Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "Various misc subsystems, before getting into the post-linux-next
  material.

  41 patches.

  Subsystems affected by this patch series: procfs, misc, core-kernel,
  lib, checkpatch, init, pipe, minix, fat, cgroups, kexec, kdump,
  taskstats, panic, kcov, resource, and ubsan"

* emailed patches from Andrew Morton <[email protected]>: (41 commits)
  Revert "ubsan, kcsan: Don't combine sanitizer with kcov on clang"
  kernel/resource: fix kfree() of bootmem memory again
  kcov: properly handle subsequent mmap calls
  kcov: split ioctl handling into locked and unlocked parts
  panic: move panic_print before kmsg dumpers
  panic: add option to dump all CPUs backtraces in panic_print
  docs: sysctl/kernel: add missing bit to panic_print
  taskstats: remove unneeded dead assignment
  kasan: no need to unset panic_on_warn in end_report()
  ubsan: no need to unset panic_on_warn in ubsan_epilogue()
  panic: unset panic_on_warn inside panic()
  docs: kdump: add scp example to write out the dump file
  docs: kdump: update description about sysfs file system support
  arm64: mm: use IS_ENABLED(CONFIG_KEXEC_CORE) instead of #ifdef
  x86/setup: use IS_ENABLED(CONFIG_KEXEC_CORE) instead of #ifdef
  riscv: mm: init: use IS_ENABLED(CONFIG_KEXEC_CORE) instead of #ifdef
  kexec: make crashk_res, crashk_low_res and crash_notes symbols always visible
  cgroup: use irqsave in cgroup_rstat_flush_locked().
  fat: use pointer to simple type in put_user()
  minix: fix bug when opening a file with O_DIRECT
  ...

Author: torvalds

Documentation/admin-guide/kdump/kdump.rst

@@ -146,9 +146,9 @@ System kernel config options
 	CONFIG_SYSFS=y
 
    Note that "sysfs file system support" might not appear in the "Pseudo
-   filesystems" menu if "Configure standard kernel features (for small
-   systems)" is not enabled in "General Setup." In this case, check the
-   .config file itself to ensure that sysfs is turned on, as follows::
+   filesystems" menu if "Configure standard kernel features (expert users)"
+   is not enabled in "General Setup." In this case, check the .config file
+   itself to ensure that sysfs is turned on, as follows::
 
 	grep 'CONFIG_SYSFS' .config
 
@@ -533,6 +533,10 @@ the following command::
 
    cp /proc/vmcore <dump-file>
 
+or use scp to write out the dump file between hosts on a network, e.g::
+
+   scp /proc/vmcore remote_username@remote_ip:<dump-file>
+
 You can also use makedumpfile utility to write out the dump file
 with specified options to filter out unwanted contents, e.g::
 

Documentation/admin-guide/kernel-parameters.txt

@@ -3792,6 +3792,11 @@
 			bit 3: print locks info if CONFIG_LOCKDEP is on
 			bit 4: print ftrace buffer
 			bit 5: print all printk messages in buffer
+			bit 6: print all CPUs backtrace (if available in the arch)
+			*Be aware* that this option may print a _lot_ of lines,
+			so there are risks of losing older messages in the log.
+			Use this option carefully, maybe worth to setup a
+			bigger log buffer with "log_buf_len" along with this.
 
 	panic_on_taint=	Bitmask for conditionally calling panic() in add_taint()
 			Format: <hex>[,nousertaint]

Documentation/admin-guide/sysctl/kernel.rst

@@ -763,6 +763,8 @@ bit 1  print system memory info
 bit 2  print timer info
 bit 3  print locks info if ``CONFIG_LOCKDEP`` is on
 bit 4  print ftrace buffer
+bit 5  print all printk messages in buffer
+bit 6  print all CPUs backtrace (if available in the arch)
 =====  ============================================
 
 So for example to print tasks and memory info on panic, user can::

Documentation/dev-tools/sparse.rst

@@ -100,3 +100,5 @@ have already built it.
 
