Resguardo inicial

linux-7.2.3/arch/um/kernel/Makefile

@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux,intel}.com)
+#
+
+# Don't instrument UML-specific code; without this, we may crash when
+# accessing the instrumentation buffer for the first time from the
+# kernel.
+KCOV_INSTRUMENT                := n
+
+CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START)		\
+                        -DELF_ARCH=$(LDS_ELF_ARCH)	\
+                        -DELF_FORMAT=$(LDS_ELF_FORMAT)	\
+			$(LDS_EXTRA)
+always-$(KBUILD_BUILTIN) := vmlinux.lds
+
+obj-y = config.o exec.o exitcode.o irq.o ksyms.o mem.o \
+	physmem.o process.o ptrace.o reboot.o sigio.o \
+	signal.o sysrq.o time.o tlb.o trap.o \
+	um_arch.o umid.o kmsg_dump.o capflags.o skas/
+obj-y += load_file.o
+
+obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
+obj-$(CONFIG_GPROF)	+= gprof_syms.o
+obj-$(CONFIG_OF) += dtb.o
+obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+obj-$(CONFIG_STACKTRACE) += stacktrace.o
+obj-$(CONFIG_SMP) += smp.o
+
+USER_OBJS := config.o
+
+include $(srctree)/arch/um/scripts/Makefile.rules
+
+targets := config.c config.tmp capflags.c
+
+# Be careful with the below Sed code - sed is pitfall-rich!
+# We use sed to lower build requirements, for "embedded" builders for instance.
+
+$(obj)/config.tmp: $(objtree)/.config FORCE
+	$(call if_changed,quote1)
+
+quiet_cmd_quote1 = QUOTE   $@
+      cmd_quote1 = sed -e 's/"/\\"/g' -e 's/^/"/' -e 's/$$/\\n",/' \
+		   $< > $@
+
+$(obj)/config.c: $(src)/config.c.in $(obj)/config.tmp FORCE
+	$(call if_changed,quote2)
+
+quiet_cmd_mkcapflags = MKCAP   $@
+      cmd_mkcapflags = $(CONFIG_SHELL) $(src)/../../x86/kernel/cpu/mkcapflags.sh $@ $^
+
+cpufeature = $(src)/../../x86/include/asm/cpufeatures.h
+vmxfeature = $(src)/../../x86/include/asm/vmxfeatures.h
+
+$(obj)/capflags.c: $(cpufeature) $(vmxfeature) $(src)/../../x86/kernel/cpu/mkcapflags.sh FORCE
+	$(call if_changed,mkcapflags)
+
+quiet_cmd_quote2 = QUOTE   $@
+      cmd_quote2 = sed -e '/CONFIG/{'          \
+		  -e 's/"CONFIG"//'            \
+		  -e 'r $(obj)/config.tmp'     \
+		  -e 'a \'                     \
+		  -e '""'                      \
+		  -e '}'                       \
+		  $< > $@

linux-7.2.3/arch/um/kernel/asm-offsets.c

@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define COMPILE_OFFSETS
+#include <linux/stddef.h>
+#include <linux/sched.h>
+#include <linux/elf.h>
+#include <linux/crypto.h>
+#include <linux/kbuild.h>
+#include <linux/audit.h>
+#include <linux/fs.h>
+#include <asm/mman.h>
+#include <asm/seccomp.h>
+#include <asm/extable.h>
+
+/* workaround for a warning with -Wmissing-prototypes */
+void foo(void);
+
+void foo(void)
+{
+	DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE);
+
+	DEFINE(UM_KERN_PAGE_SIZE, PAGE_SIZE);
+	DEFINE(UM_KERN_PAGE_MASK, PAGE_MASK);
+	DEFINE(UM_KERN_PAGE_SHIFT, PAGE_SHIFT);
+
+	DEFINE(UM_GFP_KERNEL, GFP_KERNEL);
+	DEFINE(UM_GFP_ATOMIC, GFP_ATOMIC);
+
+	DEFINE(UM_THREAD_SIZE, THREAD_SIZE);
+
+	DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC);
+	DEFINE(UM_NSEC_PER_USEC, NSEC_PER_USEC);
+
+	DEFINE(UM_KERN_GDT_ENTRY_TLS_ENTRIES, GDT_ENTRY_TLS_ENTRIES);
+
+	DEFINE(UM_SECCOMP_ARCH_NATIVE, SECCOMP_ARCH_NATIVE);
+
+	DEFINE(HOSTFS_ATTR_MODE, ATTR_MODE);
+	DEFINE(HOSTFS_ATTR_UID, ATTR_UID);
+	DEFINE(HOSTFS_ATTR_GID, ATTR_GID);
+	DEFINE(HOSTFS_ATTR_SIZE, ATTR_SIZE);
+	DEFINE(HOSTFS_ATTR_ATIME, ATTR_ATIME);
+	DEFINE(HOSTFS_ATTR_MTIME, ATTR_MTIME);
+	DEFINE(HOSTFS_ATTR_CTIME, ATTR_CTIME);
+	DEFINE(HOSTFS_ATTR_ATIME_SET, ATTR_ATIME_SET);
+	DEFINE(HOSTFS_ATTR_MTIME_SET, ATTR_MTIME_SET);
+
+	DEFINE(ALT_INSTR_SIZE, sizeof(struct alt_instr));
+	DEFINE(EXTABLE_SIZE,   sizeof(struct exception_table_entry));
+}

linux-7.2.3/arch/um/kernel/config.c.in

@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <init.h>
+
+static __initdata const char *config[] = {
+"CONFIG"
+};
+
+static int __init print_config(char *line, int *add)
+{
+	int i;
+	for (i = 0; i < sizeof(config)/sizeof(config[0]); i++)
+		printf("%s", config[i]);
+	exit(0);
+}
+
+__uml_setup("--showconfig", print_config,
+"--showconfig\n"
+"    Prints the config file that this UML binary was generated from.\n\n"
+);
+

linux-7.2.3/arch/um/kernel/dtb.c

@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/init.h>
+#include <linux/of_fdt.h>
+#include <linux/printk.h>
+#include <linux/memblock.h>
+#include <init.h>
+
+#include "um_arch.h"
+
+static char *dtb __initdata;
+
+void uml_dtb_init(void)
+{
+	long long size;
+	void *area;
+
+	area = uml_load_file(dtb, &size);
+	if (area) {
+		if (!early_init_dt_scan(area, __pa(area))) {
+			pr_err("invalid DTB %s\n", dtb);
+			memblock_free(area, size);
+			return;
+		}
+
+		early_init_fdt_scan_reserved_mem();
+	}
+
+	unflatten_device_tree();
+}
+
+static int __init uml_dtb_setup(char *line, int *add)
+{
+	*add = 0;
+	dtb = line;
+	return 0;
+}
+
+__uml_setup("dtb=", uml_dtb_setup,
+"dtb=<file>\n"
+"    Boot the kernel with the devicetree blob from the specified file.\n\n"
+);

linux-7.2.3/arch/um/kernel/dyn.lds.S

@@ -0,0 +1,182 @@
+#include <asm/vmlinux.lds.h>
+#include <asm/page.h>
+
+OUTPUT_FORMAT(ELF_FORMAT)
+OUTPUT_ARCH(ELF_ARCH)
+ENTRY(_start)
+jiffies = jiffies_64;
+
+VERSION {
+  {
+    local: *;
+  };
+}
+
+SECTIONS
+{
+  PROVIDE (__executable_start = START);
+  . = START + SIZEOF_HEADERS;
+  .interp         : { *(.interp) }
+  __binary_start = .;
+  . = ALIGN(4096);		/* Init code and data */
+  _text = .;
+  INIT_TEXT_SECTION(PAGE_SIZE)
+
+  . = ALIGN(PAGE_SIZE);
+
+  /* Read-only sections, merged into text segment: */
+  .hash           : { *(.hash) }
+  .gnu.hash       : { *(.gnu.hash) }
+  .dynsym         : { *(.dynsym) }
+  .dynstr         : { *(.dynstr) }
+  .gnu.version    : { *(.gnu.version) }
+  .gnu.version_d  : { *(.gnu.version_d) }
+  .gnu.version_r  : { *(.gnu.version_r) }
+  .rel.init       : { *(.rel.init) }
+  .rela.init      : { *(.rela.init) }
+  .rel.text       : { *(.rel.text .rel.text.* .rel.gnu.linkonce.t.*) }
+  .rela.text      : { *(.rela.text .rela.text.* .rela.gnu.linkonce.t.*) }
+  .rel.fini       : { *(.rel.fini) }
+  .rela.fini      : { *(.rela.fini) }
+  .rel.rodata     : { *(.rel.rodata .rel.rodata.* .rel.gnu.linkonce.r.*) }
+  .rela.rodata    : { *(.rela.rodata .rela.rodata.* .rela.gnu.linkonce.r.*) }
+  .rel.data       : { *(.rel.data .rel.data.* .rel.gnu.linkonce.d.*) }
+  .rela.data      : { *(.rela.data .rela.data.* .rela.gnu.linkonce.d.*) }
+  .rel.tdata	  : { *(.rel.tdata .rel.tdata.* .rel.gnu.linkonce.td.*) }
+  .rela.tdata	  : { *(.rela.tdata .rela.tdata.* .rela.gnu.linkonce.td.*) }
+  .rel.tbss	  : { *(.rel.tbss .rel.tbss.* .rel.gnu.linkonce.tb.*) }
+  .rela.tbss	  : { *(.rela.tbss .rela.tbss.* .rela.gnu.linkonce.tb.*) }
+  .rel.ctors      : { *(.rel.ctors) }
+  .rela.ctors     : { *(.rela.ctors) }
+  .rel.dtors      : { *(.rel.dtors) }
+  .rela.dtors     : { *(.rela.dtors) }
+  .rel.got        : { *(.rel.got) }
+  .rela.got       : { *(.rela.got) }
+  .rel.bss        : { *(.rel.bss .rel.bss.* .rel.gnu.linkonce.b.*) }
+  .rela.bss       : { *(.rela.bss .rela.bss.* .rela.gnu.linkonce.b.*) }
+  .rel.plt : {
+	*(.rel.plt)
+	PROVIDE_HIDDEN(__rel_iplt_start = .);
+	*(.rel.iplt)
+	PROVIDE_HIDDEN(__rel_iplt_end = .);
+  }
+  .rela.plt : {
+	*(.rela.plt)
+	PROVIDE_HIDDEN(__rela_iplt_start = .);
+	*(.rela.iplt)
+	PROVIDE_HIDDEN(__rela_iplt_end = .);
+  }
+  .init           : {
+    KEEP (*(.init))
+  } =0x90909090
+  .plt            : { *(.plt) }
+  .text           : {
+    _stext = .;
+    TEXT_TEXT
+    SCHED_TEXT
+    LOCK_TEXT
+    IRQENTRY_TEXT
+    SOFTIRQENTRY_TEXT
+    *(.fixup)
+    *(.stub .text.* .gnu.linkonce.t.*)
+    /* .gnu.warning sections are handled specially by elf32.em.  */
+    *(.gnu.warning)
+
+    . = ALIGN(PAGE_SIZE);
+  } =0x90909090
+  . = ALIGN(PAGE_SIZE);
+  .syscall_stub : {
+	__syscall_stub_start = .;
+	*(.__syscall_stub*)
+	__syscall_stub_end = .;
+  }
+  .fini           : {
+    KEEP (*(.fini))
+  } =0x90909090
+
+  .kstrtab : { *(.kstrtab) }
+
+  #include <asm/common.lds.S>
+
+  __init_begin = .;
+  init.data : { INIT_DATA }
+  __init_end = .;
+
+  /* Ensure the __preinit_array_start label is properly aligned.  We
+     could instead move the label definition inside the section, but
+     the linker would then create the section even if it turns out to
+     be empty, which isn't pretty.  */
+  . = ALIGN(32 / 8);
+  .preinit_array     : { *(.preinit_array) }
+  .init_array     : {
+    *(.kasan_init)
+    *(.init_array.*)
+    *(.init_array)
+  }
+  .fini_array     : { *(.fini_array) }
+  .data           : {
+    INIT_TASK_DATA(KERNEL_STACK_SIZE)
+    DATA_DATA
+    *(.data.* .gnu.linkonce.d.*)
+    SORT(CONSTRUCTORS)
+  }
+  .data1          : { *(.data1) }
+  .tdata	  : { *(.tdata .tdata.* .gnu.linkonce.td.*) }
+  .tbss		  : { *(.tbss .tbss.* .gnu.linkonce.tb.*) *(.tcommon) }
+  .eh_frame       : { KEEP (*(.eh_frame)) }
+  .gcc_except_table   : { *(.gcc_except_table) }
+  .dynamic        : { *(.dynamic) }
+  .ctors          : {
+    /* gcc uses crtbegin.o to find the start of
+       the constructors, so we make sure it is
+       first.  Because this is a wildcard, it
+       doesn't matter if the user does not
+       actually link against crtbegin.o; the
+       linker won't look for a file to match a
+       wildcard.  The wildcard also means that it
+       doesn't matter which directory crtbegin.o
+       is in.  */
+    KEEP (*crtbegin.o(.ctors))
+    /* We don't want to include the .ctor section from
+       from the crtend.o file until after the sorted ctors.
+       The .ctor section from the crtend file contains the
+       end of ctors marker and it must be last */
+    KEEP (*(EXCLUDE_FILE (*crtend.o ) .ctors))
+    KEEP (*(SORT(.ctors.*)))
+    KEEP (*(.ctors))
+  }
+  .dtors          : {
+    KEEP (*crtbegin.o(.dtors))
+    KEEP (*(EXCLUDE_FILE (*crtend.o ) .dtors))
+    KEEP (*(SORT(.dtors.*)))
+    KEEP (*(.dtors))
+  }
+  .jcr            : { KEEP (*(.jcr)) }
+  .got            : { *(.got.plt) *(.got) }
+  _edata = .;
+  PROVIDE (edata = .);
+  .bss            : {
+   __bss_start = .;
+   *(.dynbss)
+   *(.bss .bss.* .gnu.linkonce.b.*)
+   *(COMMON)
+   /* Align here to ensure that the .bss section occupies space up to
+      _end.  Align after .bss to ensure correct alignment even if the
+      .bss section disappears because there are no input sections.  */
+   . = ALIGN(32 / 8);
+  . = ALIGN(32 / 8);
+  }
+   __bss_stop = .;
+  _end = .;
+  PROVIDE (end = .);
+
+  STABS_DEBUG
+  DWARF_DEBUG
+  MODINFO
+  ELF_DETAILS
+
+  DISCARDS
+}
+
+ASSERT(__syscall_stub_end - __syscall_stub_start <= PAGE_SIZE,
+       "STUB code must not be larger than one page");

linux-7.2.3/arch/um/kernel/early_printk.c

@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011 Richard Weinberger <richrd@nod.at>
+ */
+
+#include <linux/kernel.h>
+#include <linux/console.h>
+#include <linux/init.h>
+#include <os.h>
+
+static void early_console_write(struct console *con, const char *s, unsigned int n)
+{
+	um_early_printk(s, n);
+}
+
+static struct console early_console_dev = {
+	.name = "earlycon",
+	.write = early_console_write,
+	.flags = CON_BOOT,
+	.index = -1,
+};
+
+static int __init setup_early_printk(char *buf)
+{
+	if (!early_console) {
+		early_console = &early_console_dev;
+		register_console(&early_console_dev);
+	}
+	return 0;
+}
+
+early_param("earlyprintk", setup_early_printk);

linux-7.2.3/arch/um/kernel/exec.c

@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/stddef.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/ptrace.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/slab.h>
+#include <asm/current.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+#include <as-layout.h>
+#include <mem_user.h>
+#include <registers.h>
+#include <skas.h>
+#include <os.h>
+
+void flush_thread(void)
+{
+	arch_flush_thread(&current->thread.arch);
+
+	get_safe_registers(current_pt_regs()->regs.gp,
+			   current_pt_regs()->regs.fp);
+}
+
+void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp)
+{
+	PT_REGS_IP(regs) = eip;
+	PT_REGS_SP(regs) = esp;
+	clear_thread_flag(TIF_SINGLESTEP);
+}
+EXPORT_SYMBOL(start_thread);

