Resguardo inicial

linux-7.2.3/fs/proc/Kconfig

@@ -0,0 +1,129 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config PROC_FS
+	bool "/proc file system support" if EXPERT
+	default y
+	help
+	  This is a virtual file system providing information about the status
+	  of the system. "Virtual" means that it doesn't take up any space on
+	  your hard disk: the files are created on the fly by the kernel when
+	  you try to access them. Also, you cannot read the files with older
+	  version of the program less: you need to use more or cat.
+
+	  It's totally cool; for example, "cat /proc/interrupts" gives
+	  information about what the different IRQs are used for at the moment
+	  (there is a small number of Interrupt ReQuest lines in your computer
+	  that are used by the attached devices to gain the CPU's attention --
+	  often a source of trouble if two devices are mistakenly configured
+	  to use the same IRQ). The program procinfo to display some
+	  information about your system gathered from the /proc file system.
+
+	  Before you can use the /proc file system, it has to be mounted,
+	  meaning it has to be given a location in the directory hierarchy.
+	  That location should be /proc. A command such as "mount -t proc proc
+	  /proc" or the equivalent line in /etc/fstab does the job.
+
+	  The /proc file system is explained in the file
+	  <file:Documentation/filesystems/proc.rst> and on the proc(5) manpage
+	  ("man 5 proc").
+
+	  This option will enlarge your kernel by about 67 KB. Several
+	  programs depend on this, so everyone should say Y here.
+
+config PROC_KCORE
+	bool "/proc/kcore support" if !ARM
+	depends on PROC_FS && MMU
+	select VMCORE_INFO
+	help
+	  Provides a virtual ELF core file of the live kernel.  This can
+	  be read with gdb and other ELF tools.  No modifications can be
+	  made using this mechanism.
+
+config PROC_VMCORE
+	bool "/proc/vmcore support"
+	depends on PROC_FS && CRASH_DUMP
+	default y
+	help
+	  Exports the dump image of crashed kernel in ELF format.
+
+config PROC_VMCORE_DEVICE_DUMP
+	bool "Device Hardware/Firmware Log Collection"
+	depends on PROC_VMCORE
+	default n
+	help
+	  After kernel panic, device drivers can collect the device
+	  specific snapshot of their hardware or firmware before the
+	  underlying devices are initialized in crash recovery kernel.
+	  Note that the device driver must be present in the crash
+	  recovery kernel's initramfs to collect its underlying device
+	  snapshot.
+
+	  If you say Y here, the collected device dumps will be added
+	  as ELF notes to /proc/vmcore. You can still disable device
+	  dump using the kernel command line option 'novmcoredd'.
+
+config NEED_PROC_VMCORE_DEVICE_RAM
+	bool
+
+config PROC_VMCORE_DEVICE_RAM
+	def_bool y
+	depends on PROC_VMCORE && NEED_PROC_VMCORE_DEVICE_RAM
+	depends on VIRTIO_MEM
+	help
+	  If the elfcore hdr is allocated and prepared by the dump kernel
+	  ("2nd kernel") instead of the crashed kernel, RAM provided by memory
+	  devices such as virtio-mem will not be included in the dump
+	  image, because only the device driver can properly detect them.
+
+	  With this config enabled, these RAM ranges will be queried from the
+	  device drivers once the device gets probed, so they can be included
+	  in the crash dump.
+
+	  Relevant architectures should select NEED_PROC_VMCORE_DEVICE_RAM.
+
+config PROC_SYSCTL
+	bool "Sysctl support (/proc/sys)" if EXPERT
+	depends on PROC_FS
+	select SYSCTL
+	default y
+	help
+	  The sysctl interface provides a means of dynamically changing
+	  certain kernel parameters and variables on the fly without requiring
+	  a recompile of the kernel or reboot of the system.  The primary
+	  interface is through /proc/sys.  If you say Y here a tree of
+	  modifiable sysctl entries will be generated beneath the
+	  /proc/sys directory. They are explained in the files
+	  in <file:Documentation/admin-guide/sysctl/>.  Note that enabling this
+	  option will enlarge the kernel by at least 8 KB.
+
+	  As it is generally a good thing, you should say Y here unless
+	  building a kernel for install/rescue disks or your system is very
+	  limited in memory.
+
+config PROC_PAGE_MONITOR
+ 	default y
+	depends on PROC_FS && MMU
+	bool "Enable /proc page monitoring" if EXPERT
+ 	help
+	  Various /proc files exist to monitor process memory utilization:
+	  /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
+	  /proc/kpagecount, and /proc/kpageflags. Disabling these
+	  interfaces will reduce the size of the kernel by approximately 4kb.
+
+config PROC_CHILDREN
+	bool "Include /proc/<pid>/task/<tid>/children file"
+	depends on PROC_FS
+	default n
+	help
+	  Provides a fast way to retrieve first level children pids of a task. See
+	  <file:Documentation/filesystems/proc.rst> for more information.
+
+	  Say Y if you are running any user-space software which takes benefit from
+	  this interface. For example, rkt is such a piece of software.
+
+config PROC_PID_ARCH_STATUS
+	def_bool n
+	depends on PROC_FS
+
+config PROC_CPU_RESCTRL
+	def_bool n
+	depends on PROC_FS

linux-7.2.3/fs/proc/Makefile

@@ -0,0 +1,38 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the Linux proc filesystem routines.
+#
+
+obj-y   += proc.o
+
+CFLAGS_task_mmu.o	+= -Wno-override-init
+proc-y			:= nommu.o task_nommu.o
+proc-$(CONFIG_MMU)	:= task_mmu.o
+
+proc-y       += inode.o root.o base.o generic.o array.o \
+		fd.o
+proc-$(CONFIG_TTY)      += proc_tty.o
+proc-y	+= cmdline.o
+proc-y	+= consoles.o
+proc-y	+= cpuinfo.o
+proc-y	+= devices.o
+ifneq ($(CONFIG_GENERIC_IRQ_SHOW),y)
+proc-y += interrupts.o
+endif
+proc-y	+= loadavg.o
+proc-y	+= meminfo.o
+proc-y	+= stat.o
+proc-y	+= uptime.o
+proc-y	+= util.o
+proc-y	+= version.o
+proc-y	+= softirqs.o
+proc-y	+= namespaces.o
+proc-y	+= self.o
+proc-y	+= thread_self.o
+proc-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
+proc-$(CONFIG_NET)		+= proc_net.o
+proc-$(CONFIG_PROC_KCORE)	+= kcore.o
+proc-$(CONFIG_PROC_VMCORE)	+= vmcore.o
+proc-$(CONFIG_PRINTK)	+= kmsg.o
+proc-$(CONFIG_PROC_PAGE_MONITOR)	+= page.o
+proc-$(CONFIG_BOOT_CONFIG)	+= bootconfig.o

linux-7.2.3/fs/proc/array.c

@@ -0,0 +1,822 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/proc/array.c
+ *
+ *  Copyright (C) 1992  by Linus Torvalds
+ *  based on ideas by Darren Senn
+ *
+ * Fixes:
+ * Michael. K. Johnson: stat,statm extensions.
+ *                      <johnsonm@stolaf.edu>
+ *
+ * Pauline Middelink :  Made cmdline,envline only break at '\0's, to
+ *                      make sure SET_PROCTITLE works. Also removed
+ *                      bad '!' which forced address recalculation for
+ *                      EVERY character on the current page.
+ *                      <middelin@polyware.iaf.nl>
+ *
+ * Danny ter Haar    :	added cpuinfo
+ *			<dth@cistron.nl>
+ *
+ * Alessandro Rubini :  profile extension.
+ *                      <rubini@ipvvis.unipv.it>
+ *
+ * Jeff Tranter      :  added BogoMips field to cpuinfo
+ *                      <Jeff_Tranter@Mitel.COM>
+ *
+ * Bruno Haible      :  remove 4K limit for the maps file
+ *			<haible@ma2s2.mathematik.uni-karlsruhe.de>
+ *
+ * Yves Arrouye      :  remove removal of trailing spaces in get_array.
+ *			<Yves.Arrouye@marin.fdn.fr>
+ *
+ * Jerome Forissier  :  added per-CPU time information to /proc/stat
+ *                      and /proc/<pid>/cpu extension
+ *                      <forissier@isia.cma.fr>
+ *			- Incorporation and non-SMP safe operation
+ *			of forissier patch in 2.1.78 by
+ *			Hans Marcus <crowbar@concepts.nl>
+ *
+ * aeb@cwi.nl        :  /proc/partitions
+ *
+ *
+ * Alan Cox	     :  security fixes.
+ *			<alan@lxorguk.ukuu.org.uk>
+ *
+ * Al Viro           :  safe handling of mm_struct
+ *
+ * Gerhard Wichert   :  added BIGMEM support
+ * Siemens AG           <Gerhard.Wichert@pdb.siemens.de>
+ *
+ * Al Viro & Jeff Garzik :  moved most of the thing into base.c and
+ *			 :  proc_misc.c. The rest may eventually go into
+ *			 :  base.c too.
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/hex.h>
+#include <linux/time.h>
+#include <linux/time_namespace.h>
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/tty.h>
+#include <linux/string.h>
+#include <linux/mman.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/numa_balancing.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/task.h>
+#include <linux/sched/cputime.h>
+#include <linux/proc_fs.h>
+#include <linux/ioport.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/signal.h>
+#include <linux/highmem.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/times.h>
+#include <linux/cpuset.h>
+#include <linux/rcupdate.h>
+#include <linux/delayacct.h>
+#include <linux/seq_file.h>
+#include <linux/pid_namespace.h>
+#include <linux/prctl.h>
+#include <linux/ptrace.h>
+#include <linux/string_helpers.h>
+#include <linux/user_namespace.h>
+#include <linux/fs_struct.h>
+#include <linux/kthread.h>
+#include <linux/mmu_context.h>
+
+#include <asm/processor.h>
+#include "internal.h"
+
+void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape)
+{
+	char tcomm[64];
+
+	/*
+	 * Test before PF_KTHREAD because all workqueue worker threads are
+	 * kernel threads.
+	 */
+	if (p->flags & PF_WQ_WORKER)
+		wq_worker_comm(tcomm, sizeof(tcomm), p);
+	else if (p->flags & PF_KTHREAD)
+		get_kthread_comm(tcomm, sizeof(tcomm), p);
+	else
+		get_task_comm(tcomm, p);
+
+	if (escape)
+		seq_escape_str(m, tcomm, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+	else
+		seq_printf(m, "%.64s", tcomm);
+}
+
+/*
+ * The task state array is a strange "bitmap" of
+ * reasons to sleep. Thus "running" is zero, and
+ * you can test for combinations of others with
+ * simple bit tests.
+ */
+static const char * const task_state_array[] = {
+
+	/* states in TASK_REPORT: */
+	"R (running)",		/* 0x00 */
+	"S (sleeping)",		/* 0x01 */
+	"D (disk sleep)",	/* 0x02 */
+	"T (stopped)",		/* 0x04 */
+	"t (tracing stop)",	/* 0x08 */
+	"X (dead)",		/* 0x10 */
+	"Z (zombie)",		/* 0x20 */
+	"P (parked)",		/* 0x40 */
+
+	/* states beyond TASK_REPORT: */
+	"I (idle)",		/* 0x80 */
+};
+
+static inline const char *get_task_state(struct task_struct *tsk)
+{
+	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array));
+	return task_state_array[task_state_index(tsk)];
+}
+
+static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *p)
+{
+	struct user_namespace *user_ns = seq_user_ns(m);
+	struct group_info *group_info;
+	int g, umask = -1;
+	struct task_struct *tracer;
+	const struct cred *cred;
+	pid_t ppid, tpid = 0, tgid, ngid;
+	unsigned int max_fds = 0;
+
+	rcu_read_lock();
+	tracer = ptrace_parent(p);
+	if (tracer)
+		tpid = task_pid_nr_ns(tracer, ns);
+
+	ppid = task_ppid_nr_ns(p, ns);
+	tgid = task_tgid_nr_ns(p, ns);
+	ngid = task_numa_group_id(p);
+	cred = get_task_cred(p);
+
+	task_lock(p);
+	if (p->fs)
+		umask = p->fs->umask;
+	if (p->files)
+		max_fds = files_fdtable(p->files)->max_fds;
+	task_unlock(p);
+	rcu_read_unlock();
+
+	if (umask >= 0)
+		seq_printf(m, "Umask:\t%#04o\n", umask);
+	seq_puts(m, "State:\t");
+	seq_puts(m, get_task_state(p));
+
+	seq_put_decimal_ull(m, "\nTgid:\t", tgid);
+	seq_put_decimal_ull(m, "\nNgid:\t", ngid);
+	seq_put_decimal_ull(m, "\nPid:\t", pid_nr_ns(pid, ns));
+	seq_put_decimal_ull(m, "\nPPid:\t", ppid);
+	seq_put_decimal_ull(m, "\nTracerPid:\t", tpid);
+	seq_put_decimal_ull(m, "\nUid:\t", from_kuid_munged(user_ns, cred->uid));
+	seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->euid));
+	seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->suid));
+	seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->fsuid));
+	seq_put_decimal_ull(m, "\nGid:\t", from_kgid_munged(user_ns, cred->gid));
+	seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->egid));
+	seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->sgid));
+	seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->fsgid));
+	seq_put_decimal_ull(m, "\nFDSize:\t", max_fds);
+
+	seq_puts(m, "\nGroups:\t");
+	group_info = cred->group_info;
+	for (g = 0; g < group_info->ngroups; g++)
+		seq_put_decimal_ull(m, g ? " " : "",
+				from_kgid_munged(user_ns, group_info->gid[g]));
+	put_cred(cred);
+	/* Trailing space shouldn't have been added in the first place. */
+	seq_putc(m, ' ');
+
+#ifdef CONFIG_PID_NS
+	seq_puts(m, "\nNStgid:");
+	for (g = ns->level; g <= pid->level; g++)
+		seq_put_decimal_ull(m, "\t", task_tgid_nr_ns(p, pid->numbers[g].ns));
+	seq_puts(m, "\nNSpid:");
+	for (g = ns->level; g <= pid->level; g++)
+		seq_put_decimal_ull(m, "\t", task_pid_nr_ns(p, pid->numbers[g].ns));
+	seq_puts(m, "\nNSpgid:");
+	for (g = ns->level; g <= pid->level; g++)
+		seq_put_decimal_ull(m, "\t", task_pgrp_nr_ns(p, pid->numbers[g].ns));
+	seq_puts(m, "\nNSsid:");
+	for (g = ns->level; g <= pid->level; g++)
+		seq_put_decimal_ull(m, "\t", task_session_nr_ns(p, pid->numbers[g].ns));
+#endif
+	seq_putc(m, '\n');
+
+	seq_printf(m, "Kthread:\t%c\n", p->flags & PF_KTHREAD ? '1' : '0');
+}
+
+void render_sigset_t(struct seq_file *m, const char *header,
+				sigset_t *set)
+{
+	int i;
+
+	seq_puts(m, header);
+
+	i = _NSIG;
+	do {
+		int x = 0;
+
+		i -= 4;
+		if (sigismember(set, i+1)) x |= 1;
+		if (sigismember(set, i+2)) x |= 2;
+		if (sigismember(set, i+3)) x |= 4;
+		if (sigismember(set, i+4)) x |= 8;
+		seq_putc(m, hex_asc[x]);
+	} while (i >= 4);
+
+	seq_putc(m, '\n');
+}
+
+static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *sigign,
+				    sigset_t *sigcatch)
+{
+	struct k_sigaction *k;
+	int i;
+
+	k = p->sighand->action;
+	for (i = 1; i <= _NSIG; ++i, ++k) {
+		if (k->sa.sa_handler == SIG_IGN)
+			sigaddset(sigign, i);
+		else if (k->sa.sa_handler != SIG_DFL)
+			sigaddset(sigcatch, i);
+	}
+}
+
+static inline void task_sig(struct seq_file *m, struct task_struct *p)
+{
+	unsigned long flags;
+	sigset_t pending, shpending, blocked, ignored, caught;
+	int num_threads = 0;
+	unsigned int qsize = 0;
+	unsigned long qlim = 0;
+
+	sigemptyset(&pending);
+	sigemptyset(&shpending);
+	sigemptyset(&blocked);
+	sigemptyset(&ignored);
+	sigemptyset(&caught);
+
+	if (lock_task_sighand(p, &flags)) {
+		pending = p->pending.signal;
+		shpending = p->signal->shared_pending.signal;
+		blocked = p->blocked;
+		collect_sigign_sigcatch(p, &ignored, &caught);
+		num_threads = get_nr_threads(p);
+		rcu_read_lock();
+		qsize = get_rlimit_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING);
+		rcu_read_unlock();
+		qlim = task_rlimit(p, RLIMIT_SIGPENDING);
+		unlock_task_sighand(p, &flags);
+	}
+
+	seq_put_decimal_ull(m, "Threads:\t", num_threads);
+	seq_put_decimal_ull(m, "\nSigQ:\t", qsize);
+	seq_put_decimal_ull(m, "/", qlim);
+
+	/* render them all */
+	render_sigset_t(m, "\nSigPnd:\t", &pending);
+	render_sigset_t(m, "ShdPnd:\t", &shpending);
+	render_sigset_t(m, "SigBlk:\t", &blocked);
+	render_sigset_t(m, "SigIgn:\t", &ignored);
+	render_sigset_t(m, "SigCgt:\t", &caught);
+}
+
+static void render_cap_t(struct seq_file *m, const char *header,
+			kernel_cap_t *a)
+{
+	seq_puts(m, header);
+	seq_put_hex_ll(m, NULL, a->val, 16);
+	seq_putc(m, '\n');
+}
+
+static inline void task_cap(struct seq_file *m, struct task_struct *p)
+{
+	const struct cred *cred;
+	kernel_cap_t cap_inheritable, cap_permitted, cap_effective,
+			cap_bset, cap_ambient;
+
+	rcu_read_lock();
+	cred = __task_cred(p);
+	cap_inheritable	= cred->cap_inheritable;
+	cap_permitted	= cred->cap_permitted;
+	cap_effective	= cred->cap_effective;
+	cap_bset	= cred->cap_bset;
+	cap_ambient	= cred->cap_ambient;
+	rcu_read_unlock();
+
+	render_cap_t(m, "CapInh:\t", &cap_inheritable);
+	render_cap_t(m, "CapPrm:\t", &cap_permitted);
+	render_cap_t(m, "CapEff:\t", &cap_effective);
+	render_cap_t(m, "CapBnd:\t", &cap_bset);
+	render_cap_t(m, "CapAmb:\t", &cap_ambient);
+}
+
+static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
+{
+	seq_put_decimal_ull(m, "NoNewPrivs:\t", task_no_new_privs(p));
+#ifdef CONFIG_SECCOMP
+	seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode);
+#ifdef CONFIG_SECCOMP_FILTER
+	seq_put_decimal_ull(m, "\nSeccomp_filters:\t",
+			    atomic_read(&p->seccomp.filter_count));
+#endif
+#endif
+	seq_puts(m, "\nSpeculation_Store_Bypass:\t");
+	switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
+	case -EINVAL:
+		seq_puts(m, "unknown");
+		break;
+	case PR_SPEC_NOT_AFFECTED:
+		seq_puts(m, "not vulnerable");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE:
+		seq_puts(m, "thread force mitigated");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_DISABLE:
+		seq_puts(m, "thread mitigated");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_ENABLE:
+		seq_puts(m, "thread vulnerable");
+		break;
+	case PR_SPEC_DISABLE:
+		seq_puts(m, "globally mitigated");
+		break;
+	default:
+		seq_puts(m, "vulnerable");
+		break;
+	}
+
+	seq_puts(m, "\nSpeculationIndirectBranch:\t");
+	switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_INDIRECT_BRANCH)) {
+	case -EINVAL:
+		seq_puts(m, "unsupported");
+		break;
+	case PR_SPEC_NOT_AFFECTED:
+		seq_puts(m, "not affected");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE:
+		seq_puts(m, "conditional force disabled");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_DISABLE:
+		seq_puts(m, "conditional disabled");
+		break;
+	case PR_SPEC_PRCTL | PR_SPEC_ENABLE:
+		seq_puts(m, "conditional enabled");
+		break;
+	case PR_SPEC_ENABLE:
+		seq_puts(m, "always enabled");
+		break;
+	case PR_SPEC_DISABLE:
+		seq_puts(m, "always disabled");
+		break;
+	default:
+		seq_puts(m, "unknown");
+		break;
+	}
+	seq_putc(m, '\n');
+}
+
+static inline void task_context_switch_counts(struct seq_file *m,
+						struct task_struct *p)
+{
+	seq_put_decimal_ull(m, "voluntary_ctxt_switches:\t", p->nvcsw);
+	seq_put_decimal_ull(m, "\nnonvoluntary_ctxt_switches:\t", p->nivcsw);
+	seq_putc(m, '\n');
+}
+
+static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
+{
+	seq_printf(m, "Cpus_allowed:\t%*pb\n",
+		   cpumask_pr_args(&task->cpus_mask));
+	seq_printf(m, "Cpus_allowed_list:\t%*pbl\n",
+		   cpumask_pr_args(&task->cpus_mask));
+}
+
+static inline void task_core_dumping(struct seq_file *m, struct task_struct *task)
+{
+	seq_put_decimal_ull(m, "CoreDumping:\t", !!task->signal->core_state);
+	seq_putc(m, '\n');
+}
+
+static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
+{
+	bool thp_enabled = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE);
+
+	if (thp_enabled)
+		thp_enabled = !mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm);
+	seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
+}
+
+static inline void task_untag_mask(struct seq_file *m, struct mm_struct *mm)
+{
+	seq_printf(m, "untag_mask:\t%#lx\n", mm_untag_mask(mm));
+}
+
+__weak void arch_proc_pid_thread_features(struct seq_file *m,
+					  struct task_struct *task)
+{
+}
+
+int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
+{
+	struct mm_struct *mm = get_task_mm(task);
+
+	seq_puts(m, "Name:\t");
+	proc_task_name(m, task, true);
+	seq_putc(m, '\n');
+
+	task_state(m, ns, pid, task);
+
+	if (mm) {
+		task_mem(m, mm);
+		task_core_dumping(m, task);
+		task_thp_status(m, mm);
+		task_untag_mask(m, mm);
+		mmput(mm);
+	}
+	task_sig(m, task);
+	task_cap(m, task);
+	task_seccomp(m, task);
+	task_cpus_allowed(m, task);
+	cpuset_task_status_allowed(m, task);
+	task_context_switch_counts(m, task);
+	arch_proc_pid_thread_features(m, task);
+	return 0;
+}
+
+static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task, int whole)
+{
+	unsigned long vsize, eip, esp, wchan = 0;
+	int priority, nice;
+	int tty_pgrp = -1, tty_nr = 0;
+	sigset_t sigign, sigcatch;
+	char state;
+	pid_t ppid = 0, pgid = -1, sid = -1;
+	int num_threads = 0;
+	int permitted;
+	struct mm_struct *mm;
+	unsigned long long start_time;
+	unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt;
+	u64 cutime, cstime, cgtime, utime, stime, gtime;
+	unsigned long rsslim = 0;
+	unsigned long flags;
+	int exit_code = task->exit_code;
+	struct signal_struct *sig = task->signal;
+	int ret;
+
+	ret = down_read_killable(&task->signal->exec_update_lock);
+	if (ret)
+		return ret;
+
+	state = *get_task_state(task);
+	vsize = eip = esp = 0;
+	permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT);
+	mm = get_task_mm(task);
+	if (mm) {
+		vsize = task_vsize(mm);
+		/*
+		 * esp and eip are intentionally zeroed out.  There is no
+		 * non-racy way to read them without freezing the task.
+		 * Programs that need reliable values can use ptrace(2).
+		 *
+		 * The only exception is if the task is core dumping because
+		 * a program is not able to use ptrace(2) in that case. It is
+		 * safe because the task has stopped executing permanently.
+		 */
+		if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE|PF_POSTCOREDUMP))) {
+			if (try_get_task_stack(task)) {
+				eip = KSTK_EIP(task);
+				esp = KSTK_ESP(task);
+				put_task_stack(task);
+			}
+		}
+	}
+
+	sigemptyset(&sigign);
+	sigemptyset(&sigcatch);
+
+	if (lock_task_sighand(task, &flags)) {
+		if (sig->tty) {
+			struct pid *pgrp = tty_get_pgrp(sig->tty);
+			tty_pgrp = pid_nr_ns(pgrp, ns);
+			put_pid(pgrp);
+			tty_nr = new_encode_dev(tty_devnum(sig->tty));
+		}
+
+		num_threads = get_nr_threads(task);
+		collect_sigign_sigcatch(task, &sigign, &sigcatch);
+
+		rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
+
+		if (whole) {
+			if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
+				exit_code = sig->group_exit_code;
+		}
+
+		sid = task_session_nr_ns(task, ns);
+		ppid = task_ppid_nr_ns(task, ns);
+		pgid = task_pgrp_nr_ns(task, ns);
+
+		unlock_task_sighand(task, &flags);
+	}
+
+	if (permitted && (!whole || num_threads < 2))
+		wchan = !task_is_running(task);
+
+	scoped_guard(rcu) {
+		scoped_seqlock_read (&sig->stats_lock, ss_lock_irqsave) {
+			cmin_flt = sig->cmin_flt;
+			cmaj_flt = sig->cmaj_flt;
+			cutime = sig->cutime;
+			cstime = sig->cstime;
+			cgtime = sig->cgtime;
+
+			if (whole) {
+				struct task_struct *t;
+
+				min_flt = sig->min_flt;
+				maj_flt = sig->maj_flt;
+				gtime = sig->gtime;
+
+				__for_each_thread(sig, t) {
+					min_flt += t->min_flt;
+					maj_flt += t->maj_flt;
+					gtime += task_gtime(t);
+				}
+			}
+		}
+	}
+
+	if (whole) {
+		thread_group_cputime_adjusted(task, &utime, &stime);
+	} else {
+		task_cputime_adjusted(task, &utime, &stime);
+		min_flt = task->min_flt;
+		maj_flt = task->maj_flt;
+		gtime = task_gtime(task);
+	}
+
+	/* scale priority and nice values from timeslices to -20..20 */
+	/* to make it look like a "normal" Unix priority/nice value  */
+	priority = task_prio(task);
+	nice = task_nice(task);
+
+	/* apply timens offset for boottime and convert nsec -> ticks */
+	start_time =
+		nsec_to_clock_t(timens_add_boottime_ns(task->start_boottime));
+
+	seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns));
+	seq_puts(m, " (");
+	proc_task_name(m, task, false);
+	seq_puts(m, ") ");
+	seq_putc(m, state);
+	seq_put_decimal_ll(m, " ", ppid);
+	seq_put_decimal_ll(m, " ", pgid);
+	seq_put_decimal_ll(m, " ", sid);
+	seq_put_decimal_ll(m, " ", tty_nr);
+	seq_put_decimal_ll(m, " ", tty_pgrp);
+	seq_put_decimal_ull(m, " ", task->flags);
+	seq_put_decimal_ull(m, " ", min_flt);
+	seq_put_decimal_ull(m, " ", cmin_flt);
+	seq_put_decimal_ull(m, " ", maj_flt);
+	seq_put_decimal_ull(m, " ", cmaj_flt);
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(utime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(stime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cutime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cstime));
+	seq_put_decimal_ll(m, " ", priority);
+	seq_put_decimal_ll(m, " ", nice);
+	seq_put_decimal_ll(m, " ", num_threads);
+	seq_put_decimal_ull(m, " ", 0);
+	seq_put_decimal_ull(m, " ", start_time);
+	seq_put_decimal_ull(m, " ", vsize);
+	seq_put_decimal_ull(m, " ", mm ? get_mm_rss(mm) : 0);
+	seq_put_decimal_ull(m, " ", rsslim);
+	seq_put_decimal_ull(m, " ", mm ? (permitted ? mm->start_code : 1) : 0);
+	seq_put_decimal_ull(m, " ", mm ? (permitted ? mm->end_code : 1) : 0);
+	seq_put_decimal_ull(m, " ", (permitted && mm) ? mm->start_stack : 0);
+	seq_put_decimal_ull(m, " ", esp);
+	seq_put_decimal_ull(m, " ", eip);
+	/* The signal information here is obsolete.
+	 * It must be decimal for Linux 2.0 compatibility.
+	 * Use /proc/#/status for real-time signals.
+	 */
+	seq_put_decimal_ull(m, " ", task->pending.signal.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, " ", task->blocked.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, " ", sigign.sig[0] & 0x7fffffffUL);
+	seq_put_decimal_ull(m, " ", sigcatch.sig[0] & 0x7fffffffUL);
+
+	/*
+	 * We used to output the absolute kernel address, but that's an
+	 * information leak - so instead we show a 0/1 flag here, to signal
+	 * to user-space whether there's a wchan field in /proc/PID/wchan.
+	 *
+	 * This works with older implementations of procps as well.
+	 */
+	seq_put_decimal_ull(m, " ", wchan);
+
+	seq_put_decimal_ull(m, " ", 0);
+	seq_put_decimal_ull(m, " ", 0);
+	seq_put_decimal_ll(m, " ", task->exit_signal);
+	seq_put_decimal_ll(m, " ", task_cpu(task));
+	seq_put_decimal_ull(m, " ", task->rt_priority);
+	seq_put_decimal_ull(m, " ", task->policy);
+	seq_put_decimal_ull(m, " ", delayacct_blkio_ticks(task));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(gtime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cgtime));
+
+	if (mm && permitted) {
+		seq_put_decimal_ull(m, " ", mm->start_data);
+		seq_put_decimal_ull(m, " ", mm->end_data);
+		seq_put_decimal_ull(m, " ", mm->start_brk);
+		seq_put_decimal_ull(m, " ", mm->arg_start);
+		seq_put_decimal_ull(m, " ", mm->arg_end);
+		seq_put_decimal_ull(m, " ", mm->env_start);
+		seq_put_decimal_ull(m, " ", mm->env_end);
+	} else
+		seq_puts(m, " 0 0 0 0 0 0 0");
+
+	if (permitted)
+		seq_put_decimal_ll(m, " ", exit_code);
+	else
+		seq_puts(m, " 0");
+
+	seq_putc(m, '\n');
+	up_read(&task->signal->exec_update_lock);
+	if (mm)
+		mmput(mm);
+	return 0;
+}
+
+int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
+{
+	return do_task_stat(m, ns, pid, task, 0);
+}
+
+int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
+{
+	return do_task_stat(m, ns, pid, task, 1);
+}
+
+int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
+{
+	struct mm_struct *mm = get_task_mm(task);
+
+	if (mm) {
+		unsigned long size;
+		unsigned long resident = 0;
+		unsigned long shared = 0;
+		unsigned long text = 0;
+		unsigned long data = 0;
+
+		size = task_statm(mm, &shared, &text, &data, &resident);
+		mmput(mm);
+
+		/*
+		 * For quick read, open code by putting numbers directly
+		 * expected format is
+		 * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n",
+		 *               size, resident, shared, text, data);
+		 */
+		seq_put_decimal_ull(m, "", size);
+		seq_put_decimal_ull(m, " ", resident);
+		seq_put_decimal_ull(m, " ", shared);
+		seq_put_decimal_ull(m, " ", text);
+		seq_put_decimal_ull(m, " ", 0);
+		seq_put_decimal_ull(m, " ", data);
+		seq_put_decimal_ull(m, " ", 0);
+		seq_putc(m, '\n');
+	} else {
+		seq_write(m, "0 0 0 0 0 0 0\n", 14);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_PROC_CHILDREN
+static struct pid *
+get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
+{
+	struct task_struct *start, *task;
+	struct pid *pid = NULL;
+
+	read_lock(&tasklist_lock);
+
+	start = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (!start)
+		goto out;
+
+	/*
+	 * Lets try to continue searching first, this gives
+	 * us significant speedup on children-rich processes.
+	 */
+	if (pid_prev) {
+		task = pid_task(pid_prev, PIDTYPE_PID);
+		if (task && task->real_parent == start &&
+		    !(list_empty(&task->sibling))) {
+			if (list_is_last(&task->sibling, &start->children))
+				goto out;
+			task = list_first_entry(&task->sibling,
+						struct task_struct, sibling);
+			pid = get_pid(task_pid(task));
+			goto out;
+		}
+	}
+
+	/*
+	 * Slow search case.
+	 *
+	 * We might miss some children here if children
+	 * are exited while we were not holding the lock,
+	 * but it was never promised to be accurate that
+	 * much.
+	 *
+	 * "Just suppose that the parent sleeps, but N children
+	 *  exit after we printed their tids. Now the slow paths
+	 *  skips N extra children, we miss N tasks." (c)
+	 *
+	 * So one need to stop or freeze the leader and all
+	 * its children to get a precise result.
+	 */
+	list_for_each_entry(task, &start->children, sibling) {
+		if (pos-- == 0) {
+			pid = get_pid(task_pid(task));
+			break;
+		}
+	}
+
+out:
+	read_unlock(&tasklist_lock);
+	return pid;
+}
+
+static int children_seq_show(struct seq_file *seq, void *v)
+{
+	struct inode *inode = file_inode(seq->file);
+
+	seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode->i_sb)));
+	return 0;
+}
+
+static void *children_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return get_children_pid(file_inode(seq->file), NULL, *pos);
+}
+
+static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct pid *pid;
+
+	pid = get_children_pid(file_inode(seq->file), v, *pos + 1);
+	put_pid(v);
+
+	++*pos;
+	return pid;
+}
+
+static void children_seq_stop(struct seq_file *seq, void *v)
+{
+	put_pid(v);
+}
+
+static const struct seq_operations children_seq_ops = {
+	.start	= children_seq_start,
+	.next	= children_seq_next,
+	.stop	= children_seq_stop,
+	.show	= children_seq_show,
+};
+
+static int children_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &children_seq_ops);
+}
+
+const struct file_operations proc_tid_children_operations = {
+	.open    = children_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+#endif /* CONFIG_PROC_CHILDREN */

