Merge tag 'mm-nonmm-stable-2024-01-09-10-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-MM updates from Andrew Morton:
 "Quite a lot of kexec work this time around. Many singleton patches in
  many places. The notable patch series are:

   - nilfs2 folio conversion from Matthew Wilcox in 'nilfs2: Folio
     conversions for file paths'.

   - Additional nilfs2 folio conversion from Ryusuke Konishi in 'nilfs2:
     Folio conversions for directory paths'.

   - IA64 remnant removal in Heiko Carstens's 'Remove unused code after
     IA-64 removal'.

   - Arnd Bergmann has enabled the -Wmissing-prototypes warning
     everywhere in 'Treewide: enable -Wmissing-prototypes'. This had
     some followup fixes:

      - Nathan Chancellor has cleaned up the hexagon build in the series
        'hexagon: Fix up instances of -Wmissing-prototypes'.

      - Nathan also addressed some s390 warnings in 's390: A couple of
        fixes for -Wmissing-prototypes'.

      - Arnd Bergmann addresses the same warnings for MIPS in his series
        'mips: address -Wmissing-prototypes warnings'.

   - Baoquan He has made kexec_file operate in a top-down-fitting manner
     similar to kexec_load in the series 'kexec_file: Load kernel at top
     of system RAM if required'

   - Baoquan He has also added the self-explanatory 'kexec_file: print
     out debugging message if required'.

   - Some checkstack maintenance work from Tiezhu Yang in the series
     'Modify some code about checkstack'.

   - Douglas Anderson has disentangled the watchdog code's logging when
     multiple reports are occurring simultaneously. The series is
     'watchdog: Better handling of concurrent lockups'.

   - Yuntao Wang has contributed some maintenance work on the crash code
     in 'crash: Some cleanups and fixes'"

* tag 'mm-nonmm-stable-2024-01-09-10-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (157 commits)
  crash_core: fix and simplify the logic of crash_exclude_mem_range()
  x86/crash: use SZ_1M macro instead of hardcoded value
  x86/crash: remove the unused image parameter from prepare_elf_headers()
  kdump: remove redundant DEFAULT_CRASH_KERNEL_LOW_SIZE
  scripts/decode_stacktrace.sh: strip unexpected CR from lines
  watchdog: if panicking and we dumped everything, don't re-enable dumping
  watchdog/hardlockup: use printk_cpu_sync_get_irqsave() to serialize reporting
  watchdog/softlockup: use printk_cpu_sync_get_irqsave() to serialize reporting
  watchdog/hardlockup: adopt softlockup logic avoiding double-dumps
  kexec_core: fix the assignment to kimage->control_page
  x86/kexec: fix incorrect end address passed to kernel_ident_mapping_init()
  lib/trace_readwrite.c:: replace asm-generic/io with linux/io
  nilfs2: cpfile: fix some kernel-doc warnings
  stacktrace: fix kernel-doc typo
  scripts/checkstack.pl: fix no space expression between sp and offset
  x86/kexec: fix incorrect argument passed to kexec_dprintk()
  x86/kexec: use pr_err() instead of kexec_dprintk() when an error occurs
  nilfs2: add missing set_freezable() for freezable kthread
  kernel: relay: remove relay_file_splice_read dead code, doesn't work
  docs: submit-checklist: remove all of "make namespacecheck"
  ...

13 files changed, 187 insertions, 314 deletions

diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 56cf4ad7abbb..d48315667752 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -13,7 +13,6 @@
 #include <linux/memory.h>
 #include <linux/cpuhotplug.h>
 #include <linux/memblock.h>
-#include <linux/kexec.h>
 #include <linux/kmemleak.h>
 
 #include <asm/page.h>
@@ -551,9 +550,11 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
 		phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
 		phdr->p_align = 0;
 		ehdr->e_phnum++;
-		pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
-			phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
-			ehdr->e_phnum, phdr->p_offset);
+#ifdef CONFIG_KEXEC_FILE
+		kexec_dprintk("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
+			      phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
+			      ehdr->e_phnum, phdr->p_offset);
+#endif
 		phdr++;
 	}
 