linux-7.2.3/arch/um/kernel/exitcode.c

@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+
+/*
+ * If read and write race, the read will still atomically read a valid
+ * value.
+ */
+int uml_exitcode = 0;
+
+static int exitcode_proc_show(struct seq_file *m, void *v)
+{
+	int val;
+
+	/*
+	 * Save uml_exitcode in a local so that we don't need to guarantee
+	 * that sprintf accesses it atomically.
+	 */
+	val = uml_exitcode;
+	seq_printf(m, "%d\n", val);
+	return 0;
+}
+
+static int exitcode_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, exitcode_proc_show, NULL);
+}
+
+static ssize_t exitcode_proc_write(struct file *file,
+		const char __user *buffer, size_t count, loff_t *pos)
+{
+	char *end, buf[sizeof("nnnnn\0")];
+	size_t size;
+	int tmp;
+
+	size = min(count, sizeof(buf));
+	if (copy_from_user(buf, buffer, size))
+		return -EFAULT;
+
+	tmp = simple_strtol(buf, &end, 0);
+	if ((*end != '\0') && !isspace(*end))
+		return -EINVAL;
+
+	uml_exitcode = tmp;
+	return count;
+}
+
+static const struct proc_ops exitcode_proc_ops = {
+	.proc_open	= exitcode_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= exitcode_proc_write,
+};
+
+static int make_proc_exitcode(void)
+{
+	struct proc_dir_entry *ent;
+
+	ent = proc_create("exitcode", 0600, NULL, &exitcode_proc_ops);
+	if (ent == NULL) {
+		printk(KERN_WARNING "make_proc_exitcode : Failed to register "
+		       "/proc/exitcode\n");
+		return 0;
+	}
+	return 0;
+}
+
+__initcall(make_proc_exitcode);

linux-7.2.3/arch/um/kernel/gprof_syms.c

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+/* 
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/module.h>
+
+extern void mcount(void);
+EXPORT_SYMBOL(mcount);

linux-7.2.3/arch/um/kernel/initrd.c

@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/init.h>
+#include <linux/memblock.h>
+#include <linux/initrd.h>
+#include <asm/types.h>
+#include <init.h>
+#include <os.h>
+
+#include "um_arch.h"
+
+/* Changed by uml_initrd_setup, which is a setup */
+static char *initrd __initdata = NULL;
+
+int __init read_initrd(void)
+{
+	unsigned long long size;
+	void *area;
+
+	if (!initrd)
+		return 0;
+
+	area = uml_load_file(initrd, &size);
+	if (!area)
+		return 0;
+
+	initrd_start = (unsigned long) area;
+	initrd_end = initrd_start + size;
+	return 0;
+}
+
+static int __init uml_initrd_setup(char *line, int *add)
+{
+	*add = 0;
+	initrd = line;
+	return 0;
+}
+
+__uml_setup("initrd=", uml_initrd_setup,
+"initrd=<initrd image>\n"
+"    This is used to boot UML from an initrd image.  The argument is the\n"
+"    name of the file containing the image.\n\n"
+);

linux-7.2.3/arch/um/kernel/irq.c

@@ -0,0 +1,728 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 - Cambridge Greys Ltd
+ * Copyright (C) 2011 - 2014 Cisco Systems Inc
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Derived (i.e. mostly copied) from arch/i386/kernel/irq.c:
+ *	Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
+ */
+
+#include <linux/cpumask.h>
+#include <linux/hardirq.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <as-layout.h>
+#include <kern_util.h>
+#include <os.h>
+#include <irq_user.h>
+#include <irq_kern.h>
+#include <linux/time-internal.h>
+
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+
+#define irq_stats(x)		(&per_cpu(irq_stat, x))
+
+/* When epoll triggers we do not know why it did so
+ * we can also have different IRQs for read and write.
+ * This is why we keep a small irq_reg array for each fd -
+ * one entry per IRQ type
+ */
+struct irq_reg {
+	void *id;
+	int irq;
+	/* it's cheaper to store this than to query it */
+	int events;
+	bool active;
+	bool pending;
+	bool wakeup;
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+	bool pending_event;
+	void (*timetravel_handler)(int, int, void *,
+				   struct time_travel_event *);
+	struct time_travel_event event;
+#endif
+};
+
+struct irq_entry {
+	struct list_head list;
+	int fd;
+	struct irq_reg reg[NUM_IRQ_TYPES];
+	bool suspended;
+	bool sigio_workaround;
+};
+
+static DEFINE_RAW_SPINLOCK(irq_lock);
+static LIST_HEAD(active_fds);
+static DECLARE_BITMAP(irqs_allocated, UM_LAST_SIGNAL_IRQ);
+static bool irqs_suspended;
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+static bool irqs_pending;
+#endif
+
+static void irq_io_loop(struct irq_reg *irq, struct uml_pt_regs *regs)
+{
+/*
+ * irq->active guards against reentry
+ * irq->pending accumulates pending requests
+ * if pending is raised the irq_handler is re-run
+ * until pending is cleared
+ */
+	if (irq->active) {
+		irq->active = false;
+
+		do {
+			irq->pending = false;
+			do_IRQ(irq->irq, regs);
+		} while (irq->pending);
+
+		irq->active = true;
+	} else {
+		irq->pending = true;
+	}
+}
+
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+static void irq_event_handler(struct time_travel_event *ev)
+{
+	struct irq_reg *reg = container_of(ev, struct irq_reg, event);
+
+	/* do nothing if suspended; just cause a wakeup and mark as pending */
+	if (irqs_suspended) {
+		irqs_pending = true;
+		reg->pending_event = true;
+		return;
+	}
+
+	generic_handle_irq(reg->irq);
+}
+
+static bool irq_do_timetravel_handler(struct irq_entry *entry,
+				      enum um_irq_type t)
+{
+	struct irq_reg *reg = &entry->reg[t];
+
+	if (!reg->timetravel_handler)
+		return false;
+
+	/*
+	 * Handle all messages - we might get multiple even while
+	 * interrupts are already suspended, due to suspend order
+	 * etc. Note that time_travel_add_irq_event() will not add
+	 * an event twice, if it's pending already "first wins".
+	 */
+	reg->timetravel_handler(reg->irq, entry->fd, reg->id, &reg->event);
+
+	if (!reg->event.pending)
+		return false;
+
+	return true;
+}
+
+static void irq_do_pending_events(bool timetravel_handlers_only)
+{
+	struct irq_entry *entry;
+
+	if (!irqs_pending || timetravel_handlers_only)
+		return;
+
+	irqs_pending = false;
+
+	list_for_each_entry(entry, &active_fds, list) {
+		enum um_irq_type t;
+
+		for (t = 0; t < NUM_IRQ_TYPES; t++) {
+			struct irq_reg *reg = &entry->reg[t];
+
+			/*
+			 * Any timetravel_handler was invoked already, just
+			 * directly run the IRQ.
+			 */
+			if (reg->pending_event) {
+				irq_enter();
+				generic_handle_irq(reg->irq);
+				irq_exit();
+				reg->pending_event = false;
+			}
+		}
+	}
+}
+#else
+static bool irq_do_timetravel_handler(struct irq_entry *entry,
+				      enum um_irq_type t)
+{
+	return false;
+}
+
+static void irq_do_pending_events(bool timetravel_handlers_only)
+{
+}
+#endif
+
+static void sigio_reg_handler(int idx, struct irq_entry *entry, enum um_irq_type t,
+			      struct uml_pt_regs *regs,
+			      bool timetravel_handlers_only)
+{
+	struct irq_reg *reg = &entry->reg[t];
+
+	if (!reg->events)
+		return;
+
+	if (os_epoll_triggered(idx, reg->events) <= 0)
+		return;
+
+	if (irq_do_timetravel_handler(entry, t))
+		return;
+
+	/*
+	 * If we're called to only run time-travel handlers then don't
+	 * actually proceed but mark sigio as pending (if applicable).
+	 * For suspend/resume, timetravel_handlers_only may be true
+	 * despite time-travel not being configured and used.
+	 */
+	if (timetravel_handlers_only) {
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+		reg->pending_event = true;
+		irqs_pending = true;
+		mark_sigio_pending();
+#endif
+		return;
+	}
+
+	irq_io_loop(reg, regs);
+}
+
+static void _sigio_handler(struct uml_pt_regs *regs,
+			   bool timetravel_handlers_only)
+{
+	struct irq_entry *irq_entry;
+	int n, i;
+
+	if (timetravel_handlers_only && !um_irq_timetravel_handler_used())
+		return;
+
+	/* Flush out pending events that were ignored due to time-travel. */
+	if (!irqs_suspended)
+		irq_do_pending_events(timetravel_handlers_only);
+
+	while (1) {
+		/* This is now lockless - epoll keeps back-referencesto the irqs
+		 * which have trigger it so there is no need to walk the irq
+		 * list and lock it every time. We avoid locking by turning off
+		 * IO for a specific fd by executing os_del_epoll_fd(fd) before
+		 * we do any changes to the actual data structures
+		 */
+		n = os_waiting_for_events_epoll();
+
+		if (n <= 0) {
+			if (n == -EINTR)
+				continue;
+			else
+				break;
+		}
+
+		for (i = 0; i < n ; i++) {
+			enum um_irq_type t;
+
+			irq_entry = os_epoll_get_data_pointer(i);
+
+			for (t = 0; t < NUM_IRQ_TYPES; t++)
+				sigio_reg_handler(i, irq_entry, t, regs,
+						  timetravel_handlers_only);
+		}
+	}
+
+	if (!timetravel_handlers_only)
+		free_irqs();
+}
+
+void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+		   void *mc)
+{
+	preempt_disable();
+	_sigio_handler(regs, irqs_suspended);
+	preempt_enable();
+}
+
+static struct irq_entry *get_irq_entry_by_fd(int fd)
+{
+	struct irq_entry *walk;
+
+	lockdep_assert_held(&irq_lock);
+
+	list_for_each_entry(walk, &active_fds, list) {
+		if (walk->fd == fd)
+			return walk;
+	}
+
+	return NULL;
+}
+
+static void remove_irq_entry(struct irq_entry *to_free, bool remove)
+{
+	if (!to_free)
+		return;
+
+	if (remove)
+		os_del_epoll_fd(to_free->fd);
+	list_del(&to_free->list);
+}
+
+static bool update_irq_entry(struct irq_entry *entry)
+{
+	enum um_irq_type i;
+	int events = 0;
+
+	for (i = 0; i < NUM_IRQ_TYPES; i++)
+		events |= entry->reg[i].events;
+
+	if (events) {
+		/* will modify (instead of add) if needed */
+		os_add_epoll_fd(events, entry->fd, entry);
+		return true;
+	}
+
+	os_del_epoll_fd(entry->fd);
+	return false;
+}
+
+static struct irq_entry *update_or_remove_irq_entry(struct irq_entry *entry)
+{
+	if (update_irq_entry(entry))
+		return NULL;
+	remove_irq_entry(entry, false);
+	return entry;
+}
+
+static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id,
+		       void (*timetravel_handler)(int, int, void *,
+						  struct time_travel_event *))
+{
+	struct irq_entry *irq_entry, *to_free = NULL;
+	int err, events = os_event_mask(type);
+	unsigned long flags;
+
+	err = os_set_fd_async(fd);
+	if (err < 0)
+		goto out;
+
+	raw_spin_lock_irqsave(&irq_lock, flags);
+	irq_entry = get_irq_entry_by_fd(fd);
+	if (irq_entry) {
+already:
+		/* cannot register the same FD twice with the same type */
+		if (WARN_ON(irq_entry->reg[type].events)) {
+			err = -EALREADY;
+			goto out_unlock;
+		}
+
+		/* temporarily disable to avoid IRQ-side locking */
+		os_del_epoll_fd(fd);
+	} else {
+		struct irq_entry *new;
+
+		/* don't restore interrupts */
+		raw_spin_unlock(&irq_lock);
+		new = kzalloc_obj(*irq_entry, GFP_ATOMIC);
+		if (!new) {
+			local_irq_restore(flags);
+			return -ENOMEM;
+		}
+		raw_spin_lock(&irq_lock);
+		irq_entry = get_irq_entry_by_fd(fd);
+		if (irq_entry) {
+			to_free = new;
+			goto already;
+		}
+		irq_entry = new;
+		irq_entry->fd = fd;
+		list_add_tail(&irq_entry->list, &active_fds);
+		maybe_sigio_broken(fd);
+	}
+
+	irq_entry->reg[type].id = dev_id;
+	irq_entry->reg[type].irq = irq;
+	irq_entry->reg[type].active = true;
+	irq_entry->reg[type].events = events;
+
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+	if (um_irq_timetravel_handler_used()) {
+		irq_entry->reg[type].timetravel_handler = timetravel_handler;
+		irq_entry->reg[type].event.fn = irq_event_handler;
+	}
+#endif
+
+	WARN_ON(!update_irq_entry(irq_entry));
+	err = 0;
+out_unlock:
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+out:
+	kfree(to_free);
+	return err;
+}
+
+/*
+ * Remove the entry or entries for a specific FD, if you
+ * don't want to remove all the possible entries then use
+ * um_free_irq() or deactivate_fd() instead.
+ */
+void free_irq_by_fd(int fd)
+{
+	struct irq_entry *to_free;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&irq_lock, flags);
+	to_free = get_irq_entry_by_fd(fd);
+	remove_irq_entry(to_free, true);
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+	kfree(to_free);
+}
+EXPORT_SYMBOL(free_irq_by_fd);
+
+static void free_irq_by_irq_and_dev(unsigned int irq, void *dev)
+{
+	struct irq_entry *entry, *to_free = NULL;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&irq_lock, flags);
+	list_for_each_entry(entry, &active_fds, list) {
+		enum um_irq_type i;
+
+		for (i = 0; i < NUM_IRQ_TYPES; i++) {
+			struct irq_reg *reg = &entry->reg[i];
+
+			if (!reg->events)
+				continue;
+			if (reg->irq != irq)
+				continue;
+			if (reg->id != dev)
+				continue;
+
+			os_del_epoll_fd(entry->fd);
+			reg->events = 0;
+			to_free = update_or_remove_irq_entry(entry);
+			goto out;
+		}
+	}
+out:
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+	kfree(to_free);
+}
+
+void deactivate_fd(int fd, int irqnum)
+{
+	struct irq_entry *entry;
+	unsigned long flags;
+	enum um_irq_type i;
+
+	os_del_epoll_fd(fd);
+
+	raw_spin_lock_irqsave(&irq_lock, flags);
+	entry = get_irq_entry_by_fd(fd);
+	if (!entry)
+		goto out;
+
+	for (i = 0; i < NUM_IRQ_TYPES; i++) {
+		if (!entry->reg[i].events)
+			continue;
+		if (entry->reg[i].irq == irqnum)
+			entry->reg[i].events = 0;
+	}
+
+	entry = update_or_remove_irq_entry(entry);
+out:
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+	kfree(entry);
+
+	ignore_sigio_fd(fd);
+}
+EXPORT_SYMBOL(deactivate_fd);
+
+/*
+ * Called just before shutdown in order to provide a clean exec
+ * environment in case the system is rebooting.  No locking because
+ * that would cause a pointless shutdown hang if something hadn't
+ * released the lock.
+ */
+int deactivate_all_fds(void)
+{
+	struct irq_entry *entry;
+
+	/* Stop IO. The IRQ loop has no lock so this is our
+	 * only way of making sure we are safe to dispose
+	 * of all IRQ handlers
+	 */
+	os_set_ioignore();
+
+	/* we can no longer call kfree() here so just deactivate */
+	list_for_each_entry(entry, &active_fds, list)
+		os_del_epoll_fd(entry->fd);
+	os_close_epoll_fd();
+	return 0;
+}
+
+/*
+ * do_IRQ handles all normal device IRQs (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+unsigned int do_IRQ(int irq, struct uml_pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs((struct pt_regs *)regs);
+	irq_enter();
+	generic_handle_irq(irq);
+	irq_exit();
+	set_irq_regs(old_regs);
+	return 1;
+}
+
+void um_free_irq(int irq, void *dev)
+{
+	if (WARN(irq < 0 || irq > UM_LAST_SIGNAL_IRQ,
+		 "freeing invalid irq %d", irq))
+		return;
+
+	free_irq_by_irq_and_dev(irq, dev);
+	free_irq(irq, dev);
+	clear_bit(irq, irqs_allocated);
+}
+EXPORT_SYMBOL(um_free_irq);
+
+static int
+_um_request_irq(int irq, int fd, enum um_irq_type type,
+		irq_handler_t handler, unsigned long irqflags,
+		const char *devname, void *dev_id,
+		void (*timetravel_handler)(int, int, void *,
+					   struct time_travel_event *))
+{
+	int err;
+
+	if (irq == UM_IRQ_ALLOC) {
+		int i;
+
+		for (i = UM_FIRST_DYN_IRQ; i < NR_IRQS; i++) {
+			if (!test_and_set_bit(i, irqs_allocated)) {
+				irq = i;
+				break;
+			}
+		}
+	}
+
+	if (irq < 0)
+		return -ENOSPC;
+
+	if (fd != -1) {
+		err = activate_fd(irq, fd, type, dev_id, timetravel_handler);
+		if (err)
+			goto error;
+	}
+
+	err = request_irq(irq, handler, irqflags, devname, dev_id);
+	if (err < 0)
+		goto error;
+
+	return irq;
+error:
+	clear_bit(irq, irqs_allocated);
+	return err;
+}
+
+int um_request_irq(int irq, int fd, enum um_irq_type type,
+		   irq_handler_t handler, unsigned long irqflags,
+		   const char *devname, void *dev_id)
+{
+	return _um_request_irq(irq, fd, type, handler, irqflags,
+			       devname, dev_id, NULL);
+}
+EXPORT_SYMBOL(um_request_irq);
+
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+int um_request_irq_tt(int irq, int fd, enum um_irq_type type,
+		      irq_handler_t handler, unsigned long irqflags,
+		      const char *devname, void *dev_id,
+		      void (*timetravel_handler)(int, int, void *,
+						 struct time_travel_event *))
+{
+	return _um_request_irq(irq, fd, type, handler, irqflags,
+			       devname, dev_id, timetravel_handler);
+}
+EXPORT_SYMBOL(um_request_irq_tt);
+
+void sigio_run_timetravel_handlers(void)
+{
+	_sigio_handler(NULL, true);
+}
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+void um_irqs_suspend(void)
+{
+	struct irq_entry *entry;
+	unsigned long flags;
+
+	irqs_suspended = true;
+
+	raw_spin_lock_irqsave(&irq_lock, flags);
+	list_for_each_entry(entry, &active_fds, list) {
+		enum um_irq_type t;
+		bool clear = true;
+
+		for (t = 0; t < NUM_IRQ_TYPES; t++) {
+			if (!entry->reg[t].events)
+				continue;
+
+			/*
+			 * For the SIGIO_WRITE_IRQ, which is used to handle the
+			 * SIGIO workaround thread, we need special handling:
+			 * enable wake for it itself, but below we tell it about
+			 * any FDs that should be suspended.
+			 */
+			if (entry->reg[t].wakeup ||
+			    entry->reg[t].irq == SIGIO_WRITE_IRQ
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+			    || entry->reg[t].timetravel_handler
+#endif
+			    ) {
+				clear = false;
+				break;
+			}
+		}
+
+		if (clear) {
+			entry->suspended = true;
+			os_clear_fd_async(entry->fd);
+			entry->sigio_workaround =
+				!__ignore_sigio_fd(entry->fd);
+		}
+	}
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+}
+
+void um_irqs_resume(void)
+{
+	struct irq_entry *entry;
+	unsigned long flags;
+
+
+	raw_spin_lock_irqsave(&irq_lock, flags);
+	list_for_each_entry(entry, &active_fds, list) {
+		if (entry->suspended) {
+			int err = os_set_fd_async(entry->fd);
+
+			WARN(err < 0, "os_set_fd_async returned %d\n", err);
+			entry->suspended = false;
+
+			if (entry->sigio_workaround) {
+				err = __add_sigio_fd(entry->fd);
+				WARN(err < 0, "add_sigio_returned %d\n", err);
+			}
+		}
+	}
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+
+	irqs_suspended = false;
+	send_sigio_to_self();
+}
+
+static int normal_irq_set_wake(struct irq_data *d, unsigned int on)
+{
+	struct irq_entry *entry;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&irq_lock, flags);
+	list_for_each_entry(entry, &active_fds, list) {
+		enum um_irq_type t;
+
+		for (t = 0; t < NUM_IRQ_TYPES; t++) {
+			if (!entry->reg[t].events)
+				continue;
+
+			if (entry->reg[t].irq != d->irq)
+				continue;
+			entry->reg[t].wakeup = on;
+			goto unlock;
+		}
+	}
+unlock:
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+	return 0;
+}
+#else
+#define normal_irq_set_wake NULL
+#endif
+
+/*
+ * irq_chip must define at least enable/disable and ack when
+ * the edge handler is used.
+ */
+static void dummy(struct irq_data *d)
+{
+}
+
+/* This is used for everything other than the timer. */
+static struct irq_chip normal_irq_type = {
+	.name = "SIGIO",
+	.irq_disable = dummy,
+	.irq_enable = dummy,
+	.irq_ack = dummy,
+	.irq_mask = dummy,
+	.irq_unmask = dummy,
+	.irq_set_wake = normal_irq_set_wake,
+};
+
+static struct irq_chip alarm_irq_type = {
+	.name = "SIGALRM",
+	.irq_disable = dummy,
+	.irq_enable = dummy,
+	.irq_ack = dummy,
+	.irq_mask = dummy,
+	.irq_unmask = dummy,
+};
+
+void __init init_IRQ(void)
+{
+	int i;
+
+	irq_set_chip_and_handler(TIMER_IRQ, &alarm_irq_type, handle_percpu_irq);
+
+	for (i = 1; i < UM_LAST_SIGNAL_IRQ; i++)
+		irq_set_chip_and_handler(i, &normal_irq_type, handle_edge_irq);
+	/* Initialize EPOLL Loop */
+	os_setup_epoll();
+}
+
+int __init arch_probe_nr_irqs(void)
+{
+	return NR_IRQS;
+}
+
+void sigchld_handler(int sig, struct siginfo *unused_si,
+		     struct uml_pt_regs *regs, void *mc)
+{
+	do_IRQ(SIGCHLD_IRQ, regs);
+}
+
+/*
+ * /proc/interrupts printing for arch specific interrupts
+ */
+int arch_show_interrupts(struct seq_file *p, int prec)
+{
+#if IS_ENABLED(CONFIG_SMP)
+	int cpu;
+
+	seq_printf(p, "%*s: ", prec, "RES");
+	for_each_online_cpu(cpu)
+		seq_printf(p, "%10u ", irq_stats(cpu)->irq_resched_count);
+	seq_puts(p, " Rescheduling interrupts\n");
+
+	seq_printf(p, "%*s: ", prec, "CAL");
+	for_each_online_cpu(cpu)
+		seq_printf(p, "%10u ", irq_stats(cpu)->irq_call_count);
+	seq_puts(p, " Function call interrupts\n");
+#endif
+
+	return 0;
+}

