1 files changed, 299 insertions, 410 deletions

diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index f895a8c8a244..52039fae1594 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  linux/drivers/char/mem.c
  *
@@ -15,26 +16,22 @@
 #include <linux/mman.h>
 #include <linux/random.h>
 #include <linux/init.h>
-#include <linux/raw.h>
 #include <linux/tty.h>
 #include <linux/capability.h>
 #include <linux/ptrace.h>
 #include <linux/device.h>
 #include <linux/highmem.h>
 #include <linux/backing-dev.h>
-#include <linux/bootmem.h>
+#include <linux/shmem_fs.h>
 #include <linux/splice.h>
 #include <linux/pfn.h>
 #include <linux/export.h>
 #include <linux/io.h>
-#include <linux/aio.h>
-
-#include <asm/uaccess.h>
-
-#ifdef CONFIG_IA64
-# include <linux/efi.h>
-#endif
+#include <linux/uio.h>
+#include <linux/uaccess.h>
+#include <linux/security.h>
 
+#define DEVMEM_MINOR	1
 #define DEVPORT_MINOR	4
 
 static inline unsigned long size_inside_page(unsigned long start,
@@ -60,33 +57,22 @@ static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
 #endif
 
 #ifdef CONFIG_STRICT_DEVMEM
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
-{
-	u64 from = ((u64)pfn) << PAGE_SHIFT;
-	u64 to = from + size;
-	u64 cursor = from;
-
-	while (cursor < to) {
-		if (!devmem_is_allowed(pfn)) {
-			printk(KERN_INFO
-		"Program %s tried to access /dev/mem between %Lx->%Lx.\n",
-				current->comm, from, to);
-			return 0;
-		}
-		cursor += PAGE_SIZE;
-		pfn++;
-	}
-	return 1;
+static inline int page_is_allowed(unsigned long pfn)
+{
+	return devmem_is_allowed(pfn);
 }
 #else
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+static inline int page_is_allowed(unsigned long pfn)
 {
 	return 1;
 }
 #endif
 
-void __weak unxlate_dev_mem_ptr(unsigned long phys, void *addr)
+static inline bool should_stop_iteration(void)
 {
+	if (need_resched())
+		cond_resched();
+	return signal_pending(current);
 }
 
 /*
@@ -98,7 +84,12 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 {
 	phys_addr_t p = *ppos;
 	ssize_t read, sz;
-	char *ptr;
+	void *ptr;
+	char *bounce;
+	int err;
+
+	if (p != *ppos)
+		return 0;
 
 	if (!valid_phys_addr_range(p, count))
 		return -EFAULT;
@@ -118,36 +109,61 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 	}
 #endif
 
+	bounce = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!bounce)
+		return -ENOMEM;
+
 	while (count > 0) {
 		unsigned long remaining;
+		int allowed, probe;
 
 		sz = size_inside_page(p, count);
 
-		if (!range_is_allowed(p >> PAGE_SHIFT, count))
-			return -EPERM;
+		err = -EPERM;
+		allowed = page_is_allowed(p >> PAGE_SHIFT);
+		if (!allowed)
+			goto failed;
 
-		/*
-		 * On ia64 if a page has been mapped somewhere as uncached, then
-		 * it must also be accessed uncached by the kernel or data
-		 * corruption may occur.
-		 */
-		ptr = xlate_dev_mem_ptr(p);
-		if (!ptr)
-			return -EFAULT;
+		err = -EFAULT;
+		if (allowed == 2) {
+			/* Show zeros for restricted memory. */
+			remaining = clear_user(buf, sz);
+		} else {
+			/*
+			 * On ia64 if a page has been mapped somewhere as
+			 * uncached, then it must also be accessed uncached
+			 * by the kernel or data corruption may occur.
+			 */
+			ptr = xlate_dev_mem_ptr(p);
+			if (!ptr)
+				goto failed;
+
+			probe = copy_from_kernel_nofault(bounce, ptr, sz);
+			unxlate_dev_mem_ptr(p, ptr);
+			if (probe)
+				goto failed;
+
+			remaining = copy_to_user(buf, bounce, sz);
+		}
 
