Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts or adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

19 files changed, 191 insertions, 190 deletions

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8a33e8747a0e..6ae02be7a48e 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -122,22 +122,6 @@ static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 	atomic_inc(&rcpu->refcnt);
 }
 
-/* called from workqueue, to workaround syscall using preempt_disable */
-static void cpu_map_kthread_stop(struct work_struct *work)
-{
-	struct bpf_cpu_map_entry *rcpu;
-
-	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
-
-	/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
-	 * as it waits until all in-flight call_rcu() callbacks complete.
-	 */
-	rcu_barrier();
-
-	/* kthread_stop will wake_up_process and wait for it to complete */
-	kthread_stop(rcpu->kthread);
-}
-
 static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 {
 	/* The tear-down procedure should have made sure that queue is
@@ -165,6 +149,30 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 	}
 }
 
+/* called from workqueue, to workaround syscall using preempt_disable */
+static void cpu_map_kthread_stop(struct work_struct *work)
+{
+	struct bpf_cpu_map_entry *rcpu;
+	int err;
+
+	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
+
+	/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
+	 * as it waits until all in-flight call_rcu() callbacks complete.
+	 */
+	rcu_barrier();
+
+	/* kthread_stop will wake_up_process and wait for it to complete */
+	err = kthread_stop(rcpu->kthread);
+	if (err) {
+		/* kthread_stop may be called before cpu_map_kthread_run
+		 * is executed, so we need to release the memory related
+		 * to rcpu.
+		 */
+		put_cpu_map_entry(rcpu);
+	}
+}
+
 static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
 				     struct list_head *listp,
 				     struct xdp_cpumap_stats *stats)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 11e54dd8b6dd..930b5555cfd3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5642,8 +5642,9 @@ continue_func:
 				verbose(env, "verifier bug. subprog has tail_call and async cb\n");
 				return -EFAULT;
 			}
-			 /* async callbacks don't increase bpf prog stack size */
-			continue;
+			/* async callbacks don't increase bpf prog stack size unless called directly */
+			if (!bpf_pseudo_call(insn + i))
+				continue;
 		}
 		i = next_insn;
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 775f7bb10ab1..2b83e3ad9dca 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -115,9 +115,16 @@ static bool round_up_default_nslabs(void)
 	return true;
 }
 
+/**
+ * swiotlb_adjust_nareas() - adjust the number of areas and slots
+ * @nareas:	Desired number of areas. Zero is treated as 1.
+ *
+ * Adjust the default number of areas in a memory pool.
+ * The default size of the memory pool may also change to meet minimum area
+ * size requirements.
+ */
 static void swiotlb_adjust_nareas(unsigned int nareas)
 {
-	/* use a single area when non is specified */
 	if (!nareas)
 		nareas = 1;
 	else if (!is_power_of_2(nareas))
@@ -131,6 +138,23 @@ static void swiotlb_adjust_nareas(unsigned int nareas)
 			(default_nslabs << IO_TLB_SHIFT) >> 20);
 }
 
+/**
+ * limit_nareas() - get the maximum number of areas for a given memory pool size
+ * @nareas:	Desired number of areas.
+ * @nslots:	Total number of slots in the memory pool.
+ *
+ * Limit the number of areas to the maximum possible number of areas in
+ * a memory pool of the given size.
+ *
+ * Return: Maximum possible number of areas.
+ */
+static unsigned int limit_nareas(unsigned int nareas, unsigned long nslots)
+{
+	if (nslots < nareas * IO_TLB_SEGSIZE)
+		return nslots / IO_TLB_SEGSIZE;
+	return nareas;
+}
+
 static int __init
 setup_io_tlb_npages(char *str)
 {
@@ -290,6 +314,7 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 {
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long nslabs;
+	unsigned int nareas;
 	size_t alloc_size;
 	void *tlb;
 
@@ -298,18 +323,16 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 	if (swiotlb_force_disable)
 		return;
 