linux-7.2.3/fs/proc/bootconfig.c

@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * /proc/bootconfig - Extra boot configuration
+ */
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/printk.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/bootconfig.h>
+#include <linux/slab.h>
+
+static char *saved_boot_config;
+
+static int boot_config_proc_show(struct seq_file *m, void *v)
+{
+	if (saved_boot_config)
+		seq_puts(m, saved_boot_config);
+	return 0;
+}
+
+/* Rest size of buffer */
+#define rest(dst, end) ((end) > (dst) ? (end) - (dst) : 0)
+
+/* Return the needed total length if @size is 0 */
+static int __init copy_xbc_key_value_list(char *dst, size_t size)
+{
+	struct xbc_node *leaf, *vnode;
+	char *key, *end = dst + size;
+	const char *val;
+	char q;
+	int ret = 0;
+
+	key = kzalloc(XBC_KEYLEN_MAX, GFP_KERNEL);
+	if (!key)
+		return -ENOMEM;
+
+	xbc_for_each_key_value(leaf, val) {
+		ret = xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX);
+		if (ret < 0)
+			break;
+		ret = snprintf(dst, rest(dst, end), "%s = ", key);
+		if (ret < 0)
+			break;
+		dst += ret;
+		vnode = xbc_node_get_child(leaf);
+		if (vnode) {
+			xbc_array_for_each_value(vnode, val) {
+				if (strchr(val, '"'))
+					q = '\'';
+				else
+					q = '"';
+				ret = snprintf(dst, rest(dst, end), "%c%s%c%s",
+					q, val, q, xbc_node_is_array(vnode) ? ", " : "\n");
+				if (ret < 0)
+					goto out;
+				dst += ret;
+			}
+		} else {
+			ret = snprintf(dst, rest(dst, end), "\"\"\n");
+			if (ret < 0)
+				break;
+			dst += ret;
+		}
+	}
+	if (cmdline_has_extra_options() && ret >= 0 && boot_command_line[0]) {
+		ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n",
+			       boot_command_line);
+		if (ret > 0)
+			dst += ret;
+	}
+out:
+	kfree(key);
+
+	return ret < 0 ? ret : dst - (end - size);
+}
+
+static int __init proc_boot_config_init(void)
+{
+	int len;
+
+	len = copy_xbc_key_value_list(NULL, 0);
+	if (len < 0)
+		return len;
+
+	if (len > 0) {
+		saved_boot_config = kzalloc(len + 1, GFP_KERNEL);
+		if (!saved_boot_config)
+			return -ENOMEM;
+
+		len = copy_xbc_key_value_list(saved_boot_config, len + 1);
+		if (len < 0) {
+			kfree(saved_boot_config);
+			return len;
+		}
+	}
+
+	proc_create_single("bootconfig", 0, NULL, boot_config_proc_show);
+
+	return 0;
+}
+fs_initcall(proc_boot_config_init);

linux-7.2.3/fs/proc/cmdline.c

@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+static int cmdline_proc_show(struct seq_file *m, void *v)
+{
+	seq_puts(m, saved_command_line);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static int __init proc_cmdline_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = proc_create_single("cmdline", 0, NULL, cmdline_proc_show);
+	pde_make_permanent(pde);
+	pde->size = saved_command_line_len + 1;
+	return 0;
+}
+fs_initcall(proc_cmdline_init);

linux-7.2.3/fs/proc/consoles.c

@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2010 Werner Fink, Jiri Slaby
+ */
+
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/tty_driver.h>
+
+/*
+ * This is handler for /proc/consoles
+ */
+static int show_console_dev(struct seq_file *m, void *v)
+{
+	static const struct {
+		short flag;
+		char name;
+	} con_flags[] = {
+		{ CON_ENABLED,		'E' },
+		{ CON_CONSDEV,		'C' },
+		{ CON_BOOT,		'B' },
+		{ CON_NBCON,		'N' },
+		{ CON_PRINTBUFFER,	'p' },
+		{ CON_BRL,		'b' },
+		{ CON_ANYTIME,		'a' },
+	};
+	char flags[ARRAY_SIZE(con_flags) + 1];
+	struct console *con = v;
+	unsigned int a;
+	dev_t dev = 0;
+
+	if (con->device) {
+		const struct tty_driver *driver;
+		int index;
+
+		/*
+		 * Take console_lock to serialize device() callback with
+		 * other console operations. For example, fg_console is
+		 * modified under console_lock when switching vt.
+		 */
+		console_lock();
+		driver = con->device(con, &index);
+		console_unlock();
+
+		if (driver) {
+			dev = MKDEV(driver->major, driver->minor_start);
+			dev += index;
+		}
+	}
+
+	for (a = 0; a < ARRAY_SIZE(con_flags); a++)
+		flags[a] = (con->flags & con_flags[a].flag) ?
+			con_flags[a].name : ' ';
+	flags[a] = 0;
+
+	seq_setwidth(m, 21 - 1);
+	seq_printf(m, "%s%d", con->name, con->index);
+	seq_pad(m, ' ');
+	seq_printf(m, "%c%c%c (%s)", con->read ? 'R' : '-',
+		   ((con->flags & CON_NBCON) || con->write) ? 'W' : '-',
+		   con->unblank ? 'U' : '-', flags);
+	if (dev)
+		seq_printf(m, " %4d:%d", MAJOR(dev), MINOR(dev));
+
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+	__acquires(&console_mutex)
+{
+	struct console *con;
+	loff_t off = 0;
+
+	/*
+	 * Hold the console_list_lock to guarantee safe traversal of the
+	 * console list. SRCU cannot be used because there is no
+	 * place to store the SRCU cookie.
+	 */
+	console_list_lock();
+	for_each_console(con)
+		if (off++ == *pos)
+			break;
+
+	return con;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct console *con = v;
+
+	++*pos;
+	return hlist_entry_safe(con->node.next, struct console, node);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+	__releases(&console_mutex)
+{
+	console_list_unlock();
+}
+
+static const struct seq_operations consoles_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= show_console_dev
+};
+
+static int __init proc_consoles_init(void)
+{
+	proc_create_seq("consoles", 0, NULL, &consoles_op);
+	return 0;
+}
+fs_initcall(proc_consoles_init);

linux-7.2.3/fs/proc/cpuinfo.c

@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cpufreq.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+extern const struct seq_operations cpuinfo_op;
+
+static int cpuinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &cpuinfo_op);
+}
+
+static const struct proc_ops cpuinfo_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_open	= cpuinfo_open,
+	.proc_read_iter	= seq_read_iter,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
+};
+
+static int __init proc_cpuinfo_init(void)
+{
+	proc_create("cpuinfo", 0, NULL, &cpuinfo_proc_ops);
+	return 0;
+}
+fs_initcall(proc_cpuinfo_init);

linux-7.2.3/fs/proc/devices.c

@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/blkdev.h>
+#include "internal.h"
+
+static int devinfo_show(struct seq_file *f, void *v)
+{
+	int i = *(loff_t *) v;
+
+	if (i < CHRDEV_MAJOR_MAX) {
+		if (i == 0)
+			seq_puts(f, "Character devices:\n");
+		chrdev_show(f, i);
+	}
+#ifdef CONFIG_BLOCK
+	else {
+		i -= CHRDEV_MAJOR_MAX;
+		if (i == 0)
+			seq_puts(f, "\nBlock devices:\n");
+		blkdev_show(f, i);
+	}
+#endif
+	return 0;
+}
+
+static void *devinfo_start(struct seq_file *f, loff_t *pos)
+{
+	if (*pos < (BLKDEV_MAJOR_MAX + CHRDEV_MAJOR_MAX))
+		return pos;
+	return NULL;
+}
+
+static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos)
+{
+	(*pos)++;
+	if (*pos >= (BLKDEV_MAJOR_MAX + CHRDEV_MAJOR_MAX))
+		return NULL;
+	return pos;
+}
+
+static void devinfo_stop(struct seq_file *f, void *v)
+{
+	/* Nothing to do */
+}
+
+static const struct seq_operations devinfo_ops = {
+	.start = devinfo_start,
+	.next  = devinfo_next,
+	.stop  = devinfo_stop,
+	.show  = devinfo_show
+};
+
+static int __init proc_devices_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = proc_create_seq("devices", 0, NULL, &devinfo_ops);
+	pde_make_permanent(pde);
+	return 0;
+}
+fs_initcall(proc_devices_init);

linux-7.2.3/fs/proc/fd.c

@@ -0,0 +1,407 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sched/signal.h>
+#include <linux/errno.h>
+#include <linux/dcache.h>
+#include <linux/path.h>
+#include <linux/fdtable.h>
+#include <linux/namei.h>
+#include <linux/pid.h>
+#include <linux/ptrace.h>
+#include <linux/bitmap.h>
+#include <linux/security.h>
+#include <linux/file.h>
+#include <linux/seq_file.h>
+#include <linux/fs.h>
+#include <linux/filelock.h>
+
+#include <linux/proc_fs.h>
+
+#include "../mount.h"
+#include "internal.h"
+#include "fd.h"
+
+static int seq_show(struct seq_file *m, void *v)
+{
+	struct files_struct *files = NULL;
+	int f_flags = 0, ret = -ENOENT;
+	struct file *file = NULL;
+	struct task_struct *task;
+
+	task = get_proc_task(m->private);
+	if (!task)
+		return -ENOENT;
+
+	task_lock(task);
+	files = task->files;
+	if (files) {
+		unsigned int fd = proc_fd(m->private);
+
+		spin_lock(&files->file_lock);
+		file = files_lookup_fd_locked(files, fd);
+		if (file) {
+			f_flags = file->f_flags;
+			if (close_on_exec(fd, files))
+				f_flags |= O_CLOEXEC;
+
+			get_file(file);
+			ret = 0;
+		}
+		spin_unlock(&files->file_lock);
+	}
+	task_unlock(task);
+	put_task_struct(task);
+
+	if (ret)
+		return ret;
+
+	seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\nino:\t%llu\n",
+		   (long long)file->f_pos, f_flags,
+		   real_mount(file->f_path.mnt)->mnt_id,
+		   file_inode(file)->i_ino);
+
+	/* show_fd_locks() never dereferences files, so a stale value is safe */
+	show_fd_locks(m, file, files);
+	if (seq_has_overflowed(m))
+		goto out;
+
+	if (file->f_op->show_fdinfo)
+		file->f_op->show_fdinfo(m, file);
+
+out:
+	fput(file);
+	return 0;
+}
+
+static int seq_fdinfo_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, seq_show, inode);
+}
+
+/*
+ * Shared /proc/pid/fdinfo and /proc/pid/fdinfo/fd permission helper to ensure
+ * that the current task has PTRACE_MODE_READ in addition to the normal
+ * POSIX-like checks.
+ */
+static int proc_fdinfo_permission(struct mnt_idmap *idmap, struct inode *inode,
+				  int mask)
+{
+	bool allowed = false;
+	struct task_struct *task = get_proc_task(inode);
+
+	if (!task)
+		return -ESRCH;
+
+	allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
+	put_task_struct(task);
+
+	if (!allowed)
+		return -EACCES;
+
+	return generic_permission(idmap, inode, mask);
+}
+
+static const struct inode_operations proc_fdinfo_file_inode_operations = {
+	.permission	= proc_fdinfo_permission,
+	.setattr	= proc_nochmod_setattr,
+};
+
+static const struct file_operations proc_fdinfo_file_operations = {
+	.open		= seq_fdinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
+{
+	struct file *file;
+
+	file = fget_task(task, fd);
+	if (file) {
+		*mode = file->f_mode;
+		fput(file);
+	}
+	return !!file;
+}
+
+static void tid_fd_update_inode(struct task_struct *task, struct inode *inode,
+				fmode_t f_mode)
+{
+	task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
+
+	if (S_ISLNK(inode->i_mode)) {
+		unsigned i_mode = S_IFLNK;
+		if (f_mode & FMODE_READ)
+			i_mode |= S_IRUSR | S_IXUSR;
+		if (f_mode & FMODE_WRITE)
+			i_mode |= S_IWUSR | S_IXUSR;
+		inode->i_mode = i_mode;
+	}
+	security_task_to_inode(task, inode);
+}
+
+static int tid_fd_revalidate(struct inode *dir, const struct qstr *name,
+			     struct dentry *dentry, unsigned int flags)
+{
+	struct task_struct *task;
+	struct inode *inode;
+	unsigned int fd;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	inode = d_inode(dentry);
+	task = get_proc_task(inode);
+	fd = proc_fd(inode);
+
+	if (task) {
+		fmode_t f_mode;
+		if (tid_fd_mode(task, fd, &f_mode)) {
+			tid_fd_update_inode(task, inode, f_mode);
+			put_task_struct(task);
+			return 1;
+		}
+		put_task_struct(task);
+	}
+	return 0;
+}
+
+static const struct dentry_operations tid_fd_dentry_operations = {
+	.d_revalidate	= tid_fd_revalidate,
+	.d_delete	= pid_delete_dentry,
+};
+
+static int proc_fd_link(struct dentry *dentry, struct path *path,
+			struct task_struct *task)
+{
+	int ret = -ENOENT;
+	unsigned int fd = proc_fd(d_inode(dentry));
+	struct file *fd_file;
+
+	fd_file = fget_task(task, fd);
+	if (fd_file) {
+		*path = fd_file->f_path;
+		path_get(&fd_file->f_path);
+		ret = 0;
+		fput(fd_file);
+	}
+
+	return ret;
+}
+
+struct fd_data {
+	fmode_t mode;
+	unsigned fd;
+};
+
+static struct dentry *proc_fd_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
+{
+	const struct fd_data *data = ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	ei = PROC_I(inode);
+	ei->fd = data->fd;
+
+	inode->i_op = &proc_pid_link_inode_operations;
+	inode->i_size = 64;
+
+	ei->op.proc_get_link = proc_fd_link;
+	tid_fd_update_inode(task, inode, data->mode);
+
+	return proc_splice_unmountable(inode, dentry,
+				       &tid_fd_dentry_operations);
+}
+
+static struct dentry *proc_lookupfd_common(struct inode *dir,
+					   struct dentry *dentry,
+					   instantiate_t instantiate)
+{
+	struct task_struct *task = get_proc_task(dir);
+	struct fd_data data = {.fd = name_to_int(&dentry->d_name)};
+	struct dentry *result = ERR_PTR(-ENOENT);
+
+	if (!task)
+		goto out_no_task;
+	if (data.fd == ~0U)
+		goto out;
+	if (!tid_fd_mode(task, data.fd, &data.mode))
+		goto out;
+
+	result = instantiate(dentry, task, &data);
+out:
+	put_task_struct(task);
+out_no_task:
+	return result;
+}
+
+static int proc_readfd_common(struct file *file, struct dir_context *ctx,
+			      instantiate_t instantiate)
+{
+	struct task_struct *p = get_proc_task(file_inode(file));
+	unsigned int fd;
+
+	if (!p)
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+
+	for (fd = ctx->pos - 2;; fd++) {
+		struct file *f;
+		struct fd_data data;
+		char name[10 + 1];
+		unsigned int len;
+
+		f = fget_task_next(p, &fd);
+		ctx->pos = fd + 2LL;
+		if (!f)
+			break;
+		data.mode = f->f_mode;
+		fput(f);
+		data.fd = fd;
+
+		len = snprintf(name, sizeof(name), "%u", fd);
+		if (!proc_fill_cache(file, ctx,
+				     name, len, instantiate, p,
+				     &data))
+			break;
+		cond_resched();
+	}
+out:
+	put_task_struct(p);
+	return 0;
+}
+
+static int proc_readfd_count(struct inode *inode, loff_t *count)
+{
+	struct task_struct *p = get_proc_task(inode);
+	struct fdtable *fdt;
+
+	if (!p)
+		return -ENOENT;
+
+	task_lock(p);
+	if (p->files) {
+		rcu_read_lock();
+
+		fdt = files_fdtable(p->files);
+		*count = bitmap_weight(fdt->open_fds, fdt->max_fds);
+
+		rcu_read_unlock();
+	}
+	task_unlock(p);
+
+	put_task_struct(p);
+
+	return 0;
+}
+
+static int proc_fd_iterate(struct file *file, struct dir_context *ctx)
+{
+	return proc_readfd_common(file, ctx, proc_fd_instantiate);
+}
+
+const struct file_operations proc_fd_operations = {
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_fd_iterate,
+	.llseek		= generic_file_llseek,
+};
+
+static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
+				    unsigned int flags)
+{
+	return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
+}
+
+/*
+ * /proc/pid/fd needs a special permission handler so that a process can still
+ * access /proc/self/fd after it has executed a setuid().
+ */
+int proc_fd_permission(struct mnt_idmap *idmap,
+		       struct inode *inode, int mask)
+{
+	struct task_struct *p;
+	int rv;
+
+	rv = generic_permission(&nop_mnt_idmap, inode, mask);
+	if (rv == 0)
+		return rv;
+
+	rcu_read_lock();
+	p = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (p && same_thread_group(p, current))
+		rv = 0;
+	rcu_read_unlock();
+
+	return rv;
+}
+
+static int proc_fd_getattr(struct mnt_idmap *idmap,
+			const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+	return proc_readfd_count(inode, &stat->size);
+}
+
+const struct inode_operations proc_fd_inode_operations = {
+	.lookup		= proc_lookupfd,
+	.permission	= proc_fd_permission,
+	.getattr	= proc_fd_getattr,
+	.setattr	= proc_nochmod_setattr,
+};
+
+static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
+{
+	const struct fd_data *data = ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUGO);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	ei = PROC_I(inode);
+	ei->fd = data->fd;
+
+	inode->i_op = &proc_fdinfo_file_inode_operations;
+
+	inode->i_fop = &proc_fdinfo_file_operations;
+	tid_fd_update_inode(task, inode, 0);
+
+	return proc_splice_unmountable(inode, dentry,
+				       &tid_fd_dentry_operations);
+}
+
+static struct dentry *
+proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
+	return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
+}
+
+static int proc_fdinfo_iterate(struct file *file, struct dir_context *ctx)
+{
+	return proc_readfd_common(file, ctx,
+				  proc_fdinfo_instantiate);
+}
+
+const struct inode_operations proc_fdinfo_inode_operations = {
+	.lookup		= proc_lookupfdinfo,
+	.permission	= proc_fdinfo_permission,
+	.setattr	= proc_nochmod_setattr,
+};
+
+const struct file_operations proc_fdinfo_operations = {
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_fdinfo_iterate,
+	.llseek		= generic_file_llseek,
+};