-		remaining = copy_to_user(buf, ptr, sz);
-		unxlate_dev_mem_ptr(p, ptr);
 		if (remaining)
-			return -EFAULT;
+			goto failed;
 
 		buf += sz;
 		p += sz;
 		count -= sz;
 		read += sz;
+		if (should_stop_iteration())
+			break;
 	}
+	kfree(bounce);
 
 	*ppos += read;
 	return read;
+
+failed:
+	kfree(bounce);
+	return err;
 }
 
 static ssize_t write_mem(struct file *file, const char __user *buf,
@@ -158,6 +174,9 @@ static ssize_t write_mem(struct file *file, const char __user *buf,
 	unsigned long copied;
 	void *ptr;
 
+	if (p != *ppos)
+		return -EFBIG;
+
 	if (!valid_phys_addr_range(p, count))
 		return -EFAULT;
 
@@ -176,36 +195,44 @@ static ssize_t write_mem(struct file *file, const char __user *buf,
 #endif
 
 	while (count > 0) {
+		int allowed;
+
 		sz = size_inside_page(p, count);
 
-		if (!range_is_allowed(p >> PAGE_SHIFT, sz))
+		allowed = page_is_allowed(p >> PAGE_SHIFT);
+		if (!allowed)
 			return -EPERM;
 
-		/*
-		 * On ia64 if a page has been mapped somewhere as uncached, then
-		 * it must also be accessed uncached by the kernel or data
-		 * corruption may occur.
-		 */
-		ptr = xlate_dev_mem_ptr(p);
-		if (!ptr) {
-			if (written)
-				break;
-			return -EFAULT;
-		}
+		/* Skip actual writing when a page is marked as restricted. */
+		if (allowed == 1) {
+			/*
+			 * On ia64 if a page has been mapped somewhere as
+			 * uncached, then it must also be accessed uncached
+			 * by the kernel or data corruption may occur.
+			 */
+			ptr = xlate_dev_mem_ptr(p);
+			if (!ptr) {
+				if (written)
+					break;
+				return -EFAULT;
+			}
 
-		copied = copy_from_user(ptr, buf, sz);
-		unxlate_dev_mem_ptr(p, ptr);
-		if (copied) {
-			written += sz - copied;
-			if (written)
-				break;
-			return -EFAULT;
+			copied = copy_from_user(ptr, buf, sz);
+			unxlate_dev_mem_ptr(p, ptr);
+			if (copied) {
+				written += sz - copied;
+				if (written)
+					break;
+				return -EFAULT;
+			}
 		}
 
 		buf += sz;
 		p += sz;
 		count -= sz;
 		written += sz;
+		if (should_stop_iteration())
+			break;
 	}
 
 	*ppos += written;
@@ -228,20 +255,6 @@ int __weak phys_mem_access_prot_allowed(struct file *file,
 #ifdef pgprot_noncached
 static int uncached_access(struct file *file, phys_addr_t addr)
 {
-#if defined(CONFIG_IA64)
-	/*
-	 * On ia64, we ignore O_DSYNC because we cannot tolerate memory
-	 * attribute aliases.
-	 */
-	return !(efi_mem_attributes(addr) & EFI_MEMORY_WB);
-#elif defined(CONFIG_MIPS)
-	{
-		extern int __uncached_access(struct file *file,
-					     unsigned long addr);
-
-		return __uncached_access(file, addr);
-	}
-#else
 	/*
 	 * Accessing memory above the top the kernel knows about or through a
 	 * file pointer
@@ -250,7 +263,6 @@ static int uncached_access(struct file *file, phys_addr_t addr)
 	if (file->f_flags & O_DSYNC)
 		return 1;
 	return addr >= __pa(high_memory);
-#endif
 }
 #endif
 
@@ -279,15 +291,26 @@ static unsigned long get_unmapped_area_mem(struct file *file,
 	return pgoff << PAGE_SHIFT;
 }
 