@@ -565,9 +566,8 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
 int crash_exclude_mem_range(struct crash_mem *mem,
 			    unsigned long long mstart, unsigned long long mend)
 {
-	int i, j;
+	int i;
 	unsigned long long start, end, p_start, p_end;
-	struct range temp_range = {0, 0};
 
 	for (i = 0; i < mem->nr_ranges; i++) {
 		start = mem->ranges[i].start;
@@ -575,72 +575,51 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 		p_start = mstart;
 		p_end = mend;
 
-		if (mstart > end || mend < start)
+		if (p_start > end)
 			continue;
 
+		/*
+		 * Because the memory ranges in mem->ranges are stored in
+		 * ascending order, when we detect `p_end < start`, we can
+		 * immediately exit the for loop, as the subsequent memory
+		 * ranges will definitely be outside the range we are looking
+		 * for.
+		 */
+		if (p_end < start)
+			break;
+
 		/* Truncate any area outside of range */
-		if (mstart < start)
+		if (p_start < start)
 			p_start = start;
-		if (mend > end)
+		if (p_end > end)
 			p_end = end;
 
 		/* Found completely overlapping range */
 		if (p_start == start && p_end == end) {
-			mem->ranges[i].start = 0;
-			mem->ranges[i].end = 0;
-			if (i < mem->nr_ranges - 1) {
-				/* Shift rest of the ranges to left */
-				for (j = i; j < mem->nr_ranges - 1; j++) {
-					mem->ranges[j].start =
-						mem->ranges[j+1].start;
-					mem->ranges[j].end =
-							mem->ranges[j+1].end;
-				}
-
-				/*
-				 * Continue to check if there are another overlapping ranges
-				 * from the current position because of shifting the above
-				 * mem ranges.
-				 */
-				i--;
-				mem->nr_ranges--;
-				continue;
-			}
+			memmove(&mem->ranges[i], &mem->ranges[i + 1],
+				(mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i]));
+			i--;
 			mem->nr_ranges--;
-			return 0;
-		}
-
-		if (p_start > start && p_end < end) {
+		} else if (p_start > start && p_end < end) {
 			/* Split original range */
+			if (mem->nr_ranges >= mem->max_nr_ranges)
+				return -ENOMEM;
+
+			memmove(&mem->ranges[i + 2], &mem->ranges[i + 1],
+				(mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i]));
+
 			mem->ranges[i].end = p_start - 1;
-			temp_range.start = p_end + 1;
-			temp_range.end = end;
+			mem->ranges[i + 1].start = p_end + 1;
+			mem->ranges[i + 1].end = end;
+
+			i++;
+			mem->nr_ranges++;
 		} else if (p_start != start)
 			mem->ranges[i].end = p_start - 1;
 		else
 			mem->ranges[i].start = p_end + 1;
-		break;
-	}
-
-	/* If a split happened, add the split to array */
-	if (!temp_range.end)
-		return 0;
-
-	/* Split happened */
-	if (i == mem->max_nr_ranges - 1)
-		return -ENOMEM;
-
-	/* Location where new range should go */
-	j = i + 1;
-	if (j < mem->nr_ranges) {
-		/* Move over all ranges one slot towards the end */
-		for (i = mem->nr_ranges - 1; i >= j; i--)
-			mem->ranges[i + 1] = mem->ranges[i];
 	}
 
-	mem->ranges[j].start = temp_range.start;
-	mem->ranges[j].end = temp_range.end;
-	mem->nr_ranges++;
 	return 0;
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 56cf276432c8..b32e323adbbf 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -165,7 +165,6 @@ void __weak arch_release_task_struct(struct task_struct *tsk)
 {
 }
 
-#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 static struct kmem_cache *task_struct_cachep;
 
 static inline struct task_struct *alloc_task_struct_node(int node)
@@ -177,9 +176,6 @@ static inline void free_task_struct(struct task_struct *tsk)
 {
 	kmem_cache_free(task_struct_cachep, tsk);
 }
-#endif
-
-#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
 
 /*
  * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
@@ -412,24 +408,6 @@ void thread_stack_cache_init(void)
 }
 
 # endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */
-#else /* CONFIG_ARCH_THREAD_STACK_ALLOCATOR */
-
-static int alloc_thread_stack_node(struct task_struct *tsk, int node)
-{
-	unsigned long *stack;
-
-	stack = arch_alloc_thread_stack_node(tsk, node);
-	tsk->stack = stack;
-	return stack ? 0 : -ENOMEM;
-}
-
-static void free_thread_stack(struct task_struct *tsk)
-{
-	arch_free_thread_stack(tsk);
-	tsk->stack = NULL;
-}
-
-#endif /* !CONFIG_ARCH_THREAD_STACK_ALLOCATOR */
 