-	/*
-	 * default_nslabs maybe changed when adjust area number.
-	 * So allocate bounce buffer after adjusting area number.
-	 */
 	if (!default_nareas)
 		swiotlb_adjust_nareas(num_possible_cpus());
 
 	nslabs = default_nslabs;
+	nareas = limit_nareas(default_nareas, nslabs);
 	while ((tlb = swiotlb_memblock_alloc(nslabs, flags, remap)) == NULL) {
 		if (nslabs <= IO_TLB_MIN_SLABS)
 			return;
 		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+		nareas = limit_nareas(nareas, nslabs);
 	}
 
 	if (default_nslabs != nslabs) {
@@ -355,6 +378,7 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 {
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
+	unsigned int nareas;
 	unsigned char *vstart = NULL;
 	unsigned int order, area_order;
 	bool retried = false;
@@ -363,6 +387,9 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 	if (swiotlb_force_disable)
 		return 0;
 
+	if (!default_nareas)
+		swiotlb_adjust_nareas(num_possible_cpus());
+
 retry:
 	order = get_order(nslabs << IO_TLB_SHIFT);
 	nslabs = SLABS_PER_PAGE << order;
@@ -397,11 +424,8 @@ retry:
 			(PAGE_SIZE << order) >> 20);
 	}
 
-	if (!default_nareas)
-		swiotlb_adjust_nareas(num_possible_cpus());
-
-	area_order = get_order(array_size(sizeof(*mem->areas),
-		default_nareas));
+	nareas = limit_nareas(default_nareas, nslabs);
+	area_order = get_order(array_size(sizeof(*mem->areas), nareas));
 	mem->areas = (struct io_tlb_area *)
 		__get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order);
 	if (!mem->areas)
@@ -415,7 +439,7 @@ retry:
 	set_memory_decrypted((unsigned long)vstart,
 			     (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
 	swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true,
-				default_nareas);
+				nareas);
 
 	swiotlb_print_info();
 	return 0;
diff --git a/kernel/fork.c b/kernel/fork.c
index b85814e614a5..d2e12b6d2b18 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -686,6 +686,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	for_each_vma(old_vmi, mpnt) {
 		struct file *file;
 
+		vma_start_write(mpnt);
 		if (mpnt->vm_flags & VM_DONTCOPY) {
 			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
 			continue;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 5bd01624e447..0bdef4fe925b 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -182,9 +182,7 @@ static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode,
 			return NULL;
 		}
 
-		strreplace(name, '/', ':');
-
-		domain->name = name;
+		domain->name = strreplace(name, '/', ':');
 		domain->fwnode = fwnode;
 		domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED;
 	}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ce13f1a35251..1fc6095d502d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1072,7 +1072,7 @@ static int kprobe_ftrace_enabled;
 static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
 			       int *cnt)
 {
-	int ret = 0;
+	int ret;
 
 	lockdep_assert_held(&kprobe_mutex);
 
@@ -1110,7 +1110,7 @@ static int arm_kprobe_ftrace(struct kprobe *p)
 static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
 				  int *cnt)
 {
-	int ret = 0;
+	int ret;
 
 	lockdep_assert_held(&kprobe_mutex);
 
@@ -2007,9 +2007,9 @@ void __weak arch_kretprobe_fixup_return(struct pt_regs *regs,
 unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 					     void *frame_pointer)
 {
-	kprobe_opcode_t *correct_ret_addr = NULL;
 	struct kretprobe_instance *ri = NULL;
 	struct llist_node *first, *node = NULL;
+	kprobe_opcode_t *correct_ret_addr;
 	struct kretprobe *rp;
 
 	/* Find correct address and all nodes for this frame. */
@@ -2693,7 +2693,7 @@ void kprobe_free_init_mem(void)
 
 static int __init init_kprobes(void)
 {
-	int i, err = 0;
+	int i, err;
 