linux-7.2.3/arch/um/kernel/kmsg_dump.c

@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kmsg_dump.h>
+#include <linux/spinlock.h>
+#include <linux/console.h>
+#include <linux/string.h>
+#include <shared/init.h>
+#include <shared/kern.h>
+#include <os.h>
+
+static void kmsg_dumper_stdout(struct kmsg_dumper *dumper,
+				struct kmsg_dump_detail *detail)
+{
+	static struct kmsg_dump_iter iter;
+	static DEFINE_SPINLOCK(lock);
+	static char line[1024];
+	struct console *con;
+	unsigned long flags;
+	size_t len = 0;
+	int cookie;
+
+	/*
+	 * If no consoles are available to output crash information, dump
+	 * the kmsg buffer to stdout.
+	 */
+
+	cookie = console_srcu_read_lock();
+	for_each_console_srcu(con) {
+		/*
+		 * The ttynull console and disabled consoles are ignored
+		 * since they cannot output. All other consoles are
+		 * expected to output the crash information.
+		 */
+		if (strcmp(con->name, "ttynull") != 0 &&
+		    console_is_usable(con, console_srcu_read_flags(con), true)) {
+			break;
+		}
+	}
+	console_srcu_read_unlock(cookie);
+	if (con)
+		return;
+
+	if (!spin_trylock_irqsave(&lock, flags))
+		return;
+
+	kmsg_dump_rewind(&iter);
+
+	printf("kmsg_dump:\n");
+	while (kmsg_dump_get_line(&iter, true, line, sizeof(line), &len)) {
+		line[len] = '\0';
+		printf("%s", line);
+	}
+
+	spin_unlock_irqrestore(&lock, flags);
+}
+
+static struct kmsg_dumper kmsg_dumper = {
+	.dump = kmsg_dumper_stdout
+};
+
+static int __init kmsg_dumper_stdout_init(void)
+{
+	return kmsg_dump_register(&kmsg_dumper);
+}
+
+__uml_postsetup(kmsg_dumper_stdout_init);

linux-7.2.3/arch/um/kernel/ksyms.c

@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* 
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/module.h>
+#include <os.h>
+
+EXPORT_SYMBOL(um_get_signals);
+EXPORT_SYMBOL(um_set_signals);
+
+EXPORT_SYMBOL(os_stat_fd);
+EXPORT_SYMBOL(os_stat_file);
+EXPORT_SYMBOL(os_access);
+EXPORT_SYMBOL(os_set_exec_close);
+EXPORT_SYMBOL(os_getpid);
+EXPORT_SYMBOL(os_open_file);
+EXPORT_SYMBOL(os_read_file);
+EXPORT_SYMBOL(os_write_file);
+EXPORT_SYMBOL(os_seek_file);
+EXPORT_SYMBOL(os_lock_file);
+EXPORT_SYMBOL(os_ioctl_generic);
+EXPORT_SYMBOL(os_pipe);
+EXPORT_SYMBOL(os_file_type);
+EXPORT_SYMBOL(os_file_mode);
+EXPORT_SYMBOL(os_file_size);
+EXPORT_SYMBOL(os_flush_stdout);
+EXPORT_SYMBOL(os_close_file);
+EXPORT_SYMBOL(os_set_fd_async);
+EXPORT_SYMBOL(os_set_fd_block);
+EXPORT_SYMBOL(helper_wait);
+EXPORT_SYMBOL(os_shutdown_socket);
+EXPORT_SYMBOL(os_create_unix_socket);
+EXPORT_SYMBOL(os_connect_socket);
+EXPORT_SYMBOL(os_accept_connection);
+EXPORT_SYMBOL(os_rcv_fd_msg);
+EXPORT_SYMBOL(run_helper);
+EXPORT_SYMBOL(os_major);
+EXPORT_SYMBOL(os_minor);
+EXPORT_SYMBOL(os_makedev);
+EXPORT_SYMBOL(os_eventfd);
+EXPORT_SYMBOL(os_sendmsg_fds);
+
+EXPORT_SYMBOL(add_sigio_fd);
+EXPORT_SYMBOL(ignore_sigio_fd);
+EXPORT_SYMBOL(sigio_broken);
+
+EXPORT_SYMBOL(syscall);

linux-7.2.3/arch/um/kernel/load_file.c

@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+#include <linux/memblock.h>
+#include <os.h>
+
+#include "um_arch.h"
+
+static int __init __uml_load_file(const char *filename, void *buf, int size)
+{
+	int fd, n;
+
+	fd = os_open_file(filename, of_read(OPENFLAGS()), 0);
+	if (fd < 0) {
+		printk(KERN_ERR "Opening '%s' failed - err = %d\n", filename,
+		       -fd);
+		return -1;
+	}
+	n = os_read_file(fd, buf, size);
+	if (n != size) {
+		printk(KERN_ERR "Read of %d bytes from '%s' failed, "
+		       "err = %d\n", size,
+		       filename, -n);
+		return -1;
+	}
+
+	os_close_file(fd);
+	return 0;
+}
+
+void *uml_load_file(const char *filename, unsigned long long *size)
+{
+	void *area;
+	int err;
+
+	*size = 0;
+
+	if (!filename)
+		return NULL;
+
+	err = os_file_size(filename, size);
+	if (err)
+		return NULL;
+
+	if (*size == 0) {
+		printk(KERN_ERR "\"%s\" is empty\n", filename);
+		return NULL;
+	}
+
+	area = memblock_alloc_or_panic(*size, SMP_CACHE_BYTES);
+
+	if (__uml_load_file(filename, area, *size)) {
+		memblock_free(area, *size);
+		return NULL;
+	}
+
+	return area;
+}

linux-7.2.3/arch/um/kernel/mem.c

@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/stddef.h>
+#include <linux/module.h>
+#include <linux/memblock.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <asm/sections.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <as-layout.h>
+#include <init.h>
+#include <kern.h>
+#include <kern_util.h>
+#include <mem_user.h>
+#include <os.h>
+#include <um_malloc.h>
+#include <linux/sched/task.h>
+#include <linux/kasan.h>
+
+#ifdef CONFIG_KASAN
+void __init kasan_init(void)
+{
+	/*
+	 * kasan_map_memory will map all of the required address space and
+	 * the host machine will allocate physical memory as necessary.
+	 */
+	kasan_map_memory((void *)KASAN_SHADOW_START, KASAN_SHADOW_SIZE);
+	init_task.kasan_depth = 0;
+	/*
+	 * Since kasan_init() is called before main(),
+	 * KASAN is initialized but the enablement is deferred after
+	 * jump_label_init(). See arch_mm_preinit().
+	 */
+}
+
+static void (*kasan_init_ptr)(void)
+__section(".kasan_init") __used
+= kasan_init;
+#endif
+
+/*
+ * Initialized during boot, and readonly for initializing page tables
+ * afterwards
+ */
+pgd_t swapper_pg_dir[PTRS_PER_PGD];
+
+/* Initialized at boot time, and readonly after that */
+int kmalloc_ok = 0;
+
+/* Used during early boot */
+static unsigned long brk_end;
+
+void __init arch_mm_preinit(void)
+{
+	/* Safe to call after jump_label_init(). Enables KASAN. */
+	kasan_init_generic();
+
+	/* Map in the area just after the brk now that kmalloc is about
+	 * to be turned on.
+	 */
+	brk_end = PAGE_ALIGN((unsigned long) sbrk(0));
+	map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0);
+	memblock_free((void *)brk_end, uml_reserved - brk_end);
+	uml_reserved = brk_end;
+	min_low_pfn = PFN_UP(__pa(uml_reserved));
+	max_pfn = max_low_pfn;
+}
+
+void __init mem_init(void)
+{
+	kmalloc_ok = 1;
+}
+
+void __init arch_zone_limits_init(unsigned long *max_zone_pfns)
+{
+	max_zone_pfns[ZONE_NORMAL] = high_physmem >> PAGE_SHIFT;
+}
+
+/*
+ * This can't do anything because nothing in the kernel image can be freed
+ * since it's not in kernel physical memory.
+ */
+
+void free_initmem(void)
+{
+}
+
+/* Allocate and free page tables. */
+
+pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *pgd = __pgd_alloc(mm, 0);
+
+	if (pgd)
+		memcpy(pgd + USER_PTRS_PER_PGD,
+		       swapper_pg_dir + USER_PTRS_PER_PGD,
+		       (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+
+	return pgd;
+}
+
+void *uml_kmalloc(int size, int flags)
+{
+	return kmalloc(size, flags);
+}
+
+static const pgprot_t protection_map[16] = {
+	[VM_NONE]					= PAGE_NONE,
+	[VM_READ]					= PAGE_READONLY,
+	[VM_WRITE]					= PAGE_COPY,
+	[VM_WRITE | VM_READ]				= PAGE_COPY,
+	[VM_EXEC]					= PAGE_READONLY,
+	[VM_EXEC | VM_READ]				= PAGE_READONLY,
+	[VM_EXEC | VM_WRITE]				= PAGE_COPY,
+	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY,
+	[VM_SHARED]					= PAGE_NONE,
+	[VM_SHARED | VM_READ]				= PAGE_READONLY,
+	[VM_SHARED | VM_WRITE]				= PAGE_SHARED,
+	[VM_SHARED | VM_WRITE | VM_READ]		= PAGE_SHARED,
+	[VM_SHARED | VM_EXEC]				= PAGE_READONLY,
+	[VM_SHARED | VM_EXEC | VM_READ]			= PAGE_READONLY,
+	[VM_SHARED | VM_EXEC | VM_WRITE]		= PAGE_SHARED,
+	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED
+};
+DECLARE_VM_GET_PAGE_PROT
+
+void mark_rodata_ro(void)
+{
+	unsigned long rodata_start = PFN_ALIGN(__start_rodata);
+	unsigned long rodata_end = PFN_ALIGN(__end_rodata);
+
+	os_protect_memory((void *)rodata_start, rodata_end - rodata_start, 1, 0, 0);
+}