linux-7.2.3/fs/proc/fd.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PROCFS_FD_H__
+#define __PROCFS_FD_H__
+
+#include <linux/fs.h>
+
+extern const struct file_operations proc_fd_operations;
+extern const struct inode_operations proc_fd_inode_operations;
+
+extern const struct file_operations proc_fdinfo_operations;
+extern const struct inode_operations proc_fdinfo_inode_operations;
+
+extern int proc_fd_permission(struct mnt_idmap *idmap,
+			      struct inode *inode, int mask);
+
+static inline unsigned int proc_fd(struct inode *inode)
+{
+	return PROC_I(inode)->fd;
+}
+
+#endif /* __PROCFS_FD_H__ */

linux-7.2.3/fs/proc/generic.c

@@ -0,0 +1,856 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * proc/fs/generic.c --- generic routines for the proc-fs
+ *
+ * This file contains generic proc-fs routines for handling
+ * directories and files.
+ * 
+ * Copyright (C) 1991, 1992 Linus Torvalds.
+ * Copyright (C) 1997 Theodore Ts'o
+ */
+
+#include <linux/cache.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/namei.h>
+#include <linux/slab.h>
+#include <linux/printk.h>
+#include <linux/mount.h>
+#include <linux/init.h>
+#include <linux/idr.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/uaccess.h>
+#include <linux/seq_file.h>
+
+#include "internal.h"
+
+static DEFINE_RWLOCK(proc_subdir_lock);
+
+struct kmem_cache *proc_dir_entry_cache __ro_after_init;
+
+void pde_free(struct proc_dir_entry *pde)
+{
+	if (S_ISLNK(pde->mode))
+		kfree(pde->data);
+	if (pde->name != pde->inline_name)
+		kfree(pde->name);
+	kmem_cache_free(proc_dir_entry_cache, pde);
+}
+
+static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int len)
+{
+	if (len < de->namelen)
+		return -1;
+	if (len > de->namelen)
+		return 1;
+
+	return memcmp(name, de->name, len);
+}
+
+static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir)
+{
+	return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry,
+			     subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir)
+{
+	return rb_entry_safe(rb_next(&dir->subdir_node), struct proc_dir_entry,
+			     subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
+					      const char *name,
+					      unsigned int len)
+{
+	struct rb_node *node = dir->subdir.rb_node;
+
+	while (node) {
+		struct proc_dir_entry *de = rb_entry(node,
+						     struct proc_dir_entry,
+						     subdir_node);
+		int result = proc_match(name, de, len);
+
+		if (result < 0)
+			node = node->rb_left;
+		else if (result > 0)
+			node = node->rb_right;
+		else
+			return de;
+	}
+	return NULL;
+}
+
+static bool pde_subdir_insert(struct proc_dir_entry *dir,
+			      struct proc_dir_entry *de)
+{
+	struct rb_root *root = &dir->subdir;
+	struct rb_node **new = &root->rb_node, *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct proc_dir_entry *this = rb_entry(*new,
+						       struct proc_dir_entry,
+						       subdir_node);
+		int result = proc_match(de->name, this, de->namelen);
+
+		parent = *new;
+		if (result < 0)
+			new = &(*new)->rb_left;
+		else if (result > 0)
+			new = &(*new)->rb_right;
+		else
+			return false;
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&de->subdir_node, parent, new);
+	rb_insert_color(&de->subdir_node, root);
+	if (S_ISDIR(de->mode))
+		dir->nlink++;
+	return true;
+}
+
+static int proc_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		struct iattr *iattr)
+{
+	struct inode *inode = d_inode(dentry);
+	struct proc_dir_entry *de = PDE(inode);
+	int error;
+
+	error = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
+	if (error)
+		return error;
+
+	setattr_copy(&nop_mnt_idmap, inode, iattr);
+
+	proc_set_user(de, inode->i_uid, inode->i_gid);
+	de->mode = inode->i_mode;
+	return 0;
+}
+
+static int proc_getattr(struct mnt_idmap *idmap,
+			const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+	struct proc_dir_entry *de = PDE(inode);
+	if (de) {
+		nlink_t nlink = READ_ONCE(de->nlink);
+		if (nlink > 0) {
+			set_nlink(inode, nlink);
+		}
+	}
+
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static const struct inode_operations proc_file_inode_operations = {
+	.setattr	= proc_setattr,
+};
+
+/*
+ * This function parses a name such as "tty/driver/serial", and
+ * returns the struct proc_dir_entry for "/proc/tty/driver", and
+ * returns "serial" in residual.
+ */
+static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
+			     const char **residual)
+{
+	const char     		*cp = name, *next;
+	struct proc_dir_entry	*de;
+
+	de = *ret ?: &proc_root;
+	while ((next = strchr(cp, '/')) != NULL) {
+		de = pde_subdir_find(de, cp, next - cp);
+		if (!de) {
+			WARN(1, "name '%s'\n", name);
+			return -ENOENT;
+		}
+		cp = next + 1;
+	}
+	*residual = cp;
+	*ret = de;
+	return 0;
+}
+
+static int xlate_proc_name(const char *name, struct proc_dir_entry **ret,
+			   const char **residual)
+{
+	int rv;
+
+	read_lock(&proc_subdir_lock);
+	rv = __xlate_proc_name(name, ret, residual);
+	read_unlock(&proc_subdir_lock);
+	return rv;
+}
+
+static DEFINE_IDA(proc_inum_ida);
+
+#define PROC_DYNAMIC_FIRST 0xF0000000U
+
+/*
+ * Return an inode number between PROC_DYNAMIC_FIRST and
+ * 0xffffffff, or zero on failure.
+ */
+int proc_alloc_inum(unsigned int *inum)
+{
+	int i;
+
+	i = ida_alloc_max(&proc_inum_ida, UINT_MAX - PROC_DYNAMIC_FIRST,
+			  GFP_KERNEL);
+	if (i < 0)
+		return i;
+
+	*inum = PROC_DYNAMIC_FIRST + (unsigned int)i;
+	return 0;
+}
+
+void proc_free_inum(unsigned int inum)
+{
+	ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
+}
+
+static int proc_misc_d_revalidate(struct inode *dir, const struct qstr *name,
+				  struct dentry *dentry, unsigned int flags)
+{
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	if (atomic_read(&PDE(d_inode(dentry))->in_use) < 0)
+		return 0; /* revalidate */
+	return 1;
+}
+
+static int proc_misc_d_delete(const struct dentry *dentry)
+{
+	return atomic_read(&PDE(d_inode(dentry))->in_use) < 0;
+}
+
+static const struct dentry_operations proc_misc_dentry_ops = {
+	.d_revalidate	= proc_misc_d_revalidate,
+	.d_delete	= proc_misc_d_delete,
+};
+
+/*
+ * Don't create negative dentries here, return -ENOENT by hand
+ * instead.
+ */
+struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
+			      struct proc_dir_entry *de)
+{
+	struct inode *inode;
+
+	read_lock(&proc_subdir_lock);
+	de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len);
+	if (de) {
+		pde_get(de);
+		read_unlock(&proc_subdir_lock);
+		inode = proc_get_inode(dir->i_sb, de);
+		if (!inode)
+			return ERR_PTR(-ENOMEM);
+		if (de->flags & PROC_ENTRY_FORCE_LOOKUP)
+			return d_splice_alias_ops(inode, dentry,
+						  &proc_net_dentry_ops);
+		return d_splice_alias_ops(inode, dentry,
+					  &proc_misc_dentry_ops);
+	}
+	read_unlock(&proc_subdir_lock);
+	return ERR_PTR(-ENOENT);
+}
+
+struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
+		unsigned int flags)
+{
+	struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb);
+
+	if (fs_info->pidonly == PROC_PIDONLY_ON)
+		return ERR_PTR(-ENOENT);
+
+	return proc_lookup_de(dir, dentry, PDE(dir));
+}
+
+/*
+ * This returns non-zero if at EOF, so that the /proc
+ * root directory can use this and check if it should
+ * continue with the <pid> entries..
+ *
+ * Note that the VFS-layer doesn't care about the return
+ * value of the readdir() call, as long as it's non-negative
+ * for success..
+ */
+int proc_readdir_de(struct file *file, struct dir_context *ctx,
+		    struct proc_dir_entry *de)
+{
+	int i;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+
+	i = ctx->pos - 2;
+	read_lock(&proc_subdir_lock);
+	de = pde_subdir_first(de);
+	for (;;) {
+		if (!de) {
+			read_unlock(&proc_subdir_lock);
+			return 0;
+		}
+		if (!i)
+			break;
+		de = pde_subdir_next(de);
+		i--;
+	}
+
+	do {
+		struct proc_dir_entry *next;
+		pde_get(de);
+		read_unlock(&proc_subdir_lock);
+		if (!dir_emit(ctx, de->name, de->namelen,
+			    de->low_ino, de->mode >> 12)) {
+			pde_put(de);
+			return 0;
+		}
+		ctx->pos++;
+		read_lock(&proc_subdir_lock);
+		next = pde_subdir_next(de);
+		pde_put(de);
+		de = next;
+	} while (de);
+	read_unlock(&proc_subdir_lock);
+	return 1;
+}
+
+int proc_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct inode *inode = file_inode(file);
+	struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
+
+	if (fs_info->pidonly == PROC_PIDONLY_ON)
+		return 1;
+
+	return proc_readdir_de(file, ctx, PDE(inode));
+}
+
+/*
+ * These are the generic /proc directory operations. They
+ * use the in-memory "struct proc_dir_entry" tree to parse
+ * the /proc directory.
+ */
+static const struct file_operations proc_dir_operations = {
+	.llseek			= generic_file_llseek,
+	.read			= generic_read_dir,
+	.iterate_shared		= proc_readdir,
+};
+
+static int proc_net_d_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
+{
+	return 0;
+}
+
+const struct dentry_operations proc_net_dentry_ops = {
+	.d_revalidate	= proc_net_d_revalidate,
+	.d_delete	= always_delete_dentry,
+};
+
+/*
+ * proc directories can do almost nothing..
+ */
+static const struct inode_operations proc_dir_inode_operations = {
+	.lookup		= proc_lookup,
+	.getattr	= proc_getattr,
+	.setattr	= proc_setattr,
+};
+
+static void pde_set_flags(struct proc_dir_entry *pde)
+{
+	const struct proc_ops *proc_ops = pde->proc_ops;
+
+	if (!proc_ops)
+		return;
+
+	if (proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
+		pde->flags |= PROC_ENTRY_PERMANENT;
+	if (proc_ops->proc_read_iter)
+		pde->flags |= PROC_ENTRY_proc_read_iter;
+#ifdef CONFIG_COMPAT
+	if (proc_ops->proc_compat_ioctl)
+		pde->flags |= PROC_ENTRY_proc_compat_ioctl;
+#endif
+	if (proc_ops->proc_lseek)
+		pde->flags |= PROC_ENTRY_proc_lseek;
+}
+
+/* returns the registered entry, or frees dp and returns NULL on failure */
+struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
+		struct proc_dir_entry *dp)
+{
+	if (proc_alloc_inum(&dp->low_ino))
+		goto out_free_entry;
+
+	if (!S_ISDIR(dp->mode))
+		pde_set_flags(dp);
+
+	write_lock(&proc_subdir_lock);
+	dp->parent = dir;
+	if (pde_subdir_insert(dir, dp) == false) {
+		WARN(1, "proc_dir_entry '%s/%s' already registered\n",
+		     dir->name, dp->name);
+		write_unlock(&proc_subdir_lock);
+		goto out_free_inum;
+	}
+	write_unlock(&proc_subdir_lock);
+
+	return dp;
+out_free_inum:
+	proc_free_inum(dp->low_ino);
+out_free_entry:
+	pde_free(dp);
+	return NULL;
+}
+
+static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
+					  const char *name,
+					  umode_t mode,
+					  nlink_t nlink)
+{
+	struct proc_dir_entry *ent = NULL;
+	const char *fn;
+	struct qstr qstr;
+
+	if (xlate_proc_name(name, parent, &fn) != 0)
+		goto out;
+	qstr.name = fn;
+	qstr.len = strnlen(fn, NAME_MAX + 1);
+	if (qstr.len == 0) {
+		WARN(1, "empty name\n");
+		return NULL;
+	}
+	if (qstr.len > NAME_MAX) {
+		WARN(1, "name too long\n");
+		return NULL;
+	}
+	if (qstr.len == 1 && fn[0] == '.') {
+		WARN(1, "name '.'\n");
+		return NULL;
+	}
+	if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') {
+		WARN(1, "name '..'\n");
+		return NULL;
+	}
+	if (*parent == &proc_root && name_to_int(&qstr) != ~0U) {
+		WARN(1, "create '/proc/%s' by hand\n", qstr.name);
+		return NULL;
+	}
+	if (is_empty_pde(*parent)) {
+		WARN(1, "attempt to add to permanently empty directory");
+		return NULL;
+	}
+
+	ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL);
+	if (!ent)
+		goto out;
+
+	if (qstr.len + 1 <= SIZEOF_PDE_INLINE_NAME) {
+		ent->name = ent->inline_name;
+	} else {
+		ent->name = kmalloc(qstr.len + 1, GFP_KERNEL);
+		if (!ent->name) {
+			pde_free(ent);
+			return NULL;
+		}
+	}
+
+	memcpy(ent->name, fn, qstr.len + 1);
+	ent->namelen = qstr.len;
+	ent->mode = mode;
+	ent->nlink = nlink;
+	ent->subdir = RB_ROOT;
+	refcount_set(&ent->refcnt, 1);
+	spin_lock_init(&ent->pde_unload_lock);
+	INIT_LIST_HEAD(&ent->pde_openers);
+	proc_set_user(ent, (*parent)->uid, (*parent)->gid);
+
+	/* Revalidate everything under /proc/${pid}/net */
+	if ((*parent)->flags & PROC_ENTRY_FORCE_LOOKUP)
+		pde_force_lookup(ent);
+
+out:
+	return ent;
+}
+
+struct proc_dir_entry *proc_symlink(const char *name,
+		struct proc_dir_entry *parent, const char *dest)
+{
+	struct proc_dir_entry *ent;
+
+	ent = __proc_create(&parent, name,
+			  (S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1);
+
+	if (ent) {
+		ent->size = strlen(dest);
+		ent->data = kmemdup(dest, ent->size + 1, GFP_KERNEL);
+		if (ent->data) {
+			ent->proc_iops = &proc_link_inode_operations;
+			ent = proc_register(parent, ent);
+		} else {
+			pde_free(ent);
+			ent = NULL;
+		}
+	}
+	return ent;
+}
+EXPORT_SYMBOL(proc_symlink);
+
+struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, void *data, bool force_lookup)
+{
+	struct proc_dir_entry *ent;
+
+	if (mode == 0)
+		mode = S_IRUGO | S_IXUGO;
+
+	ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
+	if (ent) {
+		ent->data = data;
+		ent->proc_dir_ops = &proc_dir_operations;
+		ent->proc_iops = &proc_dir_inode_operations;
+		if (force_lookup) {
+			pde_force_lookup(ent);
+		}
+		ent = proc_register(parent, ent);
+	}
+	return ent;
+}
+EXPORT_SYMBOL_GPL(_proc_mkdir);
+
+struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, void *data)
+{
+	return _proc_mkdir(name, mode, parent, data, false);
+}
+EXPORT_SYMBOL_GPL(proc_mkdir_data);
+
+struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode,
+				       struct proc_dir_entry *parent)
+{
+	return proc_mkdir_data(name, mode, parent, NULL);
+}
+EXPORT_SYMBOL(proc_mkdir_mode);
+
+struct proc_dir_entry *proc_mkdir(const char *name,
+		struct proc_dir_entry *parent)
+{
+	return proc_mkdir_data(name, 0, parent, NULL);
+}
+EXPORT_SYMBOL(proc_mkdir);
+
+struct proc_dir_entry *proc_create_mount_point(const char *name)
+{
+	umode_t mode = S_IFDIR | S_IRUGO | S_IXUGO;
+	struct proc_dir_entry *ent, *parent = NULL;
+
+	ent = __proc_create(&parent, name, mode, 2);
+	if (ent) {
+		ent->data = NULL;
+		ent->proc_dir_ops = NULL;
+		ent->proc_iops = NULL;
+		ent = proc_register(parent, ent);
+	}
+	return ent;
+}
+EXPORT_SYMBOL(proc_create_mount_point);
+
+struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
+		struct proc_dir_entry **parent, void *data)
+{
+	struct proc_dir_entry *p;
+
+	if ((mode & S_IFMT) == 0)
+		mode |= S_IFREG;
+	if ((mode & S_IALLUGO) == 0)
+		mode |= S_IRUGO;
+	if (WARN_ON_ONCE(!S_ISREG(mode)))
+		return NULL;
+
+	p = __proc_create(parent, name, mode, 1);
+	if (p) {
+		p->proc_iops = &proc_file_inode_operations;
+		p->data = data;
+	}
+	return p;
+}
+
+struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent,
+		const struct proc_ops *proc_ops, void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	p->proc_ops = proc_ops;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL(proc_create_data);
+ 
+struct proc_dir_entry *proc_create(const char *name, umode_t mode,
+				   struct proc_dir_entry *parent,
+				   const struct proc_ops *proc_ops)
+{
+	return proc_create_data(name, mode, parent, proc_ops, NULL);
+}
+EXPORT_SYMBOL(proc_create);
+
+static int proc_seq_open(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+
+	if (de->state_size)
+		return seq_open_private(file, de->seq_ops, de->state_size);
+	return seq_open(file, de->seq_ops);
+}
+
+static int proc_seq_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+
+	if (de->state_size)
+		return seq_release_private(inode, file);
+	return seq_release(inode, file);
+}
+
+static const struct proc_ops proc_seq_ops = {
+	/* not permanent -- can call into arbitrary seq_operations */
+	.proc_open	= proc_seq_open,
+	.proc_read_iter	= seq_read_iter,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= proc_seq_release,
+};
+
+struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, const struct seq_operations *ops,
+		unsigned int state_size, void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	p->proc_ops = &proc_seq_ops;
+	p->seq_ops = ops;
+	p->state_size = state_size;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL(proc_create_seq_private);
+
+static int proc_single_open(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+
+	return single_open(file, de->single_show, de->data);
+}
+
+static const struct proc_ops proc_single_ops = {
+	/* not permanent -- can call into arbitrary ->single_show */
+	.proc_open	= proc_single_open,
+	.proc_read_iter = seq_read_iter,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+};
+
+struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent,
+		int (*show)(struct seq_file *, void *), void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	p->proc_ops = &proc_single_ops;
+	p->single_show = show;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL(proc_create_single_data);
+
+void proc_set_size(struct proc_dir_entry *de, loff_t size)
+{
+	de->size = size;
+}
+EXPORT_SYMBOL(proc_set_size);
+
+void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid)
+{
+	de->uid = uid;
+	de->gid = gid;
+}
+EXPORT_SYMBOL(proc_set_user);
+
+void pde_put(struct proc_dir_entry *pde)
+{
+	if (refcount_dec_and_test(&pde->refcnt)) {
+		proc_free_inum(pde->low_ino);
+		pde_free(pde);
+	}
+}
+
+static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent)
+{
+	rb_erase(&pde->subdir_node, &parent->subdir);
+	RB_CLEAR_NODE(&pde->subdir_node);
+	if (S_ISDIR(pde->mode))
+		parent->nlink--;
+}
+
+/*
+ * Remove a /proc entry and free it if it's not currently in use.
+ */
+void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry *de = NULL;
+	const char *fn = name;
+	unsigned int len;
+
+	write_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		write_unlock(&proc_subdir_lock);
+		return;
+	}
+	len = strlen(fn);
+
+	de = pde_subdir_find(parent, fn, len);
+	if (de) {
+		if (unlikely(pde_is_permanent(de))) {
+			WARN(1, "removing permanent /proc entry '%s'", de->name);
+			de = NULL;
+		} else {
+			pde_erase(de, parent);
+		}
+	}
+	write_unlock(&proc_subdir_lock);
+	if (!de) {
+		WARN(1, "name '%s'\n", name);
+		return;
+	}
+
+	proc_entry_rundown(de);
+
+	WARN(pde_subdir_first(de),
+	     "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n",
+	     __func__, de->parent->name, de->name, pde_subdir_first(de)->name);
+	pde_put(de);
+}
+EXPORT_SYMBOL(remove_proc_entry);
+
+int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry *root = NULL, *de, *next;
+	const char *fn = name;
+	unsigned int len;
+
+	write_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		write_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	len = strlen(fn);
+
+	root = pde_subdir_find(parent, fn, len);
+	if (!root) {
+		write_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	if (unlikely(pde_is_permanent(root))) {
+		write_unlock(&proc_subdir_lock);
+		WARN(1, "removing permanent /proc entry '%s/%s'",
+			root->parent->name, root->name);
+		return -EINVAL;
+	}
+	pde_erase(root, parent);
+
+	de = root;
+	while (1) {
+		next = pde_subdir_first(de);
+		if (next) {
+			if (unlikely(pde_is_permanent(next))) {
+				write_unlock(&proc_subdir_lock);
+				WARN(1, "removing permanent /proc entry '%s/%s'",
+					next->parent->name, next->name);
+				return -EINVAL;
+			}
+			pde_erase(next, de);
+			de = next;
+			continue;
+		}
+		next = de->parent;
+		write_unlock(&proc_subdir_lock);
+
+		proc_entry_rundown(de);
+		if (de == root)
+			break;
+		pde_put(de);
+
+		write_lock(&proc_subdir_lock);
+		de = next;
+	}
+	pde_put(root);
+	return 0;
+}
+EXPORT_SYMBOL(remove_proc_subtree);
+
+void *proc_get_parent_data(const struct inode *inode)
+{
+	struct proc_dir_entry *de = PDE(inode);
+	return de->parent->data;
+}
+EXPORT_SYMBOL_GPL(proc_get_parent_data);
+
+void proc_remove(struct proc_dir_entry *de)
+{
+	if (de)
+		remove_proc_subtree(de->name, de->parent);
+}
+EXPORT_SYMBOL(proc_remove);
+
+/*
+ * Pull a user buffer into memory and pass it to the file's write handler if
+ * one is supplied.  The ->write() method is permitted to modify the
+ * kernel-side buffer.
+ */
+ssize_t proc_simple_write(struct file *f, const char __user *ubuf, size_t size,
+			  loff_t *_pos)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(f));
+	char *buf;
+	int ret;
+
+	if (!pde->write)
+		return -EACCES;
+	if (size == 0 || size > PAGE_SIZE - 1)
+		return -EINVAL;
+	buf = memdup_user_nul(ubuf, size);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+	ret = pde->write(f, buf, size);
+	kfree(buf);
+	return ret == 0 ? size : ret;
+}
+
+/*
+ * Not exported to modules:
+ * modules' /proc files aren't permanent because modules aren't permanent.
+ */
+void impl_proc_make_permanent(struct proc_dir_entry *pde)
+{
+	if (pde)
+		pde_make_permanent(pde);
+}

