548,6 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)

 	tr->trace_ref++;

-	mutex_unlock(&trace_types_lock);
 	return ret;

 fail:
@@ -6619,7 +6556,6 @@ fail_alloc_iter:
 	close_pipe_on_cpu(tr, cpu);
 fail_pipe_on_cpu:
 	__trace_array_put(tr);
-	mutex_unlock(&trace_types_lock);
 	return ret;
 }

@@ -6628,14 +6564,13 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 	struct trace_iterator *iter = file->private_data;
 	struct trace_array *tr = inode->i_private;

-	mutex_lock(&trace_types_lock);
+	scoped_guard(mutex, &trace_types_lock) {
+		tr->trace_ref--;

-	tr->trace_ref--;
-
-	if (iter->trace->pipe_close)
-		iter->trace->pipe_close(iter);
-	close_pipe_on_cpu(tr, iter->cpu_file);
-	mutex_unlock(&trace_types_lock);
+		if (iter->trace->pipe_close)
+			iter->trace->pipe_close(iter);
+		close_pipe_on_cpu(tr, iter->cpu_file);
+	}

 	free_trace_iter_content(iter);
 	kfree(iter);
@@ -7438,7 +7373,7 @@ int tracing_set_clock(struct trace_array *tr, const char *clockstr)
 	if (i == ARRAY_SIZE(trace_clocks))
 		return -EINVAL;

-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);

 	tr->clock_id = i;

@@ -7462,8 +7397,6 @@ int tracing_set_clock(struct trace_array *tr, const char *clockstr)
 		tscratch->clock_id = i;
 	}

-	mutex_unlock(&trace_types_lock);
-
 	return 0;
 }

@@ -7515,15 +7448,13 @@ static int tracing_time_stamp_mode_show(struct seq_file *m, void *v)
 {
 	struct trace_array *tr = m->private;

-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);

 	if (ring_buffer_time_stamp_abs(tr->array_buffer.buffer))
 		seq_puts(m, "delta [absolute]\n");
 	else
 		seq_puts(m, "[delta] absolute\n");

-	mutex_unlock(&trace_types_lock);
-
 	return 0;
 }

@@ -8111,14 +8042,14 @@ static void clear_tracing_err_log(struct trace_array *tr)
 {
 	struct tracing_log_err *err, *next;

-	mutex_lock(&tracing_err_log_lock);
+	guard(mutex)(&tracing_err_log_lock);
+
 	list_for_each_entry_safe(err, next, &tr->err_log, list) {
 		list_del(&err->list);
 		free_tracing_log_err(err);
 	}

 	tr->n_err_log_entries = 0;
-	mutex_unlock(&tracing_err_log_lock);
 }

 static void *tracing_err_log_seq_start(struct seq_file *m, loff_t *pos)
@@ -8389,7 +8320,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 	struct ftrace_buffer_info *info = file->private_data;
 	struct trace_iterator *iter = &info->iter;

-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);

 	iter->tr->trace_ref--;

@@ -8400,8 +8331,6 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 					   info->spare_cpu, info->spare);
 	kvfree(info);

-	mutex_unlock(&trace_types_lock);
-
 	return 0;
 }

@@ -8609,14 +8538,13 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned
 	 * An ioctl call with cmd 0 to the ring buffer file will wake up all
 	 * waiters
 	 */
-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);

 	/* Make sure the waiters see the new wait_index */
 	(void)atomic_fetch_inc_release(&iter->wait_index);

 	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);

-	mutex_unlock(&trace_types_lock);
 	return 0;
 }

@@ -8957,12 +8885,12 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash,
 out_reg:
 	ret = tracing_arm_snapshot(tr);
 	if (ret < 0)
-		goto out;
+		return ret;

 	ret = register_ftrace_function_probe(glob, tr, ops, count);
 	if (ret < 0)
 		tracing_disarm_snapshot(tr);
- out:
+
 	return ret < 0 ? ret : 0;
 }

@@ -9106,10 +9034,9 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		return -EINVAL;

 	if (!!(topt->flags->val & topt->opt->bit) != val) {
-		mutex_lock(&trace_types_lock);
+		guard(mutex)(&trace_types_lock);
 		ret = __set_tracer_option(topt->tr, topt->flags,
 					  topt->opt, !val);
-		mutex_unlock(&trace_types_lock);
 		if (ret)
 			return ret;
 	}
@@ -9418,7 +9345,7 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 		return ret;

 	if (buffer) {
-		mutex_lock(&trace_types_lock);
+		guard(mutex)(&trace_types_lock);
 		if (!!val == tracer_tracing_is_on(tr)) {
 			val = 0; /* do nothing */
 		} else if (val) {
@@ -9432,7 +9359,6 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 			/* Wake up any waiters */
 			ring_buffer_wake_waiters(buffer, RING_BUFFER_ALL_CPUS);
 		}
-		mutex_unlock(&trace_types_lock);
 	}

 	(*ppos)++;
@@ -9816,10 +9742,9 @@ static void __update_tracer_options(struct trace_array *tr)

 static void update_tracer_options(struct trace_array *tr)
 {
-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);
 	tracer_options_updated = true;
 	__update_tracer_options(tr);
-	mutex_unlock(&trace_types_lock);
 }