linux-7.2.3/arch/um/kernel/physmem.c

@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/module.h>
+#include <linux/memblock.h>
+#include <linux/mm.h>
+#include <linux/pfn.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+#include <as-layout.h>
+#include <init.h>
+#include <kern.h>
+#include <kern_util.h>
+#include <mem_user.h>
+#include <os.h>
+
+static int physmem_fd = -1;
+
+/* Changed during early boot */
+unsigned long high_physmem;
+EXPORT_SYMBOL(high_physmem);
+
+void map_memory(unsigned long virt, unsigned long phys, unsigned long len,
+		int r, int w, int x)
+{
+	__u64 offset;
+	int fd, err;
+
+	fd = phys_mapping(phys, &offset);
+	err = os_map_memory((void *) virt, fd, offset, len, r, w, x);
+	if (err) {
+		if (err == -ENOMEM)
+			printk(KERN_ERR "try increasing the host's "
+			       "/proc/sys/vm/max_map_count to <physical "
+			       "memory size>/4096\n");
+		panic("map_memory(0x%lx, %d, 0x%llx, %ld, %d, %d, %d) failed, "
+		      "err = %d\n", virt, fd, offset, len, r, w, x, err);
+	}
+}
+
+/**
+ * setup_physmem() - Setup physical memory for UML
+ * @start:	Start address of the physical kernel memory,
+ *		i.e start address of the executable image.
+ * @reserve_end:	end address of the physical kernel memory.
+ * @len:	Length of total physical memory that should be mapped/made
+ *		available, in bytes.
+ *
+ * Creates an unlinked temporary file of size (len) and memory maps
+ * it on the last executable image address (uml_reserved).
+ *
+ * The offset is needed as the length of the total physical memory
+ * (len) includes the size of the memory used be the executable image,
+ * but the mapped-to address is the last address of the executable image
+ * (uml_reserved == end address of executable image).
+ *
+ * The memory mapped memory of the temporary file is used as backing memory
+ * of all user space processes/kernel tasks.
+ */
+void __init setup_physmem(unsigned long start, unsigned long reserve_end,
+			  unsigned long len)
+{
+	unsigned long reserve = reserve_end - start;
+	unsigned long map_size = len - reserve;
+	int err;
+
+	if (len <= reserve) {
+		os_warn("Too few physical memory! Needed=%lu, given=%lu\n",
+			reserve, len);
+		exit(1);
+	}
+
+	physmem_fd = create_mem_file(len);
+
+	err = os_map_memory((void *) reserve_end, physmem_fd, reserve,
+			    map_size, 1, 1, 1);
+	if (err < 0) {
+		os_warn("setup_physmem - mapping %lu bytes of memory at 0x%p "
+			"failed - errno = %d\n", map_size,
+			(void *) reserve_end, err);
+		exit(1);
+	}
+
+	/*
+	 * Special kludge - This page will be mapped in to userspace processes
+	 * from physmem_fd, so it needs to be written out there.
+	 */
+	os_seek_file(physmem_fd, __pa(__syscall_stub_start));
+	os_write_file(physmem_fd, __syscall_stub_start, PAGE_SIZE);
+
+	memblock_add(__pa(start), len);
+	memblock_reserve(__pa(start), reserve);
+
+	min_low_pfn = PFN_UP(__pa(reserve_end));
+	max_low_pfn = min_low_pfn + (map_size >> PAGE_SHIFT);
+}
+
+int phys_mapping(unsigned long phys, unsigned long long *offset_out)
+{
+	int fd = -1;
+
+	if (phys < physmem_size) {
+		fd = physmem_fd;
+		*offset_out = phys;
+	}
+
+	return fd;
+}
+EXPORT_SYMBOL(phys_mapping);
+
+static int __init uml_mem_setup(char *line, int *add)
+{
+	char *retptr;
+
+	*add = 0;
+	physmem_size = memparse(line,&retptr);
+	return 0;
+}
+__uml_setup("mem=", uml_mem_setup,
+"mem=<Amount of desired ram>\n"
+"    This controls how much \"physical\" memory the kernel allocates\n"
+"    for the system. The size is specified as a number followed by\n"
+"    one of 'k', 'K', 'm', 'M', which have the obvious meanings.\n"
+"    This is not related to the amount of memory in the host.  It can\n"
+"    be more, and the excess, if it's ever used, will just be swapped out.\n"
+"	Example: mem=64M\n\n"
+);

linux-7.2.3/arch/um/kernel/process.c

@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2015 Anton Ivanov (aivanov@{brocade.com,kot-begemot.co.uk})
+ * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de)
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright 2003 PathScale, Inc.
+ */
+
+#include <linux/stddef.h>
+#include <linux/err.h>
+#include <linux/hardirq.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/personality.h>
+#include <linux/proc_fs.h>
+#include <linux/ptrace.h>
+#include <linux/random.h>
+#include <linux/cpu.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/seq_file.h>
+#include <linux/tick.h>
+#include <linux/threads.h>
+#include <linux/resume_user_mode.h>
+#include <asm/current.h>
+#include <asm/mmu_context.h>
+#include <asm/switch_to.h>
+#include <asm/exec.h>
+#include <linux/uaccess.h>
+#include <as-layout.h>
+#include <kern_util.h>
+#include <os.h>
+#include <skas.h>
+#include <registers.h>
+#include <linux/time-internal.h>
+#include <linux/elfcore.h>
+
+/*
+ * This is a per-cpu array.  A processor only modifies its entry and it only
+ * cares about its entry, so it's OK if another processor is modifying its
+ * entry.
+ */
+struct task_struct *cpu_tasks[NR_CPUS] = {
+	[0 ... NR_CPUS - 1] = &init_task,
+};
+EXPORT_SYMBOL(cpu_tasks);
+
+void free_stack(unsigned long stack, int order)
+{
+	free_pages(stack, order);
+}
+
+unsigned long alloc_stack(int order, int atomic)
+{
+	unsigned long page;
+	gfp_t flags = GFP_KERNEL;
+
+	if (atomic)
+		flags = GFP_ATOMIC;
+	page = __get_free_pages(flags, order);
+
+	return page;
+}
+
+static inline void set_current(struct task_struct *task)
+{
+	cpu_tasks[task_thread_info(task)->cpu] = task;
+}
+
+struct task_struct *__switch_to(struct task_struct *from, struct task_struct *to)
+{
+	to->thread.prev_sched = from;
+	set_current(to);
+
+	switch_threads(&from->thread.switch_buf, &to->thread.switch_buf);
+	arch_switch_to(current);
+
+	return current->thread.prev_sched;
+}
+
+void interrupt_end(void)
+{
+	struct pt_regs *regs = &current->thread.regs;
+	unsigned long thread_flags;
+
+	thread_flags = read_thread_flags();
+	while (thread_flags & _TIF_WORK_MASK) {
+		if (thread_flags & _TIF_NEED_RESCHED)
+			schedule();
+		if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+			do_signal(regs);
+		if (thread_flags & _TIF_NOTIFY_RESUME)
+			resume_user_mode_work(regs);
+		thread_flags = read_thread_flags();
+	}
+}
+
+int get_current_pid(void)
+{
+	return task_pid_nr(current);
+}
+
+/*
+ * This is called magically, by its address being stuffed in a jmp_buf
+ * and being longjmp-d to.
+ */
+void new_thread_handler(void)
+{
+	int (*fn)(void *);
+	void *arg;
+
+	if (current->thread.prev_sched != NULL)
+		schedule_tail(current->thread.prev_sched);
+	current->thread.prev_sched = NULL;
+
+	fn = current->thread.request.thread.proc;
+	arg = current->thread.request.thread.arg;
+
+	/*
+	 * callback returns only if the kernel thread execs a process
+	 */
+	fn(arg);
+	userspace(&current->thread.regs.regs);
+}
+
+/* Called magically, see new_thread_handler above */
+static void fork_handler(void)
+{
+	schedule_tail(current->thread.prev_sched);
+
+	/*
+	 * XXX: if interrupt_end() calls schedule, this call to
+	 * arch_switch_to isn't needed. We could want to apply this to
+	 * improve performance. -bb
+	 */
+	arch_switch_to(current);
+
+	current->thread.prev_sched = NULL;
+
+	userspace(&current->thread.regs.regs);
+}
+
+int copy_thread(struct task_struct * p, const struct kernel_clone_args *args)
+{
+	u64 clone_flags = args->flags;
+	unsigned long sp = args->stack;
+	unsigned long tls = args->tls;
+	void (*handler)(void);
+	int ret = 0;
+
+	p->thread = (struct thread_struct) INIT_THREAD;
+
+	if (!args->fn) {
+	  	memcpy(&p->thread.regs.regs, current_pt_regs(),
+		       sizeof(p->thread.regs.regs));
+		PT_REGS_SET_SYSCALL_RETURN(&p->thread.regs, 0);
+		if (sp != 0)
+			REGS_SP(p->thread.regs.regs.gp) = sp;
+
+		handler = fork_handler;
+
+		arch_copy_thread(&current->thread.arch, &p->thread.arch);
+	} else {
+		get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp);
+		p->thread.request.thread.proc = args->fn;
+		p->thread.request.thread.arg = args->fn_arg;
+		handler = new_thread_handler;
+	}
+
+	new_thread(task_stack_page(p), &p->thread.switch_buf, handler);
+
+	if (!args->fn) {
+		clear_flushed_tls(p);
+
+		/*
+		 * Set a new TLS for the child thread?
+		 */
+		if (clone_flags & CLONE_SETTLS)
+			ret = arch_set_tls(p, tls);
+	}
+
+	return ret;
+}
+
+void initial_thread_cb(void (*proc)(void *), void *arg)
+{
+	initial_thread_cb_skas(proc, arg);
+}
+
+int arch_dup_task_struct(struct task_struct *dst,
+			 struct task_struct *src)
+{
+	/* init_task is not dynamically sized (missing FPU state) */
+	if (unlikely(src == &init_task)) {
+		memcpy(dst, src, sizeof(init_task));
+		memset((void *)dst + sizeof(init_task), 0,
+		       arch_task_struct_size - sizeof(init_task));
+	} else {
+		memcpy(dst, src, arch_task_struct_size);
+	}
+
+	return 0;
+}
+
+void um_idle_sleep(void)
+{
+	if (time_travel_mode != TT_MODE_OFF)
+		time_travel_sleep();
+	else
+		os_idle_sleep();
+}
+
+void arch_cpu_idle(void)
+{
+	um_idle_sleep();
+}
+
+void arch_cpu_idle_prepare(void)
+{
+	os_idle_prepare();
+}
+
+int __uml_cant_sleep(void) {
+	return in_atomic() || irqs_disabled() || in_interrupt();
+	/* Is in_interrupt() really needed? */
+}
+
+int uml_need_resched(void)
+{
+	return need_resched();
+}
+
+extern exitcall_t __uml_exitcall_begin, __uml_exitcall_end;
+
+void do_uml_exitcalls(void)
+{
+	exitcall_t *call;
+
+	call = &__uml_exitcall_end;
+	while (--call >= &__uml_exitcall_begin)
+		(*call)();
+}
+
+char *uml_strdup(const char *string)
+{
+	return kstrdup(string, GFP_KERNEL);
+}
+EXPORT_SYMBOL(uml_strdup);
+
+int copy_from_user_proc(void *to, void __user *from, int size)
+{
+	return copy_from_user(to, from, size);
+}
+
+int singlestepping(void)
+{
+	return test_thread_flag(TIF_SINGLESTEP);
+}
+
+/*
+ * Only x86 and x86_64 have an arch_align_stack().
+ * All other arches have "#define arch_align_stack(x) (x)"
+ * in their asm/exec.h
+ * As this is included in UML from asm-um/system-generic.h,
+ * we can use it to behave as the subarch does.
+ */
+#ifndef arch_align_stack
+unsigned long arch_align_stack(unsigned long sp)
+{
+	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+		sp -= get_random_u32_below(8192);
+	return sp & ~0xf;
+}
+#endif
+
+unsigned long __get_wchan(struct task_struct *p)
+{
+	unsigned long stack_page, sp, ip;
+	bool seen_sched = 0;
+
+	stack_page = (unsigned long) task_stack_page(p);
+	/* Bail if the process has no kernel stack for some reason */
+	if (stack_page == 0)
+		return 0;
+
+	sp = p->thread.switch_buf->JB_SP;
+	/*
+	 * Bail if the stack pointer is below the bottom of the kernel
+	 * stack for some reason
+	 */
+	if (sp < stack_page)
+		return 0;
+
+	while (sp < stack_page + THREAD_SIZE) {
+		ip = *((unsigned long *) sp);
+		if (in_sched_functions(ip))
+			/* Ignore everything until we're above the scheduler */
+			seen_sched = 1;
+		else if (kernel_text_address(ip) && seen_sched)
+			return ip;
+
+		sp += sizeof(unsigned long);
+	}
+
+	return 0;
+}

