drivers/char: remove /dev/kmem for good

Patch series "drivers/char: remove /dev/kmem for good".

Exploring /dev/kmem and /dev/mem in the context of memory hot(un)plug and
memory ballooning, I started questioning the existence of /dev/kmem.

Comparing it with the /proc/kcore implementation, it does not seem to be
able to deal with things like

a) Pages unmapped from the direct mapping (e.g., to be used by secretmem)
  -> kern_addr_valid(). virt_addr_valid() is not sufficient.

b) Special cases like gart aperture memory that is not to be touched
  -> mem_pfn_is_ram()

Unless I am missing something, it's at least broken in some cases and might
fault/crash the machine.

Looks like its existence has been questioned before in 2005 and 2010 [1],
after ~11 additional years, it might make sense to revive the discussion.

CONFIG_DEVKMEM is only enabled in a single defconfig (on purpose or by
mistake?).  All distributions disable it: in Ubuntu it has been disabled
for more than 10 years, in Debian since 2.6.31, in F...

Documentation/admin-guide/devices.txt

@@ -4,7 +4,7 @@
 
    1 char	Memory devices
 		  1 = /dev/mem		Physical memory access
-		  2 = /dev/kmem		Kernel virtual memory access
+		  2 = /dev/kmem		OBSOLETE - replaced by /proc/kcore
 		  3 = /dev/null		Null device
 		  4 = /dev/port		I/O port access
 		  5 = /dev/zero		Null byte source

arch/arm/configs/dove_defconfig

@@ -63,7 +63,6 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_MOUSE_PS2 is not set
 # CONFIG_SERIO is not set
 CONFIG_LEGACY_PTY_COUNT=16
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_RUNTIME_UARTS=2

arch/arm/configs/magician_defconfig

@@ -72,7 +72,6 @@ CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_UINPUT=m
 # CONFIG_SERIO is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_PXA=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_HW_RANDOM is not set

arch/arm/configs/moxart_defconfig

@@ -79,7 +79,6 @@ CONFIG_INPUT_EVBUG=y
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=1

arch/arm/configs/mps2_defconfig

@@ -69,7 +69,6 @@ CONFIG_SMSC911X=y
 # CONFIG_VT is not set
 # CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_NONSTANDARD=y
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_MPS2_UART_CONSOLE=y
 CONFIG_SERIAL_MPS2_UART=y
 # CONFIG_HW_RANDOM is not set

arch/arm/configs/mvebu_v5_defconfig

@@ -100,7 +100,6 @@ CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_LEGACY_PTY_COUNT=16
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_RUNTIME_UARTS=2

arch/arm/configs/xcep_defconfig

@@ -53,7 +53,6 @@ CONFIG_NET_ETHERNET=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_PXA=y
 CONFIG_SERIAL_PXA_CONSOLE=y
 # CONFIG_LEGACY_PTYS is not set

arch/hexagon/configs/comet_defconfig

@@ -34,7 +34,6 @@ CONFIG_NET_ETHERNET=y
 # CONFIG_SERIO is not set
 # CONFIG_CONSOLE_TRANSLATIONS is not set
 CONFIG_LEGACY_PTY_COUNT=64
-# CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_SPI=y
 CONFIG_SPI_DEBUG=y

arch/m68k/configs/amcore_defconfig

@@ -60,7 +60,6 @@ CONFIG_DM9000=y
 # CONFIG_VT is not set
 # CONFIG_UNIX98_PTYS is not set
 # CONFIG_DEVMEM is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_BAUDRATE=115200
 CONFIG_SERIAL_MCF_CONSOLE=y

arch/openrisc/configs/or1ksim_defconfig

@@ -43,7 +43,6 @@ CONFIG_MICREL_PHY=y
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y

arch/sh/configs/edosk7705_defconfig

@@ -23,7 +23,6 @@ CONFIG_SH_PCLK_FREQ=31250000
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
-# CONFIG_DEVKMEM is not set
 # CONFIG_UNIX98_PTYS is not set
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_HW_RANDOM is not set

arch/sh/configs/se7206_defconfig

@@ -71,7 +71,6 @@ CONFIG_SMC91X=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=4
 CONFIG_SERIAL_SH_SCI_CONSOLE=y

arch/sh/configs/sh2007_defconfig

@@ -75,7 +75,6 @@ CONFIG_INPUT_FF_MEMLESS=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_VT_HW_CONSOLE_BINDING=y
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
 # CONFIG_LEGACY_PTYS is not set

arch/sh/configs/sh7724_generic_defconfig

@@ -18,7 +18,6 @@ CONFIG_CPU_IDLE=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=6
 CONFIG_SERIAL_SH_SCI_CONSOLE=y

arch/sh/configs/sh7770_generic_defconfig

@@ -20,7 +20,6 @@ CONFIG_CPU_IDLE=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=6
 CONFIG_SERIAL_SH_SCI_CONSOLE=y