linux-7.2.3/fs/proc/inode.c

@@ -0,0 +1,680 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/proc/inode.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/cache.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/kernel.h>
+#include <linux/pid_namespace.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/completion.h>
+#include <linux/poll.h>
+#include <linux/printk.h>
+#include <linux/file.h>
+#include <linux/limits.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/mount.h>
+#include <linux/bug.h>
+
+#include "internal.h"
+
+static void proc_evict_inode(struct inode *inode)
+{
+	struct ctl_table_header *head;
+	struct proc_inode *ei = PROC_I(inode);
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+
+	/* Stop tracking associated processes */
+	if (ei->pid)
+		proc_pid_evict_inode(ei);
+
+	head = ei->sysctl;
+	if (head) {
+		WRITE_ONCE(ei->sysctl, NULL);
+		proc_sys_evict_inode(inode, head);
+	}
+}
+
+static struct kmem_cache *proc_inode_cachep __ro_after_init;
+static struct kmem_cache *pde_opener_cache __ro_after_init;
+
+static struct inode *proc_alloc_inode(struct super_block *sb)
+{
+	struct proc_inode *ei;
+
+	ei = alloc_inode_sb(sb, proc_inode_cachep, GFP_KERNEL);
+	if (!ei)
+		return NULL;
+	ei->pid = NULL;
+	ei->fd = 0;
+	ei->op.proc_get_link = NULL;
+	ei->pde = NULL;
+	ei->sysctl = NULL;
+	ei->sysctl_entry = NULL;
+	INIT_HLIST_NODE(&ei->sibling_inodes);
+	ei->ns_ops = NULL;
+	return &ei->vfs_inode;
+}
+
+static void proc_free_inode(struct inode *inode)
+{
+	struct proc_inode *ei = PROC_I(inode);
+
+	if (ei->pid)
+		put_pid(ei->pid);
+	/* Let go of any associated proc directory entry */
+	if (ei->pde)
+		pde_put(ei->pde);
+	kmem_cache_free(proc_inode_cachep, PROC_I(inode));
+}
+
+static void init_once(void *foo)
+{
+	struct proc_inode *ei = (struct proc_inode *) foo;
+
+	inode_init_once(&ei->vfs_inode);
+}
+
+void __init proc_init_kmemcache(void)
+{
+	proc_inode_cachep = kmem_cache_create("proc_inode_cache",
+					     sizeof(struct proc_inode),
+					     0, (SLAB_RECLAIM_ACCOUNT|
+						SLAB_ACCOUNT|
+						SLAB_PANIC),
+					     init_once);
+	pde_opener_cache =
+		kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0,
+				  SLAB_ACCOUNT|SLAB_PANIC, NULL);
+	proc_dir_entry_cache = kmem_cache_create_usercopy(
+		"proc_dir_entry", SIZEOF_PDE, 0, SLAB_PANIC,
+		offsetof(struct proc_dir_entry, inline_name),
+		SIZEOF_PDE_INLINE_NAME, NULL);
+	BUILD_BUG_ON(sizeof(struct proc_dir_entry) >= SIZEOF_PDE);
+}
+
+void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock)
+{
+	struct hlist_node *node;
+	struct super_block *old_sb = NULL;
+
+	rcu_read_lock();
+	while ((node = hlist_first_rcu(inodes))) {
+		struct proc_inode *ei = hlist_entry(node, struct proc_inode, sibling_inodes);
+		struct super_block *sb;
+		struct inode *inode;
+
+		spin_lock(lock);
+		hlist_del_init_rcu(&ei->sibling_inodes);
+		spin_unlock(lock);
+
+		inode = &ei->vfs_inode;
+		sb = inode->i_sb;
+		if ((sb != old_sb) && !atomic_inc_not_zero(&sb->s_active))
+			continue;
+		inode = igrab(inode);
+		rcu_read_unlock();
+		if (sb != old_sb) {
+			if (old_sb)
+				deactivate_super(old_sb);
+			old_sb = sb;
+		}
+		if (unlikely(!inode)) {
+			rcu_read_lock();
+			continue;
+		}
+
+		if (S_ISDIR(inode->i_mode)) {
+			struct dentry *dir = d_find_any_alias(inode);
+			if (dir) {
+				d_invalidate(dir);
+				dput(dir);
+			}
+		} else {
+			struct dentry *dentry;
+			while ((dentry = d_find_alias(inode))) {
+				d_invalidate(dentry);
+				dput(dentry);
+			}
+		}
+		iput(inode);
+
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+	if (old_sb)
+		deactivate_super(old_sb);
+}
+
+static inline const char *hidepid2str(enum proc_hidepid v)
+{
+	switch (v) {
+		case HIDEPID_OFF: return "off";
+		case HIDEPID_NO_ACCESS: return "noaccess";
+		case HIDEPID_INVISIBLE: return "invisible";
+		case HIDEPID_NOT_PTRACEABLE: return "ptraceable";
+	}
+	WARN_ONCE(1, "bad hide_pid value: %d\n", v);
+	return "unknown";
+}
+
+static int proc_show_options(struct seq_file *seq, struct dentry *root)
+{
+	struct proc_fs_info *fs_info = proc_sb_info(root->d_sb);
+
+	if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID))
+		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid));
+	if (fs_info->hide_pid != HIDEPID_OFF)
+		seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid));
+	if (fs_info->pidonly != PROC_PIDONLY_OFF)
+		seq_printf(seq, ",subset=pid");
+
+	return 0;
+}
+
+const struct super_operations proc_sops = {
+	.alloc_inode	= proc_alloc_inode,
+	.free_inode	= proc_free_inode,
+	.drop_inode	= inode_just_drop,
+	.evict_inode	= proc_evict_inode,
+	.statfs		= simple_statfs,
+	.show_options	= proc_show_options,
+};
+
+enum {BIAS = -1U<<31};
+
+static inline int use_pde(struct proc_dir_entry *pde)
+{
+	return likely(atomic_inc_unless_negative(&pde->in_use));
+}
+
+static void unuse_pde(struct proc_dir_entry *pde)
+{
+	if (unlikely(atomic_dec_return(&pde->in_use) == BIAS))
+		complete(pde->pde_unload_completion);
+}
+
+/*
+ * At most 2 contexts can enter this function: the one doing the last
+ * close on the descriptor and whoever is deleting PDE itself.
+ *
+ * First to enter calls ->proc_release hook and signals its completion
+ * to the second one which waits and then does nothing.
+ *
+ * PDE is locked on entry, unlocked on exit.
+ */
+static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
+	__releases(&pde->pde_unload_lock)
+{
+	/*
+	 * close() (proc_reg_release()) can't delete an entry and proceed:
+	 * ->release hook needs to be available at the right moment.
+	 *
+	 * rmmod (remove_proc_entry() et al) can't delete an entry and proceed:
+	 * "struct file" needs to be available at the right moment.
+	 */
+	if (pdeo->closing) {
+		/* somebody else is doing that, just wait */
+		DECLARE_COMPLETION_ONSTACK(c);
+		pdeo->c = &c;
+		spin_unlock(&pde->pde_unload_lock);
+		wait_for_completion(&c);
+	} else {
+		struct file *file;
+		struct completion *c;
+
+		pdeo->closing = true;
+		spin_unlock(&pde->pde_unload_lock);
+
+		file = pdeo->file;
+		pde->proc_ops->proc_release(file_inode(file), file);
+
+		spin_lock(&pde->pde_unload_lock);
+		/* Strictly after ->proc_release, see above. */
+		list_del(&pdeo->lh);
+		c = pdeo->c;
+		spin_unlock(&pde->pde_unload_lock);
+		if (unlikely(c))
+			complete(c);
+		kmem_cache_free(pde_opener_cache, pdeo);
+	}
+}
+
+void proc_entry_rundown(struct proc_dir_entry *de)
+{
+	DECLARE_COMPLETION_ONSTACK(c);
+	/* Wait until all existing callers into module are done. */
+	de->pde_unload_completion = &c;
+	if (atomic_add_return(BIAS, &de->in_use) != BIAS)
+		wait_for_completion(&c);
+
+	/* ->pde_openers list can't grow from now on. */
+
+	spin_lock(&de->pde_unload_lock);
+	while (!list_empty(&de->pde_openers)) {
+		struct pde_opener *pdeo;
+		pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
+		close_pdeo(de, pdeo);
+		spin_lock(&de->pde_unload_lock);
+	}
+	spin_unlock(&de->pde_unload_lock);
+}
+
+static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	loff_t rv = -EINVAL;
+
+	if (pde_is_permanent(pde)) {
+		return pde->proc_ops->proc_lseek(file, offset, whence);
+	} else if (use_pde(pde)) {
+		rv = pde->proc_ops->proc_lseek(file, offset, whence);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp));
+	ssize_t ret;
+
+	if (pde_is_permanent(pde))
+		return pde->proc_ops->proc_read_iter(iocb, iter);
+
+	if (!use_pde(pde))
+		return -EIO;
+	ret = pde->proc_ops->proc_read_iter(iocb, iter);
+	unuse_pde(pde);
+	return ret;
+}
+
+static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	const auto read = pde->proc_ops->proc_read;
+	if (read)
+		return read(file, buf, count, ppos);
+	return -EIO;
+}
+
+static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	ssize_t rv = -EIO;
+
+	if (pde_is_permanent(pde)) {
+		return pde_read(pde, file, buf, count, ppos);
+	} else if (use_pde(pde)) {
+		rv = pde_read(pde, file, buf, count, ppos);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	const auto write = pde->proc_ops->proc_write;
+	if (write)
+		return write(file, buf, count, ppos);
+	return -EIO;
+}
+
+static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	ssize_t rv = -EIO;
+
+	if (pde_is_permanent(pde)) {
+		return pde_write(pde, file, buf, count, ppos);
+	} else if (use_pde(pde)) {
+		rv = pde_write(pde, file, buf, count, ppos);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts)
+{
+	const auto poll = pde->proc_ops->proc_poll;
+	if (poll)
+		return poll(file, pts);
+	return DEFAULT_POLLMASK;
+}
+
+static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	__poll_t rv = DEFAULT_POLLMASK;
+
+	if (pde_is_permanent(pde)) {
+		return pde_poll(pde, file, pts);
+	} else if (use_pde(pde)) {
+		rv = pde_poll(pde, file, pts);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
+{
+	const auto ioctl = pde->proc_ops->proc_ioctl;
+	if (ioctl)
+		return ioctl(file, cmd, arg);
+	return -ENOTTY;
+}
+
+static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	long rv = -ENOTTY;
+
+	if (pde_is_permanent(pde)) {
+		return pde_ioctl(pde, file, cmd, arg);
+	} else if (use_pde(pde)) {
+		rv = pde_ioctl(pde, file, cmd, arg);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+#ifdef CONFIG_COMPAT
+static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
+{
+	const auto compat_ioctl = pde->proc_ops->proc_compat_ioctl;
+	if (compat_ioctl)
+		return compat_ioctl(file, cmd, arg);
+	return -ENOTTY;
+}
+
+static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	long rv = -ENOTTY;
+	if (pde_is_permanent(pde)) {
+		return pde_compat_ioctl(pde, file, cmd, arg);
+	} else if (use_pde(pde)) {
+		rv = pde_compat_ioctl(pde, file, cmd, arg);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+#endif
+
+static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma)
+{
+	const auto mmap = pde->proc_ops->proc_mmap;
+	if (mmap)
+		return mmap(file, vma);
+	return -EIO;
+}
+
+static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	int rv = -EIO;
+
+	if (pde_is_permanent(pde)) {
+		return pde_mmap(pde, file, vma);
+	} else if (use_pde(pde)) {
+		rv = pde_mmap(pde, file, vma);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static unsigned long
+pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned long orig_addr,
+			   unsigned long len, unsigned long pgoff,
+			   unsigned long flags)
+{
+	if (pde->proc_ops->proc_get_unmapped_area)
+		return pde->proc_ops->proc_get_unmapped_area(file, orig_addr, len, pgoff, flags);
+
+#ifdef CONFIG_MMU
+	return mm_get_unmapped_area(file, orig_addr, len, pgoff, flags);
+#endif
+
+	return orig_addr;
+}
+
+static unsigned long
+proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
+			   unsigned long len, unsigned long pgoff,
+			   unsigned long flags)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	unsigned long rv = -EIO;
+
+	if (pde_is_permanent(pde)) {
+		return pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags);
+	} else if (use_pde(pde)) {
+		rv = pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static int proc_reg_open(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	int rv = 0;
+	typeof_member(struct proc_ops, proc_open) open;
+	struct pde_opener *pdeo;
+
+	if (!pde_has_proc_lseek(pde))
+		file->f_mode &= ~FMODE_LSEEK;
+
+	if (pde_is_permanent(pde)) {
+		open = pde->proc_ops->proc_open;
+		if (open)
+			rv = open(inode, file);
+		return rv;
+	}
+
+	/*
+	 * Ensure that
+	 * 1) PDE's ->release hook will be called no matter what
+	 *    either normally by close()/->release, or forcefully by
+	 *    rmmod/remove_proc_entry.
+	 *
+	 * 2) rmmod isn't blocked by opening file in /proc and sitting on
+	 *    the descriptor (including "rmmod foo </proc/foo" scenario).
+	 *
+	 * Save every "struct file" with custom ->release hook.
+	 */
+	if (!use_pde(pde))
+		return -ENOENT;
+
+	const auto release = pde->proc_ops->proc_release;
+	if (release) {
+		pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL);
+		if (!pdeo) {
+			rv = -ENOMEM;
+			goto out_unuse;
+		}
+	}
+
+	open = pde->proc_ops->proc_open;
+	if (open)
+		rv = open(inode, file);
+
+	if (release) {
+		if (rv == 0) {
+			/* To know what to release. */
+			pdeo->file = file;
+			pdeo->closing = false;
+			pdeo->c = NULL;
+			spin_lock(&pde->pde_unload_lock);
+			list_add(&pdeo->lh, &pde->pde_openers);
+			spin_unlock(&pde->pde_unload_lock);
+		} else
+			kmem_cache_free(pde_opener_cache, pdeo);
+	}
+
+out_unuse:
+	unuse_pde(pde);
+	return rv;
+}
+
+static int proc_reg_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	struct pde_opener *pdeo;
+
+	if (pde_is_permanent(pde)) {
+		const auto release = pde->proc_ops->proc_release;
+		if (release)
+			return release(inode, file);
+		return 0;
+	}
+
+	spin_lock(&pde->pde_unload_lock);
+	list_for_each_entry(pdeo, &pde->pde_openers, lh) {
+		if (pdeo->file == file) {
+			close_pdeo(pde, pdeo);
+			return 0;
+		}
+	}
+	spin_unlock(&pde->pde_unload_lock);
+	return 0;
+}
+
+static const struct file_operations proc_reg_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read		= proc_reg_read,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.splice_read	= copy_splice_read,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+#ifdef CONFIG_COMPAT
+static const struct file_operations proc_reg_file_ops_compat = {
+	.llseek		= proc_reg_llseek,
+	.read		= proc_reg_read,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops_compat = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.splice_read	= copy_splice_read,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+#endif
+
+static void proc_put_link(void *p)
+{
+	unuse_pde(p);
+}
+
+static const char *proc_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	if (!use_pde(pde))
+		return ERR_PTR(-EINVAL);
+	set_delayed_call(done, proc_put_link, pde);
+	return pde->data;
+}
+
+const struct inode_operations proc_link_inode_operations = {
+	.get_link	= proc_get_link,
+};
+
+struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
+{
+	struct inode *inode = new_inode(sb);
+
+	if (!inode) {
+		pde_put(de);
+		return NULL;
+	}
+
+	inode->i_private = de->data;
+	inode->i_ino = de->low_ino;
+	simple_inode_init_ts(inode);
+	PROC_I(inode)->pde = de;
+	if (is_empty_pde(de)) {
+		make_empty_dir_inode(inode);
+		return inode;
+	}
+
+	if (de->mode) {
+		inode->i_mode = de->mode;
+		inode->i_uid = de->uid;
+		inode->i_gid = de->gid;
+	}
+	if (de->size)
+		inode->i_size = de->size;
+	if (de->nlink)
+		set_nlink(inode, de->nlink);
+
+	if (S_ISREG(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		if (pde_has_proc_read_iter(de))
+			inode->i_fop = &proc_iter_file_ops;
+		else
+			inode->i_fop = &proc_reg_file_ops;
+#ifdef CONFIG_COMPAT
+		if (pde_has_proc_compat_ioctl(de)) {
+			if (pde_has_proc_read_iter(de))
+				inode->i_fop = &proc_iter_file_ops_compat;
+			else
+				inode->i_fop = &proc_reg_file_ops_compat;
+		}
+#endif
+	} else if (S_ISDIR(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		inode->i_fop = de->proc_dir_ops;
+	} else if (S_ISLNK(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		inode->i_fop = NULL;
+	} else {
+		BUG();
+	}
+	return inode;
+}

linux-7.2.3/fs/proc/internal.h

@@ -0,0 +1,437 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Internal procfs definitions
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/proc_ns.h>
+#include <linux/refcount.h>
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
+#include <linux/binfmts.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/task.h>
+#include <linux/mm.h>
+
+struct ctl_table_header;
+struct mempolicy;
+
+/*
+ * This is not completely implemented yet. The idea is to
+ * create an in-memory tree (like the actual /proc filesystem
+ * tree) of these proc_dir_entries, so that we can dynamically
+ * add new files to /proc.
+ *
+ * parent/subdir are used for the directory structure (every /proc file has a
+ * parent, but "subdir" is empty for all non-directory entries).
+ * subdir_node is used to build the rb tree "subdir" of the parent.
+ */
+struct proc_dir_entry {
+	/*
+	 * number of callers into module in progress;
+	 * negative -> it's going away RSN
+	 */
+	atomic_t in_use;
+	refcount_t refcnt;
+	struct list_head pde_openers;	/* who did ->open, but not ->release */
+	/* protects ->pde_openers and all struct pde_opener instances */
+	spinlock_t pde_unload_lock;
+	struct completion *pde_unload_completion;
+	const struct inode_operations *proc_iops;
+	union {
+		const struct proc_ops *proc_ops;
+		const struct file_operations *proc_dir_ops;
+	};
+	union {
+		const struct seq_operations *seq_ops;
+		int (*single_show)(struct seq_file *, void *);
+	};
+	proc_write_t write;
+	void *data;
+	unsigned int state_size;
+	unsigned int low_ino;
+	nlink_t nlink;
+	kuid_t uid;
+	kgid_t gid;
+	loff_t size;
+	struct proc_dir_entry *parent;
+	struct rb_root subdir;
+	struct rb_node subdir_node;
+	char *name;
+	umode_t mode;
+	u8 flags;
+	u8 namelen;
+	char inline_name[];
+} __randomize_layout;
+
+#define SIZEOF_PDE	(				\
+	sizeof(struct proc_dir_entry) < 128 ? 128 :	\
+	sizeof(struct proc_dir_entry) < 192 ? 192 :	\
+	sizeof(struct proc_dir_entry) < 256 ? 256 :	\
+	sizeof(struct proc_dir_entry) < 512 ? 512 :	\
+	0)
+#define SIZEOF_PDE_INLINE_NAME (SIZEOF_PDE - sizeof(struct proc_dir_entry))
+
+static inline bool pde_is_permanent(const struct proc_dir_entry *pde)
+{
+	return pde->flags & PROC_ENTRY_PERMANENT;
+}
+
+/* This is for builtin code, not even for modules which are compiled in. */
+static inline void pde_make_permanent(struct proc_dir_entry *pde)
+{
+	/* Ensure magic flag does something. */
+	static_assert(PROC_ENTRY_PERMANENT != 0);
+	pde->flags |= PROC_ENTRY_PERMANENT;
+}
+
+static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde)
+{
+	return pde->flags & PROC_ENTRY_proc_read_iter;
+}
+
+static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde)
+{
+#ifdef CONFIG_COMPAT
+	return pde->flags & PROC_ENTRY_proc_compat_ioctl;
+#else
+	return false;
+#endif
+}
+
+static inline bool pde_has_proc_lseek(const struct proc_dir_entry *pde)
+{
+	return pde->flags & PROC_ENTRY_proc_lseek;
+}
+
+extern struct kmem_cache *proc_dir_entry_cache;
+void pde_free(struct proc_dir_entry *pde);
+
+union proc_op {
+	int (*proc_get_link)(struct dentry *, struct path *, struct task_struct *);
+	int (*proc_show)(struct seq_file *m,
+		struct pid_namespace *ns, struct pid *pid,
+		struct task_struct *task);
+	int lsmid;
+};
+
+struct proc_inode {
+	struct pid *pid;
+	unsigned int fd;
+	union proc_op op;
+	struct proc_dir_entry *pde;
+	struct ctl_table_header *sysctl;
+	const struct ctl_table *sysctl_entry;
+	struct hlist_node sibling_inodes;
+	const struct proc_ns_operations *ns_ops;
+	struct inode vfs_inode;
+} __randomize_layout;
+
+/*
+ * General functions
+ */
+static inline struct proc_inode *PROC_I(const struct inode *inode)
+{
+	return container_of(inode, struct proc_inode, vfs_inode);
+}
+
+static inline struct proc_dir_entry *PDE(const struct inode *inode)
+{
+	return PROC_I(inode)->pde;
+}
+
+static inline struct pid *proc_pid(const struct inode *inode)
+{
+	return PROC_I(inode)->pid;
+}
+
+static inline struct task_struct *get_proc_task(const struct inode *inode)
+{
+	return get_pid_task(proc_pid(inode), PIDTYPE_PID);
+}
+
+void task_dump_owner(struct task_struct *task, umode_t mode,
+		     kuid_t *ruid, kgid_t *rgid);
+
+unsigned name_to_int(const struct qstr *qstr);
+/*
+ * Offset of the first process in the /proc root directory..
+ */
+#define FIRST_PROCESS_ENTRY 256
+
+/* Worst case buffer size needed for holding an integer. */
+#define PROC_NUMBUF 13
+
+#ifdef CONFIG_PAGE_MAPCOUNT
+/**
+ * folio_precise_page_mapcount() - Number of mappings of this folio page.
+ * @folio: The folio.
+ * @page: The page.
+ *
+ * The number of present user page table entries that reference this page
+ * as tracked via the RMAP: either referenced directly (PTE) or as part of
+ * a larger area that covers this page (e.g., PMD).
+ *
+ * Use this function only for the calculation of existing statistics
+ * (USS, PSS, mapcount_max) and for debugging purposes (/proc/kpagecount).
+ *
+ * Do not add new users.
+ *
+ * Returns: The number of mappings of this folio page. 0 for
+ * folios that are not mapped to user space or are not tracked via the RMAP
+ * (e.g., shared zeropage).
+ */
+static inline int folio_precise_page_mapcount(struct folio *folio,
+		struct page *page)
+{
+	int mapcount = atomic_read(&page->_mapcount) + 1;
+
+	if (page_mapcount_is_type(mapcount))
+		mapcount = 0;
+	if (folio_test_large(folio))
+		mapcount += folio_entire_mapcount(folio);
+
+	return mapcount;
+}
+#else /* !CONFIG_PAGE_MAPCOUNT */
+static inline int folio_precise_page_mapcount(struct folio *folio,
+		struct page *page)
+{
+	BUILD_BUG();
+}
+#endif /* CONFIG_PAGE_MAPCOUNT */
+
+/**
+ * folio_average_page_mapcount() - Average number of mappings per page in this
+ *				   folio
+ * @folio: The folio.
+ *
+ * The average number of user page table entries that reference each page in
+ * this folio as tracked via the RMAP: either referenced directly (PTE) or
+ * as part of a larger area that covers this page (e.g., PMD).
+ *
+ * The average is calculated by rounding to the nearest integer; however,
+ * to avoid duplicated code in current callers, the average is at least
+ * 1 if any page of the folio is mapped.
+ *
+ * Returns: The average number of mappings per page in this folio.
+ */
+static inline int folio_average_page_mapcount(struct folio *folio)
+{
+	int mapcount, entire_mapcount, avg;
+
+	if (!folio_test_large(folio))
+		return atomic_read(&folio->_mapcount) + 1;
+
+	mapcount = folio_large_mapcount(folio);
+	if (unlikely(mapcount <= 0))
+		return 0;
+	entire_mapcount = folio_entire_mapcount(folio);
+	if (mapcount <= entire_mapcount)
+		return entire_mapcount;
+	mapcount -= entire_mapcount;
+
+	/* Round to closest integer ... */
+	avg = ((unsigned int)mapcount + folio_large_nr_pages(folio) / 2) >> folio_large_order(folio);
+	/* ... but return at least 1. */
+	return max_t(int, avg + entire_mapcount, 1);
+}
+/*
+ * array.c
+ */
+extern const struct file_operations proc_tid_children_operations;
+
+extern void proc_task_name(struct seq_file *m, struct task_struct *p,
+			   bool escape);
+extern int proc_tid_stat(struct seq_file *, struct pid_namespace *,
+			 struct pid *, struct task_struct *);
+extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *,
+			  struct pid *, struct task_struct *);
+extern int proc_pid_status(struct seq_file *, struct pid_namespace *,
+			   struct pid *, struct task_struct *);
+extern int proc_pid_statm(struct seq_file *, struct pid_namespace *,
+			  struct pid *, struct task_struct *);
+
+/*
+ * base.c
+ */
+extern const struct dentry_operations pid_dentry_operations;
+extern int pid_getattr(struct mnt_idmap *, const struct path *,
+		       struct kstat *, u32, unsigned int);
+int proc_nochmod_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			struct iattr *attr);
+extern void proc_pid_evict_inode(struct proc_inode *);
+extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t);
+extern void pid_update_inode(struct task_struct *, struct inode *);
+extern int pid_delete_dentry(const struct dentry *);
+extern int proc_pid_readdir(struct file *, struct dir_context *);
+struct dentry *proc_pid_lookup(struct dentry *, unsigned int);
+extern loff_t mem_lseek(struct file *, loff_t, int);
+
+/* Lookups */
+typedef struct dentry *instantiate_t(struct dentry *,
+				     struct task_struct *, const void *);
+bool proc_fill_cache(struct file *, struct dir_context *, const char *, unsigned int,
+			   instantiate_t, struct task_struct *, const void *);
+
+/*
+ * generic.c
+ */
+struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
+		struct proc_dir_entry **parent, void *data);
+struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
+		struct proc_dir_entry *dp);
+extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
+struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_entry *);
+extern int proc_readdir(struct file *, struct dir_context *);
+int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry *);
+
+static inline void pde_get(struct proc_dir_entry *pde)
+{
+	refcount_inc(&pde->refcnt);
+}
+extern void pde_put(struct proc_dir_entry *);
+
+static inline bool is_empty_pde(const struct proc_dir_entry *pde)
+{
+	return S_ISDIR(pde->mode) && !pde->proc_iops;
+}
+extern ssize_t proc_simple_write(struct file *, const char __user *, size_t, loff_t *);
+
+/*
+ * inode.c
+ */
+struct pde_opener {
+	struct list_head lh;
+	struct file *file;
+	bool closing;
+	struct completion *c;
+} __randomize_layout;
+extern const struct inode_operations proc_link_inode_operations;
+extern const struct inode_operations proc_pid_link_inode_operations;
+extern const struct super_operations proc_sops;
+
+void proc_init_kmemcache(void);
+void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock);
+void set_proc_pid_nlink(void);
+extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
+extern void proc_entry_rundown(struct proc_dir_entry *);
+
+/*
+ * proc_namespaces.c
+ */
+extern const struct inode_operations proc_ns_dir_inode_operations;
+extern const struct file_operations proc_ns_dir_operations;
+
+/*
+ * proc_net.c
+ */
+extern const struct file_operations proc_net_operations;
+extern const struct inode_operations proc_net_inode_operations;
+
+#ifdef CONFIG_NET
+extern int proc_net_init(void);
+#else
+static inline int proc_net_init(void) { return 0; }
+#endif
+
+/*
+ * proc_self.c
+ */
+extern int proc_setup_self(struct super_block *);
+
+/*
+ * proc_thread_self.c
+ */
+extern int proc_setup_thread_self(struct super_block *);
+extern void proc_thread_self_init(void);
+
+/*
+ * proc_sysctl.c
+ */
+#ifdef CONFIG_PROC_SYSCTL
+extern int proc_sys_init(void);
+extern void proc_sys_evict_inode(struct inode *inode,
+				 struct ctl_table_header *head);
+#else
+static inline void proc_sys_init(void) { }
+static inline void proc_sys_evict_inode(struct  inode *inode,
+					struct ctl_table_header *head) { }
+#endif
+
+/*
+ * proc_tty.c
+ */
+#ifdef CONFIG_TTY
+extern void proc_tty_init(void);
+#else
+static inline void proc_tty_init(void) {}
+#endif
+
+/*
+ * root.c
+ */
+extern struct proc_dir_entry proc_root;
+
+extern void proc_self_init(void);
+extern unsigned self_inum, thread_self_inum;
+
+/*
+ * task_[no]mmu.c
+ */
+struct mem_size_stats;
+
+struct proc_maps_locking_ctx {
+	struct mm_struct *mm;
+#ifdef CONFIG_PER_VMA_LOCK
+	bool mmap_locked;
+	struct vm_area_struct *locked_vma;
+#endif
+};
+
+struct proc_maps_private {
+	struct inode *inode;
+	struct task_struct *task;
+	struct vma_iterator iter;
+	loff_t last_pos;
+	struct proc_maps_locking_ctx lock_ctx;
+#ifdef CONFIG_NUMA
+	struct mempolicy *task_mempolicy;
+#endif
+} __randomize_layout;
+
+struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode);
+
+extern const struct file_operations proc_pid_maps_operations;
+extern const struct file_operations proc_pid_numa_maps_operations;
+extern const struct file_operations proc_pid_smaps_operations;
+extern const struct file_operations proc_pid_smaps_rollup_operations;
+extern const struct file_operations proc_clear_refs_operations;
+extern const struct file_operations proc_pagemap_operations;
+
+extern unsigned long task_vsize(struct mm_struct *);
+extern unsigned long task_statm(struct mm_struct *,
+				unsigned long *, unsigned long *,
+				unsigned long *, unsigned long *);
+extern void task_mem(struct seq_file *, struct mm_struct *);
+
+extern const struct dentry_operations proc_net_dentry_ops;
+static inline void pde_force_lookup(struct proc_dir_entry *pde)
+{
+	/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
+	pde->flags |= PROC_ENTRY_FORCE_LOOKUP;
+}
+
+/*
+ * Add a new procfs dentry that can't serve as a mountpoint. That should
+ * encompass anything that is ephemeral and can just disappear while the
+ * process is still around.
+ */
+static inline struct dentry *proc_splice_unmountable(struct inode *inode,
+		struct dentry *dentry, const struct dentry_operations *d_ops)
+{
+	dont_mount(dentry);
+	return d_splice_alias_ops(inode, dentry, d_ops);
+}