linux-7.2.3/arch/um/kernel/ptrace.c

@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/audit.h>
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <asm/ptrace-abi.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+void user_enable_single_step(struct task_struct *child)
+{
+	set_tsk_thread_flag(child, TIF_SINGLESTEP);
+
+#ifdef SUBARCH_SET_SINGLESTEPPING
+	SUBARCH_SET_SINGLESTEPPING(child, 1);
+#endif
+}
+
+void user_disable_single_step(struct task_struct *child)
+{
+	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
+
+#ifdef SUBARCH_SET_SINGLESTEPPING
+	SUBARCH_SET_SINGLESTEPPING(child, 0);
+#endif
+}
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ */
+void ptrace_disable(struct task_struct *child)
+{
+	user_disable_single_step(child);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
+{
+	int i, ret;
+	unsigned long __user *p = (void __user *)data;
+	void __user *vp = p;
+
+	switch (request) {
+	/* read the word at location addr in the USER area. */
+	case PTRACE_PEEKUSR:
+		ret = peek_user(child, addr, data);
+		break;
+
+	/* write the word at location addr in the USER area */
+	case PTRACE_POKEUSR:
+		ret = poke_user(child, addr, data);
+		break;
+
+	case PTRACE_SYSEMU:
+	case PTRACE_SYSEMU_SINGLESTEP:
+		ret = -EIO;
+		break;
+
+#ifdef PTRACE_GETREGS
+	case PTRACE_GETREGS: { /* Get all gp regs from the child. */
+		if (!access_ok(p, MAX_REG_OFFSET)) {
+			ret = -EIO;
+			break;
+		}
+		for ( i = 0; i < MAX_REG_OFFSET; i += sizeof(long) ) {
+			__put_user(getreg(child, i), p);
+			p++;
+		}
+		ret = 0;
+		break;
+	}
+#endif
+#ifdef PTRACE_SETREGS
+	case PTRACE_SETREGS: { /* Set all gp regs in the child. */
+		unsigned long tmp = 0;
+		if (!access_ok(p, MAX_REG_OFFSET)) {
+			ret = -EIO;
+			break;
+		}
+		for ( i = 0; i < MAX_REG_OFFSET; i += sizeof(long) ) {
+			__get_user(tmp, p);
+			putreg(child, i, tmp);
+			p++;
+		}
+		ret = 0;
+		break;
+	}
+#endif
+	case PTRACE_GET_THREAD_AREA:
+		ret = ptrace_get_thread_area(child, addr, vp);
+		break;
+
+	case PTRACE_SET_THREAD_AREA:
+		ret = ptrace_set_thread_area(child, addr, vp);
+		break;
+
+	default:
+		ret = ptrace_request(child, request, addr, data);
+		if (ret == -EIO)
+			ret = subarch_ptrace(child, request, addr, data);
+		break;
+	}
+
+	return ret;
+}
+
+static void send_sigtrap(struct uml_pt_regs *regs, int error_code)
+{
+	/* Send us the fake SIGTRAP */
+	force_sig_fault(SIGTRAP, TRAP_BRKPT,
+			/* User-mode eip? */
+			UPT_IS_USER(regs) ? (void __user *) UPT_IP(regs) : NULL);
+}
+
+/*
+ * XXX Check TIF_SINGLESTEP for singlestepping check and
+ * PT_PTRACED vs TIF_SYSCALL_TRACE for syscall tracing check
+ */
+int syscall_trace_enter(struct pt_regs *regs)
+{
+	audit_syscall_entry(UPT_SYSCALL_NR(&regs->regs),
+			    UPT_SYSCALL_ARG1(&regs->regs),
+			    UPT_SYSCALL_ARG2(&regs->regs),
+			    UPT_SYSCALL_ARG3(&regs->regs),
+			    UPT_SYSCALL_ARG4(&regs->regs));
+
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, UPT_SYSCALL_NR(&regs->regs));
+
+	if (!test_thread_flag(TIF_SYSCALL_TRACE))
+		return 0;
+
+	return ptrace_report_syscall_entry(regs);
+}
+
+void syscall_trace_leave(struct pt_regs *regs)
+{
+	int ptraced = current->ptrace;
+
+	audit_syscall_exit(regs);
+
+	/* Fake a debug trap */
+	if (test_thread_flag(TIF_SINGLESTEP))
+		send_sigtrap(&regs->regs, 0);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_exit(regs, PT_REGS_SYSCALL_RET(regs));
+
+	if (!test_thread_flag(TIF_SYSCALL_TRACE))
+		return;
+
+	ptrace_report_syscall_exit(regs, 0);
+	/* force do_signal() --> is_syscall() */
+	if (ptraced & PT_PTRACED)
+		set_thread_flag(TIF_SIGPENDING);
+}

linux-7.2.3/arch/um/kernel/reboot.c

@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/* 
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/sched/mm.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/oom.h>
+#include <linux/reboot.h>
+#include <kern_util.h>
+#include <os.h>
+#include <skas.h>
+
+void (*pm_power_off)(void);
+EXPORT_SYMBOL(pm_power_off);
+
+static void kill_off_processes(void)
+{
+	struct task_struct *p;
+	int pid;
+
+	read_lock(&tasklist_lock);
+	for_each_process(p) {
+		struct task_struct *t;
+
+		t = find_lock_task_mm(p);
+		if (!t)
+			continue;
+		pid = t->mm->context.id.pid;
+		task_unlock(t);
+		os_kill_ptraced_process(pid, 1);
+	}
+	read_unlock(&tasklist_lock);
+}
+
+void uml_cleanup(void)
+{
+	kmalloc_ok = 0;
+	do_uml_exitcalls();
+	kill_off_processes();
+}
+
+void machine_restart(char * __unused)
+{
+	uml_cleanup();
+	reboot_skas();
+}
+
+void machine_power_off(void)
+{
+	uml_cleanup();
+	halt_skas();
+}
+
+void machine_halt(void)
+{
+	machine_power_off();
+}
+
+static int sys_power_off_handler(struct sys_off_data *data)
+{
+	machine_power_off();
+	return 0;
+}
+
+static int register_power_off(void)
+{
+	register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+				 SYS_OFF_PRIO_DEFAULT,
+				 sys_power_off_handler, NULL);
+	return 0;
+}
+__initcall(register_power_off);

linux-7.2.3/arch/um/kernel/sigio.c

@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{linux.intel,addtoit}.com)
+ */
+
+#include <linux/interrupt.h>
+#include <irq_kern.h>
+#include <os.h>
+#include <sigio.h>
+
+/* These are called from os-Linux/sigio.c to protect its pollfds arrays. */
+static DEFINE_MUTEX(sigio_mutex);
+
+void sigio_lock(void)
+{
+	mutex_lock(&sigio_mutex);
+}
+
+void sigio_unlock(void)
+{
+	mutex_unlock(&sigio_mutex);
+}

linux-7.2.3/arch/um/kernel/signal.c

@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/siginfo.h>
+#include <asm/signal.h>
+#include <asm/unistd.h>
+#include <frame_kern.h>
+#include <kern_util.h>
+#include <os.h>
+
+EXPORT_SYMBOL(block_signals);
+EXPORT_SYMBOL(unblock_signals);
+
+void block_signals_trace(void)
+{
+	block_signals();
+	if (current_thread_info())
+		trace_hardirqs_off();
+}
+
+void unblock_signals_trace(void)
+{
+	if (current_thread_info())
+		trace_hardirqs_on();
+	unblock_signals();
+}
+
+void um_trace_signals_on(void)
+{
+	if (current_thread_info())
+		trace_hardirqs_on();
+}
+
+void um_trace_signals_off(void)
+{
+	if (current_thread_info())
+		trace_hardirqs_off();
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+	sigset_t *oldset = sigmask_to_save();
+	int singlestep = 0;
+	unsigned long sp;
+	int err;
+
+	if (test_thread_flag(TIF_SINGLESTEP) && (current->ptrace & PT_PTRACED))
+		singlestep = 1;
+
+	/* Did we come from a system call? */
+	if (PT_REGS_SYSCALL_NR(regs) >= 0) {
+		/* If so, check system call restarting.. */
+		switch (PT_REGS_SYSCALL_RET(regs)) {
+		case -ERESTART_RESTARTBLOCK:
+		case -ERESTARTNOHAND:
+			PT_REGS_SYSCALL_RET(regs) = -EINTR;
+			break;
+
+		case -ERESTARTSYS:
+			if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
+				PT_REGS_SYSCALL_RET(regs) = -EINTR;
+				break;
+			}
+			fallthrough;
+		case -ERESTARTNOINTR:
+			PT_REGS_RESTART_SYSCALL(regs);
+			PT_REGS_ORIG_SYSCALL(regs) = PT_REGS_SYSCALL_NR(regs);
+			break;
+		}
+	}
+
+	sp = PT_REGS_SP(regs);
+	if ((ksig->ka.sa.sa_flags & SA_ONSTACK) && (sas_ss_flags(sp) == 0))
+		sp = current->sas_ss_sp + current->sas_ss_size;
+
+#ifdef CONFIG_ARCH_HAS_SC_SIGNALS
+	if (!(ksig->ka.sa.sa_flags & SA_SIGINFO))
+		err = setup_signal_stack_sc(sp, ksig, regs, oldset);
+	else
+#endif
+		err = setup_signal_stack_si(sp, ksig, regs, oldset);
+
+	signal_setup_done(err, ksig, singlestep);
+}
+
+void do_signal(struct pt_regs *regs)
+{
+	struct ksignal ksig;
+	int handled_sig = 0;
+
+	while (get_signal(&ksig)) {
+		handled_sig = 1;
+		/* Whee!  Actually deliver the signal.  */
+		handle_signal(&ksig, regs);
+	}
+
+	/* Did we come from a system call? */
+	if (!handled_sig && (PT_REGS_SYSCALL_NR(regs) >= 0)) {
+		/* Restart the system call - no handlers present */
+		switch (PT_REGS_SYSCALL_RET(regs)) {
+		case -ERESTARTNOHAND:
+		case -ERESTARTSYS:
+		case -ERESTARTNOINTR:
+			PT_REGS_ORIG_SYSCALL(regs) = PT_REGS_SYSCALL_NR(regs);
+			PT_REGS_RESTART_SYSCALL(regs);
+			break;
+		case -ERESTART_RESTARTBLOCK:
+			PT_REGS_ORIG_SYSCALL(regs) = __NR_restart_syscall;
+			PT_REGS_RESTART_SYSCALL(regs);
+			break;
+		}
+	}
+
+	/*
+	 * if there's no signal to deliver, we just put the saved sigmask
+	 * back
+	 */
+	if (!handled_sig)
+		restore_saved_sigmask();
+}

linux-7.2.3/arch/um/kernel/skas/.gitignore

@@ -0,0 +1,2 @@
+stub_exe
+stub_exe.dbg

linux-7.2.3/arch/um/kernel/skas/Makefile

@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+#
+
+obj-y := stub.o mmu.o process.o syscall.o uaccess.o \
+	 stub_exe_embed.o
+
+# Stub executable
+
+stub_exe_objs-y := stub_exe.o
+
+stub_exe_objs := $(foreach F,$(stub_exe_objs-y),$(obj)/$F)
+
+# Object file containing the ELF executable
+$(obj)/stub_exe_embed.o: $(src)/stub_exe_embed.S $(obj)/stub_exe
+
+$(obj)/stub_exe.dbg: $(stub_exe_objs) FORCE
+	$(call if_changed,stub_exe)
+
+$(obj)/stub_exe: OBJCOPYFLAGS := -S
+$(obj)/stub_exe: $(obj)/stub_exe.dbg FORCE
+	$(call if_changed,objcopy)
+
+quiet_cmd_stub_exe = STUB_EXE $@
+      cmd_stub_exe = $(CC) -nostdlib -o $@ \
+			   $(filter-out $(UM_GPROF_OPT) $(UM_GCOV_OPT),$(KBUILD_CFLAGS)) $(STUB_EXE_LDFLAGS) \
+			   $(filter %.o,$^)
+
+STUB_EXE_LDFLAGS = -Wl,-n -static
+
+targets += stub_exe.dbg stub_exe $(stub_exe_objs-y)
+
+# end
+
+# stub.o is in the stub, so it can't be built with profiling
+# GCC hardened also auto-enables -fpic, but we need %ebx so it can't work ->
+# disable it
+
+CFLAGS_stub.o := $(CFLAGS_NO_HARDENING)
+CFLAGS_stub_exe.o := $(CFLAGS_NO_HARDENING)
+
+# Clang will call memset() from __builtin_alloca() when stack variable
+# initialization is enabled, which is used in stub_exe.c.
+CFLAGS_stub_exe.o += $(call cc-option, -ftrivial-auto-var-init=uninitialized)
+
+UNPROFILE_OBJS := stub.o stub_exe.o
+KCOV_INSTRUMENT := n
+
+include $(srctree)/arch/um/scripts/Makefile.rules

linux-7.2.3/arch/um/kernel/skas/mmu.c

@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de)
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+
+#include <shared/irq_kern.h>
+#include <asm/pgalloc.h>
+#include <asm/sections.h>
+#include <asm/mmu_context.h>
+#include <as-layout.h>
+#include <os.h>
+#include <skas.h>
+#include <stub-data.h>
+
+/* Ensure the stub_data struct covers the allocated area */
+static_assert(sizeof(struct stub_data) == STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
+
+static spinlock_t mm_list_lock;
+static struct list_head mm_list;
+
+struct mutex *__get_turnstile(struct mm_id *mm_id)
+{
+	struct mm_context *ctx = container_of(mm_id, struct mm_context, id);
+
+	return &ctx->turnstile;
+}
+
+void enter_turnstile(struct mm_id *mm_id)
+{
+	mutex_lock(__get_turnstile(mm_id));
+}
+
+void exit_turnstile(struct mm_id *mm_id)
+{
+	mutex_unlock(__get_turnstile(mm_id));
+}
+
+int init_new_context(struct task_struct *task, struct mm_struct *mm)
+{
+	struct mm_id *new_id = &mm->context.id;
+	unsigned long stack = 0;
+	int ret = -ENOMEM;
+
+	mutex_init(&mm->context.turnstile);
+	spin_lock_init(&mm->context.sync_tlb_lock);
+
+	stack = __get_free_pages(GFP_KERNEL | __GFP_ZERO, ilog2(STUB_DATA_PAGES));
+	if (stack == 0)
+		goto out;
+
+	new_id->stack = stack;
+	new_id->syscall_data_len = 0;
+	new_id->syscall_fd_num = 0;
+
+	scoped_guard(spinlock_irqsave, &mm_list_lock) {
+		/* Insert into list, used for lookups when the child dies */
+		list_add(&mm->context.list, &mm_list);
+	}
+
+	ret = start_userspace(new_id);
+	if (ret < 0)
+		goto out_free;
+
+	/* Ensure the new MM is clean and nothing unwanted is mapped */
+	unmap(new_id, 0, STUB_START);
+
+	return 0;
+
+ out_free:
+	free_pages(new_id->stack, ilog2(STUB_DATA_PAGES));
+ out:
+	return ret;
+}
+
+void destroy_context(struct mm_struct *mm)
+{
+	struct mm_context *mmu = &mm->context;
+
+	/*
+	 * If init_new_context wasn't called, this will be
+	 * zero, resulting in a kill(0), which will result in the
+	 * whole UML suddenly dying.  Also, cover negative and
+	 * 1 cases, since they shouldn't happen either.
+	 *
+	 * Negative cases happen if the child died unexpectedly.
+	 */
+	if (mmu->id.pid >= 0 && mmu->id.pid < 2) {
+		printk(KERN_ERR "corrupt mm_context - pid = %d\n",
+		       mmu->id.pid);
+		return;
+	}
+
+	scoped_guard(spinlock_irqsave, &mm_list_lock)
+		list_del(&mm->context.list);
+
+	if (mmu->id.pid > 0) {
+		os_kill_ptraced_process(mmu->id.pid, 1);
+		mmu->id.pid = -1;
+	}
+
+	if (using_seccomp && mmu->id.sock)
+		os_close_file(mmu->id.sock);
+
+	free_pages(mmu->id.stack, ilog2(STUB_DATA_PAGES));
+}
+
+static irqreturn_t mm_sigchld_irq(int irq, void* dev)
+{
+	struct mm_context *mm_context;
+	pid_t pid;
+
+	guard(spinlock)(&mm_list_lock);
+
+	while ((pid = os_reap_child()) > 0) {
+		/*
+		* A child died, check if we have an MM with the PID. This is
+		* only relevant in SECCOMP mode (as ptrace will fail anyway).
+		*
+		* See wait_stub_done_seccomp for more details.
+		*/
+		list_for_each_entry(mm_context, &mm_list, list) {
+			if (mm_context->id.pid == pid) {
+				struct stub_data *stub_data;
+				printk("Unexpectedly lost MM child! Affected tasks will segfault.");
+
+				/* Marks the MM as dead */
+				mm_context->id.pid = -1;
+
+				stub_data = (void *)mm_context->id.stack;
+				stub_data->futex = FUTEX_IN_KERN;
+#if IS_ENABLED(CONFIG_SMP)
+				os_futex_wake(&stub_data->futex);
+#endif
+
+				/*
+				 * NOTE: Currently executing syscalls by
+				 * affected tasks may finish normally.
+				 */
+				break;
+			}
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int __init init_child_tracking(void)
+{
+	int err;
+
+	spin_lock_init(&mm_list_lock);
+	INIT_LIST_HEAD(&mm_list);
+
+	err = request_irq(SIGCHLD_IRQ, mm_sigchld_irq, 0, "SIGCHLD", NULL);
+	if (err < 0)
+		panic("Failed to register SIGCHLD IRQ: %d", err);
+
+	return 0;
+}
+early_initcall(init_child_tracking)