 The optional make variable CF can be used to pass arguments to sparse.  The
 build system passes -Wbitwise to sparse automatically.
+
+Note that sparse defines the __CHECKER__ preprocessor symbol.

arch/arm64/mm/init.c

@@ -90,7 +90,6 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit;
 phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
 #endif
 
-#ifdef CONFIG_KEXEC_CORE
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
  *
@@ -104,6 +103,9 @@ static void __init reserve_crashkernel(void)
 	unsigned long long crash_max = arm64_dma_phys_limit;
 	int ret;
 
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+		return;
+
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base);
 	/* no crashkernel= or invalid value specified */
@@ -136,11 +138,6 @@ static void __init reserve_crashkernel(void)
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
 }
-#else
-static void __init reserve_crashkernel(void)
-{
-}
-#endif /* CONFIG_KEXEC_CORE */
 
 /*
  * Return the maximum physical address for a zone accessible by the given bits

arch/riscv/mm/init.c

@@ -957,7 +957,6 @@ static inline void setup_vm_final(void)
 }
 #endif /* CONFIG_MMU */
 
-#ifdef CONFIG_KEXEC_CORE
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
  *
@@ -974,6 +973,8 @@ static void __init reserve_crashkernel(void)
 
 	int ret = 0;
 
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+		return;
 	/*
 	 * Don't reserve a region for a crash kernel on a crash kernel
 	 * since it doesn't make much sense and we have limited memory
@@ -1023,7 +1024,6 @@ static void __init reserve_crashkernel(void)
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
 }
-#endif /* CONFIG_KEXEC_CORE */
 
 void __init paging_init(void)
 {
@@ -1037,9 +1037,7 @@ void __init misc_mem_init(void)
 	arch_numa_init();
 	sparse_init();
 	zone_sizes_init();
-#ifdef CONFIG_KEXEC_CORE
 	reserve_crashkernel();
-#endif
 	memblock_dump_all();
 }
 

arch/x86/kernel/setup.c

@@ -411,8 +411,6 @@ static void __init memblock_x86_reserve_range_setup_data(void)
  * --------- Crashkernel reservation ------------------------------
  */
 
-#ifdef CONFIG_KEXEC_CORE
-
 /* 16M alignment for crash kernel regions */
 #define CRASH_ALIGN		SZ_16M
 
@@ -490,6 +488,9 @@ static void __init reserve_crashkernel(void)
 	bool high = false;
 	int ret;
 
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+		return;
+
 	total_mem = memblock_phys_mem_size();
 
 	/* crashkernel=XM */
@@ -555,11 +556,6 @@ static void __init reserve_crashkernel(void)
 	crashk_res.end   = crash_base + crash_size - 1;
 	insert_resource(&iomem_resource, &crashk_res);
 }
-#else
-static void __init reserve_crashkernel(void)
-{
-}
-#endif
 
 static struct resource standard_io_resources[] = {
 	{ .name = "dma1", .start = 0x00, .end = 0x1f,

fs/fat/dir.c

@@ -722,7 +722,7 @@ static int func(struct dir_context *ctx, const char *name, int name_len,   \
 		if (name_len >= sizeof(d1->d_name))			   \
 			name_len = sizeof(d1->d_name) - 1;		   \
 									   \
-		if (put_user(0, d2->d_name)			||	   \
+		if (put_user(0, &d2->d_name[0])			||	   \
 		    put_user(0, &d2->d_reclen)			||	   \
 		    copy_to_user(d1->d_name, name, name_len)	||	   \
 		    put_user(0, d1->d_name + name_len)		||	   \

fs/minix/inode.c

@@ -448,7 +448,8 @@ static const struct address_space_operations minix_aops = {
 	.writepage = minix_writepage,
 	.write_begin = minix_write_begin,
 	.write_end = generic_write_end,
-	.bmap = minix_bmap
+	.bmap = minix_bmap,
+	.direct_IO = noop_direct_IO
 };
 
 static const struct inode_operations minix_symlink_inode_operations = {

fs/pipe.c

@@ -607,7 +607,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct pipe_inode_info *pipe = filp->private_data;
-	int count, head, tail, mask;
+	unsigned int count, head, tail, mask;
 
 	switch (cmd) {
 	case FIONREAD:
@@ -804,7 +804,7 @@ struct pipe_inode_info *alloc_pipe_info(void)
 	if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user())
 		goto out_revert_acct;
 