+/* permit direct mmap, for read, write or exec */
+static unsigned memory_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_DIRECT |
+		NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC;
+}
+
+static unsigned zero_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_COPY;
+}
+
 /* can't do an in-place private mapping if there's no MMU */
-static inline int private_mapping_ok(struct vm_area_struct *vma)
+static inline int private_mapping_ok(struct vm_area_desc *desc)
 {
-	return vma->vm_flags & VM_MAYSHARE;
+	return is_nommu_shared_mapping(desc->vm_flags);
 }
 #else
-#define get_unmapped_area_mem	NULL
 
-static inline int private_mapping_ok(struct vm_area_struct *vma)
+static inline int private_mapping_ok(struct vm_area_desc *desc)
 {
 	return 1;
 }
@@ -299,244 +322,51 @@ static const struct vm_operations_struct mmap_mem_ops = {
 #endif
 };
 
-static int mmap_mem(struct file *file, struct vm_area_struct *vma)
+static int mmap_filter_error(int err)
 {
-	size_t size = vma->vm_end - vma->vm_start;
-
-	if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size))
-		return -EINVAL;
-
-	if (!private_mapping_ok(vma))
-		return -ENOSYS;
-
-	if (!range_is_allowed(vma->vm_pgoff, size))
-		return -EPERM;
-
-	if (!phys_mem_access_prot_allowed(file, vma->vm_pgoff, size,
-						&vma->vm_page_prot))
-		return -EINVAL;
-
-	vma->vm_page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
-						 size,
-						 vma->vm_page_prot);
-
-	vma->vm_ops = &mmap_mem_ops;
-
-	/* Remap-pfn-range will mark the range VM_IO */
-	if (remap_pfn_range(vma,
-			    vma->vm_start,
-			    vma->vm_pgoff,
-			    size,
-			    vma->vm_page_prot)) {
-		return -EAGAIN;
-	}
-	return 0;
-}
-
-#ifdef CONFIG_DEVKMEM
-static int mmap_kmem(struct file *file, struct vm_area_struct *vma)
-{
-	unsigned long pfn;
-
-	/* Turn a kernel-virtual address into a physical page frame */
-	pfn = __pa((u64)vma->vm_pgoff << PAGE_SHIFT) >> PAGE_SHIFT;
-
-	/*
-	 * RED-PEN: on some architectures there is more mapped memory than
-	 * available in mem_map which pfn_valid checks for. Perhaps should add a
-	 * new macro here.
-	 *
-	 * RED-PEN: vmalloc is not supported right now.
-	 */
-	if (!pfn_valid(pfn))
-		return -EIO;
-
-	vma->vm_pgoff = pfn;
-	return mmap_mem(file, vma);
-}
-#endif
-
-#ifdef CONFIG_DEVKMEM
-/*
- * This function reads the *virtual* memory as seen by the kernel.
- */
-static ssize_t read_kmem(struct file *file, char __user *buf,
-			 size_t count, loff_t *ppos)
-{
-	unsigned long p = *ppos;
-	ssize_t low_count, read, sz;
-	char *kbuf; /* k-addr because vread() takes vmlist_lock rwlock */
-	int err = 0;
-
-	read = 0;
-	if (p < (unsigned long) high_memory) {
-		low_count = count;
-		if (count > (unsigned long)high_memory - p)
-			low_count = (unsigned long)high_memory - p;
-
-#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
-		/* we don't have page 0 mapped on sparc and m68k.. */
-		if (p < PAGE_SIZE && low_count > 0) {
-			sz = size_inside_page(p, low_count);
-			if (clear_user(buf, sz))
-				return -EFAULT;
-			buf += sz;
-			p += sz;
-			read += sz;
-			low_count -= sz;
-			count -= sz;
-		}
-#endif
-		while (low_count > 0) {
-			sz = size_inside_page(p, low_count);
-
-			/*
-			 * On ia64 if a page has been mapped somewhere as
-			 * uncached, then it must also be accessed uncached
-			 * by the kernel or data corruption may occur
-			 */
-			kbuf = xlate_dev_kmem_ptr((char *)p);
-
-			if (copy_to_user(buf, kbuf, sz))
-				return -EFAULT;
-			buf += sz;
-			p += sz;
-			read += sz;
-			low_count -= sz;
-			count -= sz;
-		}
-	}
-
-	if (count > 0) {
-		kbuf = (char *)__get_free_page(GFP_KERNEL);
-		if (!kbuf)
-			return -ENOMEM;
-		while (count > 0) {
-			sz = size_inside_page(p, count);
-			if (!is_vmalloc_or_module_addr((void *)p)) {
-				err = -ENXIO;
-				break;
-			}
-			sz = vread(kbuf, (char *)p, sz);
-			if (!sz)
-				break;
-			if (copy_to_user(buf, kbuf, sz)) {
-				err = -EFAULT;
-				break;
-			}
-			count -= sz;
-			buf += sz;
-			read += sz;
-			p += sz;
-		}
-		free_page((unsigned long)kbuf);
-	}
-	*ppos = p;
-	return read ? read : err;
+	return -EAGAIN;
 }
 