 /* SLAB cache for signal_struct structures (tsk->signal) */
 static struct kmem_cache *signal_cachep;
@@ -1039,7 +1017,6 @@ static void set_max_threads(unsigned int max_threads_suggested)
 int arch_task_struct_size __read_mostly;
 #endif
 
-#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
 {
 	/* Fetch thread_struct whitelist for the architecture. */
@@ -1054,12 +1031,10 @@ static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
 	else
 		*offset += offsetof(struct task_struct, thread);
 }
-#endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */
 
 void __init fork_init(void)
 {
 	int i;
-#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 #ifndef ARCH_MIN_TASKALIGN
 #define ARCH_MIN_TASKALIGN	0
 #endif
@@ -1072,7 +1047,6 @@ void __init fork_init(void)
 			arch_task_struct_size, align,
 			SLAB_PANIC|SLAB_ACCOUNT,
 			useroffset, usersize, NULL);
-#endif
 
 	/* do the arch specific task caches init */
 	arch_task_cache_init();
@@ -1606,7 +1580,7 @@ static void complete_vfork_done(struct task_struct *tsk)
 static int wait_for_vfork_done(struct task_struct *child,
 				struct completion *vfork)
 {
-	unsigned int state = TASK_UNINTERRUPTIBLE|TASK_KILLABLE|TASK_FREEZABLE;
+	unsigned int state = TASK_KILLABLE|TASK_FREEZABLE;
 	int killed;
 
 	cgroup_enter_frozen();
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index be5642a4ec49..a08031b57a61 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -52,6 +52,8 @@ atomic_t __kexec_lock = ATOMIC_INIT(0);
 /* Flag to indicate we are going to kexec a new kernel */
 bool kexec_in_progress = false;
 
+bool kexec_file_dbg_print;
+
 int kexec_should_crash(struct task_struct *p)
 {
 	/*
@@ -276,8 +278,8 @@ int kimage_is_destination_range(struct kimage *image,
 		unsigned long mstart, mend;
 
 		mstart = image->segment[i].mem;
-		mend = mstart + image->segment[i].memsz;
-		if ((end > mstart) && (start < mend))
+		mend = mstart + image->segment[i].memsz - 1;
+		if ((end >= mstart) && (start <= mend))
 			return 1;
 	}
 
@@ -370,7 +372,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
 		pfn   = page_to_boot_pfn(pages);
 		epfn  = pfn + count;
 		addr  = pfn << PAGE_SHIFT;
-		eaddr = epfn << PAGE_SHIFT;
+		eaddr = (epfn << PAGE_SHIFT) - 1;
 		if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
 			      kimage_is_destination_range(image, addr, eaddr)) {
 			list_add(&pages->lru, &extra_pages);
@@ -430,7 +432,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
 
 	pages = NULL;
 	size = (1 << order) << PAGE_SHIFT;
-	hole_start = (image->control_page + (size - 1)) & ~(size - 1);
+	hole_start = ALIGN(image->control_page, size);
 	hole_end   = hole_start + size - 1;
 	while (hole_end <= crashk_res.end) {
 		unsigned long i;
@@ -447,7 +449,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
 			mend   = mstart + image->segment[i].memsz - 1;
 			if ((hole_end >= mstart) && (hole_start <= mend)) {
 				/* Advance the hole to the end of the segment */
-				hole_start = (mend + (size - 1)) & ~(size - 1);
+				hole_start = ALIGN(mend, size);
 				hole_end   = hole_start + size - 1;
 				break;
 			}
@@ -455,7 +457,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
 		/* If I don't overlap any segments I have found my hole! */
 		if (i == image->nr_segments) {
 			pages = pfn_to_page(hole_start >> PAGE_SHIFT);
-			image->control_page = hole_end;
+			image->control_page = hole_end + 1;
 			break;
 		}
 	}
@@ -716,7 +718,7 @@ static struct page *kimage_alloc_page(struct kimage *image,
 
 		/* If the page is not a destination page use it */
 		if (!kimage_is_destination_range(image, addr,
-						  addr + PAGE_SIZE))
+						  addr + PAGE_SIZE - 1))
 			break;
 