-	pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer),
+	pipe->bufs = kvcalloc(pipe_bufs, sizeof(struct pipe_buffer),
 			     GFP_KERNEL_ACCOUNT);
 
 	if (pipe->bufs) {
@@ -829,7 +829,7 @@ struct pipe_inode_info *alloc_pipe_info(void)
 
 void free_pipe_info(struct pipe_inode_info *pipe)
 {
-	int i;
+	unsigned int i;
 
 #ifdef CONFIG_WATCH_QUEUE
 	if (pipe->watch_queue)
@@ -849,7 +849,7 @@ void free_pipe_info(struct pipe_inode_info *pipe)
 #endif
 	if (pipe->tmp_page)
 		__free_page(pipe->tmp_page);
-	kfree(pipe->bufs);
+	kvfree(pipe->bufs);
 	kfree(pipe);
 }
 
@@ -1264,8 +1264,7 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots)
 	if (nr_slots < n)
 		return -EBUSY;
 
-	bufs = kcalloc(nr_slots, sizeof(*bufs),
-		       GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+	bufs = kvcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT);
 	if (unlikely(!bufs))
 		return -ENOMEM;
 
@@ -1292,7 +1291,7 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots)
 	head = n;
 	tail = 0;
 
-	kfree(pipe->bufs);
+	kvfree(pipe->bufs);
 	pipe->bufs = bufs;
 	pipe->ring_size = nr_slots;
 	if (pipe->max_usage > nr_slots)

fs/proc/base.c

@@ -1764,25 +1764,25 @@ static const char *proc_pid_get_link(struct dentry *dentry,
 
 static int do_proc_readlink(struct path *path, char __user *buffer, int buflen)
 {
-	char *tmp = (char *)__get_free_page(GFP_KERNEL);
+	char *tmp = kmalloc(PATH_MAX, GFP_KERNEL);
 	char *pathname;
 	int len;
 
 	if (!tmp)
 		return -ENOMEM;
 
-	pathname = d_path(path, tmp, PAGE_SIZE);
+	pathname = d_path(path, tmp, PATH_MAX);
 	len = PTR_ERR(pathname);
 	if (IS_ERR(pathname))
 		goto out;
-	len = tmp + PAGE_SIZE - 1 - pathname;
+	len = tmp + PATH_MAX - 1 - pathname;
 
 	if (len > buflen)
 		len = buflen;
 	if (copy_to_user(buffer, pathname, len))
 		len = -EFAULT;
  out:
-	free_page((unsigned long)tmp);
+	kfree(tmp);
 	return len;
 }
 

fs/proc/vmcore.c

@@ -62,39 +62,42 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0);
 /* Device Dump Size */
 static size_t vmcoredd_orig_sz;
 
-static DECLARE_RWSEM(vmcore_cb_rwsem);
+static DEFINE_SPINLOCK(vmcore_cb_lock);
+DEFINE_STATIC_SRCU(vmcore_cb_srcu);
 /* List of registered vmcore callbacks. */
 static LIST_HEAD(vmcore_cb_list);
 /* Whether the vmcore has been opened once. */
 static bool vmcore_opened;
 
 void register_vmcore_cb(struct vmcore_cb *cb)
 {
-	down_write(&vmcore_cb_rwsem);
 	INIT_LIST_HEAD(&cb->next);
+	spin_lock(&vmcore_cb_lock);
 	list_add_tail(&cb->next, &vmcore_cb_list);
 	/*
 	 * Registering a vmcore callback after the vmcore was opened is
 	 * very unusual (e.g., manual driver loading).
 	 */
 	if (vmcore_opened)
 		pr_warn_once("Unexpected vmcore callback registration\n");
-	up_write(&vmcore_cb_rwsem);
+	spin_unlock(&vmcore_cb_lock);
 }
 EXPORT_SYMBOL_GPL(register_vmcore_cb);
 