linux-7.2.3/fs/proc/interrupts.c

@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irqnr.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+/*
+ * /proc/interrupts
+ */
+static void *int_seq_start(struct seq_file *f, loff_t *pos)
+{
+	return *pos <= irq_get_nr_irqs() ? pos : NULL;
+}
+
+static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos)
+{
+	(*pos)++;
+	if (*pos > irq_get_nr_irqs())
+		return NULL;
+	return pos;
+}
+
+static void int_seq_stop(struct seq_file *f, void *v)
+{
+	/* Nothing to do */
+}
+
+static const struct seq_operations int_seq_ops = {
+	.start = int_seq_start,
+	.next  = int_seq_next,
+	.stop  = int_seq_stop,
+	.show  = show_interrupts
+};
+
+static int __init proc_interrupts_init(void)
+{
+	proc_create_seq("interrupts", 0, NULL, &int_seq_ops);
+	return 0;
+}
+fs_initcall(proc_interrupts_init);

linux-7.2.3/fs/proc/kcore.c

@@ -0,0 +1,742 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *	fs/proc/kcore.c kernel ELF core dumper
+ *
+ *	Modelled on fs/exec.c:aout_core_dump()
+ *	Jeremy Fitzhardinge <jeremy@sw.oz.au>
+ *	ELF version written by David Howells <David.Howells@nexor.co.uk>
+ *	Modified and incorporated into 2.3.x by Tigran Aivazian <tigran@veritas.com>
+ *	Support to dump vmalloc'd areas (ELF only), Tigran Aivazian <tigran@veritas.com>
+ *	Safe accesses to vmalloc/direct-mapped discontiguous areas, Kanoj Sarcar <kanoj@sgi.com>
+ */
+
+#include <linux/vmcore_info.h>
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/kcore.h>
+#include <linux/user.h>
+#include <linux/capability.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/vmalloc.h>
+#include <linux/highmem.h>
+#include <linux/printk.h>
+#include <linux/memblock.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/uio.h>
+#include <asm/io.h>
+#include <linux/list.h>
+#include <linux/ioport.h>
+#include <linux/memory.h>
+#include <linux/sched/task.h>
+#include <linux/security.h>
+#include <asm/sections.h>
+#include "internal.h"
+
+#ifndef ELF_CORE_EFLAGS
+#define ELF_CORE_EFLAGS	0
+#endif
+
+static struct proc_dir_entry *proc_root_kcore;
+
+
+#ifndef kc_vaddr_to_offset
+#define	kc_vaddr_to_offset(v) ((v) - PAGE_OFFSET)
+#endif
+#ifndef	kc_offset_to_vaddr
+#define	kc_offset_to_vaddr(o) ((o) + PAGE_OFFSET)
+#endif
+
+#ifndef kc_xlate_dev_mem_ptr
+#define kc_xlate_dev_mem_ptr kc_xlate_dev_mem_ptr
+static inline void *kc_xlate_dev_mem_ptr(phys_addr_t phys)
+{
+	return __va(phys);
+}
+#endif
+#ifndef kc_unxlate_dev_mem_ptr
+#define kc_unxlate_dev_mem_ptr kc_unxlate_dev_mem_ptr
+static inline void kc_unxlate_dev_mem_ptr(phys_addr_t phys, void *virt)
+{
+}
+#endif
+
+static LIST_HEAD(kclist_head);
+static int kcore_nphdr;
+static size_t kcore_phdrs_len;
+static size_t kcore_notes_len;
+static size_t kcore_data_offset;
+DEFINE_STATIC_PERCPU_RWSEM(kclist_lock);
+static int kcore_need_update = 1;
+
+/*
+ * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
+ * Same as oldmem_pfn_is_ram in vmcore
+ */
+static int (*mem_pfn_is_ram)(unsigned long pfn);
+
+int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn))
+{
+	if (mem_pfn_is_ram)
+		return -EBUSY;
+	mem_pfn_is_ram = fn;
+	return 0;
+}
+
+static int pfn_is_ram(unsigned long pfn)
+{
+	if (mem_pfn_is_ram)
+		return mem_pfn_is_ram(pfn);
+	else
+		return 1;
+}
+
+/* This doesn't grab kclist_lock, so it should only be used at init time. */
+void __init kclist_add(struct kcore_list *new, void *addr, size_t size,
+		       int type)
+{
+	new->addr = (unsigned long)addr;
+	new->size = size;
+	new->type = type;
+
+	list_add_tail(&new->list, &kclist_head);
+}
+
+static void update_kcore_size(void)
+{
+	size_t try, size;
+	struct kcore_list *m;
+
+	kcore_nphdr = 1; /* PT_NOTE */
+	size = 0;
+
+	list_for_each_entry(m, &kclist_head, list) {
+		try = kc_vaddr_to_offset((size_t)m->addr + m->size);
+		if (try > size)
+			size = try;
+		kcore_nphdr++;
+	}
+
+	kcore_phdrs_len = kcore_nphdr * sizeof(struct elf_phdr);
+	kcore_notes_len = (4 * sizeof(struct elf_note) +
+			   ALIGN(sizeof(NN_PRSTATUS), 4) +
+			   ALIGN(sizeof(NN_PRPSINFO), 4) +
+			   ALIGN(sizeof(NN_TASKSTRUCT), 4) +
+			   VMCOREINFO_NOTE_NAME_BYTES +
+			   ALIGN(sizeof(struct elf_prstatus), 4) +
+			   ALIGN(sizeof(struct elf_prpsinfo), 4) +
+			   ALIGN(arch_task_struct_size, 4) +
+			   ALIGN(vmcoreinfo_size, 4));
+	kcore_data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + kcore_phdrs_len +
+				       kcore_notes_len);
+	proc_root_kcore->size = kcore_data_offset + size;
+}
+
+#ifdef CONFIG_HIGHMEM
+/*
+ * If no highmem, we can assume [0...max_low_pfn) continuous range of memory
+ * because memory hole is not as big as !HIGHMEM case.
+ * (HIGHMEM is special because part of memory is _invisible_ from the kernel.)
+ */
+static int kcore_ram_list(struct list_head *head)
+{
+	struct kcore_list *ent;
+
+	ent = kmalloc_obj(*ent);
+	if (!ent)
+		return -ENOMEM;
+	ent->addr = (unsigned long)__va(0);
+	ent->size = max_low_pfn << PAGE_SHIFT;
+	ent->type = KCORE_RAM;
+	list_add(&ent->list, head);
+	return 0;
+}
+
+#else /* !CONFIG_HIGHMEM */
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+/* calculate vmemmap's address from given system ram pfn and register it */
+static int
+get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
+{
+	unsigned long pfn = __pa(ent->addr) >> PAGE_SHIFT;
+	unsigned long nr_pages = ent->size >> PAGE_SHIFT;
+	unsigned long start, end;
+	struct kcore_list *vmm, *tmp;
+
+
+	start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK;
+	end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1;
+	end = PAGE_ALIGN(end);
+	/* overlap check (because we have to align page */
+	list_for_each_entry(tmp, head, list) {
+		if (tmp->type != KCORE_VMEMMAP)
+			continue;
+		if (start < tmp->addr + tmp->size)
+			if (end > tmp->addr)
+				end = tmp->addr;
+	}
+	if (start < end) {
+		vmm = kmalloc_obj(*vmm);
+		if (!vmm)
+			return 0;
+		vmm->addr = start;
+		vmm->size = end - start;
+		vmm->type = KCORE_VMEMMAP;
+		list_add_tail(&vmm->list, head);
+	}
+	return 1;
+
+}
+#else
+static int
+get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
+{
+	return 1;
+}
+
+#endif
+
+static int
+kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg)
+{
+	struct list_head *head = (struct list_head *)arg;
+	struct kcore_list *ent;
+	struct page *p;
+
+	if (!pfn_valid(pfn))
+		return 1;
+
+	p = pfn_to_page(pfn);
+
+	ent = kmalloc_obj(*ent);
+	if (!ent)
+		return -ENOMEM;
+	ent->addr = (unsigned long)page_to_virt(p);
+	ent->size = nr_pages << PAGE_SHIFT;
+
+	if (!virt_addr_valid((void *)ent->addr))
+		goto free_out;
+
+	/* cut not-mapped area. ....from ppc-32 code. */
+	if (ULONG_MAX - ent->addr < ent->size)
+		ent->size = ULONG_MAX - ent->addr;
+
+	/*
+	 * We've already checked virt_addr_valid so we know this address
+	 * is a valid pointer, therefore we can check against it to determine
+	 * if we need to trim
+	 */
+	if (VMALLOC_START > ent->addr) {
+		if (VMALLOC_START - ent->addr < ent->size)
+			ent->size = VMALLOC_START - ent->addr;
+	}
+
+	ent->type = KCORE_RAM;
+	list_add_tail(&ent->list, head);
+
+	if (!get_sparsemem_vmemmap_info(ent, head)) {
+		list_del(&ent->list);
+		goto free_out;
+	}
+
+	return 0;
+free_out:
+	kfree(ent);
+	return 1;
+}
+
+static int kcore_ram_list(struct list_head *list)
+{
+	int nid, ret;
+	unsigned long end_pfn;
+
+	/* Not initialized....update now */
+	/* find out "max pfn" */
+	end_pfn = 0;
+	for_each_node_state(nid, N_MEMORY) {
+		unsigned long node_end;
+		node_end = node_end_pfn(nid);
+		if (end_pfn < node_end)
+			end_pfn = node_end;
+	}
+	/* scan 0 to max_pfn */
+	ret = walk_system_ram_range(0, end_pfn, list, kclist_add_private);
+	if (ret)
+		return -ENOMEM;
+	return 0;
+}
+#endif /* CONFIG_HIGHMEM */
+
+static int kcore_update_ram(void)
+{
+	LIST_HEAD(list);
+	LIST_HEAD(garbage);
+	struct kcore_list *tmp, *pos;
+	int ret = 0;
+
+	percpu_down_write(&kclist_lock);
+	if (!xchg(&kcore_need_update, 0))
+		goto out;
+
+	ret = kcore_ram_list(&list);
+	if (ret) {
+		/* Couldn't get the RAM list, try again next time. */
+		WRITE_ONCE(kcore_need_update, 1);
+		list_splice_tail(&list, &garbage);
+		goto out;
+	}
+
+	list_for_each_entry_safe(pos, tmp, &kclist_head, list) {
+		if (pos->type == KCORE_RAM || pos->type == KCORE_VMEMMAP)
+			list_move(&pos->list, &garbage);
+	}
+	list_splice_tail(&list, &kclist_head);
+
+	update_kcore_size();
+
+out:
+	percpu_up_write(&kclist_lock);
+	list_for_each_entry_safe(pos, tmp, &garbage, list) {
+		list_del(&pos->list);
+		kfree(pos);
+	}
+	return ret;
+}
+
+static void append_kcore_note(char *notes, size_t *i, const char *name,
+			      unsigned int type, const void *desc,
+			      size_t descsz)
+{
+	struct elf_note *note = (struct elf_note *)&notes[*i];
+
+	note->n_namesz = strlen(name) + 1;
+	note->n_descsz = descsz;
+	note->n_type = type;
+	*i += sizeof(*note);
+	memcpy(&notes[*i], name, note->n_namesz);
+	*i = ALIGN(*i + note->n_namesz, 4);
+	memcpy(&notes[*i], desc, descsz);
+	*i = ALIGN(*i + descsz, 4);
+}
+
+static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	char *buf = file->private_data;
+	loff_t *fpos = &iocb->ki_pos;
+	size_t phdrs_offset, notes_offset;
+	size_t page_offline_frozen = 1;
+	struct kcore_list *m;
+	size_t tsz;
+	unsigned long start;
+	size_t buflen = iov_iter_count(iter);
+	size_t orig_buflen = buflen;
+	int ret = 0;
+
+	percpu_down_read(&kclist_lock);
+	/*
+	 * Don't race against drivers that set PageOffline() and expect no
+	 * further page access.
+	 */
+	page_offline_freeze();
+
+	phdrs_offset = sizeof(struct elfhdr);
+	notes_offset = phdrs_offset + kcore_phdrs_len;
+
+	/* ELF file header. */
+	if (buflen && *fpos < sizeof(struct elfhdr)) {
+		struct elfhdr ehdr = {
+			.e_ident = {
+				[EI_MAG0] = ELFMAG0,
+				[EI_MAG1] = ELFMAG1,
+				[EI_MAG2] = ELFMAG2,
+				[EI_MAG3] = ELFMAG3,
+				[EI_CLASS] = ELF_CLASS,
+				[EI_DATA] = ELF_DATA,
+				[EI_VERSION] = EV_CURRENT,
+				[EI_OSABI] = ELF_OSABI,
+			},
+			.e_type = ET_CORE,
+			.e_machine = ELF_ARCH,
+			.e_version = EV_CURRENT,
+			.e_phoff = sizeof(struct elfhdr),
+			.e_flags = ELF_CORE_EFLAGS,
+			.e_ehsize = sizeof(struct elfhdr),
+			.e_phentsize = sizeof(struct elf_phdr),
+			.e_phnum = kcore_nphdr,
+		};
+
+		tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos);
+		if (copy_to_iter((char *)&ehdr + *fpos, tsz, iter) != tsz) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		buflen -= tsz;
+		*fpos += tsz;
+	}
+
+	/* ELF program headers. */
+	if (buflen && *fpos < phdrs_offset + kcore_phdrs_len) {
+		struct elf_phdr *phdrs, *phdr;
+
+		phdrs = kzalloc(kcore_phdrs_len, GFP_KERNEL);
+		if (!phdrs) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		phdrs[0].p_type = PT_NOTE;
+		phdrs[0].p_offset = notes_offset;
+		phdrs[0].p_filesz = kcore_notes_len;
+
+		phdr = &phdrs[1];
+		list_for_each_entry(m, &kclist_head, list) {
+			phdr->p_type = PT_LOAD;
+			phdr->p_flags = PF_R | PF_W | PF_X;
+			phdr->p_offset = kc_vaddr_to_offset(m->addr)
+					 + kcore_data_offset;
+			phdr->p_vaddr = (size_t)m->addr;
+			if (m->type == KCORE_RAM)
+				phdr->p_paddr = __pa(m->addr);
+			else if (m->type == KCORE_TEXT)
+				phdr->p_paddr = __pa_symbol(m->addr);
+			else
+				phdr->p_paddr = (elf_addr_t)-1;
+			phdr->p_filesz = phdr->p_memsz = m->size;
+			phdr->p_align = PAGE_SIZE;
+			phdr++;
+		}
+
+		tsz = min_t(size_t, buflen,
+			    phdrs_offset + kcore_phdrs_len - *fpos);
+		if (copy_to_iter((char *)phdrs + *fpos - phdrs_offset, tsz,
+				 iter) != tsz) {
+			kfree(phdrs);
+			ret = -EFAULT;
+			goto out;
+		}
+		kfree(phdrs);
+
+		buflen -= tsz;
+		*fpos += tsz;
+	}
+
+	/* ELF note segment. */
+	if (buflen && *fpos < notes_offset + kcore_notes_len) {
+		struct elf_prstatus prstatus = {};
+		struct elf_prpsinfo prpsinfo = {
+			.pr_sname = 'R',
+			.pr_fname = "vmlinux",
+		};
+		char *notes;
+		size_t i = 0;
+
+		strscpy(prpsinfo.pr_psargs, saved_command_line,
+			sizeof(prpsinfo.pr_psargs));
+
+		notes = kzalloc(kcore_notes_len, GFP_KERNEL);
+		if (!notes) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		append_kcore_note(notes, &i, NN_PRSTATUS, NT_PRSTATUS, &prstatus,
+				  sizeof(prstatus));
+		append_kcore_note(notes, &i, NN_PRPSINFO, NT_PRPSINFO, &prpsinfo,
+				  sizeof(prpsinfo));
+		append_kcore_note(notes, &i, NN_TASKSTRUCT, NT_TASKSTRUCT, current,
+				  arch_task_struct_size);
+		/*
+		 * vmcoreinfo_size is mostly constant after init time, but it
+		 * can be changed by crash_save_vmcoreinfo(). Racing here with a
+		 * panic on another CPU before the machine goes down is insanely
+		 * unlikely, but it's better to not leave potential buffer
+		 * overflows lying around, regardless.
+		 */
+		append_kcore_note(notes, &i, VMCOREINFO_NOTE_NAME, 0,
+				  vmcoreinfo_data,
+				  min(vmcoreinfo_size, kcore_notes_len - i));
+
+		tsz = min_t(size_t, buflen,
+			    notes_offset + kcore_notes_len - *fpos);
+		if (copy_to_iter(notes + *fpos - notes_offset, tsz, iter) != tsz) {
+			kfree(notes);
+			ret = -EFAULT;
+			goto out;
+		}
+		kfree(notes);
+
+		buflen -= tsz;
+		*fpos += tsz;
+	}
+
+	/*
+	 * Check to see if our file offset matches with any of
+	 * the addresses in the elf_phdr on our list.
+	 */
+	start = kc_offset_to_vaddr(*fpos - kcore_data_offset);
+	if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
+		tsz = buflen;
+
+	m = NULL;
+	while (buflen) {
+		struct page *page;
+		unsigned long pfn;
+		phys_addr_t phys;
+		void *__start;
+
+		/*
+		 * If this is the first iteration or the address is not within
+		 * the previous entry, search for a matching entry.
+		 */
+		if (!m || start < m->addr || start >= m->addr + m->size) {
+			struct kcore_list *pos;
+
+			m = NULL;
+			list_for_each_entry(pos, &kclist_head, list) {
+				if (start >= pos->addr &&
+				    start < pos->addr + pos->size) {
+					m = pos;
+					break;
+				}
+			}
+		}
+
+		if (page_offline_frozen++ % MAX_ORDER_NR_PAGES == 0) {
+			page_offline_thaw();
+			cond_resched();
+			page_offline_freeze();
+		}
+
+		if (!m) {
+			if (iov_iter_zero(tsz, iter) != tsz) {
+				ret = -EFAULT;
+				goto out;
+			}
+			goto skip;
+		}
+
+		switch (m->type) {
+		case KCORE_VMALLOC:
+		{
+			const char *src = (char *)start;
+			size_t read = 0, left = tsz;
+
+			/*
+			 * vmalloc uses spinlocks, so we optimistically try to
+			 * read memory. If this fails, fault pages in and try
+			 * again until we are done.
+			 */
+			while (true) {
+				read += vread_iter(iter, src, left);
+				if (read == tsz)
+					break;
+
+				src += read;
+				left -= read;
+
+				if (fault_in_iov_iter_writeable(iter, left)) {
+					ret = -EFAULT;
+					goto out;
+				}
+			}
+			break;
+		}
+		case KCORE_USER:
+			/* User page is handled prior to normal kernel page: */
+			if (copy_to_iter((char *)start, tsz, iter) != tsz) {
+				ret = -EFAULT;
+				goto out;
+			}
+			break;
+		case KCORE_RAM:
+			phys = __pa(start);
+			pfn =  phys >> PAGE_SHIFT;
+			page = pfn_to_online_page(pfn);
+
+			/*
+			 * Don't read offline sections, logically offline pages
+			 * (e.g., inflated in a balloon), hwpoisoned pages,
+			 * and explicitly excluded physical ranges.
+			 */
+			if (!page || PageOffline(page) ||
+			    is_page_hwpoison(page) || !pfn_is_ram(pfn) ||
+			    pfn_is_unaccepted_memory(pfn)) {
+				if (iov_iter_zero(tsz, iter) != tsz) {
+					ret = -EFAULT;
+					goto out;
+				}
+				break;
+			}
+			fallthrough;
+		case KCORE_VMEMMAP:
+		case KCORE_TEXT:
+			if (m->type == KCORE_RAM) {
+				__start = kc_xlate_dev_mem_ptr(phys);
+				if (!__start) {
+					ret = -ENOMEM;
+					if (iov_iter_zero(tsz, iter) != tsz)
+						ret = -EFAULT;
+					goto out;
+				}
+			} else {
+				__start = (void *)start;
+			}
+
+			/*
+			 * Sadly we must use a bounce buffer here to be able to
+			 * make use of copy_from_kernel_nofault(), as these
+			 * memory regions might not always be mapped on all
+			 * architectures.
+			 */
+			ret = copy_from_kernel_nofault(buf, __start, tsz);
+			if (m->type == KCORE_RAM)
+				kc_unxlate_dev_mem_ptr(phys, __start);
+			if (ret) {
+				if (iov_iter_zero(tsz, iter) != tsz) {
+					ret = -EFAULT;
+					goto out;
+				}
+				ret = 0;
+			/*
+			 * We know the bounce buffer is safe to copy from, so
+			 * use _copy_to_iter() directly.
+			 */
+			} else if (_copy_to_iter(buf, tsz, iter) != tsz) {
+				ret = -EFAULT;
+				goto out;
+			}
+			break;
+		default:
+			pr_warn_once("Unhandled KCORE type: %d\n", m->type);
+			if (iov_iter_zero(tsz, iter) != tsz) {
+				ret = -EFAULT;
+				goto out;
+			}
+		}
+skip:
+		buflen -= tsz;
+		*fpos += tsz;
+		start += tsz;
+		tsz = (buflen > PAGE_SIZE ? PAGE_SIZE : buflen);
+	}
+
+out:
+	page_offline_thaw();
+	percpu_up_read(&kclist_lock);
+	if (ret)
+		return ret;
+	return orig_buflen - buflen;
+}
+
+static int open_kcore(struct inode *inode, struct file *filp)
+{
+	int ret = security_locked_down(LOCKDOWN_KCORE);
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	if (ret)
+		return ret;
+
+	filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!filp->private_data)
+		return -ENOMEM;
+
+	if (kcore_need_update)
+		kcore_update_ram();
+	if (i_size_read(inode) != proc_root_kcore->size) {
+		inode_lock(inode);
+		i_size_write(inode, proc_root_kcore->size);
+		inode_unlock(inode);
+	}
+	return 0;
+}
+
+static int release_kcore(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static const struct proc_ops kcore_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_read_iter	= read_kcore_iter,
+	.proc_open	= open_kcore,
+	.proc_release	= release_kcore,
+	.proc_lseek	= default_llseek,
+};
+
+/* just remember that we have to update kcore */
+static int __meminit kcore_callback(struct notifier_block *self,
+				    unsigned long action, void *arg)
+{
+	switch (action) {
+	case MEM_ONLINE:
+	case MEM_OFFLINE:
+		kcore_need_update = 1;
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+
+static struct kcore_list kcore_vmalloc;
+
+#ifdef CONFIG_ARCH_PROC_KCORE_TEXT
+static struct kcore_list kcore_text;
+/*
+ * If defined, special segment is used for mapping kernel text instead of
+ * direct-map area. We need to create special TEXT section.
+ */
+static void __init proc_kcore_text_init(void)
+{
+	kclist_add(&kcore_text, _text, _end - _text, KCORE_TEXT);
+}
+#else
+static void __init proc_kcore_text_init(void)
+{
+}
+#endif
+
+#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
+/*
+ * MODULES_VADDR has no intersection with VMALLOC_ADDR.
+ */
+static struct kcore_list kcore_modules;
+static void __init add_modules_range(void)
+{
+	if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) {
+		kclist_add(&kcore_modules, (void *)MODULES_VADDR,
+			MODULES_END - MODULES_VADDR, KCORE_VMALLOC);
+	}
+}
+#else
+static void __init add_modules_range(void)
+{
+}
+#endif
+
+static int __init proc_kcore_init(void)
+{
+	proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &kcore_proc_ops);
+	if (!proc_root_kcore) {
+		pr_err("couldn't create /proc/kcore\n");
+		return 0; /* Always returns 0. */
+	}
+	/* Store text area if it's special */
+	proc_kcore_text_init();
+	/* Store vmalloc area */
+	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
+		VMALLOC_END - VMALLOC_START, KCORE_VMALLOC);
+	add_modules_range();
+	/* Store direct-map area from physical memory map */
+	kcore_update_ram();
+	hotplug_memory_notifier(kcore_callback, DEFAULT_CALLBACK_PRI);
+
+	return 0;
+}
+fs_initcall(proc_kcore_init);