 		/*
@@ -1063,9 +1065,10 @@ __bpf_kfunc void crash_kexec(struct pt_regs *regs)
 	 * panic().  Otherwise parallel calls of panic() and crash_kexec()
 	 * may stop each other.  To exclude them, we use panic_cpu here too.
 	 */
+	old_cpu = PANIC_CPU_INVALID;
 	this_cpu = raw_smp_processor_id();
-	old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
-	if (old_cpu == PANIC_CPU_INVALID) {
+
+	if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) {
 		/* This is the 1st CPU which comes here, so go ahead. */
 		__crash_kexec(regs);
 
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index f9a419cd22d4..bef2f6f2571b 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -123,6 +123,8 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 	 */
 	kfree(image->image_loader_data);
 	image->image_loader_data = NULL;
+
+	kexec_file_dbg_print = false;
 }
 
 #ifdef CONFIG_KEXEC_SIG
@@ -202,6 +204,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	if (ret < 0)
 		return ret;
 	image->kernel_buf_len = ret;
+	kexec_dprintk("kernel: %p kernel_size: %#lx\n",
+		      image->kernel_buf, image->kernel_buf_len);
 
 	/* Call arch image probe handlers */
 	ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
@@ -278,6 +282,7 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
 	if (!image)
 		return -ENOMEM;
 
+	kexec_file_dbg_print = !!(flags & KEXEC_FILE_DEBUG);
 	image->file_mode = 1;
 
 	if (kexec_on_panic) {
@@ -384,13 +389,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 	if (ret)
 		goto out;
 
+	kexec_dprintk("nr_segments = %lu\n", image->nr_segments);
 	for (i = 0; i < image->nr_segments; i++) {
 		struct kexec_segment *ksegment;
 
 		ksegment = &image->segment[i];
-		pr_debug("Loading segment %d: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n",
-			 i, ksegment->buf, ksegment->bufsz, ksegment->mem,
-			 ksegment->memsz);
+		kexec_dprintk("segment[%d]: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n",
+			      i, ksegment->buf, ksegment->bufsz, ksegment->mem,
+			      ksegment->memsz);
 
 		ret = kimage_load_segment(image, &image->segment[i]);
 		if (ret)
@@ -403,6 +409,8 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 	if (ret)
 		goto out;
 
+	kexec_dprintk("kexec_file_load: type:%u, start:0x%lx head:0x%lx flags:0x%lx\n",
+		      image->type, image->start, image->head, flags);
 	/*
 	 * Free up any temporary buffers allocated which are not needed
 	 * after image has been loaded
@@ -426,11 +434,11 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
 	unsigned long temp_start, temp_end;
 
 	temp_end = min(end, kbuf->buf_max);
-	temp_start = temp_end - kbuf->memsz;
+	temp_start = temp_end - kbuf->memsz + 1;
 
 	do {
 		/* align down start */
-		temp_start = temp_start & (~(kbuf->buf_align - 1));
+		temp_start = ALIGN_DOWN(temp_start, kbuf->buf_align);
 
 		if (temp_start < start || temp_start < kbuf->buf_min)
 			return 0;
@@ -592,6 +600,8 @@ static int kexec_walk_resources(struct kexec_buf *kbuf,
 					   IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
 					   crashk_res.start, crashk_res.end,
 					   kbuf, func);
+	else if (kbuf->top_down)
+		return walk_system_ram_res_rev(0, ULONG_MAX, kbuf, func);
 	else
 		return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
 }
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 5c579fb9a5e3..2fabd497d659 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -145,20 +145,9 @@ void __ptrace_unlink(struct task_struct *child)
 	 */
 	if (!(child->flags & PF_EXITING) &&
 	    (child->signal->flags & SIGNAL_STOP_STOPPED ||
-	     child->signal->group_stop_count)) {
+	     child->signal->group_stop_count))
 		child->jobctl |= JOBCTL_STOP_PENDING;
 
-		/*
-		 * This is only possible if this thread was cloned by the
-		 * traced task running in the stopped group, set the signal
-		 * for the future reports.
-		 * FIXME: we should change ptrace_init_task() to handle this
-		 * case.
-		 */
-		if (!(child->jobctl & JOBCTL_STOP_SIGMASK))
-			child->jobctl |= SIGSTOP;
-	}
-
 	/*
 	 * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick
 	 * @child in the butt.  Note that @resume should be used iff @child
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 395a0ea3c7a8..c3a3b82c4f64 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -59,6 +59,14 @@ struct sys_off_handler {
 };
 