 void unregister_vmcore_cb(struct vmcore_cb *cb)
 {
-	down_write(&vmcore_cb_rwsem);
-	list_del(&cb->next);
+	spin_lock(&vmcore_cb_lock);
+	list_del_rcu(&cb->next);
 	/*
 	 * Unregistering a vmcore callback after the vmcore was opened is
 	 * very unusual (e.g., forced driver removal), but we cannot stop
 	 * unregistering.
 	 */
 	if (vmcore_opened)
 		pr_warn_once("Unexpected vmcore callback unregistration\n");
-	up_write(&vmcore_cb_rwsem);
+	spin_unlock(&vmcore_cb_lock);
+
+	synchronize_srcu(&vmcore_cb_srcu);
 }
 EXPORT_SYMBOL_GPL(unregister_vmcore_cb);
 
@@ -103,9 +106,8 @@ static bool pfn_is_ram(unsigned long pfn)
 	struct vmcore_cb *cb;
 	bool ret = true;
 
-	lockdep_assert_held_read(&vmcore_cb_rwsem);
-
-	list_for_each_entry(cb, &vmcore_cb_list, next) {
+	list_for_each_entry_srcu(cb, &vmcore_cb_list, next,
+				 srcu_read_lock_held(&vmcore_cb_srcu)) {
 		if (unlikely(!cb->pfn_is_ram))
 			continue;
 		ret = cb->pfn_is_ram(cb, pfn);
@@ -118,9 +120,9 @@ static bool pfn_is_ram(unsigned long pfn)
 
 static int open_vmcore(struct inode *inode, struct file *file)
 {
-	down_read(&vmcore_cb_rwsem);
+	spin_lock(&vmcore_cb_lock);
 	vmcore_opened = true;
-	up_read(&vmcore_cb_rwsem);
+	spin_unlock(&vmcore_cb_lock);
 
 	return 0;
 }
@@ -133,14 +135,15 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 	unsigned long pfn, offset;
 	size_t nr_bytes;
 	ssize_t read = 0, tmp;
+	int idx;
 
 	if (!count)
 		return 0;
 
 	offset = (unsigned long)(*ppos % PAGE_SIZE);
 	pfn = (unsigned long)(*ppos / PAGE_SIZE);
 
-	down_read(&vmcore_cb_rwsem);
+	idx = srcu_read_lock(&vmcore_cb_srcu);
 	do {
 		if (count > (PAGE_SIZE - offset))
 			nr_bytes = PAGE_SIZE - offset;
@@ -165,7 +168,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 						       offset, userbuf);
 		}
 		if (tmp < 0) {
-			up_read(&vmcore_cb_rwsem);
+			srcu_read_unlock(&vmcore_cb_srcu, idx);
 			return tmp;
 		}
 
@@ -176,8 +179,8 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 		++pfn;
 		offset = 0;
 	} while (count);
+	srcu_read_unlock(&vmcore_cb_srcu, idx);
 
-	up_read(&vmcore_cb_rwsem);
 	return read;
 }
 
@@ -477,7 +480,7 @@ static const struct vm_operations_struct vmcore_mmap_ops = {
 
 /**
  * vmcore_alloc_buf - allocate buffer in vmalloc memory
- * @sizez: size of buffer
+ * @size: size of buffer
  *
  * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap
  * the buffer to user-space by means of remap_vmalloc_range().
@@ -568,18 +571,18 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
 			    unsigned long from, unsigned long pfn,
 			    unsigned long size, pgprot_t prot)
 {
-	int ret;
+	int ret, idx;
 
 	/*
-	 * Check if oldmem_pfn_is_ram was registered to avoid
-	 * looping over all pages without a reason.
+	 * Check if a callback was registered to avoid looping over all
+	 * pages without a reason.
 	 */
-	down_read(&vmcore_cb_rwsem);
+	idx = srcu_read_lock(&vmcore_cb_srcu);
 	if (!list_empty(&vmcore_cb_list))
 		ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
 	else
 		ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot);
-	up_read(&vmcore_cb_rwsem);
+	srcu_read_unlock(&vmcore_cb_srcu, idx);
 	return ret;
 }