-
-static ssize_t do_write_kmem(unsigned long p, const char __user *buf,
-				size_t count, loff_t *ppos)
+static int mmap_mem_prepare(struct vm_area_desc *desc)
 {
-	ssize_t written, sz;
-	unsigned long copied;
+	struct file *file = desc->file;
+	const size_t size = vma_desc_size(desc);
+	const phys_addr_t offset = (phys_addr_t)desc->pgoff << PAGE_SHIFT;
 
-	written = 0;
-#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
-	/* we don't have page 0 mapped on sparc and m68k.. */
-	if (p < PAGE_SIZE) {
-		sz = size_inside_page(p, count);
-		/* Hmm. Do something? */
-		buf += sz;
-		p += sz;
-		count -= sz;
-		written += sz;
-	}
-#endif
+	/* Does it even fit in phys_addr_t? */
+	if (offset >> PAGE_SHIFT != desc->pgoff)
+		return -EINVAL;
 
-	while (count > 0) {
-		char *ptr;
+	/* It's illegal to wrap around the end of the physical address space. */
+	if (offset + (phys_addr_t)size - 1 < offset)
+		return -EINVAL;
 
-		sz = size_inside_page(p, count);
+	if (!valid_mmap_phys_addr_range(desc->pgoff, size))
+		return -EINVAL;
 
-		/*
-		 * On ia64 if a page has been mapped somewhere as uncached, then
-		 * it must also be accessed uncached by the kernel or data
-		 * corruption may occur.
-		 */
-		ptr = xlate_dev_kmem_ptr((char *)p);
+	if (!private_mapping_ok(desc))
+		return -ENOSYS;
 
-		copied = copy_from_user(ptr, buf, sz);
-		if (copied) {
-			written += sz - copied;
-			if (written)
-				break;
-			return -EFAULT;
-		}
-		buf += sz;
-		p += sz;
-		count -= sz;
-		written += sz;
-	}
+	if (!range_is_allowed(desc->pgoff, size))
+		return -EPERM;
 
-	*ppos += written;
-	return written;
-}
+	if (!phys_mem_access_prot_allowed(file, desc->pgoff, size,
+					  &desc->page_prot))
+		return -EINVAL;
 
-/*
- * This function writes to the *virtual* memory as seen by the kernel.
- */
-static ssize_t write_kmem(struct file *file, const char __user *buf,
-			  size_t count, loff_t *ppos)
-{
-	unsigned long p = *ppos;
-	ssize_t wrote = 0;
-	ssize_t virtr = 0;
-	char *kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */
-	int err = 0;
-
-	if (p < (unsigned long) high_memory) {
-		unsigned long to_write = min_t(unsigned long, count,
-					       (unsigned long)high_memory - p);
-		wrote = do_write_kmem(p, buf, to_write, ppos);
-		if (wrote != to_write)
-			return wrote;
-		p += wrote;
-		buf += wrote;
-		count -= wrote;
-	}
+	desc->page_prot = phys_mem_access_prot(file, desc->pgoff,
+					       size,
+					       desc->page_prot);
 