linux-7.2.3/arch/um/kernel/skas/process.c

@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/init.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/task.h>
+#include <linux/smp-internal.h>
+
+#include <asm/tlbflush.h>
+
+#include <as-layout.h>
+#include <kern.h>
+#include <os.h>
+#include <skas.h>
+#include <kern_util.h>
+
+extern void start_kernel(void);
+
+static int __init start_kernel_proc(void *unused)
+{
+	block_signals_trace();
+
+	start_kernel();
+	return 0;
+}
+
+char cpu_irqstacks[NR_CPUS][THREAD_SIZE] __aligned(THREAD_SIZE);
+
+int __init start_uml(void)
+{
+	stack_protections((unsigned long) &cpu_irqstacks[0]);
+	set_sigstack(cpu_irqstacks[0], THREAD_SIZE);
+
+	init_new_thread_signals();
+
+	init_task.thread.request.thread.proc = start_kernel_proc;
+	init_task.thread.request.thread.arg = NULL;
+	return start_idle_thread(task_stack_page(&init_task),
+				 &init_task.thread.switch_buf);
+}
+
+unsigned long current_stub_stack(void)
+{
+	if (current->mm == NULL)
+		return 0;
+
+	return current->mm->context.id.stack;
+}
+
+struct mm_id *current_mm_id(void)
+{
+	if (current->mm == NULL)
+		return NULL;
+
+	return &current->mm->context.id;
+}
+
+void current_mm_sync(void)
+{
+	if (current->mm == NULL)
+		return;
+
+	um_tlb_sync(current->mm);
+}
+
+static DEFINE_SPINLOCK(initial_jmpbuf_spinlock);
+
+void initial_jmpbuf_lock(void)
+{
+	spin_lock_irq(&initial_jmpbuf_spinlock);
+}
+
+void initial_jmpbuf_unlock(void)
+{
+	spin_unlock_irq(&initial_jmpbuf_spinlock);
+}

linux-7.2.3/arch/um/kernel/skas/stub.c

@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Benjamin Berg <benjamin@sipsolutions.net>
+ */
+
+#include <sysdep/stub.h>
+
+#include <linux/futex.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+/*
+ * Known security issues
+ *
+ * Userspace can jump to this address to execute *any* syscall that is
+ * permitted by the stub. As we will return afterwards, it can do
+ * whatever it likes, including:
+ * - Tricking the kernel into handing out the memory FD
+ * - Using this memory FD to read/write all physical memory
+ * - Running in parallel to the kernel processing a syscall
+ *   (possibly creating data races?)
+ * - Blocking e.g. SIGALRM to avoid time based scheduling
+ *
+ * To avoid this, the permitted location for each syscall needs to be
+ * checked for in the SECCOMP filter (which is reasonably simple). Also,
+ * more care will need to go into considerations how the code might be
+ * tricked by using a prepared stack (or even modifying the stack from
+ * another thread in case SMP support is added).
+ *
+ * As for the SIGALRM, the best counter measure will be to check in the
+ * kernel that the process is reporting back the SIGALRM in a timely
+ * fashion.
+ */
+static __always_inline int syscall_handler(int fd_map[STUB_MAX_FDS])
+{
+	struct stub_data *d = get_stub_data();
+	int i;
+	unsigned long res;
+	int fd;
+
+	for (i = 0; i < d->syscall_data_len; i++) {
+		struct stub_syscall *sc = &d->syscall_data[i];
+
+		switch (sc->syscall) {
+		case STUB_SYSCALL_MMAP:
+			if (fd_map)
+				fd = fd_map[sc->mem.fd];
+			else
+				fd = sc->mem.fd;
+
+			res = stub_syscall6(STUB_MMAP_NR,
+					    sc->mem.addr, sc->mem.length,
+					    sc->mem.prot,
+					    MAP_SHARED | MAP_FIXED,
+					    fd, sc->mem.offset);
+			if (res != sc->mem.addr) {
+				d->err = res;
+				d->syscall_data_len = i;
+				return -1;
+			}
+			break;
+		case STUB_SYSCALL_MUNMAP:
+			res = stub_syscall2(__NR_munmap,
+					    sc->mem.addr, sc->mem.length);
+			if (res) {
+				d->err = res;
+				d->syscall_data_len = i;
+				return -1;
+			}
+			break;
+		default:
+			d->err = -95; /* EOPNOTSUPP */
+			d->syscall_data_len = i;
+			return -1;
+		}
+	}
+
+	d->err = 0;
+	d->syscall_data_len = 0;
+
+	return 0;
+}
+
+void __section(".__syscall_stub")
+stub_syscall_handler(void)
+{
+	syscall_handler(NULL);
+
+	trap_myself();
+}
+
+void __section(".__syscall_stub")
+stub_signal_interrupt(int sig, siginfo_t *info, void *p)
+{
+	struct stub_data *d = get_stub_data();
+	char rcv_data;
+	union {
+		char data[CMSG_SPACE(sizeof(int) * STUB_MAX_FDS)];
+		struct cmsghdr align;
+	} ctrl = {};
+	struct iovec iov = {
+		.iov_base = &rcv_data,
+		.iov_len = 1,
+	};
+	struct msghdr msghdr = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+		.msg_control = &ctrl,
+		.msg_controllen = sizeof(ctrl),
+	};
+	ucontext_t *uc = p;
+	struct cmsghdr *fd_msg;
+	int *fd_map;
+	int num_fds;
+	long res;
+
+	d->signal = sig;
+	d->si_offset = (unsigned long)info - (unsigned long)&d->sigstack[0];
+	d->mctx_offset = (unsigned long)&uc->uc_mcontext - (unsigned long)&d->sigstack[0];
+
+restart_wait:
+	d->futex = FUTEX_IN_KERN;
+	do {
+		res = stub_syscall3(__NR_futex, (unsigned long)&d->futex,
+				    FUTEX_WAKE, 1);
+	} while (res == -EINTR);
+
+	do {
+		res = stub_syscall4(__NR_futex, (unsigned long)&d->futex,
+				    FUTEX_WAIT, FUTEX_IN_KERN, 0);
+	} while (res == -EINTR || d->futex == FUTEX_IN_KERN);
+
+	if (res < 0 && res != -EAGAIN)
+		stub_syscall1(__NR_exit_group, 1);
+
+	if (d->syscall_data_len) {
+		/* Read passed FDs (if any) */
+		do {
+			res = stub_syscall3(__NR_recvmsg, 0, (unsigned long)&msghdr, 0);
+		} while (res == -EINTR);
+
+		/* We should never have a receive error (other than -EAGAIN) */
+		if (res < 0 && res != -EAGAIN)
+			stub_syscall1(__NR_exit_group, 1);
+
+		/* Receive the FDs */
+		num_fds = 0;
+		fd_msg = msghdr.msg_control;
+		fd_map = (void *)CMSG_DATA(fd_msg);
+		if (res == iov.iov_len && msghdr.msg_controllen > sizeof(struct cmsghdr))
+			num_fds = (fd_msg->cmsg_len - CMSG_LEN(0)) / sizeof(int);
+
+		/* Try running queued syscalls. */
+		res = syscall_handler(fd_map);
+
+		while (num_fds)
+			stub_syscall2(__NR_close, fd_map[--num_fds], 0);
+	} else {
+		res = 0;
+	}
+
+	if (res < 0 || d->restart_wait) {
+		/* Report SIGSYS if we restart. */
+		d->signal = SIGSYS;
+		d->restart_wait = 0;
+
+		goto restart_wait;
+	}
+
+	/* Restore arch dependent state that is not part of the mcontext */
+	stub_seccomp_restore_state(&d->arch_data);
+
+	/* Return so that the host modified mcontext is restored. */
+}
+
+void __section(".__syscall_stub")
+stub_signal_restorer(void)
+{
+	/* We must not have anything on the stack when doing rt_sigreturn */
+	stub_syscall0(__NR_rt_sigreturn);
+}

linux-7.2.3/arch/um/kernel/skas/stub_exe.c

@@ -0,0 +1,230 @@
+#include <sys/ptrace.h>
+#include <sys/prctl.h>
+#include <sys/fcntl.h>
+#include <asm/unistd.h>
+#include <sysdep/stub.h>
+#include <stub-data.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <generated/asm-offsets.h>
+
+void _start(void);
+
+noinline static void real_init(void)
+{
+	struct stub_init_data init_data;
+	unsigned long res;
+	struct {
+		void  *ss_sp;
+		int    ss_flags;
+		size_t ss_size;
+	} stack = {
+		.ss_size = STUB_DATA_PAGES * UM_KERN_PAGE_SIZE,
+	};
+	struct {
+		void *sa_handler_;
+		unsigned long sa_flags;
+		void *sa_restorer;
+		unsigned long long sa_mask;
+	} sa = {
+		/* Need to set SA_RESTORER (but the handler never returns) */
+		.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO | 0x04000000,
+	};
+
+	/* set a nice name */
+	stub_syscall2(__NR_prctl, PR_SET_NAME, (unsigned long)"uml-userspace");
+
+	/* Make sure this process dies if the kernel dies */
+	stub_syscall2(__NR_prctl, PR_SET_PDEATHSIG, SIGKILL);
+
+	/* Needed in SECCOMP mode (and safe to do anyway) */
+	stub_syscall5(__NR_prctl, PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+
+	/* read information from STDIN and close it */
+	res = stub_syscall3(__NR_read, 0,
+			    (unsigned long)&init_data, sizeof(init_data));
+	if (res != sizeof(init_data))
+		stub_syscall1(__NR_exit, 10);
+
+	/* In SECCOMP mode, FD 0 is a socket and is later used for FD passing */
+	if (!init_data.seccomp)
+		stub_syscall1(__NR_close, 0);
+	else
+		stub_syscall3(__NR_fcntl, 0, F_SETFL, O_NONBLOCK);
+
+	/* map stub code + data */
+	res = stub_syscall6(STUB_MMAP_NR,
+			    init_data.stub_start, UM_KERN_PAGE_SIZE,
+			    PROT_READ | PROT_EXEC, MAP_FIXED | MAP_SHARED,
+			    init_data.stub_code_fd, init_data.stub_code_offset);
+	if (res != init_data.stub_start)
+		stub_syscall1(__NR_exit, 11);
+
+	res = stub_syscall6(STUB_MMAP_NR,
+			    init_data.stub_start + UM_KERN_PAGE_SIZE,
+			    STUB_DATA_PAGES * UM_KERN_PAGE_SIZE,
+			    PROT_READ | PROT_WRITE, MAP_FIXED | MAP_SHARED,
+			    init_data.stub_data_fd, init_data.stub_data_offset);
+	if (res != init_data.stub_start + UM_KERN_PAGE_SIZE)
+		stub_syscall1(__NR_exit, 12);
+
+	/* In SECCOMP mode, we only need the signalling FD from now on */
+	if (init_data.seccomp) {
+		res = stub_syscall3(__NR_close_range, 1, ~0U, 0);
+		if (res != 0)
+			stub_syscall1(__NR_exit, 13);
+	}
+
+	/* setup signal stack inside stub data */
+	stack.ss_sp = (void *)init_data.stub_start + UM_KERN_PAGE_SIZE;
+	stub_syscall2(__NR_sigaltstack, (unsigned long)&stack, 0);
+
+	/* register signal handlers */
+	sa.sa_handler_ = (void *) init_data.signal_handler;
+	sa.sa_restorer = (void *) init_data.signal_restorer;
+	if (!init_data.seccomp) {
+		/* In ptrace mode, the SIGSEGV handler never returns */
+		sa.sa_mask = 0;
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGSEGV,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 14);
+	} else {
+		/* SECCOMP mode uses rt_sigreturn, need to mask all signals */
+		sa.sa_mask = ~0ULL;
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGSEGV,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 15);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGSYS,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 16);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGALRM,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 17);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGTRAP,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 18);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGILL,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 19);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGFPE,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 20);
+	}
+
+	/*
+	 * If in seccomp mode, install the SECCOMP filter and trigger a syscall.
+	 * Otherwise set PTRACE_TRACEME and do a SIGSTOP.
+	 */
+	if (init_data.seccomp) {
+		struct sock_filter filter[] = {
+#if __BITS_PER_LONG > 32
+			/* [0] Load upper 32bit of instruction pointer from seccomp_data */
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 (offsetof(struct seccomp_data, instruction_pointer) + 4)),
+
+			/* [1] Jump forward 3 instructions if the upper address is not identical */
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, (init_data.stub_start) >> 32, 0, 3),
+#endif
+			/* [2] Load lower 32bit of instruction pointer from seccomp_data */
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 (offsetof(struct seccomp_data, instruction_pointer))),
+
+			/* [3] Mask out lower bits */
+			BPF_STMT(BPF_ALU | BPF_AND | BPF_K, 0xfffff000),
+
+			/* [4] Jump to [6] if the lower bits are not on the expected page */
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, (init_data.stub_start) & 0xfffff000, 1, 0),
+
+			/* [5] Trap call, allow */
+			BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_TRAP),
+
+			/* [6,7] Check architecture */
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 offsetof(struct seccomp_data, arch)),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K,
+				 UM_SECCOMP_ARCH_NATIVE, 1, 0),
+
+			/* [8] Kill (for architecture check) */
+			BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_KILL_PROCESS),
+
+			/* [9] Load syscall number */
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 offsetof(struct seccomp_data, nr)),
+
+			/* [10-16] Check against permitted syscalls */
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_futex,
+				 7, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K,__NR_recvmsg,
+				 6, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K,__NR_close,
+				 5, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, STUB_MMAP_NR,
+				 4, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_munmap,
+				 3, 0),
+#ifdef __i386__
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_set_thread_area,
+				 2, 0),
+#else
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_arch_prctl,
+				 2, 0),
+#endif
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_rt_sigreturn,
+				 1, 0),
+
+			/* [17] Not one of the permitted syscalls */
+			BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_KILL_PROCESS),
+
+			/* [18] Permitted call for the stub */
+			BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW),
+		};
+		struct sock_fprog prog = {
+			.len = sizeof(filter) / sizeof(filter[0]),
+			.filter = filter,
+		};
+
+		if (stub_syscall3(__NR_seccomp, SECCOMP_SET_MODE_FILTER,
+				  SECCOMP_FILTER_FLAG_TSYNC,
+				  (unsigned long)&prog) != 0)
+			stub_syscall1(__NR_exit, 21);
+
+		/* Fall through, the exit syscall will cause SIGSYS */
+	} else {
+		stub_syscall4(__NR_ptrace, PTRACE_TRACEME, 0, 0, 0);
+
+		stub_syscall2(__NR_kill, stub_syscall0(__NR_getpid), SIGSTOP);
+	}
+
+	stub_syscall1(__NR_exit, 30);
+
+	__builtin_unreachable();
+}
+
+__attribute__((naked)) void _start(void)
+{
+	/*
+	 * Since the stack after exec() starts at the top-most address,
+	 * but that's exactly where we also want to map the stub data
+	 * and code, this must:
+	 *  - push the stack by 1 code and STUB_DATA_PAGES data pages
+	 *  - call real_init()
+	 * This way, real_init() can use the stack normally, while the
+	 * original stack further down (higher address) will become
+	 * inaccessible after the mmap() calls above.
+	 */
+	stub_start(real_init);
+}

linux-7.2.3/arch/um/kernel/skas/stub_exe_embed.S

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/init.h>
+#include <linux/linkage.h>
+
+__INITDATA
+
+SYM_DATA_START(stub_exe_start)
+	.incbin "arch/um/kernel/skas/stub_exe"
+SYM_DATA_END_LABEL(stub_exe_start, SYM_L_GLOBAL, stub_exe_end)
+
+__FINIT