linux-7.2.3/fs/proc/kmsg.c

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/proc/kmsg.c
+ *
+ *  Copyright (C) 1992  by Linus Torvalds
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/fs.h>
+#include <linux/syslog.h>
+
+#include <asm/io.h>
+
+static int kmsg_open(struct inode * inode, struct file * file)
+{
+	return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC);
+}
+
+static int kmsg_release(struct inode * inode, struct file * file)
+{
+	(void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_PROC);
+	return 0;
+}
+
+static ssize_t kmsg_read(struct file *file, char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	if ((file->f_flags & O_NONBLOCK) &&
+	    !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
+		return -EAGAIN;
+	return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_PROC);
+}
+
+static __poll_t kmsg_poll(struct file *file, poll_table *wait)
+{
+	poll_wait(file, &log_wait, wait);
+	if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
+		return EPOLLIN | EPOLLRDNORM;
+	return 0;
+}
+
+
+static const struct proc_ops kmsg_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_read	= kmsg_read,
+	.proc_poll	= kmsg_poll,
+	.proc_open	= kmsg_open,
+	.proc_release	= kmsg_release,
+	.proc_lseek	= generic_file_llseek,
+};
+
+static int __init proc_kmsg_init(void)
+{
+	proc_create("kmsg", S_IRUSR, NULL, &kmsg_proc_ops);
+	return 0;
+}
+fs_initcall(proc_kmsg_init);

linux-7.2.3/fs/proc/loadavg.c

@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/pid_namespace.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/sched/loadavg.h>
+#include <linux/sched/stat.h>
+#include <linux/seq_file.h>
+#include <linux/seqlock.h>
+#include <linux/time.h>
+#include "internal.h"
+
+static int loadavg_proc_show(struct seq_file *m, void *v)
+{
+	unsigned long avnrun[3];
+
+	get_avenrun(avnrun, FIXED_1/200, 0);
+
+	seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %u/%d %d\n",
+		LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]),
+		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
+		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
+		nr_running(), nr_threads,
+		idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
+	return 0;
+}
+
+static int __init proc_loadavg_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = proc_create_single("loadavg", 0, NULL, loadavg_proc_show);
+	pde_make_permanent(pde);
+	return 0;
+}
+fs_initcall(proc_loadavg_init);

linux-7.2.3/fs/proc/meminfo.c

@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/mman.h>
+#include <linux/mmzone.h>
+#include <linux/memblock.h>
+#include <linux/proc_fs.h>
+#include <linux/percpu.h>
+#include <linux/seq_file.h>
+#include <linux/swap.h>
+#include <linux/vmstat.h>
+#include <linux/atomic.h>
+#include <linux/vmalloc.h>
+#ifdef CONFIG_CMA
+#include <linux/cma.h>
+#endif
+#include <linux/zswap.h>
+#include <asm/page.h>
+#include "internal.h"
+
+void __attribute__((weak)) arch_report_meminfo(struct seq_file *m)
+{
+}
+
+static void show_val_kb(struct seq_file *m, const char *s, unsigned long num)
+{
+	seq_put_decimal_ull_width(m, s, num << (PAGE_SHIFT - 10), 8);
+	seq_write(m, " kB\n", 4);
+}
+
+static int meminfo_proc_show(struct seq_file *m, void *v)
+{
+	struct sysinfo i;
+	unsigned long committed;
+	long cached;
+	long available;
+	unsigned long pages[NR_LRU_LISTS];
+	unsigned long sreclaimable, sunreclaim;
+	int lru;
+
+	si_meminfo(&i);
+	si_swapinfo(&i);
+	committed = vm_memory_committed();
+
+	cached = global_node_page_state(NR_FILE_PAGES) -
+			total_swapcache_pages() - i.bufferram;
+	if (cached < 0)
+		cached = 0;
+
+	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+		pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
+
+	available = si_mem_available();
+	sreclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B);
+	sunreclaim = global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B);
+
+	show_val_kb(m, "MemTotal:       ", i.totalram);
+	show_val_kb(m, "MemFree:        ", i.freeram);
+	show_val_kb(m, "MemAvailable:   ", available);
+	show_val_kb(m, "Buffers:        ", i.bufferram);
+	show_val_kb(m, "Cached:         ", cached);
+	show_val_kb(m, "SwapCached:     ", total_swapcache_pages());
+	show_val_kb(m, "Active:         ", pages[LRU_ACTIVE_ANON] +
+					   pages[LRU_ACTIVE_FILE]);
+	show_val_kb(m, "Inactive:       ", pages[LRU_INACTIVE_ANON] +
+					   pages[LRU_INACTIVE_FILE]);
+	show_val_kb(m, "Active(anon):   ", pages[LRU_ACTIVE_ANON]);
+	show_val_kb(m, "Inactive(anon): ", pages[LRU_INACTIVE_ANON]);
+	show_val_kb(m, "Active(file):   ", pages[LRU_ACTIVE_FILE]);
+	show_val_kb(m, "Inactive(file): ", pages[LRU_INACTIVE_FILE]);
+	show_val_kb(m, "Unevictable:    ", pages[LRU_UNEVICTABLE]);
+	show_val_kb(m, "Mlocked:        ", global_zone_page_state(NR_MLOCK));
+
+#ifdef CONFIG_HIGHMEM
+	show_val_kb(m, "HighTotal:      ", i.totalhigh);
+	show_val_kb(m, "HighFree:       ", i.freehigh);
+	show_val_kb(m, "LowTotal:       ", i.totalram - i.totalhigh);
+	show_val_kb(m, "LowFree:        ", i.freeram - i.freehigh);
+#endif
+
+#ifndef CONFIG_MMU
+	show_val_kb(m, "MmapCopy:       ",
+		    (unsigned long)atomic_long_read(&mmap_pages_allocated));
+#endif
+
+	show_val_kb(m, "SwapTotal:      ", i.totalswap);
+	show_val_kb(m, "SwapFree:       ", i.freeswap);
+#ifdef CONFIG_ZSWAP
+	show_val_kb(m, "Zswap:          ", zswap_total_pages());
+	seq_printf(m,  "Zswapped:       %8lu kB\n",
+		   (unsigned long)atomic_long_read(&zswap_stored_pages) <<
+		   (PAGE_SHIFT - 10));
+#endif
+	show_val_kb(m, "Dirty:          ",
+		    global_node_page_state(NR_FILE_DIRTY));
+	show_val_kb(m, "Writeback:      ",
+		    global_node_page_state(NR_WRITEBACK));
+	show_val_kb(m, "AnonPages:      ",
+		    global_node_page_state(NR_ANON_MAPPED));
+	show_val_kb(m, "Mapped:         ",
+		    global_node_page_state(NR_FILE_MAPPED));
+	show_val_kb(m, "Shmem:          ", i.sharedram);
+	show_val_kb(m, "KReclaimable:   ", sreclaimable +
+		    global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE));
+	show_val_kb(m, "Slab:           ", sreclaimable + sunreclaim);
+	show_val_kb(m, "SReclaimable:   ", sreclaimable);
+	show_val_kb(m, "SUnreclaim:     ", sunreclaim);
+	seq_printf(m, "KernelStack:    %8lu kB\n",
+		   global_node_page_state(NR_KERNEL_STACK_KB));
+#ifdef CONFIG_SHADOW_CALL_STACK
+	seq_printf(m, "ShadowCallStack:%8lu kB\n",
+		   global_node_page_state(NR_KERNEL_SCS_KB));
+#endif
+	show_val_kb(m, "PageTables:     ",
+		    global_node_page_state(NR_PAGETABLE));
+	show_val_kb(m, "SecPageTables:  ",
+		    global_node_page_state(NR_SECONDARY_PAGETABLE));
+
+	show_val_kb(m, "NFS_Unstable:   ", 0);
+	show_val_kb(m, "Bounce:         ", 0);
+	show_val_kb(m, "WritebackTmp:   ", 0);
+	show_val_kb(m, "CommitLimit:    ", vm_commit_limit());
+	show_val_kb(m, "Committed_AS:   ", committed);
+	seq_printf(m, "VmallocTotal:   %8lu kB\n",
+		   (unsigned long)VMALLOC_TOTAL >> 10);
+	show_val_kb(m, "VmallocUsed:    ",
+		    global_node_page_state(NR_VMALLOC));
+	show_val_kb(m, "VmallocChunk:   ", 0ul);
+	show_val_kb(m, "Percpu:         ", pcpu_nr_pages());
+
+	memtest_report_meminfo(m);
+
+#ifdef CONFIG_MEMORY_FAILURE
+	seq_printf(m, "HardwareCorrupted: %5lu kB\n",
+		   atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10));
+#endif
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	show_val_kb(m, "AnonHugePages:  ",
+		    global_node_page_state(NR_ANON_THPS));
+	show_val_kb(m, "ShmemHugePages: ",
+		    global_node_page_state(NR_SHMEM_THPS));
+	show_val_kb(m, "ShmemPmdMapped: ",
+		    global_node_page_state(NR_SHMEM_PMDMAPPED));
+	show_val_kb(m, "FileHugePages:  ",
+		    global_node_page_state(NR_FILE_THPS));
+	show_val_kb(m, "FilePmdMapped:  ",
+		    global_node_page_state(NR_FILE_PMDMAPPED));
+#endif
+
+#ifdef CONFIG_CMA
+	show_val_kb(m, "CmaTotal:       ", totalcma_pages);
+	show_val_kb(m, "CmaFree:        ",
+		    global_zone_page_state(NR_FREE_CMA_PAGES));
+#endif
+
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	show_val_kb(m, "Unaccepted:     ",
+		    global_zone_page_state(NR_UNACCEPTED));
+#endif
+	show_val_kb(m, "Balloon:        ",
+		    global_node_page_state(NR_BALLOON_PAGES));
+
+	show_val_kb(m, "GPUActive:      ",
+		    global_node_page_state(NR_GPU_ACTIVE));
+
+	show_val_kb(m, "GPUReclaim:     ",
+		    global_node_page_state(NR_GPU_RECLAIM));
+
+	hugetlb_report_meminfo(m);
+
+	arch_report_meminfo(m);
+
+	return 0;
+}
+
+static int __init proc_meminfo_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = proc_create_single("meminfo", 0, NULL, meminfo_proc_show);
+	pde_make_permanent(pde);
+	return 0;
+}
+fs_initcall(proc_meminfo_init);

linux-7.2.3/fs/proc/namespaces.c

@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <linux/ptrace.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+#include <net/net_namespace.h>
+#include <linux/ipc_namespace.h>
+#include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
+#include "internal.h"
+
+
+static const struct proc_ns_operations *const ns_entries[] = {
+#ifdef CONFIG_NET_NS
+	&netns_operations,
+#endif
+#ifdef CONFIG_UTS_NS
+	&utsns_operations,
+#endif
+#ifdef CONFIG_IPC_NS
+	&ipcns_operations,
+#endif
+#ifdef CONFIG_PID_NS
+	&pidns_operations,
+	&pidns_for_children_operations,
+#endif
+#ifdef CONFIG_USER_NS
+	&userns_operations,
+#endif
+	&mntns_operations,
+#ifdef CONFIG_CGROUPS
+	&cgroupns_operations,
+#endif
+#ifdef CONFIG_TIME_NS
+	&timens_operations,
+	&timens_for_children_operations,
+#endif
+};
+
+static const char *proc_ns_get_link(struct dentry *dentry,
+				    struct inode *inode,
+				    struct delayed_call *done)
+{
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	struct path ns_path;
+	int error;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	task = get_proc_task(inode);
+	if (!task)
+		return ERR_PTR(-EACCES);
+
+	error = down_read_killable(&task->signal->exec_update_lock);
+	if (error)
+		goto out_put_task;
+
+	error = -EACCES;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
+		goto out;
+
+	error = ns_get_path(&ns_path, task, ns_ops);
+	if (error)
+		goto out;
+
+	error = nd_jump_link(&ns_path);
+out:
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
+	put_task_struct(task);
+	return ERR_PTR(error);
+}
+
+static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen)
+{
+	struct inode *inode = d_inode(dentry);
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	char name[50];
+	int res = -EACCES;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return res;
+
+	res = down_read_killable(&task->signal->exec_update_lock);
+	if (res)
+		goto out_put_task;
+
+	res = -EACCES;
+	if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
+		res = ns_get_name(name, sizeof(name), task, ns_ops);
+		if (res >= 0)
+			res = readlink_copy(buffer, buflen, name, strlen(name));
+	}
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
+	put_task_struct(task);
+	return res;
+}
+
+static const struct inode_operations proc_ns_link_inode_operations = {
+	.readlink	= proc_ns_readlink,
+	.get_link	= proc_ns_get_link,
+	.setattr	= proc_nochmod_setattr,
+};
+
+static struct dentry *proc_ns_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
+{
+	const struct proc_ns_operations *ns_ops = ptr;
+	struct inode *inode;
+	struct proc_inode *ei;
+
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	ei = PROC_I(inode);
+	inode->i_op = &proc_ns_link_inode_operations;
+	ei->ns_ops = ns_ops;
+	pid_update_inode(task, inode);
+
+	return d_splice_alias_ops(inode, dentry, &pid_dentry_operations);
+}
+
+static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	const struct proc_ns_operations *const *entry, *const *last;
+
+	if (!task)
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+	if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries))
+		goto out;
+	entry = ns_entries + (ctx->pos - 2);
+	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
+	while (entry <= last) {
+		const struct proc_ns_operations *ops = *entry;
+		if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name),
+				     proc_ns_instantiate, task, ops))
+			break;
+		ctx->pos++;
+		entry++;
+	}
+out:
+	put_task_struct(task);
+	return 0;
+}
+
+const struct file_operations proc_ns_dir_operations = {
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_ns_dir_readdir,
+	.llseek		= generic_file_llseek,
+};
+
+static struct dentry *proc_ns_dir_lookup(struct inode *dir,
+				struct dentry *dentry, unsigned int flags)
+{
+	struct task_struct *task = get_proc_task(dir);
+	const struct proc_ns_operations *const *entry, *const *last;
+	unsigned int len = dentry->d_name.len;
+	struct dentry *res = ERR_PTR(-ENOENT);
+
+	if (!task)
+		goto out_no_task;
+
+	last = &ns_entries[ARRAY_SIZE(ns_entries)];
+	for (entry = ns_entries; entry < last; entry++) {
+		if (strlen((*entry)->name) != len)
+			continue;
+		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
+			break;
+	}
+	if (entry == last)
+		goto out;
+
+	res = proc_ns_instantiate(dentry, task, *entry);
+out:
+	put_task_struct(task);
+out_no_task:
+	return res;
+}
+
+const struct inode_operations proc_ns_dir_inode_operations = {
+	.lookup		= proc_ns_dir_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_nochmod_setattr,
+};

linux-7.2.3/fs/proc/nommu.c

@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* nommu.c: mmu-less memory info files
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/mman.h>
+#include <linux/proc_fs.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/seq_file.h>
+#include <linux/hugetlb.h>
+#include <linux/vmalloc.h>
+#include <asm/tlb.h>
+#include <asm/div64.h>
+#include "internal.h"
+
+/*
+ * display a single region to a sequenced file
+ */
+static int nommu_region_show(struct seq_file *m, struct vm_region *region)
+{
+	unsigned long ino = 0;
+	struct file *file;
+	dev_t dev = 0;
+	int flags;
+
+	flags = region->vm_flags;
+	file = region->vm_file;
+
+	if (file) {
+		struct inode *inode = file_inode(region->vm_file);
+		dev = inode->i_sb->s_dev;
+		ino = inode->i_ino;
+	}
+
+	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+	seq_printf(m,
+		   "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
+		   region->vm_start,
+		   region->vm_end,
+		   flags & VM_READ ? 'r' : '-',
+		   flags & VM_WRITE ? 'w' : '-',
+		   flags & VM_EXEC ? 'x' : '-',
+		   flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
+		   ((loff_t)region->vm_pgoff) << PAGE_SHIFT,
+		   MAJOR(dev), MINOR(dev), ino);
+
+	if (file) {
+		seq_pad(m, ' ');
+		seq_path(m, file_user_path(file), "");
+	}
+
+	seq_putc(m, '\n');
+	return 0;
+}
+
+/*
+ * display a list of all the REGIONs the kernel knows about
+ * - nommu kernels have a single flat list
+ */
+static int nommu_region_list_show(struct seq_file *m, void *_p)
+{
+	struct rb_node *p = _p;
+
+	return nommu_region_show(m, rb_entry(p, struct vm_region, vm_rb));
+}
+
+static void *nommu_region_list_start(struct seq_file *m, loff_t *_pos)
+{
+	struct rb_node *p;
+	loff_t pos = *_pos;
+
+	down_read(&nommu_region_sem);
+
+	for (p = rb_first(&nommu_region_tree); p; p = rb_next(p))
+		if (pos-- == 0)
+			return p;
+	return NULL;
+}
+
+static void nommu_region_list_stop(struct seq_file *m, void *v)
+{
+	up_read(&nommu_region_sem);
+}
+
+static void *nommu_region_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return rb_next((struct rb_node *) v);
+}
+
+static const struct seq_operations proc_nommu_region_list_seqop = {
+	.start	= nommu_region_list_start,
+	.next	= nommu_region_list_next,
+	.stop	= nommu_region_list_stop,
+	.show	= nommu_region_list_show
+};
+
+static int __init proc_nommu_init(void)
+{
+	proc_create_seq("maps", S_IRUGO, NULL, &proc_nommu_region_list_seqop);
+	return 0;
+}
+
+fs_initcall(proc_nommu_init);

linux-7.2.3/fs/proc/page.c

@@ -0,0 +1,299 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/memblock.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/ksm.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/huge_mm.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/hugetlb.h>
+#include <linux/memremap.h>
+#include <linux/memcontrol.h>
+#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
+#include <linux/kernel-page-flags.h>
+#include <linux/uaccess.h>
+#include "internal.h"
+
+#define KPMSIZE sizeof(u64)
+#define KPMMASK (KPMSIZE - 1)
+
+enum kpage_operation {
+	KPAGE_FLAGS,
+	KPAGE_COUNT,
+	KPAGE_CGROUP,
+};
+
+static inline unsigned long get_max_dump_pfn(void)
+{
+#ifdef CONFIG_SPARSEMEM
+	/*
+	 * The memmap of early sections is completely populated and marked
+	 * online even if max_pfn does not fall on a section boundary -
+	 * pfn_to_online_page() will succeed on all pages. Allow inspecting
+	 * these memmaps.
+	 */
+	return round_up(max_pfn, PAGES_PER_SECTION);
+#else
+	return max_pfn;
+#endif
+}
+
+static u64 get_kpage_count(const struct page *page)
+{
+	struct page_snapshot ps;
+	u64 ret;
+
+	snapshot_page(&ps, page);
+
+	if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+		ret = folio_precise_page_mapcount(&ps.folio_snapshot,
+						  &ps.page_snapshot);
+	else
+		ret = folio_average_page_mapcount(&ps.folio_snapshot);
+
+	return ret;
+}
+
+static ssize_t kpage_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos,
+		enum kpage_operation op)
+{
+	const unsigned long max_dump_pfn = get_max_dump_pfn();
+	u64 __user *out = (u64 __user *)buf;
+	struct page *page;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+	u64 info;
+
+	pfn = src / KPMSIZE;
+	if (src & KPMMASK || count & KPMMASK)
+		return -EINVAL;
+	if (src >= max_dump_pfn * KPMSIZE)
+		return 0;
+	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
+
+	while (count > 0) {
+		/*
+		 * TODO: ZONE_DEVICE support requires to identify
+		 * memmaps that were actually initialized.
+		 */
+		page = pfn_to_online_page(pfn);
+
+		if (page) {
+			switch (op) {
+			case KPAGE_FLAGS:
+				info = stable_page_flags(page);
+				break;
+			case KPAGE_COUNT:
+				info = get_kpage_count(page);
+				break;
+			case KPAGE_CGROUP:
+				info = page_cgroup_ino(page);
+				break;
+			default:
+				info = 0;
+				break;
+			}
+		} else
+			info = 0;
+
+		if (put_user(info, out)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		pfn++;
+		out++;
+		count -= KPMSIZE;
+
+		cond_resched();
+	}
+
+	*ppos += (char __user *)out - buf;
+	if (!ret)
+		ret = (char __user *)out - buf;
+	return ret;
+}
+
+/* /proc/kpagecount - an array exposing page mapcounts
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page mapcount.
+ */
+static ssize_t kpagecount_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_COUNT);
+}
+
+static const struct proc_ops kpagecount_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpagecount_read,
+};
+
+
+static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
+{
+	return ((kflags >> kbit) & 1) << ubit;
+}
+
+u64 stable_page_flags(const struct page *page)
+{
+	const struct folio *folio;
+	struct page_snapshot ps;
+	unsigned long k;
+	unsigned long mapping;
+	bool is_anon;
+	u64 u = 0;
+
+	/*
+	 * pseudo flag: KPF_NOPAGE
+	 * it differentiates a memory hole from a page with no flags
+	 */
+	if (!page)
+		return 1 << KPF_NOPAGE;
+
+	snapshot_page(&ps, page);
+	folio = &ps.folio_snapshot;
+
+	k = folio->flags.f;
+	mapping = (unsigned long)folio->mapping;
+	is_anon = mapping & FOLIO_MAPPING_ANON;
+
+	/*
+	 * pseudo flags for the well known (anonymous) memory mapped pages
+	 */
+	if (folio_mapped(folio))
+		u |= 1 << KPF_MMAP;
+	if (is_anon) {
+		u |= 1 << KPF_ANON;
+		if ((mapping & FOLIO_MAPPING_FLAGS) == FOLIO_MAPPING_KSM)
+			u |= 1 << KPF_KSM;
+	}
+
+	/*
+	 * compound pages: export both head/tail info
+	 * they together define a compound page's start/end pos and order
+	 */
+	if (ps.idx == 0)
+		u |= kpf_copy_bit(k, KPF_COMPOUND_HEAD, PG_head);
+	else
+		u |= 1 << KPF_COMPOUND_TAIL;
+	if (folio_test_hugetlb(folio))
+		u |= 1 << KPF_HUGE;
+	else if (folio_test_large(folio) &&
+	         folio_test_large_rmappable(folio)) {
+		/* Note: we indicate any THPs here, not just PMD-sized ones */
+		u |= 1 << KPF_THP;
+	} else if (is_huge_zero_pfn(ps.pfn)) {
+		u |= 1 << KPF_ZERO_PAGE;
+		u |= 1 << KPF_THP;
+	} else if (is_zero_pfn(ps.pfn)) {
+		u |= 1 << KPF_ZERO_PAGE;
+	}
+
+	if (ps.flags & PAGE_SNAPSHOT_PG_BUDDY)
+		u |= 1 << KPF_BUDDY;
+
+	if (folio_test_offline(folio))
+		u |= 1 << KPF_OFFLINE;
+	if (folio_test_pgtable(folio))
+		u |= 1 << KPF_PGTABLE;
+	if (folio_test_slab(folio))
+		u |= 1 << KPF_SLAB;
+
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
+	u |= kpf_copy_bit(k, KPF_IDLE,          PG_idle);
+#else
+	if (ps.flags & PAGE_SNAPSHOT_PG_IDLE)
+		u |= 1 << KPF_IDLE;
+#endif
+
+	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
+	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);
+	u |= kpf_copy_bit(k, KPF_UPTODATE,	PG_uptodate);
+	u |= kpf_copy_bit(k, KPF_WRITEBACK,	PG_writeback);
+
+	u |= kpf_copy_bit(k, KPF_LRU,		PG_lru);
+	u |= kpf_copy_bit(k, KPF_REFERENCED,	PG_referenced);
+	u |= kpf_copy_bit(k, KPF_ACTIVE,	PG_active);
+	u |= kpf_copy_bit(k, KPF_RECLAIM,	PG_reclaim);
+
+#define SWAPCACHE ((1 << PG_swapbacked) | (1 << PG_swapcache))
+	if ((k & SWAPCACHE) == SWAPCACHE)
+		u |= 1 << KPF_SWAPCACHE;
+	u |= kpf_copy_bit(k, KPF_SWAPBACKED,	PG_swapbacked);
+
+	u |= kpf_copy_bit(k, KPF_UNEVICTABLE,	PG_unevictable);
+	u |= kpf_copy_bit(k, KPF_MLOCKED,	PG_mlocked);
+
+#ifdef CONFIG_MEMORY_FAILURE
+	if (u & (1 << KPF_HUGE))
+		u |= kpf_copy_bit(k, KPF_HWPOISON,	PG_hwpoison);
+	else
+		u |= kpf_copy_bit(ps.page_snapshot.flags.f, KPF_HWPOISON, PG_hwpoison);
+#endif
+
+	u |= kpf_copy_bit(k, KPF_RESERVED,	PG_reserved);
+	u |= kpf_copy_bit(k, KPF_OWNER_2,	PG_owner_2);
+	u |= kpf_copy_bit(k, KPF_PRIVATE,	PG_private);
+	u |= kpf_copy_bit(k, KPF_PRIVATE_2,	PG_private_2);
+	u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE,	PG_owner_priv_1);
+	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
+#ifdef CONFIG_ARCH_USES_PG_ARCH_2
+	u |= kpf_copy_bit(k, KPF_ARCH_2,	PG_arch_2);
+#endif
+#ifdef CONFIG_ARCH_USES_PG_ARCH_3
+	u |= kpf_copy_bit(k, KPF_ARCH_3,	PG_arch_3);
+#endif
+
+	return u;
+}
+EXPORT_SYMBOL_GPL(stable_page_flags);
+
+/* /proc/kpageflags - an array exposing page flags
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page flags.
+ */
+static ssize_t kpageflags_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_FLAGS);
+}
+
+static const struct proc_ops kpageflags_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpageflags_read,
+};
+
+#ifdef CONFIG_MEMCG
+static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_CGROUP);
+}
+static const struct proc_ops kpagecgroup_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpagecgroup_read,
+};
+#endif /* CONFIG_MEMCG */
+
+static int __init proc_page_init(void)
+{
+	proc_create("kpagecount", S_IRUSR, NULL, &kpagecount_proc_ops);
+	proc_create("kpageflags", S_IRUSR, NULL, &kpageflags_proc_ops);
+#ifdef CONFIG_MEMCG
+	proc_create("kpagecgroup", S_IRUSR, NULL, &kpagecgroup_proc_ops);
+#endif
+	return 0;
+}
+fs_initcall(proc_page_init);