 	/* FIXME allocate the probe table, currently defined statically */
 	/* initialize all list heads */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 04bfb1e4d377..781de7cc6a4e 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -51,99 +51,35 @@ COND_SYSCALL_COMPAT(io_pgetevents);
 COND_SYSCALL(io_uring_setup);
 COND_SYSCALL(io_uring_enter);
 COND_SYSCALL(io_uring_register);
-
-/* fs/xattr.c */
-
-/* fs/dcache.c */
-
-/* fs/cookies.c */
 COND_SYSCALL(lookup_dcookie);
 COND_SYSCALL_COMPAT(lookup_dcookie);
-
-/* fs/eventfd.c */
 COND_SYSCALL(eventfd2);
-
-/* fs/eventfd.c */
 COND_SYSCALL(epoll_create1);
 COND_SYSCALL(epoll_ctl);
 COND_SYSCALL(epoll_pwait);
 COND_SYSCALL_COMPAT(epoll_pwait);
 COND_SYSCALL(epoll_pwait2);
 COND_SYSCALL_COMPAT(epoll_pwait2);
-
-/* fs/fcntl.c */
-
-/* fs/inotify_user.c */
 COND_SYSCALL(inotify_init1);
 COND_SYSCALL(inotify_add_watch);
 COND_SYSCALL(inotify_rm_watch);
-
-/* fs/ioctl.c */
-
-/* fs/ioprio.c */
 COND_SYSCALL(ioprio_set);
 COND_SYSCALL(ioprio_get);
-
-/* fs/locks.c */
 COND_SYSCALL(flock);
-
-/* fs/namei.c */
-
-/* fs/namespace.c */
-
-/* fs/nfsctl.c */
-
-/* fs/open.c */
-
-/* fs/pipe.c */
-
-/* fs/quota.c */
 COND_SYSCALL(quotactl);
 COND_SYSCALL(quotactl_fd);
-
-/* fs/readdir.c */
-
-/* fs/read_write.c */
-
-/* fs/sendfile.c */
-
-/* fs/select.c */
-
-/* fs/signalfd.c */
 COND_SYSCALL(signalfd4);
 COND_SYSCALL_COMPAT(signalfd4);
-
-/* fs/splice.c */
-
-/* fs/stat.c */
-
-/* fs/sync.c */
-
-/* fs/timerfd.c */
 COND_SYSCALL(timerfd_create);
 COND_SYSCALL(timerfd_settime);
 COND_SYSCALL(timerfd_settime32);
 COND_SYSCALL(timerfd_gettime);
 COND_SYSCALL(timerfd_gettime32);
-
-/* fs/utimes.c */
-
-/* kernel/acct.c */
 COND_SYSCALL(acct);
-
-/* kernel/capability.c */
 COND_SYSCALL(capget);
 COND_SYSCALL(capset);
-
-/* kernel/exec_domain.c */
-
-/* kernel/exit.c */
-
-/* kernel/fork.c */
 /* __ARCH_WANT_SYS_CLONE3 */
 COND_SYSCALL(clone3);
-
-/* kernel/futex/syscalls.c */
 COND_SYSCALL(futex);
 COND_SYSCALL(futex_time32);
 COND_SYSCALL(set_robust_list);
@@ -151,29 +87,11 @@ COND_SYSCALL_COMPAT(set_robust_list);
 COND_SYSCALL(get_robust_list);
 COND_SYSCALL_COMPAT(get_robust_list);
 COND_SYSCALL(futex_waitv);
-
-/* kernel/hrtimer.c */
-
-/* kernel/itimer.c */
-
-/* kernel/kexec.c */
 COND_SYSCALL(kexec_load);
 COND_SYSCALL_COMPAT(kexec_load);
-
-/* kernel/module.c */
 COND_SYSCALL(init_module);
 COND_SYSCALL(delete_module);
-
-/* kernel/posix-timers.c */
-
-/* kernel/printk.c */
 COND_SYSCALL(syslog);
-
-/* kernel/ptrace.c */
-
-/* kernel/sched/core.c */
-
-/* kernel/sys.c */
 COND_SYSCALL(setregid);
 COND_SYSCALL(setgid);
 COND_SYSCALL(setreuid);
@@ -186,12 +104,6 @@ COND_SYSCALL(setfsuid);
 COND_SYSCALL(setfsgid);
 COND_SYSCALL(setgroups);
 COND_SYSCALL(getgroups);
-
-/* kernel/time.c */
-
-/* kernel/timer.c */
-
-/* ipc/mqueue.c */
 COND_SYSCALL(mq_open);
 COND_SYSCALL_COMPAT(mq_open);
 COND_SYSCALL(mq_unlink);
@@ -203,8 +115,6 @@ COND_SYSCALL(mq_notify);
 COND_SYSCALL_COMPAT(mq_notify);
 COND_SYSCALL(mq_getsetattr);
 COND_SYSCALL_COMPAT(mq_getsetattr);
-
-/* ipc/msg.c */
 COND_SYSCALL(msgget);
 COND_SYSCALL(old_msgctl);
 COND_SYSCALL(msgctl);
@@ -214,8 +124,6 @@ COND_SYSCALL(msgrcv);
 COND_SYSCALL_COMPAT(msgrcv);
 COND_SYSCALL(msgsnd);
 COND_SYSCALL_COMPAT(msgsnd);
-
-/* ipc/sem.c */
 COND_SYSCALL(semget);
 COND_SYSCALL(old_semctl);
 COND_SYSCALL(semctl);
@@ -224,8 +132,6 @@ COND_SYSCALL_COMPAT(old_semctl);
 COND_SYSCALL(semtimedop);
 COND_SYSCALL(semtimedop_time32);
 COND_SYSCALL(semop);
-
-/* ipc/shm.c */
 COND_SYSCALL(shmget);
 COND_SYSCALL(old_shmctl);
 COND_SYSCALL(shmctl);
@@ -234,8 +140,6 @@ COND_SYSCALL_COMPAT(old_shmctl);
 COND_SYSCALL(shmat);
 COND_SYSCALL_COMPAT(shmat);
 COND_SYSCALL(shmdt);
-
-/* net/socket.c */
 COND_SYSCALL(socket);
 COND_SYSCALL(socketpair);
 COND_SYSCALL(bind);
@@ -256,30 +160,18 @@ COND_SYSCALL(sendmsg);
 COND_SYSCALL_COMPAT(sendmsg);
 COND_SYSCALL(recvmsg);
 COND_SYSCALL_COMPAT(recvmsg);
-
-/* mm/filemap.c */
-
-/* mm/nommu.c, also with MMU */
 COND_SYSCALL(mremap);
-
-/* security/keys/keyctl.c */
 COND_SYSCALL(add_key);
 COND_SYSCALL(request_key);
 COND_SYSCALL(keyctl);
 COND_SYSCALL_COMPAT(keyctl);
-
-/* security/landlock/syscalls.c */
 COND_SYSCALL(landlock_create_ruleset);
 COND_SYSCALL(landlock_add_rule);
 COND_SYSCALL(landlock_restrict_self);
-
-/* arch/example/kernel/sys_example.c */
-
-/* mm/fadvise.c */
 COND_SYSCALL(fadvise64_64);
 COND_SYSCALL_COMPAT(fadvise64_64);
 