linux-7.2.3/arch/um/kernel/skas/syscall.c

@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/ptrace.h>
+#include <linux/seccomp.h>
+#include <kern_util.h>
+#include <sysdep/ptrace.h>
+#include <sysdep/ptrace_user.h>
+#include <linux/time-internal.h>
+#include <asm/syscall.h>
+#include <asm/unistd.h>
+#include <asm/delay.h>
+
+void handle_syscall(struct uml_pt_regs *r)
+{
+	struct pt_regs *regs = container_of(r, struct pt_regs, regs);
+	int syscall;
+
+	/* Initialize the syscall number and default return value. */
+	UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
+	PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS);
+
+	if (syscall_trace_enter(regs))
+		goto out;
+
+	/* Do the seccomp check after ptrace; failures should be fast. */
+	if (secure_computing() == -1)
+		goto out;
+
+	syscall = UPT_SYSCALL_NR(r);
+
+	/*
+	 * If no time passes, then sched_yield may not actually yield, causing
+	 * broken spinlock implementations in userspace (ASAN) to hang for long
+	 * periods of time.
+	 */
+	if ((time_travel_mode == TT_MODE_INFCPU ||
+	     time_travel_mode == TT_MODE_EXTERNAL) &&
+	    syscall == __NR_sched_yield)
+		tt_extra_sched_jiffies += 1;
+
+	if (syscall >= 0 && syscall < __NR_syscalls) {
+		unsigned long ret;
+
+		ret = (*sys_call_table[syscall])(UPT_SYSCALL_ARG1(&regs->regs),
+						 UPT_SYSCALL_ARG2(&regs->regs),
+						 UPT_SYSCALL_ARG3(&regs->regs),
+						 UPT_SYSCALL_ARG4(&regs->regs),
+						 UPT_SYSCALL_ARG5(&regs->regs),
+						 UPT_SYSCALL_ARG6(&regs->regs));
+
+		PT_REGS_SET_SYSCALL_RETURN(regs, ret);
+
+		/*
+		 * An error value here can be some form of -ERESTARTSYS
+		 * and then we'd just loop. Make any error syscalls take
+		 * some time, so that it won't just loop if something is
+		 * not ready, and hopefully other things will make some
+		 * progress.
+		 */
+		if (IS_ERR_VALUE(ret) &&
+		    (time_travel_mode == TT_MODE_INFCPU ||
+		     time_travel_mode == TT_MODE_EXTERNAL)) {
+			um_udelay(1);
+			schedule();
+		}
+	}
+
+out:
+	syscall_trace_leave(regs);
+}

linux-7.2.3/arch/um/kernel/skas/uaccess.c

@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <asm/current.h>
+#include <asm/page.h>
+#include <kern_util.h>
+#include <asm/futex.h>
+#include <os.h>
+
+pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	if (mm == NULL)
+		return NULL;
+
+	pgd = pgd_offset(mm, addr);
+	if (!pgd_present(*pgd))
+		return NULL;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return NULL;
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd))
+		return NULL;
+
+	return pte_offset_kernel(pmd, addr);
+}
+
+static pte_t *maybe_map(unsigned long virt, int is_write)
+{
+	pte_t *pte = virt_to_pte(current->mm, virt);
+	int err, dummy_code;
+
+	if ((pte == NULL) || !pte_present(*pte) ||
+	    (is_write && !pte_write(*pte))) {
+		err = handle_page_fault(virt, 0, is_write, 1, &dummy_code);
+		if (err)
+			return NULL;
+		pte = virt_to_pte(current->mm, virt);
+	}
+	if (!pte_present(*pte))
+		pte = NULL;
+
+	return pte;
+}
+
+static int do_op_one_page(unsigned long addr, int len, int is_write,
+		 int (*op)(unsigned long addr, int len, void *arg), void *arg)
+{
+	struct page *page;
+	pte_t *pte;
+	int n;
+
+	pte = maybe_map(addr, is_write);
+	if (pte == NULL)
+		return -1;
+
+	page = pte_page(*pte);
+#ifdef CONFIG_64BIT
+	pagefault_disable();
+	addr = (unsigned long) page_address(page) +
+		(addr & ~PAGE_MASK);
+#else
+	addr = (unsigned long) kmap_atomic(page) +
+		(addr & ~PAGE_MASK);
+#endif
+	n = (*op)(addr, len, arg);
+
+#ifdef CONFIG_64BIT
+	pagefault_enable();
+#else
+	kunmap_atomic((void *)addr);
+#endif
+
+	return n;
+}
+
+static long buffer_op(unsigned long addr, int len, int is_write,
+		      int (*op)(unsigned long, int, void *), void *arg)
+{
+	long size, remain, n;
+
+	size = min(PAGE_ALIGN(addr) - addr, (unsigned long) len);
+	remain = len;
+
+	n = do_op_one_page(addr, size, is_write, op, arg);
+	if (n != 0) {
+		remain = (n < 0 ? remain : 0);
+		goto out;
+	}
+
+	addr += size;
+	remain -= size;
+	if (remain == 0)
+		goto out;
+
+	while (addr < ((addr + remain) & PAGE_MASK)) {
+		n = do_op_one_page(addr, PAGE_SIZE, is_write, op, arg);
+		if (n != 0) {
+			remain = (n < 0 ? remain : 0);
+			goto out;
+		}
+
+		addr += PAGE_SIZE;
+		remain -= PAGE_SIZE;
+	}
+	if (remain == 0)
+		goto out;
+
+	n = do_op_one_page(addr, remain, is_write, op, arg);
+	if (n != 0) {
+		remain = (n < 0 ? remain : 0);
+		goto out;
+	}
+
+	return 0;
+ out:
+	return remain;
+}
+
+static int copy_chunk_from_user(unsigned long from, int len, void *arg)
+{
+	unsigned long *to_ptr = arg, to = *to_ptr;
+
+	memcpy((void *) to, (void *) from, len);
+	*to_ptr += len;
+	return 0;
+}
+
+unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	return buffer_op((unsigned long) from, n, 0, copy_chunk_from_user, &to);
+}
+EXPORT_SYMBOL(raw_copy_from_user);
+
+static int copy_chunk_to_user(unsigned long to, int len, void *arg)
+{
+	unsigned long *from_ptr = arg, from = *from_ptr;
+
+	memcpy((void *) to, (void *) from, len);
+	*from_ptr += len;
+	return 0;
+}
+
+unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	return buffer_op((unsigned long) to, n, 1, copy_chunk_to_user, &from);
+}
+EXPORT_SYMBOL(raw_copy_to_user);
+
+static int strncpy_chunk_from_user(unsigned long from, int len, void *arg)
+{
+	char **to_ptr = arg, *to = *to_ptr;
+	int n;
+
+	n = strnlen((void *) from, len);
+	memcpy_and_pad(to, len, (void *) from, n, 0);
+	*to_ptr += n;
+
+	if (n < len)
+	        return 1;
+	return 0;
+}
+
+long strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	long n;
+	char *ptr = dst;
+
+	if (!access_ok(src, 1))
+		return -EFAULT;
+	n = buffer_op((unsigned long) src, count, 0, strncpy_chunk_from_user,
+		      &ptr);
+	if (n != 0)
+		return -EFAULT;
+	return strnlen(dst, count);
+}
+EXPORT_SYMBOL(strncpy_from_user);
+
+static int clear_chunk(unsigned long addr, int len, void *unused)
+{
+	memset((void *) addr, 0, len);
+	return 0;
+}
+
+unsigned long __clear_user(void __user *mem, unsigned long len)
+{
+	return buffer_op((unsigned long) mem, len, 1, clear_chunk, NULL);
+}
+EXPORT_SYMBOL(__clear_user);
+
+static int strnlen_chunk(unsigned long str, int len, void *arg)
+{
+	int *len_ptr = arg, n;
+
+	n = strnlen((void *) str, len);
+	*len_ptr += n;
+
+	if (n < len)
+		return 1;
+	return 0;
+}
+
+long strnlen_user(const char __user *str, long len)
+{
+	int count = 0, n;
+
+	if (!access_ok(str, 1))
+		return -EFAULT;
+	n = buffer_op((unsigned long) str, len, 0, strnlen_chunk, &count);
+	if (n == 0)
+		return count + 1;
+	return 0;
+}
+EXPORT_SYMBOL(strnlen_user);
+
+/**
+ * arch_futex_atomic_op_inuser() - Atomic arithmetic operation with constant
+ *			  argument and comparison of the previous
+ *			  futex value with another constant.
+ *
+ * @op:		operation to execute
+ * @oparg:	argument to operation
+ * @oval:	old value at uaddr
+ * @uaddr:	pointer to user space address
+ *
+ * Return:
+ * 0 - On success
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ * -ENOSYS - Operation not supported
+ */
+
+int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
+{
+	int oldval, ret;
+	struct page *page;
+	unsigned long addr = (unsigned long) uaddr;
+	pte_t *pte;
+
+	ret = -EFAULT;
+	if (!access_ok(uaddr, sizeof(*uaddr)))
+		return -EFAULT;
+	preempt_disable();
+	pte = maybe_map(addr, 1);
+	if (pte == NULL)
+		goto out_inuser;
+
+	page = pte_page(*pte);
+#ifdef CONFIG_64BIT
+	pagefault_disable();
+	addr = (unsigned long) page_address(page) +
+			(((unsigned long) addr) & ~PAGE_MASK);
+#else
+	addr = (unsigned long) kmap_atomic(page) +
+		((unsigned long) addr & ~PAGE_MASK);
+#endif
+	uaddr = (u32 *) addr;
+	oldval = *uaddr;
+
+	ret = 0;
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		*uaddr = oparg;
+		break;
+	case FUTEX_OP_ADD:
+		*uaddr += oparg;
+		break;
+	case FUTEX_OP_OR:
+		*uaddr |= oparg;
+		break;
+	case FUTEX_OP_ANDN:
+		*uaddr &= ~oparg;
+		break;
+	case FUTEX_OP_XOR:
+		*uaddr ^= oparg;
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+#ifdef CONFIG_64BIT
+	pagefault_enable();
+#else
+	kunmap_atomic((void *)addr);
+#endif
+
+out_inuser:
+	preempt_enable();
+
+	if (ret == 0)
+		*oval = oldval;
+
+	return ret;
+}
+EXPORT_SYMBOL(arch_futex_atomic_op_inuser);
+
+/**
+ * futex_atomic_cmpxchg_inatomic() - Compare and exchange the content of the
+ *				uaddr with newval if the current value is
+ *				oldval.
+ * @uval:	pointer to store content of @uaddr
+ * @uaddr:	pointer to user space address
+ * @oldval:	old value
+ * @newval:	new value to store to @uaddr
+ *
+ * Return:
+ * 0 - On success
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ */
+
+int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	struct page *page;
+	pte_t *pte;
+	int ret = -EFAULT;
+
+	if (!access_ok(uaddr, sizeof(*uaddr)))
+		return -EFAULT;
+
+	preempt_disable();
+	pte = maybe_map((unsigned long) uaddr, 1);
+	if (pte == NULL)
+		goto out_inatomic;
+
+	page = pte_page(*pte);
+#ifdef CONFIG_64BIT
+	pagefault_disable();
+	uaddr = page_address(page) + (((unsigned long) uaddr) & ~PAGE_MASK);
+#else
+	uaddr = kmap_atomic(page) + ((unsigned long) uaddr & ~PAGE_MASK);
+#endif
+
+	*uval = *uaddr;
+
+	ret = cmpxchg(uaddr, oldval, newval);
+
+#ifdef CONFIG_64BIT
+	pagefault_enable();
+#else
+	kunmap_atomic(uaddr);
+#endif
+	ret = 0;
+
+out_inatomic:
+	preempt_enable();
+	return ret;
+}
+EXPORT_SYMBOL(futex_atomic_cmpxchg_inatomic);

linux-7.2.3/arch/um/kernel/smp.c

@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 Ant Group
+ * Author: Tiwei Bie <tiwei.btw@antgroup.com>
+ *
+ * Based on the previous implementation in TT mode
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/module.h>
+#include <linux/processor.h>
+#include <linux/threads.h>
+#include <linux/cpu.h>
+#include <linux/hardirq.h>
+#include <linux/smp.h>
+#include <linux/smp-internal.h>
+#include <init.h>
+#include <kern.h>
+#include <os.h>
+#include <smp.h>
+
+enum {
+	UML_IPI_RES = 0,
+	UML_IPI_CALL_SINGLE,
+	UML_IPI_CALL,
+	UML_IPI_STOP,
+};
+
+void arch_smp_send_reschedule(int cpu)
+{
+	os_send_ipi(cpu, UML_IPI_RES);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	os_send_ipi(cpu, UML_IPI_CALL_SINGLE);
+}
+
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
+{
+	int cpu;
+
+	for_each_cpu(cpu, mask)
+		os_send_ipi(cpu, UML_IPI_CALL);
+}
+
+void smp_send_stop(void)
+{
+	int cpu, me = smp_processor_id();
+
+	for_each_online_cpu(cpu) {
+		if (cpu == me)
+			continue;
+		os_send_ipi(cpu, UML_IPI_STOP);
+	}
+}
+
+static void ipi_handler(int vector, struct uml_pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs((struct pt_regs *)regs);
+	int cpu = raw_smp_processor_id();
+
+	irq_enter();
+
+	if (current->mm)
+		os_alarm_process(current->mm->context.id.pid);
+
+	switch (vector) {
+	case UML_IPI_RES:
+		inc_irq_stat(irq_resched_count);
+		scheduler_ipi();
+		break;
+
+	case UML_IPI_CALL_SINGLE:
+		inc_irq_stat(irq_call_count);
+		generic_smp_call_function_single_interrupt();
+		break;
+
+	case UML_IPI_CALL:
+		inc_irq_stat(irq_call_count);
+		generic_smp_call_function_interrupt();
+		break;
+
+	case UML_IPI_STOP:
+		set_cpu_online(cpu, false);
+		while (1)
+			pause();
+		break;
+
+	default:
+		pr_err("CPU#%d received unknown IPI (vector=%d)!\n", cpu, vector);
+		break;
+	}
+
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
+void uml_ipi_handler(int vector)
+{
+	struct uml_pt_regs r = { .is_user = 0 };
+
+	preempt_disable();
+	ipi_handler(vector, &r);
+	preempt_enable();
+}
+
+/* AP states used only during CPU startup */
+enum {
+	UML_CPU_PAUSED = 0,
+	UML_CPU_RUNNING,
+};
+
+static int cpu_states[NR_CPUS];
+
+static int start_secondary(void *unused)
+{
+	int err, cpu = raw_smp_processor_id();
+
+	notify_cpu_starting(cpu);
+	set_cpu_online(cpu, true);
+
+	err = um_setup_timer();
+	if (err)
+		panic("CPU#%d failed to setup timer, err = %d", cpu, err);
+
+	local_irq_enable();
+
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+
+	return 0;
+}
+
+void uml_start_secondary(void *opaque)
+{
+	int cpu = raw_smp_processor_id();
+	struct mm_struct *mm = &init_mm;
+	struct task_struct *idle;
+
+	stack_protections((unsigned long) &cpu_irqstacks[cpu]);
+	set_sigstack(&cpu_irqstacks[cpu], THREAD_SIZE);
+
+	set_cpu_present(cpu, true);
+	os_futex_wait(&cpu_states[cpu], UML_CPU_PAUSED);
+
+	smp_rmb(); /* paired with smp_wmb() in __cpu_up() */
+
+	idle = cpu_tasks[cpu];
+	idle->thread_info.cpu = cpu;
+
+	mmgrab(mm);
+	idle->active_mm = mm;
+
+	idle->thread.request.thread.proc = start_secondary;
+	idle->thread.request.thread.arg = NULL;
+
+	new_thread(task_stack_page(idle), &idle->thread.switch_buf,
+		   new_thread_handler);
+	os_start_secondary(opaque, &idle->thread.switch_buf);
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	int err, cpu, me = smp_processor_id();
+	unsigned long deadline;
+
+	os_init_smp();
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == me)
+			continue;
+
+		pr_debug("Booting processor %d...\n", cpu);
+		err = os_start_cpu_thread(cpu);
+		if (err) {
+			pr_crit("CPU#%d failed to start cpu thread, err = %d",
+				cpu, err);
+			continue;
+		}
+
+		deadline = jiffies + msecs_to_jiffies(1000);
+		spin_until_cond(cpu_present(cpu) ||
+				time_is_before_jiffies(deadline));
+
+		if (!cpu_present(cpu))
+			pr_crit("CPU#%d failed to boot\n", cpu);
+	}
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+	cpu_tasks[cpu] = tidle;
+	smp_wmb(); /* paired with smp_rmb() in uml_start_secondary() */
+	cpu_states[cpu] = UML_CPU_RUNNING;
+	os_futex_wake(&cpu_states[cpu]);
+	spin_until_cond(cpu_online(cpu));
+
+	return 0;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+/* Set in uml_ncpus_setup */
+int uml_ncpus = 1;
+
+void __init prefill_possible_map(void)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < uml_ncpus; cpu++)
+		set_cpu_possible(cpu, true);
+	for (; cpu < NR_CPUS; cpu++)
+		set_cpu_possible(cpu, false);
+}
+
+static int __init uml_ncpus_setup(char *line, int *add)
+{
+	*add = 0;
+
+	if (kstrtoint(line, 10, &uml_ncpus)) {
+		os_warn("%s: Couldn't parse '%s'\n", __func__, line);
+		return -1;
+	}
+
+	uml_ncpus = clamp(uml_ncpus, 1, NR_CPUS);
+
+	return 0;
+}
+
+__uml_setup("ncpus=", uml_ncpus_setup,
+"ncpus=<# of desired CPUs>\n"
+"    This tells UML how many virtual processors to start. The maximum\n"
+"    number of supported virtual processors can be obtained by querying\n"
+"    the CONFIG_NR_CPUS option using --showconfig.\n\n"
+);
+
+EXPORT_SYMBOL(uml_curr_cpu);