 /* Must have trace_types_lock held */
@@ -9841,11 +9766,10 @@ struct trace_array *trace_array_find_get(const char *instance)
 {
 	struct trace_array *tr;

-	mutex_lock(&trace_types_lock);
+	guard(mutex)(&trace_types_lock);
 	tr = trace_array_find(instance);
 	if (tr)
 		tr->ref++;
-	mutex_unlock(&trace_types_lock);

 	return tr;
 }
@@ -10376,7 +10300,7 @@ bool module_exists(const char *module)
 {
 	/* All modules have the symbol __this_module */
 	static const char this_mod[] = "__this_module";
-	char modname[MAX_PARAM_PREFIX_LEN + sizeof(this_mod) + 2];
+	char modname[MODULE_NAME_LEN + sizeof(this_mod) + 2];
 	unsigned long val;
 	int n;

@@ -10803,7 +10727,8 @@ ssize_t trace_parse_run_command(struct file *file, const char __user *buffer,
 				size_t count, loff_t *ppos,
 				int (*createfn)(const char *))
 {
-	char *kbuf, *buf, *tmp;
+	char *kbuf __free(kfree) = NULL;
+	char *buf, *tmp;
 	int ret = 0;
 	size_t done = 0;
 	size_t size;
@@ -10818,10 +10743,9 @@ ssize_t trace_parse_run_command(struct file *file, const char __user *buffer,
 		if (size >= WRITE_BUFSIZE)
 			size = WRITE_BUFSIZE - 1;

-		if (copy_from_user(kbuf, buffer + done, size)) {
-			ret = -EFAULT;
-			goto out;
-		}
+		if (copy_from_user(kbuf, buffer + done, size))
+			return -EFAULT;
+
 		kbuf[size] = '\0';
 		buf = kbuf;
 		do {
@@ -10837,8 +10761,7 @@ ssize_t trace_parse_run_command(struct file *file, const char __user *buffer,
 					/* This can accept WRITE_BUFSIZE - 2 ('\n' + '\0') */
 					pr_warn("Line length is too long: Should be less than %d\n",
 						WRITE_BUFSIZE - 2);
-					ret = -EINVAL;
-					goto out;
+					return -EINVAL;
 				}
 			}
 			done += size;
@@ -10851,17 +10774,12 @@ ssize_t trace_parse_run_command(struct file *file, const char __user *buffer,

 			ret = createfn(buf);
 			if (ret)
-				goto out;
+				return ret;
 			buf += size;

 		} while (done < count);
 	}
-	ret = done;
-
-out:
-	kfree(kbuf);
-
-	return ret;
+	return done;
 }

 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -11064,7 +10982,7 @@ __init static int tracer_alloc_buffers(void)
 	BUILD_BUG_ON(TRACE_ITER_LAST_BIT > TRACE_FLAGS_MAX_SIZE);

 	if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
-		goto out;
+		return -ENOMEM;

 	if (!alloc_cpumask_var(&global_trace.tracing_cpumask, GFP_KERNEL))
 		goto out_free_buffer_mask;
@@ -11182,7 +11100,6 @@ out_free_cpumask:
 	free_cpumask_var(global_trace.tracing_cpumask);
 out_free_buffer_mask:
 	free_cpumask_var(tracing_buffer_mask);
-out:
 	return ret;
 }

@@ -536,12 +536,12 @@ static notrace void trace_event_raw_event_synth(void *__data,
 	 * is being performed within another event.
 	 */
 	buffer = trace_file->tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
+	guard(ring_buffer_nest)(buffer);

 	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
 					   sizeof(*entry) + fields_size);
 	if (!entry)
-		goto out;
+		return;

 	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
 		val_idx = var_ref_idx[i];
@@ -584,8 +584,6 @@ static notrace void trace_event_raw_event_synth(void *__data,
 	}

 	trace_event_buffer_commit(&fbuffer);
-out:
-	ring_buffer_nest_end(buffer);
 }

 static void free_synth_event_print_fmt(struct trace_event_call *call)
@@ -701,6 +701,7 @@ void print_function_args(struct trace_seq *s, unsigned long *args,
 	struct btf *btf;
 	s32 tid, nr = 0;
 	int a, p, x;
+	u16 encode;

 	trace_seq_printf(s, "(");

@@ -744,7 +745,12 @@ void print_function_args(struct trace_seq *s, unsigned long *args,
 			trace_seq_printf(s, "0x%lx", arg);
 			break;
 		case BTF_KIND_INT:
-			trace_seq_printf(s, "%ld", arg);
+			encode = btf_int_encoding(t);
+			/* Print unsigned ints as hex */
+			if (encode & BTF_INT_SIGNED)
+				trace_seq_printf(s, "%ld", arg);
+			else
+				trace_seq_printf(s, "0x%lx", arg);
 			break;
 		case BTF_KIND_ENUM:
 			trace_seq_printf(s, "%ld", arg);
@@ -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,