-/* mm/, CONFIG_MMU only */
+/* CONFIG_MMU only */
 COND_SYSCALL(swapon);
 COND_SYSCALL(swapoff);
 COND_SYSCALL(mprotect);
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index cd2c35b1dd8f..c83c005e654e 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -15,6 +15,7 @@
 #include <trace/events/sched.h>
 
 #include "ftrace_internal.h"
+#include "trace.h"
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define ASSIGN_OPS_HASH(opsname, val) \
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index e4704ec26df7..b70de44e6d3d 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -102,12 +102,14 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
 
 	if (unlikely(kprobe_running())) {
 		fp->nmissed++;
-		return;
+		goto recursion_unlock;
 	}
 
 	kprobe_busy_begin();
 	__fprobe_handler(ip, parent_ip, ops, fregs);
 	kprobe_busy_end();
+
+recursion_unlock:
 	ftrace_test_recursion_unlock(bit);
 }
 
@@ -371,19 +373,16 @@ int unregister_fprobe(struct fprobe *fp)
 	if (!fprobe_is_registered(fp))
 		return -EINVAL;
 
-	/*
-	 * rethook_free() starts disabling the rethook, but the rethook handlers
-	 * may be running on other processors at this point. To make sure that all
-	 * current running handlers are finished, call unregister_ftrace_function()
-	 * after this.
-	 */
 	if (fp->rethook)
-		rethook_free(fp->rethook);
+		rethook_stop(fp->rethook);
 
 	ret = unregister_ftrace_function(&fp->ops);
 	if (ret < 0)
 		return ret;
 
+	if (fp->rethook)
+		rethook_free(fp->rethook);
+
 	ftrace_free_filter(&fp->ops);
 
 	return ret;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3740aca79fe7..05c0024815bf 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3305,6 +3305,22 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count)
 	return cnt;
 }
 