linux-7.2.3/fs/proc/proc_net.c

@@ -0,0 +1,426 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/fs/proc/net.c
+ *
+ *  Copyright (C) 2007
+ *
+ *  Author: Eric Biederman <ebiederm@xmission.com>
+ *
+ *  proc net directory handling functions
+ */
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/mount.h>
+#include <linux/nsproxy.h>
+#include <linux/uidgid.h>
+#include <net/net_namespace.h>
+#include <linux/seq_file.h>
+#include <linux/security.h>
+
+#include "internal.h"
+
+static inline struct net *PDE_NET(struct proc_dir_entry *pde)
+{
+	return pde->parent->data;
+}
+
+static struct net *get_proc_net(const struct inode *inode)
+{
+	return maybe_get_net(PDE_NET(PDE(inode)));
+}
+
+static int seq_open_net(struct inode *inode, struct file *file)
+{
+	unsigned int state_size = PDE(inode)->state_size;
+	struct seq_net_private *p;
+	struct net *net;
+
+	WARN_ON_ONCE(state_size < sizeof(*p));
+
+	if (file->f_mode & FMODE_WRITE && !PDE(inode)->write)
+		return -EACCES;
+
+	net = get_proc_net(inode);
+	if (!net)
+		return -ENXIO;
+
+	p = __seq_open_private(file, PDE(inode)->seq_ops, state_size);
+	if (!p) {
+		put_net(net);
+		return -ENOMEM;
+	}
+#ifdef CONFIG_NET_NS
+	p->net = net;
+	netns_tracker_alloc(net, &p->ns_tracker, GFP_KERNEL);
+#endif
+	return 0;
+}
+
+static void seq_file_net_put_net(struct seq_file *seq)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *priv = seq->private;
+
+	put_net_track(priv->net, &priv->ns_tracker);
+#else
+	put_net(&init_net);
+#endif
+}
+
+static int seq_release_net(struct inode *ino, struct file *f)
+{
+	struct seq_file *seq = f->private_data;
+
+	seq_file_net_put_net(seq);
+	seq_release_private(ino, f);
+	return 0;
+}
+
+static const struct proc_ops proc_net_seq_ops = {
+	.proc_open	= seq_open_net,
+	.proc_read	= seq_read,
+	.proc_write	= proc_simple_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release_net,
+};
+
+int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *p = priv_data;
+
+	p->net = get_net_track(current->nsproxy->net_ns, &p->ns_tracker,
+			       GFP_KERNEL);
+#endif
+	return 0;
+}
+
+void bpf_iter_fini_seq_net(void *priv_data)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *p = priv_data;
+
+	put_net_track(p->net, &p->ns_tracker);
+#endif
+}
+
+struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, const struct seq_operations *ops,
+		unsigned int state_size, void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	pde_force_lookup(p);
+	p->proc_ops = &proc_net_seq_ops;
+	p->seq_ops = ops;
+	p->state_size = state_size;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_data);
+
+/**
+ * proc_create_net_data_write - Create a writable net_ns-specific proc file
+ * @name: The name of the file.
+ * @mode: The file's access mode.
+ * @parent: The parent directory in which to create.
+ * @ops: The seq_file ops with which to read the file.
+ * @write: The write method with which to 'modify' the file.
+ * @state_size: The size of the per-file private state to allocate.
+ * @data: Data for retrieval by pde_data().
+ *
+ * Create a network namespaced proc file in the @parent directory with the
+ * specified @name and @mode that allows reading of a file that displays a
+ * series of elements and also provides for the file accepting writes that have
+ * some arbitrary effect.
+ *
+ * The functions in the @ops table are used to iterate over items to be
+ * presented and extract the readable content using the seq_file interface.
+ *
+ * The @write function is called with the data copied into a kernel space
+ * scratch buffer and has a NUL appended for convenience.  The buffer may be
+ * modified by the @write function.  @write should return 0 on success.
+ *
+ * The @data value is accessible from the @show and @write functions by calling
+ * pde_data() on the file inode.  The network namespace must be accessed by
+ * calling seq_file_net() on the seq_file struct.
+ */
+struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode,
+						  struct proc_dir_entry *parent,
+						  const struct seq_operations *ops,
+						  proc_write_t write,
+						  unsigned int state_size, void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	pde_force_lookup(p);
+	p->proc_ops = &proc_net_seq_ops;
+	p->seq_ops = ops;
+	p->state_size = state_size;
+	p->write = write;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_data_write);
+
+static int single_open_net(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+	struct net *net;
+	int err;
+
+	net = get_proc_net(inode);
+	if (!net)
+		return -ENXIO;
+
+	err = single_open(file, de->single_show, net);
+	if (err)
+		put_net(net);
+	return err;
+}
+
+static int single_release_net(struct inode *ino, struct file *f)
+{
+	struct seq_file *seq = f->private_data;
+	put_net(seq->private);
+	return single_release(ino, f);
+}
+
+static const struct proc_ops proc_net_single_ops = {
+	.proc_open	= single_open_net,
+	.proc_read	= seq_read,
+	.proc_write	= proc_simple_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release_net,
+};
+
+struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
+		struct proc_dir_entry *parent,
+		int (*show)(struct seq_file *, void *), void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	pde_force_lookup(p);
+	p->proc_ops = &proc_net_single_ops;
+	p->single_show = show;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_single);
+
+/**
+ * proc_create_net_single_write - Create a writable net_ns-specific proc file
+ * @name: The name of the file.
+ * @mode: The file's access mode.
+ * @parent: The parent directory in which to create.
+ * @show: The seqfile show method with which to read the file.
+ * @write: The write method with which to 'modify' the file.
+ * @data: Data for retrieval by pde_data().
+ *
+ * Create a network-namespaced proc file in the @parent directory with the
+ * specified @name and @mode that allows reading of a file that displays a
+ * single element rather than a series and also provides for the file accepting
+ * writes that have some arbitrary effect.
+ *
+ * The @show function is called to extract the readable content via the
+ * seq_file interface.
+ *
+ * The @write function is called with the data copied into a kernel space
+ * scratch buffer and has a NUL appended for convenience.  The buffer may be
+ * modified by the @write function.  @write should return 0 on success.
+ *
+ * The @data value is accessible from the @show and @write functions by calling
+ * pde_data() on the file inode.  The network namespace must be accessed by
+ * calling seq_file_single_net() on the seq_file struct.
+ */
+struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode,
+						    struct proc_dir_entry *parent,
+						    int (*show)(struct seq_file *, void *),
+						    proc_write_t write,
+						    void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	pde_force_lookup(p);
+	p->proc_ops = &proc_net_single_ops;
+	p->single_show = show;
+	p->write = write;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_single_write);
+
+static struct net *get_proc_task_net(struct inode *dir)
+{
+	struct task_struct *task;
+	struct nsproxy *ns;
+	struct net *net = NULL;
+	struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb);
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(dir), PIDTYPE_PID);
+	if (task != NULL) {
+		task_lock(task);
+		ns = task->nsproxy;
+		if (ns != NULL)
+			net = get_net(ns->net_ns);
+		task_unlock(task);
+	}
+	rcu_read_unlock();
+
+	if (net && (fs_info->pidonly == PROC_PIDONLY_ON) &&
+	    security_capable(fs_info->mounter_cred, net->user_ns, CAP_NET_ADMIN, CAP_OPT_NONE) < 0) {
+		put_net(net);
+		net = NULL;
+	}
+
+	return net;
+}
+
+static struct dentry *proc_tgid_net_lookup(struct inode *dir,
+		struct dentry *dentry, unsigned int flags)
+{
+	struct dentry *de;
+	struct net *net;
+
+	de = ERR_PTR(-ENOENT);
+	net = get_proc_task_net(dir);
+	if (net != NULL) {
+		de = proc_lookup_de(dir, dentry, net->proc_net);
+		put_net(net);
+	}
+	return de;
+}
+
+static int proc_tgid_net_getattr(struct mnt_idmap *idmap,
+				 const struct path *path, struct kstat *stat,
+				 u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+	struct net *net;
+
+	net = get_proc_task_net(inode);
+
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+
+	if (net != NULL) {
+		stat->nlink = net->proc_net->nlink;
+		put_net(net);
+	}
+
+	return 0;
+}
+
+const struct inode_operations proc_net_inode_operations = {
+	.lookup		= proc_tgid_net_lookup,
+	.getattr	= proc_tgid_net_getattr,
+	.setattr        = proc_nochmod_setattr,
+};
+
+static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx)
+{
+	int ret;
+	struct net *net;
+
+	ret = -EINVAL;
+	net = get_proc_task_net(file_inode(file));
+	if (net != NULL) {
+		ret = proc_readdir_de(file, ctx, net->proc_net);
+		put_net(net);
+	}
+	return ret;
+}
+
+const struct file_operations proc_net_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_tgid_net_readdir,
+};
+
+static __net_init int proc_net_ns_init(struct net *net)
+{
+	struct proc_dir_entry *netd, *net_statd;
+	kuid_t uid;
+	kgid_t gid;
+	int err;
+
+	/*
+	 * This PDE acts only as an anchor for /proc/${pid}/net hierarchy.
+	 * Corresponding inode (PDE(inode) == net->proc_net) is never
+	 * instantiated therefore blanket zeroing is fine.
+	 * net->proc_net_stat inode is instantiated normally.
+	 */
+	err = -ENOMEM;
+	netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL);
+	if (!netd)
+		goto out;
+
+	netd->subdir = RB_ROOT;
+	netd->data = net;
+	netd->nlink = 2;
+	netd->namelen = 3;
+	netd->parent = &proc_root;
+	netd->name = netd->inline_name;
+	memcpy(netd->name, "net", 4);
+
+	uid = make_kuid(net->user_ns, 0);
+	if (!uid_valid(uid))
+		uid = netd->uid;
+
+	gid = make_kgid(net->user_ns, 0);
+	if (!gid_valid(gid))
+		gid = netd->gid;
+
+	proc_set_user(netd, uid, gid);
+
+	/* Seed dentry revalidation for /proc/${pid}/net */
+	pde_force_lookup(netd);
+
+	err = -EEXIST;
+	net_statd = proc_net_mkdir(net, "stat", netd);
+	if (!net_statd)
+		goto free_net;
+
+	net->proc_net = netd;
+	net->proc_net_stat = net_statd;
+	return 0;
+
+free_net:
+	pde_free(netd);
+out:
+	return err;
+}
+
+static __net_exit void proc_net_ns_exit(struct net *net)
+{
+	remove_proc_entry("stat", net->proc_net);
+	pde_free(net->proc_net);
+}
+
+static struct pernet_operations __net_initdata proc_net_ns_ops = {
+	.init = proc_net_ns_init,
+	.exit = proc_net_ns_exit,
+};
+
+int __init proc_net_init(void)
+{
+	proc_symlink("net", NULL, "self/net");
+
+	return register_pernet_subsys(&proc_net_ns_ops);
+}

linux-7.2.3/fs/proc/proc_tty.c

@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * proc_tty.c -- handles /proc/tty
+ *
+ * Copyright 1997, Theodore Ts'o
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/tty.h>
+#include <linux/seq_file.h>
+#include <linux/bitops.h>
+#include "internal.h"
+
+/*
+ * The /proc/tty directory inodes...
+ */
+static struct proc_dir_entry *proc_tty_driver;
+
+/*
+ * This is the handler for /proc/tty/drivers
+ */
+static void show_tty_range(struct seq_file *m, struct tty_driver *p,
+	dev_t from, int num)
+{
+	seq_printf(m, "%-20s ", p->driver_name ? p->driver_name : "unknown");
+	seq_printf(m, "/dev/%-8s ", p->name);
+	if (p->num > 1) {
+		seq_printf(m, "%3d %d-%d ", MAJOR(from), MINOR(from),
+			MINOR(from) + num - 1);
+	} else {
+		seq_printf(m, "%3d %7d ", MAJOR(from), MINOR(from));
+	}
+	switch (p->type) {
+	case TTY_DRIVER_TYPE_SYSTEM:
+		seq_puts(m, "system");
+		if (p->subtype == SYSTEM_TYPE_TTY)
+			seq_puts(m, ":/dev/tty");
+		else if (p->subtype == SYSTEM_TYPE_SYSCONS)
+			seq_puts(m, ":console");
+		else if (p->subtype == SYSTEM_TYPE_CONSOLE)
+			seq_puts(m, ":vtmaster");
+		break;
+	case TTY_DRIVER_TYPE_CONSOLE:
+		seq_puts(m, "console");
+		break;
+	case TTY_DRIVER_TYPE_SERIAL:
+		seq_puts(m, "serial");
+		break;
+	case TTY_DRIVER_TYPE_PTY:
+		if (p->subtype == PTY_TYPE_MASTER)
+			seq_puts(m, "pty:master");
+		else if (p->subtype == PTY_TYPE_SLAVE)
+			seq_puts(m, "pty:slave");
+		else
+			seq_puts(m, "pty");
+		break;
+	default:
+		seq_printf(m, "type:%d.%d", p->type, p->subtype);
+	}
+	seq_putc(m, '\n');
+}
+
+static int show_tty_driver(struct seq_file *m, void *v)
+{
+	struct tty_driver *p = list_entry(v, struct tty_driver, tty_drivers);
+	dev_t from = MKDEV(p->major, p->minor_start);
+	dev_t to = from + p->num;
+
+	if (&p->tty_drivers == tty_drivers.next) {
+		/* pseudo-drivers first */
+		seq_printf(m, "%-20s /dev/%-8s ", "/dev/tty", "tty");
+		seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 0);
+		seq_puts(m, "system:/dev/tty\n");
+		seq_printf(m, "%-20s /dev/%-8s ", "/dev/console", "console");
+		seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 1);
+		seq_puts(m, "system:console\n");
+#ifdef CONFIG_UNIX98_PTYS
+		seq_printf(m, "%-20s /dev/%-8s ", "/dev/ptmx", "ptmx");
+		seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 2);
+		seq_puts(m, "system\n");
+#endif
+#ifdef CONFIG_VT
+		seq_printf(m, "%-20s /dev/%-8s ", "/dev/vc/0", "vc/0");
+		seq_printf(m, "%3d %7d ", TTY_MAJOR, 0);
+		seq_puts(m, "system:vtmaster\n");
+#endif
+	}
+
+	while (MAJOR(from) < MAJOR(to)) {
+		dev_t next = MKDEV(MAJOR(from)+1, 0);
+		show_tty_range(m, p, from, next - from);
+		from = next;
+	}
+	if (from != to)
+		show_tty_range(m, p, from, to - from);
+	return 0;
+}
+
+/* iterator */
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&tty_mutex);
+	return seq_list_start(&tty_drivers, *pos);
+}
+
+static void *t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return seq_list_next(v, &tty_drivers, pos);
+}
+
+static void t_stop(struct seq_file *m, void *v)
+{
+	mutex_unlock(&tty_mutex);
+}
+
+static const struct seq_operations tty_drivers_op = {
+	.start	= t_start,
+	.next	= t_next,
+	.stop	= t_stop,
+	.show	= show_tty_driver
+};
+
+/*
+ * This function is called by tty_register_driver() to handle
+ * registering the driver's /proc handler into /proc/tty/driver/<foo>
+ */
+void proc_tty_register_driver(struct tty_driver *driver)
+{
+	struct proc_dir_entry *ent;
+		
+	if (!driver->driver_name || driver->proc_entry ||
+	    !driver->ops->proc_show)
+		return;
+
+	ent = proc_create_single_data(driver->driver_name, 0, proc_tty_driver,
+			       driver->ops->proc_show, driver);
+	driver->proc_entry = ent;
+}
+
+/*
+ * This function is called by tty_unregister_driver()
+ */
+void proc_tty_unregister_driver(struct tty_driver *driver)
+{
+	struct proc_dir_entry *ent;
+
+	ent = driver->proc_entry;
+	if (!ent)
+		return;
+		
+	remove_proc_entry(ent->name, proc_tty_driver);
+	
+	driver->proc_entry = NULL;
+}
+
+/*
+ * Called by proc_root_init() to initialize the /proc/tty subtree
+ */
+void __init proc_tty_init(void)
+{
+	if (!proc_mkdir("tty", NULL))
+		return;
+	proc_mkdir("tty/ldisc", NULL);	/* Preserved: it's userspace visible */
+	/*
+	 * /proc/tty/driver/serial reveals the exact character counts for
+	 * serial links which is just too easy to abuse for inferring
+	 * password lengths and inter-keystroke timings during password
+	 * entry.
+	 */
+	proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL);
+	proc_create_seq("tty/ldiscs", 0, NULL, &tty_ldiscs_seq_ops);
+	proc_create_seq("tty/drivers", 0, NULL, &tty_drivers_op);
+}

linux-7.2.3/fs/proc/root.c

@@ -0,0 +1,468 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/proc/root.c
+ *
+ *  Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ *  proc root directory handling functions
+ */
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/stat.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/user_namespace.h>
+#include <linux/fs_context.h>
+#include <linux/mount.h>
+#include <linux/pid_namespace.h>
+#include <linux/fs_parser.h>
+#include <linux/cred.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+
+#include "internal.h"
+
+struct proc_fs_context {
+	struct pid_namespace	*pid_ns;
+	unsigned int		mask;
+	enum proc_hidepid	hidepid;
+	int			gid;
+	enum proc_pidonly	pidonly;
+};
+
+enum proc_param {
+	Opt_gid,
+	Opt_hidepid,
+	Opt_subset,
+	Opt_pidns,
+};
+
+static const struct fs_parameter_spec proc_fs_parameters[] = {
+	fsparam_u32("gid",		Opt_gid),
+	fsparam_string("hidepid",	Opt_hidepid),
+	fsparam_string("subset",	Opt_subset),
+	fsparam_file_or_string("pidns",	Opt_pidns),
+	{}
+};
+
+static inline int valid_hidepid(unsigned int value)
+{
+	return (value == HIDEPID_OFF ||
+		value == HIDEPID_NO_ACCESS ||
+		value == HIDEPID_INVISIBLE ||
+		value == HIDEPID_NOT_PTRACEABLE);
+}
+
+static int proc_parse_hidepid_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid);
+	struct fs_parse_result result;
+	int base = (unsigned long)hidepid_u32_spec.data;
+
+	if (param->type != fs_value_is_string)
+		return invalf(fc, "proc: unexpected type of hidepid value\n");
+
+	if (!kstrtouint(param->string, base, &result.uint_32)) {
+		if (!valid_hidepid(result.uint_32))
+			return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);
+		ctx->hidepid = result.uint_32;
+		return 0;
+	}
+
+	if (!strcmp(param->string, "off"))
+		ctx->hidepid = HIDEPID_OFF;
+	else if (!strcmp(param->string, "noaccess"))
+		ctx->hidepid = HIDEPID_NO_ACCESS;
+	else if (!strcmp(param->string, "invisible"))
+		ctx->hidepid = HIDEPID_INVISIBLE;
+	else if (!strcmp(param->string, "ptraceable"))
+		ctx->hidepid = HIDEPID_NOT_PTRACEABLE;
+	else
+		return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);
+
+	return 0;
+}
+
+static int proc_parse_subset_param(struct fs_context *fc, char *value)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	while (value) {
+		char *ptr = strchr(value, ',');
+
+		if (ptr != NULL)
+			*ptr++ = '\0';
+
+		if (*value != '\0') {
+			if (!strcmp(value, "pid")) {
+				ctx->pidonly = PROC_PIDONLY_ON;
+			} else {
+				return invalf(fc, "proc: unsupported subset option - %s\n", value);
+			}
+		}
+		value = ptr;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_PID_NS
+static int proc_parse_pidns_param(struct fs_context *fc,
+				  struct fs_parameter *param,
+				  struct fs_parse_result *result)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct pid_namespace *target, *active = task_active_pid_ns(current);
+	struct ns_common *ns;
+	struct file *ns_filp __free(fput) = NULL;
+
+	switch (param->type) {
+	case fs_value_is_file:
+		/* came through fsconfig, steal the file reference */
+		ns_filp = no_free_ptr(param->file);
+		break;
+	case fs_value_is_string:
+		ns_filp = filp_open(param->string, O_RDONLY, 0);
+		break;
+	default:
+		WARN_ON_ONCE(true);
+		break;
+	}
+	if (!ns_filp)
+		ns_filp = ERR_PTR(-EBADF);
+	if (IS_ERR(ns_filp)) {
+		errorfc(fc, "could not get file from pidns argument");
+		return PTR_ERR(ns_filp);
+	}
+
+	if (!proc_ns_file(ns_filp))
+		return invalfc(fc, "pidns argument is not an nsfs file");
+	ns = get_proc_ns(file_inode(ns_filp));
+	if (ns->ns_type != CLONE_NEWPID)
+		return invalfc(fc, "pidns argument is not a pidns file");
+	target = container_of(ns, struct pid_namespace, ns);
+
+	/*
+	 * pidns= is shorthand for joining the pidns to get a fsopen fd, so the
+	 * permission model should be the same as pidns_install().
+	 */
+	if (!ns_capable(target->user_ns, CAP_SYS_ADMIN)) {
+		errorfc(fc, "insufficient permissions to set pidns");
+		return -EPERM;
+	}
+	if (!pidns_is_ancestor(target, active))
+		return invalfc(fc, "cannot set pidns to non-descendant pidns");
+
+	put_pid_ns(ctx->pid_ns);
+	ctx->pid_ns = get_pid_ns(target);
+	put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+	return 0;
+}
+#endif /* CONFIG_PID_NS */
+
+static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct fs_parse_result result;
+	int opt, err;
+
+	opt = fs_parse(fc, proc_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_gid:
+		ctx->gid = result.uint_32;
+		break;
+
+	case Opt_hidepid:
+		err = proc_parse_hidepid_param(fc, param);
+		if (err)
+			return err;
+		break;
+
+	case Opt_subset:
+		err = proc_parse_subset_param(fc, param->string);
+		if (err)
+			return err;
+		break;
+
+	case Opt_pidns:
+#ifdef CONFIG_PID_NS
+		/*
+		 * We would have to RCU-protect every proc_pid_ns() or
+		 * proc_sb_info() access if we allowed this to be reconfigured
+		 * for an existing procfs instance. Luckily, procfs instances
+		 * are cheap to create, and mount-beneath would let you
+		 * atomically replace an instance even with overmounts.
+		 */
+		if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+			errorfc(fc, "cannot reconfigure pidns for existing procfs");
+			return -EBUSY;
+		}
+		err = proc_parse_pidns_param(fc, param, &result);
+		if (err)
+			return err;
+		break;
+#else
+		errorfc(fc, "pidns mount flag not supported on this system");
+		return -EOPNOTSUPP;
+#endif
+
+	default:
+		return -EINVAL;
+	}
+
+	ctx->mask |= 1 << opt;
+	return 0;
+}
+
+static int proc_apply_options(struct proc_fs_info *fs_info,
+			       struct fs_context *fc,
+			       struct user_namespace *user_ns)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	if ((ctx->mask & (1 << Opt_subset)) &&
+	    fc->purpose == FS_CONTEXT_FOR_RECONFIGURE &&
+	    ctx->pidonly != fs_info->pidonly)
+		return invalf(fc, "proc: subset=pid cannot be changed\n");
+
+	if (ctx->mask & (1 << Opt_gid))
+		fs_info->pid_gid = make_kgid(user_ns, ctx->gid);
+	if (ctx->mask & (1 << Opt_hidepid))
+		fs_info->hide_pid = ctx->hidepid;
+	if (ctx->mask & (1 << Opt_subset))
+		fs_info->pidonly = ctx->pidonly;
+	if (ctx->mask & (1 << Opt_pidns) &&
+	    !WARN_ON_ONCE(fc->purpose == FS_CONTEXT_FOR_RECONFIGURE)) {
+		put_pid_ns(fs_info->pid_ns);
+		fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+	}
+	return 0;
+}
+
+static int proc_fill_super(struct super_block *s, struct fs_context *fc)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct inode *root_inode;
+	struct proc_fs_info *fs_info;
+	int ret;
+
+	fs_info = kzalloc_obj(*fs_info);
+	if (!fs_info)
+		return -ENOMEM;
+
+	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+	fs_info->mounter_cred = get_cred(fc->cred);
+	ret = proc_apply_options(fs_info, fc, current_user_ns());
+	if (ret)
+		return ret;
+
+	/* User space would break if executables or devices appear on proc */
+	s->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
+	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
+	s->s_blocksize = 1024;
+	s->s_blocksize_bits = 10;
+	s->s_magic = PROC_SUPER_MAGIC;
+	s->s_op = &proc_sops;
+	s->s_time_gran = 1;
+	s->s_fs_info = fs_info;
+
+	if (fs_info->pidonly == PROC_PIDONLY_ON)
+		s->s_iflags |= SB_I_RESTRICTED_VARIANT;
+
+	/*
+	 * procfs isn't actually a stacking filesystem; however, there is
+	 * too much magic going on inside it to permit stacking things on
+	 * top of it
+	 */
+	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
+
+	/* procfs dentries and inodes don't require IO to create */
+	s->s_shrink->seeks = 0;
+
+	pde_get(&proc_root);
+	root_inode = proc_get_inode(s, &proc_root);
+	if (!root_inode) {
+		pr_err("proc_fill_super: get root inode failed\n");
+		return -ENOMEM;
+	}
+
+	s->s_root = d_make_root(root_inode);
+	if (!s->s_root) {
+		pr_err("proc_fill_super: allocate dentry failed\n");
+		return -ENOMEM;
+	}
+
+	ret = proc_setup_self(s);
+	if (ret) {
+		return ret;
+	}
+	return proc_setup_thread_self(s);
+}
+
+static int proc_reconfigure(struct fs_context *fc)
+{
+	struct super_block *sb = fc->root->d_sb;
+	struct proc_fs_info *fs_info = proc_sb_info(sb);
+
+	sync_filesystem(sb);
+
+	return proc_apply_options(fs_info, fc, current_user_ns());
+}
+
+static int proc_get_tree(struct fs_context *fc)
+{
+	return get_tree_nodev(fc, proc_fill_super);
+}
+
+static void proc_fs_context_free(struct fs_context *fc)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	put_pid_ns(ctx->pid_ns);
+	kfree(ctx);
+}
+
+static const struct fs_context_operations proc_fs_context_ops = {
+	.free		= proc_fs_context_free,
+	.parse_param	= proc_parse_param,
+	.get_tree	= proc_get_tree,
+	.reconfigure	= proc_reconfigure,
+};
+
+static int proc_init_fs_context(struct fs_context *fc)
+{
+	struct proc_fs_context *ctx;
+
+	ctx = kzalloc_obj(struct proc_fs_context);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->pid_ns = get_pid_ns(task_active_pid_ns(current));
+	put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+	fc->fs_private = ctx;
+	fc->ops = &proc_fs_context_ops;
+	return 0;
+}
+
+static void proc_kill_sb(struct super_block *sb)
+{
+	struct proc_fs_info *fs_info = proc_sb_info(sb);
+
+	kill_anon_super(sb);
+	if (fs_info) {
+		put_pid_ns(fs_info->pid_ns);
+		put_cred(fs_info->mounter_cred);
+		kfree_rcu(fs_info, rcu);
+	}
+}
+
+static struct file_system_type proc_fs_type = {
+	.name			= "proc",
+	.init_fs_context	= proc_init_fs_context,
+	.parameters		= proc_fs_parameters,
+	.kill_sb		= proc_kill_sb,
+	.fs_flags		= FS_USERNS_MOUNT | FS_USERNS_MOUNT_RESTRICTED | FS_DISALLOW_NOTIFY_PERM,
+};
+
+void __init proc_root_init(void)
+{
+	proc_init_kmemcache();
+	set_proc_pid_nlink();
+	proc_self_init();
+	proc_thread_self_init();
+	proc_symlink("mounts", NULL, "self/mounts");
+
+	proc_net_init();
+	proc_mkdir("fs", NULL);
+	proc_mkdir("driver", NULL);
+	proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */
+#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
+	/* just give it a mountpoint */
+	proc_create_mount_point("openprom");
+#endif
+	proc_tty_init();
+	proc_mkdir("bus", NULL);
+	proc_sys_init();
+
+	/*
+	 * Last things last. It is not like userspace processes eager
+	 * to open /proc files exist at this point but register last
+	 * anyway.
+	 */
+	register_filesystem(&proc_fs_type);
+}
+
+static int proc_root_getattr(struct mnt_idmap *idmap,
+			     const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
+{
+	generic_fillattr(&nop_mnt_idmap, request_mask, d_inode(path->dentry),
+			 stat);
+	stat->nlink = proc_root.nlink + nr_processes();
+	return 0;
+}
+
+static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
+{
+	if (!proc_pid_lookup(dentry, flags))
+		return NULL;
+
+	return proc_lookup(dir, dentry, flags);
+}
+
+static int proc_root_readdir(struct file *file, struct dir_context *ctx)
+{
+	if (ctx->pos < FIRST_PROCESS_ENTRY) {
+		int error = proc_readdir(file, ctx);
+		if (unlikely(error <= 0))
+			return error;
+		ctx->pos = FIRST_PROCESS_ENTRY;
+	}
+
+	return proc_pid_readdir(file, ctx);
+}
+
+/*
+ * The root /proc directory is special, as it has the
+ * <pid> directories. Thus we don't use the generic
+ * directory handling functions for that..
+ */
+static const struct file_operations proc_root_operations = {
+	.read		 = generic_read_dir,
+	.iterate_shared	 = proc_root_readdir,
+	.llseek		= generic_file_llseek,
+};
+
+/*
+ * proc root can do almost nothing..
+ */
+static const struct inode_operations proc_root_inode_operations = {
+	.lookup		= proc_root_lookup,
+	.getattr	= proc_root_getattr,
+};
+
+/*
+ * This is the root "inode" in the /proc tree..
+ */
+struct proc_dir_entry proc_root = {
+	.low_ino	= PROCFS_ROOT_INO,
+	.namelen	= 5,
+	.mode		= S_IFDIR | S_IRUGO | S_IXUGO,
+	.nlink		= 2,
+	.refcnt		= REFCOUNT_INIT(1),
+	.proc_iops	= &proc_root_inode_operations,
+	.proc_dir_ops	= &proc_root_operations,
+	.parent		= &proc_root,
+	.subdir		= RB_ROOT,
+	.name		= "/proc",
+};

