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, 432 insertions, 0 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
new file mode 100644
index 000000000..372653b92
--- /dev/null
+++ b/fs/file_table.c
@@ -0,0 +1,432 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/fs/file_table.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
+ */
+
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/filelock.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include <linux/eventpoll.h>
+#include <linux/rcupdate.h>
+#include <linux/mount.h>
+#include <linux/capability.h>
+#include <linux/cdev.h>
+#include <linux/fsnotify.h>
+#include <linux/sysctl.h>
+#include <linux/percpu_counter.h>
+#include <linux/percpu.h>
+#include <linux/task_work.h>
+#include <linux/ima.h>
+#include <linux/swap.h>
+#include <linux/kmemleak.h>
+
+#include <linux/atomic.h>
+
+#include "internal.h"
+
+/* sysctl tunables... */
+static struct files_stat_struct files_stat = {
+	.max_files = NR_FILE
+};
+
+/* SLAB cache for file structures */
+static struct kmem_cache *filp_cachep __read_mostly;
+
+static struct percpu_counter nr_files __cacheline_aligned_in_smp;
+
+static void file_free_rcu(struct rcu_head *head)
+{
+	struct file *f = container_of(head, struct file, f_rcuhead);
+
+	put_cred(f->f_cred);
+	kmem_cache_free(filp_cachep, f);
+}
+
+static inline void file_free(struct file *f)
+{
+	security_file_free(f);
+	if (!(f->f_mode & FMODE_NOACCOUNT))
+		percpu_counter_dec(&nr_files);
+	call_rcu(&f->f_rcuhead, file_free_rcu);
+}
+
+/*
+ * Return the total number of open files in the system
+ */
+static long get_nr_files(void)
+{
+	return percpu_counter_read_positive(&nr_files);
+}
+
+/*
+ * Return the maximum number of open files in the system
+ */
+unsigned long get_max_files(void)
+{
+	return files_stat.max_files;
+}
+EXPORT_SYMBOL_GPL(get_max_files);
+
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+
+/*
+ * Handle nr_files sysctl
+ */
+static int proc_nr_files(struct ctl_table *table, int write, void *buffer,
+			 size_t *lenp, loff_t *ppos)
+{
+	files_stat.nr_files = get_nr_files();
+	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+}
+
+static struct ctl_table fs_stat_sysctls[] = {
+	{
+		.procname	= "file-nr",
+		.data		= &files_stat,
+		.maxlen		= sizeof(files_stat),
+		.mode		= 0444,
+		.proc_handler	= proc_nr_files,
+	},
+	{
+		.procname	= "file-max",
+		.data		= &files_stat.max_files,
+		.maxlen		= sizeof(files_stat.max_files),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+		.extra1		= SYSCTL_LONG_ZERO,
+		.extra2		= SYSCTL_LONG_MAX,
+	},
+	{
+		.procname	= "nr_open",
+		.data		= &sysctl_nr_open,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &sysctl_nr_open_min,
+		.extra2		= &sysctl_nr_open_max,
+	},
+	{ }
+};
+
+static int __init init_fs_stat_sysctls(void)
+{
+	register_sysctl_init("fs", fs_stat_sysctls);
+	if (IS_ENABLED(CONFIG_BINFMT_MISC)) {
+		struct ctl_table_header *hdr;
+		hdr = register_sysctl_mount_point("fs/binfmt_misc");
+		kmemleak_not_leak(hdr);
+	}
+	return 0;
+}
+fs_initcall(init_fs_stat_sysctls);
+#endif
+
+static struct file *__alloc_file(int flags, const struct cred *cred)
+{
+	struct file *f;
+	int error;
+
+	f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
+	if (unlikely(!f))
+		return ERR_PTR(-ENOMEM);
+
+	f->f_cred = get_cred(cred);
+	error = security_file_alloc(f);
+	if (unlikely(error)) {
+		file_free_rcu(&f->f_rcuhead);
+		return ERR_PTR(error);
+	}
+
+	atomic_long_set(&f->f_count, 1);
+	rwlock_init(&f->f_owner.lock);
+	spin_lock_init(&f->f_lock);
+	mutex_init(&f->f_pos_lock);
+	f->f_flags = flags;
+	f->f_mode = OPEN_FMODE(flags);
+	/* f->f_version: 0 */
+
+	return f;
+}
+
+/* Find an unused file structure and return a pointer to it.