+static void ftrace_free_pages(struct ftrace_page *pages)
+{
+	struct ftrace_page *pg = pages;
+
+	while (pg) {
+		if (pg->records) {
+			free_pages((unsigned long)pg->records, pg->order);
+			ftrace_number_of_pages -= 1 << pg->order;
+		}
+		pages = pg->next;
+		kfree(pg);
+		pg = pages;
+		ftrace_number_of_groups--;
+	}
+}
+
 static struct ftrace_page *
 ftrace_allocate_pages(unsigned long num_to_init)
 {
@@ -3343,17 +3359,7 @@ ftrace_allocate_pages(unsigned long num_to_init)
 	return start_pg;
 
  free_pages:
-	pg = start_pg;
-	while (pg) {
-		if (pg->records) {
-			free_pages((unsigned long)pg->records, pg->order);
-			ftrace_number_of_pages -= 1 << pg->order;
-		}
-		start_pg = pg->next;
-		kfree(pg);
-		pg = start_pg;
-		ftrace_number_of_groups--;
-	}
+	ftrace_free_pages(start_pg);
 	pr_info("ftrace: FAILED to allocate memory for functions\n");
 	return NULL;
 }
@@ -6471,9 +6477,11 @@ static int ftrace_process_locs(struct module *mod,
 			       unsigned long *start,
 			       unsigned long *end)
 {
+	struct ftrace_page *pg_unuse = NULL;
 	struct ftrace_page *start_pg;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
+	unsigned long skipped = 0;
 	unsigned long count;
 	unsigned long *p;
 	unsigned long addr;
@@ -6536,8 +6544,10 @@ static int ftrace_process_locs(struct module *mod,
 		 * object files to satisfy alignments.
 		 * Skip any NULL pointers.
 		 */
-		if (!addr)
+		if (!addr) {
+			skipped++;
 			continue;
+		}
 
 		end_offset = (pg->index+1) * sizeof(pg->records[0]);
 		if (end_offset > PAGE_SIZE << pg->order) {
@@ -6551,8 +6561,10 @@ static int ftrace_process_locs(struct module *mod,
 		rec->ip = addr;
 	}
 
-	/* We should have used all pages */
-	WARN_ON(pg->next);
+	if (pg->next) {
+		pg_unuse = pg->next;
+		pg->next = NULL;
+	}
 
 	/* Assign the last page to ftrace_pages */
 	ftrace_pages = pg;
@@ -6574,6 +6586,11 @@ static int ftrace_process_locs(struct module *mod,
  out:
 	mutex_unlock(&ftrace_lock);
 
+	/* We should have used all pages unless we skipped some */
+	if (pg_unuse) {
+		WARN_ON(!skipped);
+		ftrace_free_pages(pg_unuse);
+	}
 	return ret;
 }
 
diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h
index 382775edf690..5012c04f92c0 100644
--- a/kernel/trace/ftrace_internal.h
+++ b/kernel/trace/ftrace_internal.h
@@ -2,6 +2,9 @@
 #ifndef _LINUX_KERNEL_FTRACE_INTERNAL_H
 #define  _LINUX_KERNEL_FTRACE_INTERNAL_H
 
+int __register_ftrace_function(struct ftrace_ops *ops);
+int __unregister_ftrace_function(struct ftrace_ops *ops);
+
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern struct mutex ftrace_lock;
@@ -15,8 +18,6 @@ int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs);
 
 #else /* !CONFIG_DYNAMIC_FTRACE */
 
-int __register_ftrace_function(struct ftrace_ops *ops);
-int __unregister_ftrace_function(struct ftrace_ops *ops);
 /* Keep as macros so we do not need to define the commands */
 # define ftrace_startup(ops, command)					\
 	({								\
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index f32ee484391a..5eb9b598f4e9 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -54,6 +54,19 @@ static void rethook_free_rcu(struct rcu_head *head)
 }
 
