Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 787 insertions, 0 deletions

diff --git a/drivers/char/mem.c b/drivers/char/mem.c
new file mode 100644
index 000000000..83bf2a4dc
--- /dev/null
+++ b/drivers/char/mem.c
@@ -0,0 +1,787 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/drivers/char/mem.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  Added devfs support.
+ *    Jan-11-1998, C. Scott Ananian <cananian@alumni.princeton.edu>
+ *  Shared /dev/zero mmapping support, Feb 2000, Kanoj Sarcar <kanoj@sgi.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/miscdevice.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mman.h>
+#include <linux/random.h>
+#include <linux/init.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/shmem_fs.h>
+#include <linux/splice.h>
+#include <linux/pfn.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/uio.h>
+#include <linux/uaccess.h>
+#include <linux/security.h>
+
+#ifdef CONFIG_IA64
+# include <linux/efi.h>
+#endif
+
+#define DEVMEM_MINOR	1
+#define DEVPORT_MINOR	4
+
+static inline unsigned long size_inside_page(unsigned long start,
+					     unsigned long size)
+{
+	unsigned long sz;
+
+	sz = PAGE_SIZE - (start & (PAGE_SIZE - 1));
+
+	return min(sz, size);
+}
+
+#ifndef ARCH_HAS_VALID_PHYS_ADDR_RANGE
+static inline int valid_phys_addr_range(phys_addr_t addr, size_t count)
+{
+	return addr + count <= __pa(high_memory);
+}
+
+static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
+{
+	return 1;
+}
+#endif
+
+#ifdef CONFIG_STRICT_DEVMEM
+static inline int page_is_allowed(unsigned long pfn)
+{
+	return devmem_is_allowed(pfn);
+}
+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))
+			return 0;
+		cursor += PAGE_SIZE;
+		pfn++;
+	}
+	return 1;
+}
+#else
+static inline int page_is_allowed(unsigned long pfn)
+{
+	return 1;
+}
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+	return 1;
+}
+#endif
+
+#ifndef unxlate_dev_mem_ptr
+#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr
+void __weak unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
+{
+}
+#endif
+
+static inline bool should_stop_iteration(void)
+{
+	if (need_resched())
+		cond_resched();
+	return signal_pending(current);
+}
+
+/*
+ * This funcion reads the *physical* memory. The f_pos points directly to the
+ * memory location.
+ */
+static ssize_t read_mem(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	phys_addr_t p = *ppos;
+	ssize_t read, sz;
+	void *ptr;
+	char *bounce;
+	int err;
+
+	if (p != *ppos)
+		return 0;
+
+	if (!valid_phys_addr_range(p, count))
+		return -EFAULT;
+	read = 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);
+		if (sz > 0) {
+			if (clear_user(buf, sz))
+				return -EFAULT;
+			buf += sz;
+			p += sz;
+			count -= sz;
+			read += sz;
+		}
+	}
+#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);
+
+		err = -EPERM;
+		allowed = page_is_allowed(p >> PAGE_SHIFT);
+		if (!allowed)
+			goto failed;
+
+		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);
+		}
+
+		if (remaining)
+			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,
+			 size_t count, loff_t *ppos)
+{
+	phys_addr_t p = *ppos;
+	ssize_t written, sz;
+	unsigned long copied;
+	void *ptr;
+
+	if (p != *ppos)
+		return -EFBIG;
+
+	if (!valid_phys_addr_range(p, count))
+		return -EFAULT;
+
+	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) {
+		int allowed;
+
+		sz = size_inside_page(p, count);
+
+		allowed = page_is_allowed(p >> PAGE_SHIFT);
+		if (!allowed)
+			return -EPERM;
+
+		/* 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;
+			}
+		}
+
+		buf += sz;
+		p += sz;
+		count -= sz;
+		written += sz;
+		if (should_stop_iteration())
+			break;
+	}
+
+	*ppos += written;
+	return written;
+}
+
+int __weak phys_mem_access_prot_allowed(struct file *file,
+	unsigned long pfn, unsigned long size, pgprot_t *vma_prot)
+{
+	return 1;
+}
+
+#ifndef __HAVE_PHYS_MEM_ACCESS_PROT
+
+/*
+ * Architectures vary in how they handle caching for addresses
+ * outside of main memory.
+ *
+ */
+#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);
+#else
+	/*
+	 * Accessing memory above the top the kernel knows about or through a
+	 * file pointer
+	 * that was marked O_DSYNC will be done non-cached.