+ * Returns an error pointer if some error happend e.g. we over file
+ * structures limit, run out of memory or operation is not permitted.
+ *
+ * Be very careful using this.  You are responsible for
+ * getting write access to any mount that you might assign
+ * to this filp, if it is opened for write.  If this is not
+ * done, you will imbalance int the mount's writer count
+ * and a warning at __fput() time.
+ */
+struct file *alloc_empty_file(int flags, const struct cred *cred)
+{
+	static long old_max;
+	struct file *f;
+
+	/*
+	 * Privileged users can go above max_files
+	 */
+	if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) {
+		/*
+		 * percpu_counters are inaccurate.  Do an expensive check before
+		 * we go and fail.
+		 */
+		if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files)
+			goto over;
+	}
+
+	f = __alloc_file(flags, cred);
+	if (!IS_ERR(f))
+		percpu_counter_inc(&nr_files);
+
+	return f;
+
+over:
+	/* Ran out of filps - report that */
+	if (get_nr_files() > old_max) {
+		pr_info("VFS: file-max limit %lu reached\n", get_max_files());
+		old_max = get_nr_files();
+	}
+	return ERR_PTR(-ENFILE);
+}
+
+/*
+ * Variant of alloc_empty_file() that doesn't check and modify nr_files.
+ *
+ * Should not be used unless there's a very good reason to do so.
+ */
+struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
+{
+	struct file *f = __alloc_file(flags, cred);
+
+	if (!IS_ERR(f))
+		f->f_mode |= FMODE_NOACCOUNT;
+
+	return f;
+}
+
+/**
+ * alloc_file - allocate and initialize a 'struct file'
+ *
+ * @path: the (dentry, vfsmount) pair for the new file
+ * @flags: O_... flags with which the new file will be opened
+ * @fop: the 'struct file_operations' for the new file
+ */
+static struct file *alloc_file(const struct path *path, int flags,
+		const struct file_operations *fop)
+{
+	struct file *file;
+
+	file = alloc_empty_file(flags, current_cred());
+	if (IS_ERR(file))
+		return file;
+
+	file->f_path = *path;
+	file->f_inode = path->dentry->d_inode;
+	file->f_mapping = path->dentry->d_inode->i_mapping;
+	file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
+	file->f_sb_err = file_sample_sb_err(file);
+	if (fop->llseek)
+		file->f_mode |= FMODE_LSEEK;
+	if ((file->f_mode & FMODE_READ) &&
+	     likely(fop->read || fop->read_iter))
+		file->f_mode |= FMODE_CAN_READ;
+	if ((file->f_mode & FMODE_WRITE) &&
+	     likely(fop->write || fop->write_iter))
+		file->f_mode |= FMODE_CAN_WRITE;
+	file->f_iocb_flags = iocb_flags(file);
+	file->f_mode |= FMODE_OPENED;
+	file->f_op = fop;
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+		i_readcount_inc(path->dentry->d_inode);
+	return file;
+}
+
+struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
+				const char *name, int flags,
+				const struct file_operations *fops)
+{
+	static const struct dentry_operations anon_ops = {
+		.d_dname = simple_dname
+	};
+	struct qstr this = QSTR_INIT(name, strlen(name));
+	struct path path;
+	struct file *file;
+
+	path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
+	if (!path.dentry)
+		return ERR_PTR(-ENOMEM);
+	if (!mnt->mnt_sb->s_d_op)
+		d_set_d_op(path.dentry, &anon_ops);
+	path.mnt = mntget(mnt);
+	d_instantiate(path.dentry, inode);
+	file = alloc_file(&path, flags, fops);
+	if (IS_ERR(file)) {
+		ihold(inode);
+		path_put(&path);
+	}
+	return file;
+}
+EXPORT_SYMBOL(alloc_file_pseudo);
+
+struct file *alloc_file_clone(struct file *base, int flags,
+				const struct file_operations *fops)
+{
+	struct file *f = alloc_file(&base->f_path, flags, fops);
+	if (!IS_ERR(f)) {
+		path_get(&f->f_path);
+		f->f_mapping = base->f_mapping;
+	}
+	return f;
+}
+
+/* the real guts of fput() - releasing the last reference to file
+ */
+static void __fput(struct file *file)
+{
+	struct dentry *dentry = file->f_path.dentry;
+	struct vfsmount *mnt = file->f_path.mnt;
+	struct inode *inode = file->f_inode;
+	fmode_t mode = file->f_mode;
+
+	if (unlikely(!(file->f_mode & FMODE_OPENED)))
+		goto out;
+
+	might_sleep();
+
+	fsnotify_close(file);
+	/*
+	 * The function eventpoll_release() should be the first called
+	 * in the file cleanup chain.