arch/sh/configs/sh7785lcr_32bit_defconfig

@@ -66,7 +66,6 @@ CONFIG_INPUT_FF_MEMLESS=m
 CONFIG_INPUT_EVDEV=y
 CONFIG_INPUT_EVBUG=m
 CONFIG_VT_HW_CONSOLE_BINDING=y
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=6
 CONFIG_SERIAL_SH_SCI_CONSOLE=y

arch/sparc/configs/sparc64_defconfig

@@ -122,7 +122,6 @@ CONFIG_INPUT_SPARCSPKR=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIO_PCIPS2=m
 CONFIG_SERIO_RAW=m
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_SUNSU=y
 CONFIG_SERIAL_SUNSU_CONSOLE=y
 CONFIG_SERIAL_SUNSAB=y

arch/xtensa/configs/xip_kc705_defconfig

@@ -72,7 +72,6 @@ CONFIG_MARVELL_PHY=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
-CONFIG_DEVKMEM=y
 CONFIG_SERIAL_8250=y
 # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
 CONFIG_SERIAL_8250_CONSOLE=y

drivers/char/Kconfig

@@ -334,16 +334,6 @@ config DEVMEM
 	  memory.
 	  When in doubt, say "Y".
 
-config DEVKMEM
-	bool "/dev/kmem virtual device support"
-	# On arm64, VMALLOC_START < PAGE_OFFSET, which confuses kmem read/write
-	depends on !ARM64
-	help
-	  Say Y here if you want to support the /dev/kmem device. The
-	  /dev/kmem device is rarely used, but can be used for certain
-	  kind of kernel debugging operations.
-	  When in doubt, say "N".
-
 config NVRAM
 	tristate "/dev/nvram support"
 	depends on X86 || HAVE_ARCH_NVRAM_OPS

drivers/char/mem.c

@@ -403,221 +403,6 @@ static int mmap_mem(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-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);
-}
-
-/*
- * 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((void *)p);
-			if (!virt_addr_valid(kbuf))
-				return -ENXIO;
-
-			if (copy_to_user(buf, kbuf, sz))
-				return -EFAULT;
-			buf += sz;
-			p += sz;
-			read += sz;
-			low_count -= sz;
-			count -= sz;
-			if (should_stop_iteration()) {
-				count = 0;
-				break;
-			}
-		}
-	}
-
-	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;
-			if (should_stop_iteration())
-				break;
-		}
-		free_page((unsigned long)kbuf);
-	}
-	*ppos = p;
-	return read ? read : err;
-}
-
-
-static ssize_t do_write_kmem(unsigned long p, const char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	ssize_t written, sz;
-	unsigned long copied;
-
-	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
-
-	while (count > 0) {
-		void *ptr;
-
-		sz = size_inside_page(p, 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.
-		 */
-		ptr = xlate_dev_kmem_ptr((void *)p);
-		if (!virt_addr_valid(ptr))
-			return -ENXIO;
-
-		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 (should_stop_iteration())
-			break;
-	}
-
-	*ppos += written;
-	return written;
-}
-
-/*
- * 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;
-	}
-
-	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;
-
-			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;
-			if (should_stop_iteration())
-				break;
-		}
-		free_page((unsigned long)kbuf);
-	}
-
-	*ppos = p;
-	return virtr + wrote ? : err;
-}
-
 static ssize_t read_port(struct file *file, char __user *buf,
 			 size_t count, loff_t *ppos)
 {
@@ -855,7 +640,6 @@ static int open_port(struct inode *inode, struct file *filp)
 #define write_zero	write_null
 #define write_iter_zero	write_iter_null
 #define open_mem	open_port
-#define open_kmem	open_mem
 
 static const struct file_operations __maybe_unused mem_fops = {
 	.llseek		= memory_lseek,
@@ -869,18 +653,6 @@ static const struct file_operations __maybe_unused mem_fops = {
 #endif
 };
 
-static const struct file_operations __maybe_unused kmem_fops = {
-	.llseek		= memory_lseek,
-	.read		= read_kmem,
-	.write		= write_kmem,
-	.mmap		= mmap_kmem,
-	.open		= open_kmem,
-#ifndef CONFIG_MMU
-	.get_unmapped_area = get_unmapped_area_mem,
-	.mmap_capabilities = memory_mmap_capabilities,
-#endif
-};
-
 static const struct file_operations null_fops = {
 	.llseek		= null_lseek,
 	.read		= read_null,
@@ -924,9 +696,6 @@ static const struct memdev {
 } devlist[] = {
 #ifdef CONFIG_DEVMEM
 	 [DEVMEM_MINOR] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET },
-#endif
-#ifdef CONFIG_DEVKMEM
-	 [2] = { "kmem", 0, &kmem_fops, FMODE_UNSIGNED_OFFSET },
 #endif
 	 [3] = { "null", 0666, &null_fops, 0 },
 #ifdef CONFIG_DEVPORT