 /*
+ * This variable is used to indicate if a halt was initiated instead of a
+ * reboot when the reboot call was invoked with LINUX_REBOOT_CMD_POWER_OFF, but
+ * the system cannot be powered off. This allowes kernel_halt() to notify users
+ * of that.
+ */
+static bool poweroff_fallback_to_halt;
+
+/*
  * Temporary stub that prevents linkage failure while we're in process
  * of removing all uses of legacy pm_power_off() around the kernel.
  */
@@ -297,7 +305,10 @@ void kernel_halt(void)
 	kernel_shutdown_prepare(SYSTEM_HALT);
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
-	pr_emerg("System halted\n");
+	if (poweroff_fallback_to_halt)
+		pr_emerg("Power off not available: System halted instead\n");
+	else
+		pr_emerg("System halted\n");
 	kmsg_dump(KMSG_DUMP_SHUTDOWN);
 	machine_halt();
 }
@@ -732,8 +743,10 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	/* Instead of trying to make the power_off code look like
 	 * halt when pm_power_off is not set do it the easy way.
 	 */
-	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off())
+	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off()) {
+		poweroff_fallback_to_halt = true;
 		cmd = LINUX_REBOOT_CMD_HALT;
+	}
 
 	mutex_lock(&system_transition_mutex);
 	switch (cmd) {
diff --git a/kernel/relay.c b/kernel/relay.c
index 83fe0325cde1..a8e90e98bf2c 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1073,167 +1073,6 @@ static ssize_t relay_file_read(struct file *filp,
 	return written;
 }
 