-	if (count > 0) {
-		kbuf = (char *)__get_free_page(GFP_KERNEL);
-		if (!kbuf)
-			return wrote ? wrote : -ENOMEM;
-		while (count > 0) {
-			unsigned long sz = size_inside_page(p, count);
-			unsigned long n;
+	desc->vm_ops = &mmap_mem_ops;
 
-			if (!is_vmalloc_or_module_addr((void *)p)) {
-				err = -ENXIO;
-				break;
-			}
-			n = copy_from_user(kbuf, buf, sz);
-			if (n) {
-				err = -EFAULT;
-				break;
-			}
-			vwrite(kbuf, (char *)p, sz);
-			count -= sz;
-			buf += sz;
-			virtr += sz;
-			p += sz;
-		}
-		free_page((unsigned long)kbuf);
-	}
+	/* Remap-pfn-range will mark the range VM_IO. */
+	mmap_action_remap_full(desc, desc->pgoff);
+	/* We filter remap errors to -EAGAIN. */
+	desc->action.error_hook = mmap_filter_error;
 
-	*ppos = p;
-	return virtr + wrote ? : err;
+	return 0;
 }
-#endif
 
 #ifdef CONFIG_DEVPORT
 static ssize_t read_port(struct file *file, char __user *buf,
@@ -545,7 +375,7 @@ static ssize_t read_port(struct file *file, char __user *buf,
 	unsigned long i = *ppos;
 	char __user *tmp = buf;
 
-	if (!access_ok(VERIFY_WRITE, buf, count))
+	if (!access_ok(buf, count))
 		return -EFAULT;
 	while (count-- > 0 && i < 65536) {
 		if (__put_user(inb(i), tmp) < 0)
@@ -563,10 +393,11 @@ static ssize_t write_port(struct file *file, const char __user *buf,
 	unsigned long i = *ppos;
 	const char __user *tmp = buf;
 
-	if (!access_ok(VERIFY_READ, buf, count))
+	if (!access_ok(buf, count))
 		return -EFAULT;
 	while (count-- > 0 && i < 65536) {
 		char c;
+
 		if (__get_user(c, tmp)) {
 			if (tmp > buf)
 				break;
@@ -593,16 +424,16 @@ static ssize_t write_null(struct file *file, const char __user *buf,
 	return count;
 }
 
-static ssize_t aio_read_null(struct kiocb *iocb, const struct iovec *iov,
-			     unsigned long nr_segs, loff_t pos)
+static ssize_t read_iter_null(struct kiocb *iocb, struct iov_iter *to)
 {
 	return 0;
 }
 
-static ssize_t aio_write_null(struct kiocb *iocb, const struct iovec *iov,
-			      unsigned long nr_segs, loff_t pos)
+static ssize_t write_iter_null(struct kiocb *iocb, struct iov_iter *from)
 {
-	return iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(from);
+	iov_iter_advance(from, count);
+	return count;
 }
 
 static int pipe_to_null(struct pipe_inode_info *info, struct pipe_buffer *buf,
@@ -617,65 +448,121 @@ static ssize_t splice_write_null(struct pipe_inode_info *pipe, struct file *out,
 	return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_null);
 }
 
-static ssize_t read_zero(struct file *file, char __user *buf,
-			 size_t count, loff_t *ppos)
+static int uring_cmd_null(struct io_uring_cmd *ioucmd, unsigned int issue_flags)
 {
-	size_t written;
-
-	if (!count)
-		return 0;
+	return 0;
+}
 
-	if (!access_ok(VERIFY_WRITE, buf, count))
-		return -EFAULT;
+static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
+{
+	size_t written = 0;
 
-	written = 0;
-	while (count) {
-		unsigned long unwritten;
-		size_t chunk = count;
+	while (iov_iter_count(iter)) {
+		size_t chunk = iov_iter_count(iter), n;
 
 		if (chunk > PAGE_SIZE)
 			chunk = PAGE_SIZE;	/* Just for latency reasons */
-		unwritten = __clear_user(buf, chunk);
-		written += chunk - unwritten;
-		if (unwritten)
-			break;
+		n = iov_iter_zero(chunk, iter);
+		if (!n && iov_iter_count(iter))
+			return written ? written : -EFAULT;
+		written += n;
 		if (signal_pending(current))
 			return written ? written : -ERESTARTSYS;
-		buf += chunk;
-		count -= chunk;
+		if (!need_resched())
+			continue;
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return written ? written : -EAGAIN;
 		cond_resched();
 	}
-	return written ? written : -EFAULT;
+	return written;
 }
 