linux-7.2.3/fs/proc/self.c

@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cache.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+/*
+ * /proc/self:
+ */
+static const char *proc_self_get_link(struct dentry *dentry,
+				      struct inode *inode,
+				      struct delayed_call *done)
+{
+	struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
+	pid_t tgid = task_tgid_nr_ns(current, ns);
+	char *name;
+
+	if (!tgid)
+		return ERR_PTR(-ENOENT);
+	/* max length of unsigned int in decimal + NULL term */
+	name = kmalloc(10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!name))
+		return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD);
+	sprintf(name, "%u", tgid);
+	set_delayed_call(done, kfree_link, name);
+	return name;
+}
+
+static const struct inode_operations proc_self_inode_operations = {
+	.get_link	= proc_self_get_link,
+};
+
+unsigned self_inum __ro_after_init;
+
+int proc_setup_self(struct super_block *s)
+{
+	struct dentry *self;
+	int ret = -ENOMEM;
+
+	self = d_alloc_name(s->s_root, "self");
+	if (self) {
+		struct inode *inode = new_inode(s);
+		if (inode) {
+			inode->i_ino = self_inum;
+			simple_inode_init_ts(inode);
+			inode->i_mode = S_IFLNK | S_IRWXUGO;
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
+			inode->i_op = &proc_self_inode_operations;
+			d_make_persistent(self, inode);
+			ret = 0;
+		}
+		dput(self);
+	}
+
+	if (ret)
+		pr_err("proc_fill_super: can't allocate /proc/self\n");
+
+	return ret;
+}
+
+void __init proc_self_init(void)
+{
+	proc_alloc_inum(&self_inum);
+}

linux-7.2.3/fs/proc/softirqs.c

@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+/*
+ * /proc/softirqs  ... display the number of softirqs
+ */
+static int show_softirqs(struct seq_file *p, void *v)
+{
+	int i, j;
+
+	seq_puts(p, "                    ");
+	for_each_possible_cpu(i)
+		seq_printf(p, "CPU%-8d", i);
+	seq_putc(p, '\n');
+
+	for (i = 0; i < NR_SOFTIRQS; i++) {
+		seq_printf(p, "%12s:", softirq_to_name[i]);
+		for_each_possible_cpu(j)
+			seq_put_decimal_ull_width(p, " ", kstat_softirqs_cpu(i, j), 10);
+		seq_putc(p, '\n');
+	}
+	return 0;
+}
+
+static int __init proc_softirqs_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = proc_create_single("softirqs", 0, NULL, show_softirqs);
+	pde_make_permanent(pde);
+	return 0;
+}
+fs_initcall(proc_softirqs_init);

linux-7.2.3/fs/proc/stat.c

@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cpumask.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/sched/stat.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/time_namespace.h>
+#include <linux/irqnr.h>
+#include <linux/sched/cputime.h>
+#include <linux/tick.h>
+
+#ifndef arch_irq_stat_cpu
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+
+static void show_irq_gap(struct seq_file *p, unsigned int gap)
+{
+	static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0";
+
+	while (gap > 0) {
+		unsigned int inc;
+
+		inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2);
+		seq_write(p, zeros, 2 * inc);
+		gap -= inc;
+	}
+}
+
+static void show_all_irqs(struct seq_file *p)
+{
+	unsigned int i, next = 0;
+
+	for_each_active_irq(i) {
+		show_irq_gap(p, i - next);
+		seq_put_decimal_ull(p, " ", kstat_irqs_usr(i));
+		next = i + 1;
+	}
+	show_irq_gap(p, irq_get_nr_irqs() - next);
+}
+
+static int show_stat(struct seq_file *p, void *v)
+{
+	int i, j;
+	u64 user, nice, system, idle, iowait, irq, softirq, steal;
+	u64 guest, guest_nice;
+	u64 sum = 0;
+	u64 sum_softirq = 0;
+	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
+	struct timespec64 boottime;
+
+	user = nice = system = idle = iowait =
+		irq = softirq = steal = 0;
+	guest = guest_nice = 0;
+	getboottime64(&boottime);
+	/* shift boot timestamp according to the timens offset */
+	timens_sub_boottime(&boottime);
+
+	for_each_possible_cpu(i) {
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		user		+= cpustat[CPUTIME_USER];
+		nice		+= cpustat[CPUTIME_NICE];
+		system		+= cpustat[CPUTIME_SYSTEM];
+		idle		+= cpustat[CPUTIME_IDLE];
+		iowait		+= cpustat[CPUTIME_IOWAIT];
+		irq		+= cpustat[CPUTIME_IRQ];
+		softirq		+= cpustat[CPUTIME_SOFTIRQ];
+		steal		+= cpustat[CPUTIME_STEAL];
+		guest		+= cpustat[CPUTIME_GUEST];
+		guest_nice	+= cpustat[CPUTIME_GUEST_NICE];
+		sum		+= kstat_cpu_irqs_sum(i);
+		sum		+= arch_irq_stat_cpu(i);
+
+		for (j = 0; j < NR_SOFTIRQS; j++) {
+			unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
+
+			per_softirq_sums[j] += softirq_stat;
+			sum_softirq += softirq_stat;
+		}
+	}
+
+	seq_put_decimal_ull(p, "cpu  ", nsec_to_clock_t(user));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
+	seq_putc(p, '\n');
+
+	for_each_online_cpu(i) {
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
+		user		= cpustat[CPUTIME_USER];
+		nice		= cpustat[CPUTIME_NICE];
+		system		= cpustat[CPUTIME_SYSTEM];
+		idle		= cpustat[CPUTIME_IDLE];
+		iowait		= cpustat[CPUTIME_IOWAIT];
+		irq		= cpustat[CPUTIME_IRQ];
+		softirq		= cpustat[CPUTIME_SOFTIRQ];
+		steal		= cpustat[CPUTIME_STEAL];
+		guest		= cpustat[CPUTIME_GUEST];
+		guest_nice	= cpustat[CPUTIME_GUEST_NICE];
+		seq_printf(p, "cpu%d", i);
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
+		seq_putc(p, '\n');
+	}
+	seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);
+
+	show_all_irqs(p);
+
+	seq_printf(p,
+		"\nctxt %llu\n"
+		"btime %llu\n"
+		"processes %lu\n"
+		"procs_running %u\n"
+		"procs_blocked %u\n",
+		nr_context_switches(),
+		(unsigned long long)boottime.tv_sec,
+		total_forks,
+		nr_running(),
+		nr_iowait());
+
+	seq_put_decimal_ull(p, "softirq ", (unsigned long long)sum_softirq);
+
+	for (i = 0; i < NR_SOFTIRQS; i++)
+		seq_put_decimal_ull(p, " ", per_softirq_sums[i]);
+	seq_putc(p, '\n');
+
+	return 0;
+}
+
+static int stat_open(struct inode *inode, struct file *file)
+{
+	unsigned int size = 1024 + 128 * num_online_cpus();
+
+	/* minimum size to display an interrupt count : 2 bytes */
+	size += 2 * irq_get_nr_irqs();
+	return single_open_size(file, show_stat, NULL, size);
+}
+
+static const struct proc_ops stat_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_open	= stat_open,
+	.proc_read_iter	= seq_read_iter,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+};
+
+static int __init proc_stat_init(void)
+{
+	proc_create("stat", 0, NULL, &stat_proc_ops);
+	return 0;
+}
+fs_initcall(proc_stat_init);

linux-7.2.3/fs/proc/task_nommu.c

@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/mm.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/fs_struct.h>
+#include <linux/mount.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include <linux/sched/mm.h>
+
+#include "internal.h"
+
+/*
+ * Logic: we've got two memory sums for each process, "shared", and
+ * "non-shared". Shared memory may get counted more than once, for
+ * each process that owns it. Non-shared memory is counted
+ * accurately.
+ */
+void task_mem(struct seq_file *m, struct mm_struct *mm)
+{
+	VMA_ITERATOR(vmi, mm, 0);
+	struct vm_area_struct *vma;
+	struct vm_region *region;
+	unsigned long bytes = 0, sbytes = 0, slack = 0, size;
+
+	mmap_read_lock(mm);
+	for_each_vma(vmi, vma) {
+		bytes += kobjsize(vma);
+
+		region = vma->vm_region;
+		if (region) {
+			size = kobjsize(region);
+			size += region->vm_end - region->vm_start;
+		} else {
+			size = vma->vm_end - vma->vm_start;
+		}
+
+		if (atomic_read(&mm->mm_count) > 1 ||
+		    is_nommu_shared_mapping(vma->vm_flags)) {
+			sbytes += size;
+		} else {
+			bytes += size;
+			if (region)
+				slack = region->vm_end - vma->vm_end;
+		}
+	}
+
+	if (atomic_read(&mm->mm_count) > 1)
+		sbytes += kobjsize(mm);
+	else
+		bytes += kobjsize(mm);
+
+	if (current->fs && current->fs->users > 1)
+		sbytes += kobjsize(current->fs);
+	else
+		bytes += kobjsize(current->fs);
+
+	if (current->files && atomic_read(&current->files->count) > 1)
+		sbytes += kobjsize(current->files);
+	else
+		bytes += kobjsize(current->files);
+
+	if (current->sighand && refcount_read(&current->sighand->count) > 1)
+		sbytes += kobjsize(current->sighand);
+	else
+		bytes += kobjsize(current->sighand);
+
+	bytes += kobjsize(current); /* includes kernel stack */
+
+	mmap_read_unlock(mm);
+
+	seq_printf(m,
+		"Mem:\t%8lu bytes\n"
+		"Slack:\t%8lu bytes\n"
+		"Shared:\t%8lu bytes\n",
+		bytes, slack, sbytes);
+}
+
+unsigned long task_vsize(struct mm_struct *mm)
+{
+	VMA_ITERATOR(vmi, mm, 0);
+	struct vm_area_struct *vma;
+	unsigned long vsize = 0;
+
+	mmap_read_lock(mm);
+	for_each_vma(vmi, vma)
+		vsize += vma->vm_end - vma->vm_start;
+	mmap_read_unlock(mm);
+	return vsize;
+}
+
+unsigned long task_statm(struct mm_struct *mm,
+			 unsigned long *shared, unsigned long *text,
+			 unsigned long *data, unsigned long *resident)
+{
+	VMA_ITERATOR(vmi, mm, 0);
+	struct vm_area_struct *vma;
+	struct vm_region *region;
+	unsigned long size = kobjsize(mm);
+
+	mmap_read_lock(mm);
+	for_each_vma(vmi, vma) {
+		size += kobjsize(vma);
+		region = vma->vm_region;
+		if (region) {
+			size += kobjsize(region);
+			size += region->vm_end - region->vm_start;
+		}
+	}
+
+	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
+		>> PAGE_SHIFT;
+	*data = (PAGE_ALIGN(mm->start_stack) - (mm->start_data & PAGE_MASK))
+		>> PAGE_SHIFT;
+	mmap_read_unlock(mm);
+	size >>= PAGE_SHIFT;
+	size += *text + *data;
+	*resident = size;
+	return size;
+}
+
+/*
+ * display a single VMA to a sequenced file
+ */
+static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long ino = 0;
+	struct file *file;
+	dev_t dev = 0;
+	int flags;
+	unsigned long long pgoff = 0;
+
+	flags = vma->vm_flags;
+	file = vma->vm_file;
+
+	if (file) {
+		struct inode *inode = file_inode(vma->vm_file);
+		dev = inode->i_sb->s_dev;
+		ino = inode->i_ino;
+		pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
+	}
+
+	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+	seq_printf(m,
+		   "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
+		   vma->vm_start,
+		   vma->vm_end,
+		   flags & VM_READ ? 'r' : '-',
+		   flags & VM_WRITE ? 'w' : '-',
+		   flags & VM_EXEC ? 'x' : '-',
+		   flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
+		   pgoff,
+		   MAJOR(dev), MINOR(dev), ino);
+
+	if (file) {
+		seq_pad(m, ' ');
+		seq_path(m, file_user_path(file), "");
+	} else if (mm && vma_is_initial_stack(vma)) {
+		seq_pad(m, ' ');
+		seq_puts(m, "[stack]");
+	}
+
+	seq_putc(m, '\n');
+	return 0;
+}
+
+/*
+ * display mapping lines for a particular process's /proc/pid/maps
+ */
+static int show_map(struct seq_file *m, void *_p)
+{
+	return nommu_vma_show(m, _p);
+}
+
+static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv,
+						loff_t *ppos)
+{
+	struct vm_area_struct *vma = vma_next(&priv->iter);
+
+	if (vma) {
+		*ppos = vma->vm_start;
+	} else {
+		*ppos = -1UL;
+	}
+
+	return vma;
+}
+
+static void *m_start(struct seq_file *m, loff_t *ppos)
+{
+	struct proc_maps_private *priv = m->private;
+	unsigned long last_addr = *ppos;
+	struct mm_struct *mm;
+
+	/* See proc_get_vma(). Zero at the start or after lseek. */
+	if (last_addr == -1UL)
+		return NULL;
+
+	/* pin the task and mm whilst we play with them */
+	priv->task = get_proc_task(priv->inode);
+	if (!priv->task)
+		return ERR_PTR(-ESRCH);
+
+	mm = priv->lock_ctx.mm;
+	if (!mm || !mmget_not_zero(mm)) {
+		put_task_struct(priv->task);
+		priv->task = NULL;
+		return NULL;
+	}
+
+	if (mmap_read_lock_killable(mm)) {
+		mmput(mm);
+		put_task_struct(priv->task);
+		priv->task = NULL;
+		return ERR_PTR(-EINTR);
+	}
+
+	vma_iter_init(&priv->iter, mm, last_addr);
+
+	return proc_get_vma(priv, ppos);
+}
+
+static void m_stop(struct seq_file *m, void *v)
+{
+	struct proc_maps_private *priv = m->private;
+	struct mm_struct *mm = priv->lock_ctx.mm;
+
+	if (!priv->task)
+		return;
+
+	mmap_read_unlock(mm);
+	mmput(mm);
+	put_task_struct(priv->task);
+	priv->task = NULL;
+}
+
+static void *m_next(struct seq_file *m, void *_p, loff_t *ppos)
+{
+	return proc_get_vma(m->private, ppos);
+}
+
+static const struct seq_operations proc_pid_maps_ops = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_map
+};
+
+static int maps_open(struct inode *inode, struct file *file,
+		     const struct seq_operations *ops)
+{
+	struct proc_maps_private *priv;
+
+	priv = __seq_open_private(file, ops, sizeof(*priv));
+	if (!priv)
+		return -ENOMEM;
+
+	priv->inode = inode;
+	priv->lock_ctx.mm = proc_mem_open(inode, PTRACE_MODE_READ);
+	if (IS_ERR_OR_NULL(priv->lock_ctx.mm)) {
+		int err = priv->lock_ctx.mm ? PTR_ERR(priv->lock_ctx.mm) : -ESRCH;
+
+		seq_release_private(inode, file);
+		return err;
+	}
+
+	return 0;
+}
+
+
+static int map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct proc_maps_private *priv = seq->private;
+
+	if (priv->lock_ctx.mm)
+		mmdrop(priv->lock_ctx.mm);
+
+	return seq_release_private(inode, file);
+}
+
+static int pid_maps_open(struct inode *inode, struct file *file)
+{
+	return maps_open(inode, file, &proc_pid_maps_ops);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+	.open		= pid_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= map_release,
+};
+

linux-7.2.3/fs/proc/thread_self.c

@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cache.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+/*
+ * /proc/thread_self:
+ */
+static const char *proc_thread_self_get_link(struct dentry *dentry,
+					     struct inode *inode,
+					     struct delayed_call *done)
+{
+	struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
+	pid_t tgid = task_tgid_nr_ns(current, ns);
+	pid_t pid = task_pid_nr_ns(current, ns);
+	char *name;
+
+	if (!pid)
+		return ERR_PTR(-ENOENT);
+	name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!name))
+		return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD);
+	sprintf(name, "%u/task/%u", tgid, pid);
+	set_delayed_call(done, kfree_link, name);
+	return name;
+}
+
+static const struct inode_operations proc_thread_self_inode_operations = {
+	.get_link	= proc_thread_self_get_link,
+};
+
+unsigned thread_self_inum __ro_after_init;
+
+int proc_setup_thread_self(struct super_block *s)
+{
+	struct dentry *thread_self;
+	int ret = -ENOMEM;
+
+	thread_self = d_alloc_name(s->s_root, "thread-self");
+	if (thread_self) {
+		struct inode *inode = new_inode(s);
+		if (inode) {
+			inode->i_ino = thread_self_inum;
+			simple_inode_init_ts(inode);
+			inode->i_mode = S_IFLNK | S_IRWXUGO;
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
+			inode->i_op = &proc_thread_self_inode_operations;
+			d_make_persistent(thread_self, inode);
+			ret = 0;
+		}
+		dput(thread_self);
+	}
+
+	if (ret)
+		pr_err("proc_fill_super: can't allocate /proc/thread-self\n");
+	return ret;
+}
+
+void __init proc_thread_self_init(void)
+{
+	proc_alloc_inum(&thread_self_inum);
+}

linux-7.2.3/fs/proc/uptime.c

@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/time.h>
+#include <linux/time_namespace.h>
+#include <linux/kernel_stat.h>
+#include "internal.h"
+
+static int uptime_proc_show(struct seq_file *m, void *v)
+{
+	struct timespec64 uptime;
+	struct timespec64 idle;
+	u64 idle_nsec;
+	u32 rem;
+	int i;
+
+	idle_nsec = 0;
+	for_each_possible_cpu(i)
+		idle_nsec += kcpustat_field(CPUTIME_IDLE, i);
+
+	ktime_get_boottime_ts64(&uptime);
+	timens_add_boottime(&uptime);
+
+	idle.tv_sec = div_u64_rem(idle_nsec, NSEC_PER_SEC, &rem);
+	idle.tv_nsec = rem;
+	seq_printf(m, "%lu.%02lu %lu.%02lu\n",
+			(unsigned long) uptime.tv_sec,
+			(uptime.tv_nsec / (NSEC_PER_SEC / 100)),
+			(unsigned long) idle.tv_sec,
+			(idle.tv_nsec / (NSEC_PER_SEC / 100)));
+	return 0;
+}
+
+static int __init proc_uptime_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = proc_create_single("uptime", 0, NULL, uptime_proc_show);
+	pde_make_permanent(pde);
+	return 0;
+}
+fs_initcall(proc_uptime_init);

linux-7.2.3/fs/proc/util.c

@@ -0,0 +1,24 @@
+#include <linux/dcache.h>
+#include "internal.h"
+
+unsigned name_to_int(const struct qstr *qstr)
+{
+	const char *name = qstr->name;
+	int len = qstr->len;
+	unsigned n = 0;
+
+	if (len > 1 && *name == '0')
+		goto out;
+	do {
+		unsigned c = *name++ - '0';
+		if (c > 9)
+			goto out;
+		if (n >= (~0U-9)/10)
+			goto out;
+		n *= 10;
+		n += c;
+	} while (--len > 0);
+	return n;
+out:
+	return ~0U;
+}

linux-7.2.3/fs/proc/version.c

@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/utsname.h>
+#include "internal.h"
+
+static int version_proc_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, linux_proc_banner,
+		utsname()->sysname,
+		utsname()->release,
+		utsname()->version);
+	return 0;
+}
+
+static int __init proc_version_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = proc_create_single("version", 0, NULL, version_proc_show);
+	pde_make_permanent(pde);
+	return 0;
+}
+fs_initcall(proc_version_init);