+	 */
+	if (file->f_flags & O_DSYNC)
+		return 1;
+	return addr >= __pa(high_memory);
+#endif
+}
+#endif
+
+static pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot)
+{
+#ifdef pgprot_noncached
+	phys_addr_t offset = pfn << PAGE_SHIFT;
+
+	if (uncached_access(file, offset))
+		return pgprot_noncached(vma_prot);
+#endif
+	return vma_prot;
+}
+#endif
+
+#ifndef CONFIG_MMU
+static unsigned long get_unmapped_area_mem(struct file *file,
+					   unsigned long addr,
+					   unsigned long len,
+					   unsigned long pgoff,
+					   unsigned long flags)
+{
+	if (!valid_mmap_phys_addr_range(pgoff, len))
+		return (unsigned long) -EINVAL;
+	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)
+{
+	return vma->vm_flags & VM_MAYSHARE;
+}
+#else
+
+static inline int private_mapping_ok(struct vm_area_struct *vma)
+{
+	return 1;
+}
+#endif
+
+static const struct vm_operations_struct mmap_mem_ops = {
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+	.access = generic_access_phys
+#endif
+};
+
+static int mmap_mem(struct file *file, struct vm_area_struct *vma)
+{
+	size_t size = vma->vm_end - vma->vm_start;
+	phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
+
+	/* Does it even fit in phys_addr_t? */
+	if (offset >> PAGE_SHIFT != vma->vm_pgoff)
+		return -EINVAL;
+
+	/* It's illegal to wrap around the end of the physical address space. */
+	if (offset + (phys_addr_t)size - 1 < offset)
+		return -EINVAL;
+
+	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;
+}
+
+static ssize_t read_port(struct file *file, char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	unsigned long i = *ppos;
+	char __user *tmp = buf;
+
+	if (!access_ok(buf, count))
+		return -EFAULT;
+	while (count-- > 0 && i < 65536) {
+		if (__put_user(inb(i), tmp) < 0)
+			return -EFAULT;
+		i++;
+		tmp++;
+	}
+	*ppos = i;
+	return tmp-buf;
+}
+
+static ssize_t write_port(struct file *file, const char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	unsigned long i = *ppos;
+	const char __user *tmp = buf;
+
+	if (!access_ok(buf, count))
+		return -EFAULT;
+	while (count-- > 0 && i < 65536) {
+		char c;
+
+		if (__get_user(c, tmp)) {
+			if (tmp > buf)
+				break;
+			return -EFAULT;
+		}
+		outb(c, i);
+		i++;
+		tmp++;
+	}
+	*ppos = i;
+	return tmp-buf;
+}
+
+static ssize_t read_null(struct file *file, char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	return 0;
+}
+
+static ssize_t write_null(struct file *file, const char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	return count;
+}
+
+static ssize_t read_iter_null(struct kiocb *iocb, struct iov_iter *to)
+{
+	return 0;
+}
+
+static ssize_t write_iter_null(struct kiocb *iocb, struct iov_iter *from)
+{
+	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,
+			struct splice_desc *sd)
+{
+	return sd->len;
+}
+
+static ssize_t splice_write_null(struct pipe_inode_info *pipe, struct file *out,
+				 loff_t *ppos, size_t len, unsigned int flags)
+{
+	return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_null);
+}
+
+static int uring_cmd_null(struct io_uring_cmd *ioucmd, unsigned int issue_flags)
+{
+	return 0;
+}
+
+static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
+{
+	size_t written = 0;
+
+	while (iov_iter_count(iter)) {
+		size_t chunk = iov_iter_count(iter), n;
+
+		if (chunk > PAGE_SIZE)
+			chunk = PAGE_SIZE;	/* Just for latency reasons */
+		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;
+		if (!need_resched())
+			continue;
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return written ? written : -EAGAIN;
+		cond_resched();
+	}
+	return written;
+}
+
+static ssize_t read_zero(struct file *file, char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	size_t cleared = 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;
+		cond_resched();
+	}
+
+	return cleared;
+}
+
+static int mmap_zero(struct file *file, struct vm_area_struct *vma)
+{
+#ifndef CONFIG_MMU
+	return -ENOSYS;
+#endif
+	if (vma->vm_flags & VM_SHARED)
+		return shmem_zero_setup(vma);
+	vma_set_anonymous(vma);
+	return 0;
+}
+
+static unsigned long get_unmapped_area_zero(struct file *file,
+				unsigned long addr, unsigned long len,
+				unsigned long pgoff, unsigned long flags)
+{
+#ifdef CONFIG_MMU
+	if (flags & MAP_SHARED) {
+		/*
+		 * mmap_zero() 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 */
+	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+#else
+	return -ENOSYS;
+#endif
+}
+
+static ssize_t write_full(struct file *file, const char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	return -ENOSPC;
+}
+
+/*
+ * Special lseek() function for /dev/null and /dev/zero.  Most notably, you
+ * can fopen() both devices with "a" now.  This was previously impossible.