-static ssize_t aio_read_zero(struct kiocb *iocb, const struct iovec *iov,
-			     unsigned long nr_segs, loff_t pos)
+static ssize_t read_zero(struct file *file, char __user *buf,
+			 size_t count, loff_t *ppos)
 {
-	size_t written = 0;
-	unsigned long i;
-	ssize_t ret;
+	size_t cleared = 0;
 
-	for (i = 0; i < nr_segs; i++) {
-		ret = read_zero(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len,
-				&pos);
-		if (ret < 0)
+	while (count) {
+		size_t chunk = min_t(size_t, count, PAGE_SIZE);
+		size_t left;
+
+		left = clear_user(buf + cleared, chunk);
+		if (unlikely(left)) {
+			cleared += (chunk - left);
+			if (!cleared)
+				return -EFAULT;
+			break;
+		}
+		cleared += chunk;
+		count -= chunk;
+
+		if (signal_pending(current))
 			break;
-		written += ret;
+		cond_resched();
 	}
 
-	return written ? written : -EFAULT;
+	return cleared;
+}
+
+static int mmap_zero_private_success(const struct vm_area_struct *vma)
+{
+	/*
+	 * This is a highly unique situation where we mark a MAP_PRIVATE mapping
+	 * of /dev/zero anonymous, despite it not being.
+	 */
+	vma_set_anonymous((struct vm_area_struct *)vma);
+
+	return 0;
 }
 
-static int mmap_zero(struct file *file, struct vm_area_struct *vma)
+static int mmap_zero_prepare(struct vm_area_desc *desc)
 {
 #ifndef CONFIG_MMU
 	return -ENOSYS;
 #endif
-	if (vma->vm_flags & VM_SHARED)
-		return shmem_zero_setup(vma);
+	if (desc->vm_flags & VM_SHARED)
+		return shmem_zero_setup_desc(desc);
+
+	desc->action.success_hook = mmap_zero_private_success;
 	return 0;
 }
 
+#ifndef CONFIG_MMU
+static unsigned long get_unmapped_area_zero(struct file *file,
+				unsigned long addr, unsigned long len,
+				unsigned long pgoff, unsigned long flags)
+{
+	return -ENOSYS;
+}
+#else
+static unsigned long get_unmapped_area_zero(struct file *file,
+				unsigned long addr, unsigned long len,
+				unsigned long pgoff, unsigned long flags)
+{
+	if (flags & MAP_SHARED) {
+		/*
+		 * mmap_zero_prepare() will call shmem_zero_setup() to create a
+		 * file, so use shmem's get_unmapped_area in case it can be
+		 * huge; and pass NULL for file as in mmap.c's
+		 * get_unmapped_area(), so as not to confuse shmem with our
+		 * handle on "/dev/zero".
+		 */
+		return shmem_get_unmapped_area(NULL, addr, len, pgoff, flags);
+	}
+
+	/*
+	 * Otherwise flags & MAP_PRIVATE: with no shmem object beneath it,
+	 * attempt to map aligned to huge page size if possible, otherwise we
+	 * fall back to system page size mappings.
+	 */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return thp_get_unmapped_area(file, addr, len, pgoff, flags);
+#else
+	return mm_get_unmapped_area(file, addr, len, pgoff, flags);
+#endif
+}
+#endif /* CONFIG_MMU */
+
 static ssize_t write_full(struct file *file, const char __user *buf,
 			  size_t count, loff_t *ppos)
 {
@@ -704,13 +591,14 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig)
 {
 	loff_t ret;
 