-static void relay_consume_bytes(struct rchan_buf *rbuf, int bytes_consumed)
-{
-	rbuf->bytes_consumed += bytes_consumed;
-
-	if (rbuf->bytes_consumed >= rbuf->chan->subbuf_size) {
-		relay_subbufs_consumed(rbuf->chan, rbuf->cpu, 1);
-		rbuf->bytes_consumed %= rbuf->chan->subbuf_size;
-	}
-}
-
-static void relay_pipe_buf_release(struct pipe_inode_info *pipe,
-				   struct pipe_buffer *buf)
-{
-	struct rchan_buf *rbuf;
-
-	rbuf = (struct rchan_buf *)page_private(buf->page);
-	relay_consume_bytes(rbuf, buf->private);
-}
-
-static const struct pipe_buf_operations relay_pipe_buf_ops = {
-	.release	= relay_pipe_buf_release,
-	.try_steal	= generic_pipe_buf_try_steal,
-	.get		= generic_pipe_buf_get,
-};
-
-static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i)
-{
-}
-
-/*
- *	subbuf_splice_actor - splice up to one subbuf's worth of data
- */
-static ssize_t subbuf_splice_actor(struct file *in,
-			       loff_t *ppos,
-			       struct pipe_inode_info *pipe,
-			       size_t len,
-			       unsigned int flags,
-			       int *nonpad_ret)
-{
-	unsigned int pidx, poff, total_len, subbuf_pages, nr_pages;
-	struct rchan_buf *rbuf = in->private_data;
-	unsigned int subbuf_size = rbuf->chan->subbuf_size;
-	uint64_t pos = (uint64_t) *ppos;
-	uint32_t alloc_size = (uint32_t) rbuf->chan->alloc_size;
-	size_t read_start = (size_t) do_div(pos, alloc_size);
-	size_t read_subbuf = read_start / subbuf_size;
-	size_t padding = rbuf->padding[read_subbuf];
-	size_t nonpad_end = read_subbuf * subbuf_size + subbuf_size - padding;
-	struct page *pages[PIPE_DEF_BUFFERS];
-	struct partial_page partial[PIPE_DEF_BUFFERS];
-	struct splice_pipe_desc spd = {
-		.pages = pages,
-		.nr_pages = 0,
-		.nr_pages_max = PIPE_DEF_BUFFERS,
-		.partial = partial,
-		.ops = &relay_pipe_buf_ops,
-		.spd_release = relay_page_release,
-	};
-	ssize_t ret;
-
-	if (rbuf->subbufs_produced == rbuf->subbufs_consumed)
-		return 0;
-	if (splice_grow_spd(pipe, &spd))
-		return -ENOMEM;
-
-	/*
-	 * Adjust read len, if longer than what is available
-	 */
-	if (len > (subbuf_size - read_start % subbuf_size))
-		len = subbuf_size - read_start % subbuf_size;
-
-	subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT;
-	pidx = (read_start / PAGE_SIZE) % subbuf_pages;
-	poff = read_start & ~PAGE_MASK;
-	nr_pages = min_t(unsigned int, subbuf_pages, spd.nr_pages_max);
-
-	for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) {
-		unsigned int this_len, this_end, private;
-		unsigned int cur_pos = read_start + total_len;
-
-		if (!len)
-			break;
-
-		this_len = min_t(unsigned long, len, PAGE_SIZE - poff);
-		private = this_len;
-
-		spd.pages[spd.nr_pages] = rbuf->page_array[pidx];
-		spd.partial[spd.nr_pages].offset = poff;
-
-		this_end = cur_pos + this_len;
-		if (this_end >= nonpad_end) {
-			this_len = nonpad_end - cur_pos;
-			private = this_len + padding;
-		}
-		spd.partial[spd.nr_pages].len = this_len;
-		spd.partial[spd.nr_pages].private = private;
-
-		len -= this_len;
-		total_len += this_len;
-		poff = 0;
-		pidx = (pidx + 1) % subbuf_pages;
-
-		if (this_end >= nonpad_end) {
-			spd.nr_pages++;
-			break;
-		}
-	}
-
-	ret = 0;
-	if (!spd.nr_pages)
-		goto out;
-
-	ret = *nonpad_ret = splice_to_pipe(pipe, &spd);
-	if (ret < 0 || ret < total_len)
-		goto out;
-
-        if (read_start + ret == nonpad_end)
-                ret += padding;
-
-out:
-	splice_shrink_spd(&spd);
-	return ret;
-}
-
-static ssize_t relay_file_splice_read(struct file *in,
-				      loff_t *ppos,
-				      struct pipe_inode_info *pipe,
-				      size_t len,
-				      unsigned int flags)
-{
-	ssize_t spliced;
-	int ret;
-	int nonpad_ret = 0;
-
-	ret = 0;
-	spliced = 0;
-
-	while (len && !spliced) {
-		ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret);
-		if (ret < 0)
-			break;
-		else if (!ret) {
-			if (flags & SPLICE_F_NONBLOCK)
-				ret = -EAGAIN;
-			break;
-		}
-
-		*ppos += ret;
-		if (ret > len)
-			len = 0;
-		else
-			len -= ret;
-		spliced += nonpad_ret;
-		nonpad_ret = 0;
-	}
-
-	if (spliced)
-		return spliced;
-
-	return ret;
-}
 
 const struct file_operations relay_file_operations = {
 	.open		= relay_file_open,
@@ -1242,6 +1081,5 @@ const struct file_operations relay_file_operations = {
 	.read		= relay_file_read,
 	.llseek		= no_llseek,
 	.release	= relay_file_release,
-	.splice_read	= relay_file_splice_read,
 };
 EXPORT_SYMBOL_GPL(relay_file_operations);
diff --git a/kernel/resource.c b/kernel/resource.c
index 91be1bc50b60..fcbca39dbc45 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -27,6 +27,8 @@
 #include <linux/mount.h>
 #include <linux/resource_ext.h>
 #include <uapi/linux/magic.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
 #include <asm/io.h>
 