 /**
+ * rethook_stop() - Stop using a rethook.
+ * @rh: the struct rethook to stop.
+ *
+ * Stop using a rethook to prepare for freeing it. If you want to wait for
+ * all running rethook handler before calling rethook_free(), you need to
+ * call this first and wait RCU, and call rethook_free().
+ */
+void rethook_stop(struct rethook *rh)
+{
+	WRITE_ONCE(rh->handler, NULL);
+}
+
+/**
  * rethook_free() - Free struct rethook.
  * @rh: the struct rethook to be freed.
  *
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 834b361a4a66..14d8001140c8 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5242,28 +5242,34 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
+static void rb_clear_buffer_page(struct buffer_page *page)
+{
+	local_set(&page->write, 0);
+	local_set(&page->entries, 0);
+	rb_init_page(page->page);
+	page->read = 0;
+}
+
 static void
 rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	struct buffer_page *page;
+
 	rb_head_page_deactivate(cpu_buffer);
 
 	cpu_buffer->head_page
 		= list_entry(cpu_buffer->pages, struct buffer_page, list);
-	local_set(&cpu_buffer->head_page->write, 0);
-	local_set(&cpu_buffer->head_page->entries, 0);
-	local_set(&cpu_buffer->head_page->page->commit, 0);
-
-	cpu_buffer->head_page->read = 0;
+	rb_clear_buffer_page(cpu_buffer->head_page);
+	list_for_each_entry(page, cpu_buffer->pages, list) {
+		rb_clear_buffer_page(page);
+	}
 
 	cpu_buffer->tail_page = cpu_buffer->head_page;
 	cpu_buffer->commit_page = cpu_buffer->head_page;
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
 	INIT_LIST_HEAD(&cpu_buffer->new_pages);
-	local_set(&cpu_buffer->reader_page->write, 0);
-	local_set(&cpu_buffer->reader_page->entries, 0);
-	local_set(&cpu_buffer->reader_page->page->commit, 0);
-	cpu_buffer->reader_page->read = 0;
+	rb_clear_buffer_page(cpu_buffer->reader_page);
 
 	local_set(&cpu_buffer->entries_bytes, 0);
 	local_set(&cpu_buffer->overrun, 0);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b04f52e7cd28..be847d45d81c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3118,6 +3118,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 	struct ftrace_stack *fstack;
 	struct stack_entry *entry;
 	int stackidx;
+	void *ptr;
 
 	/*
 	 * Add one, for this function and the call to save_stack_trace()
@@ -3161,9 +3162,25 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 				    trace_ctx);
 	if (!event)
 		goto out;
-	entry = ring_buffer_event_data(event);
+	ptr = ring_buffer_event_data(event);
+	entry = ptr;
+
+	/*
+	 * For backward compatibility reasons, the entry->caller is an
+	 * array of 8 slots to store the stack. This is also exported
+	 * to user space. The amount allocated on the ring buffer actually
+	 * holds enough for the stack specified by nr_entries. This will
+	 * go into the location of entry->caller. Due to string fortifiers
+	 * checking the size of the destination of memcpy() it triggers
+	 * when it detects that size is greater than 8. To hide this from
+	 * the fortifiers, we use "ptr" and pointer arithmetic to assign caller.
+	 *
+	 * The below is really just:
+	 *   memcpy(&entry->caller, fstack->calls, size);
+	 */
+	ptr += offsetof(typeof(*entry), caller);
+	memcpy(ptr, fstack->calls, size);
 
-	memcpy(&entry->caller, fstack->calls, size);
 	entry->size = nr_entries;
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
@@ -6764,6 +6781,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	free_cpumask_var(iter->started);
 	kfree(iter->fmt);
+	kfree(iter->temp);
 	mutex_destroy(&iter->mutex);
 	kfree(iter);
 
@@ -8146,7 +8164,7 @@ static const struct file_operations tracing_err_log_fops = {
 	.open           = tracing_err_log_open,
 	.write		= tracing_err_log_write,
 	.read           = seq_read,
-	.llseek         = seq_lseek,
+	.llseek         = tracing_lseek,
 	.release        = tracing_err_log_release,
 };
 
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 5fe525f1b8cc..7ccc7a8e155b 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -31,7 +31,7 @@ trace_boot_set_instance_options(struct trace_array *tr, struct xbc_node *node)
 