+	 */
+	eventpoll_release(file);
+	locks_remove_file(file);
+
+	ima_file_free(file);
+	if (unlikely(file->f_flags & FASYNC)) {
+		if (file->f_op->fasync)
+			file->f_op->fasync(-1, file, 0);
+	}
+	if (file->f_op->release)
+		file->f_op->release(inode, file);
+	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
+		     !(mode & FMODE_PATH))) {
+		cdev_put(inode->i_cdev);
+	}
+	fops_put(file->f_op);
+	put_pid(file->f_owner.pid);
+	put_file_access(file);
+	dput(dentry);
+	if (unlikely(mode & FMODE_NEED_UNMOUNT))
+		dissolve_on_fput(mnt);
+	mntput(mnt);
+out:
+	file_free(file);
+}
+
+static LLIST_HEAD(delayed_fput_list);
+static void delayed_fput(struct work_struct *unused)
+{
+	struct llist_node *node = llist_del_all(&delayed_fput_list);
+	struct file *f, *t;
+
+	llist_for_each_entry_safe(f, t, node, f_llist)
+		__fput(f);
+}
+
+static void ____fput(struct callback_head *work)
+{
+	__fput(container_of(work, struct file, f_rcuhead));
+}
+
+/*
+ * If kernel thread really needs to have the final fput() it has done
+ * to complete, call this.  The only user right now is the boot - we
+ * *do* need to make sure our writes to binaries on initramfs has
+ * not left us with opened struct file waiting for __fput() - execve()
+ * won't work without that.  Please, don't add more callers without
+ * very good reasons; in particular, never call that with locks
+ * held and never call that from a thread that might need to do
+ * some work on any kind of umount.
+ */
+void flush_delayed_fput(void)
+{
+	delayed_fput(NULL);
+}
+EXPORT_SYMBOL_GPL(flush_delayed_fput);
+
+static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
+
+void fput(struct file *file)
+{
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		struct task_struct *task = current;
+
+		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
+			init_task_work(&file->f_rcuhead, ____fput);
+			if (!task_work_add(task, &file->f_rcuhead, TWA_RESUME))
+				return;
+			/*
+			 * After this task has run exit_task_work(),
+			 * task_work_add() will fail.  Fall through to delayed
+			 * fput to avoid leaking *file.
+			 */
+		}
+
+		if (llist_add(&file->f_llist, &delayed_fput_list))
+			schedule_delayed_work(&delayed_fput_work, 1);
+	}
+}
+
+/*
+ * synchronous analog of fput(); for kernel threads that might be needed
+ * in some umount() (and thus can't use flush_delayed_fput() without
+ * risking deadlocks), need to wait for completion of __fput() and know
+ * for this specific struct file it won't involve anything that would
+ * need them.  Use only if you really need it - at the very least,
+ * don't blindly convert fput() by kernel thread to that.
+ */
+void __fput_sync(struct file *file)
+{
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		struct task_struct *task = current;
+		BUG_ON(!(task->flags & PF_KTHREAD));
+		__fput(file);
+	}
+}
+
+EXPORT_SYMBOL(fput);
+EXPORT_SYMBOL(__fput_sync);
+
+void __init files_init(void)
+{
+	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
+			SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL);
+	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
+}
+
+/*
+ * One file with associated inode and dcache is very roughly 1K. Per default
+ * do not use more than 10% of our memory for files.
+ */
+void __init files_maxfiles_init(void)
+{
+	unsigned long n;
+	unsigned long nr_pages = totalram_pages();
+	unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2;
+
+	memreserve = min(memreserve, nr_pages - 1);
+	n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
+
+	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
+}