 
@@ -430,6 +432,61 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 }
 
 /*
+ * This function, being a variant of walk_system_ram_res(), calls the @func
+ * callback against all memory ranges of type System RAM which are marked as
+ * IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY in reversed order, i.e., from
+ * higher to lower.
+ */
+int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+				int (*func)(struct resource *, void *))
+{
+	struct resource res, *rams;
+	int rams_size = 16, i;
+	unsigned long flags;
+	int ret = -1;
+
+	/* create a list */
+	rams = kvcalloc(rams_size, sizeof(struct resource), GFP_KERNEL);
+	if (!rams)
+		return ret;
+
+	flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	i = 0;
+	while ((start < end) &&
+		(!find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res))) {
+		if (i >= rams_size) {
+			/* re-alloc */
+			struct resource *rams_new;
+
+			rams_new = kvrealloc(rams, rams_size * sizeof(struct resource),
+					     (rams_size + 16) * sizeof(struct resource),
+					     GFP_KERNEL);
+			if (!rams_new)
+				goto out;
+
+			rams = rams_new;
+			rams_size += 16;
+		}
+
+		rams[i].start = res.start;
+		rams[i++].end = res.end;
+
+		start = res.end + 1;
+	}
+
+	/* go reverse */
+	for (i--; i >= 0; i--) {
+		ret = (*func)(&rams[i], arg);
+		if (ret)
+			break;
+	}
+
+out:
+	kvfree(rams);
+	return ret;
+}
+
+/*
  * This function calls the @func callback against all memory ranges, which
  * are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY.
  */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b803030c3a03..533547e3c90a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -13097,19 +13097,6 @@ next_cpu:
 	return 0;
 }
 
-#else /* CONFIG_FAIR_GROUP_SCHED */
-
-void free_fair_sched_group(struct task_group *tg) { }
-
-int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
-{
-	return 1;
-}
-
-void online_fair_sched_group(struct task_group *tg) { }
-
-void unregister_fair_sched_group(struct task_group *tg) { }
-
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e58a54bda77d..001fe047bd5d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -461,10 +461,21 @@ static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
 
 extern int tg_nop(struct task_group *tg, void *data);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
 extern void free_fair_sched_group(struct task_group *tg);
 extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
 extern void online_fair_sched_group(struct task_group *tg);
 extern void unregister_fair_sched_group(struct task_group *tg);
+#else
+static inline void free_fair_sched_group(struct task_group *tg) { }
+static inline int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
+{
+       return 1;
+}
+static inline void online_fair_sched_group(struct task_group *tg) { }
+static inline void unregister_fair_sched_group(struct task_group *tg) { }
+#endif
+
 extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 			struct sched_entity *se, int cpu,
 			struct sched_entity *parent);
diff --git a/kernel/signal.c b/kernel/signal.c
index 47a7602dfe8d..c9c57d053ce4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -171,16 +171,6 @@ static bool recalc_sigpending_tsk(struct task_struct *t)
 	return false;
 }
 
-/*
- * After recalculating TIF_SIGPENDING, we need to make sure the task wakes up.
- * This is superfluous when called on current, the wakeup is a harmless no-op.
- */
-void recalc_sigpending_and_wake(struct task_struct *t)
-{
-	if (recalc_sigpending_tsk(t))
-		signal_wake_up(t, 0);
-}
-
 void recalc_sigpending(void)
 {
 	if (!recalc_sigpending_tsk(current) && !freezing(current))
@@ -1348,10 +1338,8 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
 		action->sa.sa_handler = SIG_DFL;
 		if (handler == HANDLER_EXIT)
 			action->sa.sa_flags |= SA_IMMUTABLE;
-		if (blocked) {
+		if (blocked)
 			sigdelset(&t->blocked, sig);
-			recalc_sigpending_and_wake(t);
-		}
 	}
 	/*
 	 * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect
@@ -1361,6 +1349,9 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
 	    (!t->ptrace || (handler == HANDLER_EXIT)))
 		t->signal->flags &= ~SIGNAL_UNKILLABLE;
 	ret = send_signal_locked(sig, info, t, PIDTYPE_PID);
+	/* This can happen if the signal was already pending and blocked */
+	if (!task_sigpending(t))
+		signal_wake_up(t, 0);
 	spin_unlock_irqrestore(&t->sighand->siglock, flags);
 
 	return ret;
@@ -1376,12 +1367,12 @@ int force_sig_info(struct kernel_siginfo *info)
  */
 int zap_other_threads(struct task_struct *p)
 {
-	struct task_struct *t = p;
+	struct task_struct *t;
 	int count = 0;
 
 	p->signal->group_stop_count = 0;
 
-	while_each_thread(p, t) {
+	for_other_threads(p, t) {
 		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
 		/* Don't require de_thread to wait for the vhost_worker */
 		if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)
@@ -2465,12 +2456,10 @@ static bool do_signal_stop(int signr)
 			sig->group_exit_code = signr;
 
 		sig->group_stop_count = 0;
-
 		if (task_set_jobctl_pending(current, signr | gstop))
 			sig->group_stop_count++;
 