-	mutex_lock(&file_inode(file)->i_mutex);
+	inode_lock(file_inode(file));
 	switch (orig) {
 	case SEEK_CUR:
 		offset += file->f_pos;
+		fallthrough;
 	case SEEK_SET:
 		/* to avoid userland mistaking f_pos=-9 as -EBADF=-9 */
-		if (IS_ERR_VALUE((unsigned long long)offset)) {
+		if ((unsigned long long)offset >= -MAX_ERRNO) {
 			ret = -EOVERFLOW;
 			break;
 		}
@@ -721,50 +609,62 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig)
 	default:
 		ret = -EINVAL;
 	}
-	mutex_unlock(&file_inode(file)->i_mutex);
+	inode_unlock(file_inode(file));
 	return ret;
 }
 
 static int open_port(struct inode *inode, struct file *filp)
 {
-	return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
+	int rc;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	rc = security_locked_down(LOCKDOWN_DEV_MEM);
+	if (rc)
+		return rc;
+
+	if (iminor(inode) != DEVMEM_MINOR)
+		return 0;
+
+	/*
+	 * Use a unified address space to have a single point to manage
+	 * revocations when drivers want to take over a /dev/mem mapped
+	 * range.
+	 */
+	filp->f_mapping = iomem_get_mapping();
+
+	return 0;
 }
 
 #define zero_lseek	null_lseek
 #define full_lseek      null_lseek
 #define write_zero	write_null
-#define read_full       read_zero
-#define aio_write_zero	aio_write_null
+#define write_iter_zero	write_iter_null
+#define splice_write_zero	splice_write_null
 #define open_mem	open_port
-#define open_kmem	open_mem
 
-static const struct file_operations mem_fops = {
+static const struct file_operations __maybe_unused mem_fops = {
 	.llseek		= memory_lseek,
 	.read		= read_mem,
 	.write		= write_mem,
-	.mmap		= mmap_mem,
+	.mmap_prepare	= mmap_mem_prepare,
 	.open		= open_mem,
+#ifndef CONFIG_MMU
 	.get_unmapped_area = get_unmapped_area_mem,
-};
-
-#ifdef CONFIG_DEVKMEM
-static const struct file_operations kmem_fops = {
-	.llseek		= memory_lseek,
-	.read		= read_kmem,
-	.write		= write_kmem,
-	.mmap		= mmap_kmem,
-	.open		= open_kmem,
-	.get_unmapped_area = get_unmapped_area_mem,
-};
+	.mmap_capabilities = memory_mmap_capabilities,
 #endif
+	.fop_flags	= FOP_UNSIGNED_OFFSET,
+};
 
 static const struct file_operations null_fops = {
 	.llseek		= null_lseek,
 	.read		= read_null,
 	.write		= write_null,
-	.aio_read	= aio_read_null,
-	.aio_write	= aio_write_null,
+	.read_iter	= read_iter_null,
+	.write_iter	= write_iter_null,
 	.splice_write	= splice_write_null,
+	.uring_cmd	= uring_cmd_null,
 };
 
 #ifdef CONFIG_DEVPORT
@@ -778,49 +678,45 @@ static const struct file_operations port_fops = {
 
 static const struct file_operations zero_fops = {
 	.llseek		= zero_lseek,
-	.read		= read_zero,
 	.write		= write_zero,
-	.aio_read	= aio_read_zero,
-	.aio_write	= aio_write_zero,
-	.mmap		= mmap_zero,
-};
-
-/*
- * capabilities for /dev/zero
- * - permits private mappings, "copies" are taken of the source of zeros
- * - no writeback happens
- */
-static struct backing_dev_info zero_bdi = {
-	.name		= "char/mem",
-	.capabilities	= BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK,
+	.read_iter	= read_iter_zero,
+	.read		= read_zero,
+	.write_iter	= write_iter_zero,
+	.splice_read	= copy_splice_read,
+	.splice_write	= splice_write_zero,
+	.mmap_prepare	= mmap_zero_prepare,
+	.get_unmapped_area = get_unmapped_area_zero,
+#ifndef CONFIG_MMU
+	.mmap_capabilities = zero_mmap_capabilities,
+#endif
 };
 
 static const struct file_operations full_fops = {
 	.llseek		= full_lseek,
-	.read		= read_full,
+	.read_iter	= read_iter_zero,
 	.write		= write_full,
+	.splice_read	= copy_splice_read,
 };
 