 	/* Common ftrace options */
 	xbc_node_for_each_array_value(node, "options", anode, p) {
-		if (strscpy(buf, p, ARRAY_SIZE(buf)) == -E2BIG) {
+		if (strscpy(buf, p, ARRAY_SIZE(buf)) < 0) {
 			pr_err("String is too long: %s\n", p);
 			continue;
 		}
@@ -87,7 +87,7 @@ trace_boot_enable_events(struct trace_array *tr, struct xbc_node *node)
 	const char *p;
 
 	xbc_node_for_each_array_value(node, "events", anode, p) {
-		if (strscpy(buf, p, ARRAY_SIZE(buf)) == -E2BIG) {
+		if (strscpy(buf, p, ARRAY_SIZE(buf)) < 0) {
 			pr_err("String is too long: %s\n", p);
 			continue;
 		}
@@ -486,7 +486,7 @@ trace_boot_init_one_event(struct trace_array *tr, struct xbc_node *gnode,
 
 	p = xbc_node_find_value(enode, "filter", NULL);
 	if (p && *p != '\0') {
-		if (strscpy(buf, p, ARRAY_SIZE(buf)) == -E2BIG)
+		if (strscpy(buf, p, ARRAY_SIZE(buf)) < 0)
 			pr_err("filter string is too long: %s\n", p);
 		else if (apply_event_filter(file, buf) < 0)
 			pr_err("Failed to apply filter: %s\n", buf);
@@ -494,7 +494,7 @@ trace_boot_init_one_event(struct trace_array *tr, struct xbc_node *gnode,
 
 	if (IS_ENABLED(CONFIG_HIST_TRIGGERS)) {
 		xbc_node_for_each_array_value(enode, "actions", anode, p) {
-			if (strscpy(buf, p, ARRAY_SIZE(buf)) == -E2BIG)
+			if (strscpy(buf, p, ARRAY_SIZE(buf)) < 0)
 				pr_err("action string is too long: %s\n", p);
 			else if (trigger_process_regex(file, buf) < 0)
 				pr_err("Failed to apply an action: %s\n", p);
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index cb0077ba2b49..a0a704ba27db 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -644,6 +644,7 @@ static int enable_trace_eprobe(struct trace_event_call *call,
 	struct trace_eprobe *ep;
 	bool enabled;
 	int ret = 0;
+	int cnt = 0;
 
 	tp = trace_probe_primary_from_call(call);
 	if (WARN_ON_ONCE(!tp))
@@ -667,12 +668,25 @@ static int enable_trace_eprobe(struct trace_event_call *call,
 		if (ret)
 			break;
 		enabled = true;
+		cnt++;
 	}
 
 	if (ret) {
 		/* Failed to enable one of them. Roll back all */
-		if (enabled)
-			disable_eprobe(ep, file->tr);
+		if (enabled) {
+			/*
+			 * It's a bug if one failed for something other than memory
+			 * not being available but another eprobe succeeded.
+			 */
+			WARN_ON_ONCE(ret != -ENOMEM);
+
+			list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+				ep = container_of(pos, struct trace_eprobe, tp);
+				disable_eprobe(ep, file->tr);
+				if (!--cnt)
+					break;
+			}
+		}
 		if (file)
 			trace_probe_remove_file(tp, file);
 		else
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index b97d3ad832f1..c8c61381eba4 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6663,13 +6663,15 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 	if (get_named_trigger_data(trigger_data))
 		goto enable;
 
-	if (has_hist_vars(hist_data))
-		save_hist_vars(hist_data);
-
 	ret = create_actions(hist_data);
 	if (ret)
 		goto out_unreg;
 
+	if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
+		if (save_hist_vars(hist_data))
+			goto out_unreg;
+	}
+
 	ret = tracing_map_init(hist_data->map);
 	if (ret)
 		goto out_unreg;
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 4f5e74bbdab2..33cb6af31f39 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -1317,6 +1317,9 @@ static int user_field_set_string(struct ftrace_event_field *field,
 	pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", field->name);
 
+	if (str_has_prefix(field->type, "struct "))
+		pos += snprintf(buf + pos, LEN_OR_ZERO, " %d", field->size);
+
 	if (colon)
 		pos += snprintf(buf + pos, LEN_OR_ZERO, ";");
 
diff --git a/kernel/trace/trace_kprobe_selftest.c b/kernel/trace/trace_kprobe_selftest.c
index 16548ee4c8c6..3851cd1e6a62 100644
--- a/kernel/trace/trace_kprobe_selftest.c
+++ b/kernel/trace/trace_kprobe_selftest.c
@@ -1,4 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+
+#include "trace_kprobe_selftest.h"
+
 /*
  * Function used during the kprobe self test. This function is in a separate
  * compile unit so it can be compile with CC_FLAGS_FTRACE to ensure that it