-		t = current;
-		while_each_thread(current, t) {
+		for_other_threads(current, t) {
 			/*
 			 * Setting state to TASK_STOPPED for a group
 			 * stop is always done with the siglock held,
@@ -2966,8 +2955,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which)
 	if (sigisemptyset(&retarget))
 		return;
 
-	t = tsk;
-	while_each_thread(tsk, t) {
+	for_other_threads(tsk, t) {
 		if (t->flags & PF_EXITING)
 			continue;
 
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 4f65824879ab..afb3c116da91 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -126,7 +126,7 @@ EXPORT_SYMBOL_GPL(stack_trace_save);
 
 /**
  * stack_trace_save_tsk - Save a task stack trace into a storage array
- * @task:	The task to examine
+ * @tsk:	The task to examine
  * @store:	Pointer to storage array
  * @size:	Size of the storage array
  * @skipnr:	Number of entries to skip at the start of the stack trace
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 5cd6d4e26915..81a8862295d6 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -91,7 +91,7 @@ static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts);
 static DEFINE_PER_CPU(int, hrtimer_interrupts_saved);
 static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned);
 static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched);
-static unsigned long watchdog_hardlockup_all_cpu_dumped;
+static unsigned long hard_lockup_nmi_warn;
 
 notrace void arch_touch_nmi_watchdog(void)
 {
@@ -151,12 +151,32 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
 	 */
 	if (is_hardlockup(cpu)) {
 		unsigned int this_cpu = smp_processor_id();
+		unsigned long flags;
 
 		/* Only print hardlockups once. */
 		if (per_cpu(watchdog_hardlockup_warned, cpu))
 			return;
 
+		/*
+		 * Prevent multiple hard-lockup reports if one cpu is already
+		 * engaged in dumping all cpu back traces.
+		 */
+		if (sysctl_hardlockup_all_cpu_backtrace) {
+			if (test_and_set_bit_lock(0, &hard_lockup_nmi_warn))
+				return;
+		}
+
+		/*
+		 * NOTE: we call printk_cpu_sync_get_irqsave() after printing
+		 * the lockup message. While it would be nice to serialize
+		 * that printout, we really want to make sure that if some
+		 * other CPU somehow locked up while holding the lock associated
+		 * with printk_cpu_sync_get_irqsave() that we can still at least
+		 * get the message about the lockup out.
+		 */
 		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", cpu);
+		printk_cpu_sync_get_irqsave(flags);
+
 		print_modules();
 		print_irqtrace_events(current);
 		if (cpu == this_cpu) {
@@ -164,17 +184,17 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
 				show_regs(regs);
 			else
 				dump_stack();
+			printk_cpu_sync_put_irqrestore(flags);
 		} else {
+			printk_cpu_sync_put_irqrestore(flags);
 			trigger_single_cpu_backtrace(cpu);
 		}
 
-		/*
-		 * Perform multi-CPU dump only once to avoid multiple
-		 * hardlockups generating interleaving traces
-		 */
-		if (sysctl_hardlockup_all_cpu_backtrace &&
-		    !test_and_set_bit(0, &watchdog_hardlockup_all_cpu_dumped))
+		if (sysctl_hardlockup_all_cpu_backtrace) {
 			trigger_allbutcpu_cpu_backtrace(cpu);
+			if (!hardlockup_panic)
+				clear_bit_unlock(0, &hard_lockup_nmi_warn);
+		}
 
 		if (hardlockup_panic)
 			nmi_panic(regs, "Hard LOCKUP");
@@ -448,6 +468,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	struct pt_regs *regs = get_irq_regs();
 	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
+	unsigned long flags;
 
 	if (!watchdog_enabled)
 		return HRTIMER_NORESTART;
@@ -514,6 +535,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		/* Start period for the next softlockup warning. */
 		update_report_ts();
 
+		printk_cpu_sync_get_irqsave(flags);
 		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
@@ -523,10 +545,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			show_regs(regs);
 		else
 			dump_stack();
+		printk_cpu_sync_put_irqrestore(flags);
 
 		if (softlockup_all_cpu_backtrace) {
 			trigger_allbutcpu_cpu_backtrace(smp_processor_id());
-			clear_bit_unlock(0, &soft_lockup_nmi_warn);
+			if (!softlockup_panic)
+				clear_bit_unlock(0, &soft_lockup_nmi_warn);
 		}
 
 		add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);