 static const struct memdev {
 	const char *name;
-	umode_t mode;
 	const struct file_operations *fops;
-	struct backing_dev_info *dev_info;
+	fmode_t fmode;
+	umode_t mode;
 } devlist[] = {
-	 [1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi },
-#ifdef CONFIG_DEVKMEM
-	 [2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi },
+#ifdef CONFIG_DEVMEM
+	[DEVMEM_MINOR] = { "mem", &mem_fops, 0, 0 },
 #endif
-	 [3] = { "null", 0666, &null_fops, NULL },
+	[3] = { "null", &null_fops, FMODE_NOWAIT, 0666 },
 #ifdef CONFIG_DEVPORT
-	 [4] = { "port", 0, &port_fops, NULL },
+	[4] = { "port", &port_fops, 0, 0 },
 #endif
-	 [5] = { "zero", 0666, &zero_fops, &zero_bdi },
-	 [7] = { "full", 0666, &full_fops, NULL },
-	 [8] = { "random", 0666, &random_fops, NULL },
-	 [9] = { "urandom", 0666, &urandom_fops, NULL },
+	[5] = { "zero", &zero_fops, FMODE_NOWAIT, 0666 },
+	[7] = { "full", &full_fops, 0, 0666 },
+	[8] = { "random", &random_fops, FMODE_NOWAIT, 0666 },
+	[9] = { "urandom", &urandom_fops, FMODE_NOWAIT, 0666 },
 #ifdef CONFIG_PRINTK
-	[11] = { "kmsg", 0644, &kmsg_fops, NULL },
+	[11] = { "kmsg", &kmsg_fops, 0, 0644 },
 #endif
 };
 
@@ -838,12 +734,7 @@ static int memory_open(struct inode *inode, struct file *filp)
 		return -ENXIO;
 
 	filp->f_op = dev->fops;
-	if (dev->dev_info)
-		filp->f_mapping->backing_dev_info = dev->dev_info;
-
-	/* Is /dev/mem or /dev/kmem ? */
-	if (dev->dev_info == &directly_mappable_cdev_bdi)
-		filp->f_mode |= FMODE_UNSIGNED_OFFSET;
+	filp->f_mode |= dev->fmode;
 
 	if (dev->fops->open)
 		return dev->fops->open(inode, filp);
@@ -856,32 +747,30 @@ static const struct file_operations memory_fops = {
 	.llseek = noop_llseek,
 };
 
-static char *mem_devnode(struct device *dev, umode_t *mode)
+static char *mem_devnode(const struct device *dev, umode_t *mode)
 {
 	if (mode && devlist[MINOR(dev->devt)].mode)
 		*mode = devlist[MINOR(dev->devt)].mode;
 	return NULL;
 }
 
-static struct class *mem_class;
+static const struct class mem_class = {
+	.name		= "mem",
+	.devnode	= mem_devnode,
+};
 
 static int __init chr_dev_init(void)
 {
+	int retval;
 	int minor;
-	int err;
-
-	err = bdi_init(&zero_bdi);
-	if (err)
-		return err;
 
 	if (register_chrdev(MEM_MAJOR, "mem", &memory_fops))
 		printk("unable to get major %d for memory devs\n", MEM_MAJOR);
 
-	mem_class = class_create(THIS_MODULE, "mem");
-	if (IS_ERR(mem_class))
-		return PTR_ERR(mem_class);
+	retval = class_register(&mem_class);
+	if (retval)
+		return retval;
 
-	mem_class->devnode = mem_devnode;
 	for (minor = 1; minor < ARRAY_SIZE(devlist); minor++) {
 		if (!devlist[minor].name)
 			continue;
@@ -892,7 +781,7 @@ static int __init chr_dev_init(void)
 		if ((minor == DEVPORT_MINOR) && !arch_has_dev_port())
 			continue;
 
-		device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor),
+		device_create(&mem_class, NULL, MKDEV(MEM_MAJOR, minor),
 			      NULL, devlist[minor].name);
 	}