+ * -- SRB.
+ */
+static loff_t null_lseek(struct file *file, loff_t offset, int orig)
+{
+	return file->f_pos = 0;
+}
+
+/*
+ * The memory devices use the full 32/64 bits of the offset, and so we cannot
+ * check against negative addresses: they are ok. The return value is weird,
+ * though, in that case (0).
+ *
+ * also note that seeking relative to the "end of file" isn't supported:
+ * it has no meaning, so it returns -EINVAL.
+ */
+static loff_t memory_lseek(struct file *file, loff_t offset, int orig)
+{
+	loff_t ret;
+
+	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 ((unsigned long long)offset >= -MAX_ERRNO) {
+			ret = -EOVERFLOW;
+			break;
+		}
+		file->f_pos = offset;
+		ret = file->f_pos;
+		force_successful_syscall_return();
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	inode_unlock(file_inode(file));
+	return ret;
+}
+
+static int open_port(struct inode *inode, struct file *filp)
+{
+	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 write_iter_zero	write_iter_null
+#define open_mem	open_port
+
+static const struct file_operations __maybe_unused mem_fops = {
+	.llseek		= memory_lseek,
+	.read		= read_mem,
+	.write		= write_mem,
+	.mmap		= mmap_mem,
+	.open		= open_mem,
+#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,
+	.write		= write_null,
+	.read_iter	= read_iter_null,
+	.write_iter	= write_iter_null,
+	.splice_write	= splice_write_null,
+	.uring_cmd	= uring_cmd_null,
+};
+
+static const struct file_operations __maybe_unused port_fops = {
+	.llseek		= memory_lseek,
+	.read		= read_port,
+	.write		= write_port,
+	.open		= open_port,
+};
+
+static const struct file_operations zero_fops = {
+	.llseek		= zero_lseek,
+	.write		= write_zero,
+	.read_iter	= read_iter_zero,
+	.read		= read_zero,
+	.write_iter	= write_iter_zero,
+	.mmap		= mmap_zero,
+	.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_iter	= read_iter_zero,
+	.write		= write_full,
+};
+
+static const struct memdev {
+	const char *name;
+	umode_t mode;
+	const struct file_operations *fops;
+	fmode_t fmode;
+} devlist[] = {
+#ifdef CONFIG_DEVMEM
+	 [DEVMEM_MINOR] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET },
+#endif
+	 [3] = { "null", 0666, &null_fops, FMODE_NOWAIT },
+#ifdef CONFIG_DEVPORT
+	 [4] = { "port", 0, &port_fops, 0 },
+#endif
+	 [5] = { "zero", 0666, &zero_fops, FMODE_NOWAIT },
+	 [7] = { "full", 0666, &full_fops, 0 },
+	 [8] = { "random", 0666, &random_fops, FMODE_NOWAIT },
+	 [9] = { "urandom", 0666, &urandom_fops, FMODE_NOWAIT },
+#ifdef CONFIG_PRINTK
+	[11] = { "kmsg", 0644, &kmsg_fops, 0 },
+#endif
+};
+
+static int memory_open(struct inode *inode, struct file *filp)
+{
+	int minor;
+	const struct memdev *dev;
+
+	minor = iminor(inode);
+	if (minor >= ARRAY_SIZE(devlist))
+		return -ENXIO;
+
+	dev = &devlist[minor];
+	if (!dev->fops)
+		return -ENXIO;
+
+	filp->f_op = dev->fops;
+	filp->f_mode |= dev->fmode;
+
+	if (dev->fops->open)
+		return dev->fops->open(inode, filp);
+
+	return 0;
+}
+
+static const struct file_operations memory_fops = {
+	.open = memory_open,
+	.llseek = noop_llseek,
+};
+
+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 int __init chr_dev_init(void)
+{
+	int minor;
+
+	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);
+
+	mem_class->devnode = mem_devnode;
+	for (minor = 1; minor < ARRAY_SIZE(devlist); minor++) {
+		if (!devlist[minor].name)
+			continue;
+
+		/*
+		 * Create /dev/port?
+		 */
+		if ((minor == DEVPORT_MINOR) && !arch_has_dev_port())
+			continue;
+
+		device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor),
+			      NULL, devlist[minor].name);
+	}
+
+	return tty_init();
+}
+
+fs_initcall(chr_dev_init);