linux-7.2.3/arch/um/kernel/stacktrace.c

@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright (C) 2013 Richard Weinberger <richard@nod.at>
+ * Copyright (C) 2014 Google Inc., Author: Daniel Walter <dwalter@google.com>
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/stacktrace.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <asm/stacktrace.h>
+
+void dump_trace(struct task_struct *tsk,
+		const struct stacktrace_ops *ops,
+		void *data)
+{
+	int reliable = 0;
+	unsigned long *sp, bp, addr;
+	struct pt_regs *segv_regs = tsk->thread.segv_regs;
+	struct stack_frame *frame;
+
+	bp = get_frame_pointer(tsk, segv_regs);
+	sp = get_stack_pointer(tsk, segv_regs);
+
+	frame = (struct stack_frame *)bp;
+	while (((long) sp & (THREAD_SIZE-1)) != 0) {
+		addr = READ_ONCE_NOCHECK(*sp);
+		if (__kernel_text_address(addr)) {
+			reliable = 0;
+			if ((unsigned long) sp == bp + sizeof(long)) {
+				frame = frame ? frame->next_frame : NULL;
+				bp = (unsigned long)frame;
+				reliable = 1;
+			}
+			ops->address(data, addr, reliable);
+		}
+		sp++;
+	}
+}
+
+static void save_addr(void *data, unsigned long address, int reliable)
+{
+	struct stack_trace *trace = data;
+
+	if (!reliable)
+		return;
+	if (trace->nr_entries >= trace->max_entries)
+		return;
+
+	trace->entries[trace->nr_entries++] = address;
+}
+
+static const struct stacktrace_ops dump_ops = {
+	.address = save_addr
+};
+
+static void __save_stack_trace(struct task_struct *tsk, struct stack_trace *trace)
+{
+	dump_trace(tsk, &dump_ops, trace);
+}
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	__save_stack_trace(current, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	__save_stack_trace(tsk, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);

linux-7.2.3/arch/um/kernel/sysrq.c

@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright (C) 2013 Richard Weinberger <richrd@nod.at>
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/stacktrace.h>
+#include <os.h>
+
+static void _print_addr(void *data, unsigned long address, int reliable)
+{
+	const char *loglvl = data;
+
+	printk("%s [<%08lx>] %s%pS\n", loglvl, address, reliable ? "" : "? ",
+		(void *)address);
+}
+
+static const struct stacktrace_ops stackops = {
+	.address = _print_addr
+};
+
+void show_stack(struct task_struct *task, unsigned long *stack,
+		       const char *loglvl)
+{
+	struct pt_regs *segv_regs = current->thread.segv_regs;
+	int i;
+
+	if (!stack)
+		stack = get_stack_pointer(task, segv_regs);
+
+	printk("%sStack:\n", loglvl);
+	for (i = 0; i < 3 * STACKSLOTS_PER_LINE; i++) {
+		if (kstack_end(stack))
+			break;
+		if (i && ((i % STACKSLOTS_PER_LINE) == 0))
+			pr_cont("\n");
+		pr_cont(" %08lx", READ_ONCE_NOCHECK(*stack));
+		stack++;
+	}
+
+	printk("%sCall Trace:\n", loglvl);
+	dump_trace(task ?: current, &stackops, (void *)loglvl);
+}

linux-7.2.3/arch/um/kernel/tlb.c

@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/sched/signal.h>
+
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include <as-layout.h>
+#include <mem_user.h>
+#include <os.h>
+#include <skas.h>
+#include <kern_util.h>
+
+struct vm_ops {
+	struct mm_id *mm_idp;
+
+	int (*mmap)(struct mm_id *mm_idp,
+		    unsigned long virt, unsigned long len, int prot,
+		    int phys_fd, unsigned long long offset);
+	int (*unmap)(struct mm_id *mm_idp,
+		     unsigned long virt, unsigned long len);
+};
+
+static int kern_map(struct mm_id *mm_idp,
+		    unsigned long virt, unsigned long len, int prot,
+		    int phys_fd, unsigned long long offset)
+{
+	return os_map_memory((void *)virt, phys_fd, offset, len,
+			     prot & UM_PROT_READ, prot & UM_PROT_WRITE,
+			     prot & UM_PROT_EXEC);
+}
+
+static int kern_unmap(struct mm_id *mm_idp,
+		      unsigned long virt, unsigned long len)
+{
+	return os_unmap_memory((void *)virt, len);
+}
+
+void report_enomem(void)
+{
+	printk(KERN_ERR "UML ran out of memory on the host side! "
+			"This can happen due to a memory limitation or "
+			"vm.max_map_count has been reached.\n");
+}
+
+static inline int update_pte_range(pmd_t *pmd, unsigned long addr,
+				   unsigned long end,
+				   struct vm_ops *ops)
+{
+	pte_t *pte;
+	int ret = 0;
+
+	pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_needsync(*pte))
+			continue;
+
+		if (pte_present(*pte)) {
+			__u64 offset;
+			unsigned long phys = pte_val(*pte) & PAGE_MASK;
+			int fd = phys_mapping(phys, &offset);
+			int r, w, x, prot;
+
+			r = pte_read(*pte);
+			w = pte_write(*pte);
+			x = pte_exec(*pte);
+			if (!pte_young(*pte)) {
+				r = 0;
+				w = 0;
+			} else if (!pte_dirty(*pte))
+				w = 0;
+
+			prot = (r ? UM_PROT_READ : 0) |
+			       (w ? UM_PROT_WRITE : 0) |
+			       (x ? UM_PROT_EXEC : 0);
+
+			ret = ops->mmap(ops->mm_idp, addr, PAGE_SIZE,
+					prot, fd, offset);
+		} else
+			ret = ops->unmap(ops->mm_idp, addr, PAGE_SIZE);
+
+		*pte = pte_mkuptodate(*pte);
+	} while (pte++, addr += PAGE_SIZE, ((addr < end) && !ret));
+	return ret;
+}
+
+static inline int update_pmd_range(pud_t *pud, unsigned long addr,
+				   unsigned long end,
+				   struct vm_ops *ops)
+{
+	pmd_t *pmd;
+	unsigned long next;
+	int ret = 0;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (!pmd_present(*pmd)) {
+			if (pmd_needsync(*pmd)) {
+				ret = ops->unmap(ops->mm_idp, addr,
+						 next - addr);
+				pmd_mkuptodate(*pmd);
+			}
+		}
+		else ret = update_pte_range(pmd, addr, next, ops);
+	} while (pmd++, addr = next, ((addr < end) && !ret));
+	return ret;
+}
+
+static inline int update_pud_range(p4d_t *p4d, unsigned long addr,
+				   unsigned long end,
+				   struct vm_ops *ops)
+{
+	pud_t *pud;
+	unsigned long next;
+	int ret = 0;
+
+	pud = pud_offset(p4d, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (!pud_present(*pud)) {
+			if (pud_needsync(*pud)) {
+				ret = ops->unmap(ops->mm_idp, addr,
+						 next - addr);
+				pud_mkuptodate(*pud);
+			}
+		}
+		else ret = update_pmd_range(pud, addr, next, ops);
+	} while (pud++, addr = next, ((addr < end) && !ret));
+	return ret;
+}
+
+static inline int update_p4d_range(pgd_t *pgd, unsigned long addr,
+				   unsigned long end,
+				   struct vm_ops *ops)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int ret = 0;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (!p4d_present(*p4d)) {
+			if (p4d_needsync(*p4d)) {
+				ret = ops->unmap(ops->mm_idp, addr,
+						 next - addr);
+				p4d_mkuptodate(*p4d);
+			}
+		} else
+			ret = update_pud_range(p4d, addr, next, ops);
+	} while (p4d++, addr = next, ((addr < end) && !ret));
+	return ret;
+}
+
+int um_tlb_sync(struct mm_struct *mm)
+{
+	pgd_t *pgd;
+	struct vm_ops ops;
+	unsigned long addr, next;
+	int ret = 0;
+
+	guard(spinlock_irqsave)(&mm->page_table_lock);
+	guard(spinlock_irqsave)(&mm->context.sync_tlb_lock);
+
+	if (mm->context.sync_tlb_range_to == 0)
+		return 0;
+
+	ops.mm_idp = &mm->context.id;
+	if (mm == &init_mm) {
+		ops.mmap = kern_map;
+		ops.unmap = kern_unmap;
+	} else {
+		ops.mmap = map;
+		ops.unmap = unmap;
+	}
+
+	addr = mm->context.sync_tlb_range_from;
+	pgd = pgd_offset(mm, addr);
+	do {
+		next = pgd_addr_end(addr, mm->context.sync_tlb_range_to);
+		if (!pgd_present(*pgd)) {
+			if (pgd_needsync(*pgd)) {
+				ret = ops.unmap(ops.mm_idp, addr,
+						next - addr);
+				pgd_mkuptodate(*pgd);
+			}
+		} else
+			ret = update_p4d_range(pgd, addr, next, &ops);
+	} while (pgd++, addr = next,
+		 ((addr < mm->context.sync_tlb_range_to) && !ret));
+
+	if (ret == -ENOMEM)
+		report_enomem();
+
+	mm->context.sync_tlb_range_from = 0;
+	mm->context.sync_tlb_range_to = 0;
+
+	return ret;
+}
+
+void flush_tlb_all(void)
+{
+	/*
+	 * Don't bother flushing if this address space is about to be
+	 * destroyed.
+	 */
+	if (atomic_read(&current->mm->mm_users) == 0)
+		return;
+
+	flush_tlb_mm(current->mm);
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
+
+	for_each_vma(vmi, vma)
+		um_tlb_mark_sync(mm, vma->vm_start, vma->vm_end);
+}

linux-7.2.3/arch/um/kernel/trap.c

@@ -0,0 +1,430 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/hardirq.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/sched/debug.h>
+#include <asm/current.h>
+#include <asm/tlbflush.h>
+#include <arch.h>
+#include <as-layout.h>
+#include <kern_util.h>
+#include <os.h>
+#include <skas.h>
+
+/*
+ * NOTE: UML does not have exception tables. As such, this is almost a copy
+ * of the code in mm/memory.c, only adjusting the logic to simply check whether
+ * we are coming from the kernel instead of doing an additional lookup in the
+ * exception table.
+ * We can do this simplification because we never get here if the exception was
+ * fixable.
+ */
+static inline bool get_mmap_lock_carefully(struct mm_struct *mm, bool is_user)
+{
+	if (likely(mmap_read_trylock(mm)))
+		return true;
+
+	if (!is_user)
+		return false;
+
+	return !mmap_read_lock_killable(mm);
+}
+
+static inline bool mmap_upgrade_trylock(struct mm_struct *mm)
+{
+	/*
+	 * We don't have this operation yet.
+	 *
+	 * It should be easy enough to do: it's basically a
+	 *    atomic_long_try_cmpxchg_acquire()
+	 * from RWSEM_READER_BIAS -> RWSEM_WRITER_LOCKED, but
+	 * it also needs the proper lockdep magic etc.
+	 */
+	return false;
+}
+
+static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, bool is_user)
+{
+	mmap_read_unlock(mm);
+	if (!is_user)
+		return false;
+
+	return !mmap_write_lock_killable(mm);
+}
+
+/*
+ * Helper for page fault handling.
+ *
+ * This is kind of equivalend to "mmap_read_lock()" followed
+ * by "find_extend_vma()", except it's a lot more careful about
+ * the locking (and will drop the lock on failure).
+ *
+ * For example, if we have a kernel bug that causes a page
+ * fault, we don't want to just use mmap_read_lock() to get
+ * the mm lock, because that would deadlock if the bug were
+ * to happen while we're holding the mm lock for writing.
+ *
+ * So this checks the exception tables on kernel faults in
+ * order to only do this all for instructions that are actually
+ * expected to fault.
+ *
+ * We can also actually take the mm lock for writing if we
+ * need to extend the vma, which helps the VM layer a lot.
+ */
+static struct vm_area_struct *
+um_lock_mm_and_find_vma(struct mm_struct *mm,
+			unsigned long addr, bool is_user)
+{
+	struct vm_area_struct *vma;
+
+	if (!get_mmap_lock_carefully(mm, is_user))
+		return NULL;
+
+	vma = find_vma(mm, addr);
+	if (likely(vma && (vma->vm_start <= addr)))
+		return vma;
+
+	/*
+	 * Well, dang. We might still be successful, but only
+	 * if we can extend a vma to do so.
+	 */
+	if (!vma || !(vma->vm_flags & VM_GROWSDOWN)) {
+		mmap_read_unlock(mm);
+		return NULL;
+	}
+
+	/*
+	 * We can try to upgrade the mmap lock atomically,
+	 * in which case we can continue to use the vma
+	 * we already looked up.
+	 *
+	 * Otherwise we'll have to drop the mmap lock and
+	 * re-take it, and also look up the vma again,
+	 * re-checking it.
+	 */
+	if (!mmap_upgrade_trylock(mm)) {
+		if (!upgrade_mmap_lock_carefully(mm, is_user))
+			return NULL;
+
+		vma = find_vma(mm, addr);
+		if (!vma)
+			goto fail;
+		if (vma->vm_start <= addr)
+			goto success;
+		if (!(vma->vm_flags & VM_GROWSDOWN))
+			goto fail;
+	}
+
+	if (expand_stack_locked(vma, addr))
+		goto fail;
+
+success:
+	mmap_write_downgrade(mm);
+	return vma;
+
+fail:
+	mmap_write_unlock(mm);
+	return NULL;
+}
+
+/*
+ * Note this is constrained to return 0, -EFAULT, -EACCES, -ENOMEM by
+ * segv().
+ */
+int handle_page_fault(unsigned long address, unsigned long ip,
+		      int is_write, int is_user, int *code_out)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	pmd_t *pmd;
+	pte_t *pte;
+	int err = -EFAULT;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
+
+	*code_out = SEGV_MAPERR;
+
+	/*
+	 * If the fault was with pagefaults disabled, don't take the fault, just
+	 * fail.
+	 */
+	if (faulthandler_disabled())
+		goto out_nosemaphore;
+
+	if (is_user)
+		flags |= FAULT_FLAG_USER;
+retry:
+	vma = um_lock_mm_and_find_vma(mm, address, is_user);
+	if (!vma)
+		goto out_nosemaphore;
+
+	*code_out = SEGV_ACCERR;
+	if (is_write) {
+		if (!(vma->vm_flags & VM_WRITE))
+			goto out;
+		flags |= FAULT_FLAG_WRITE;
+	} else {
+		/* Don't require VM_READ|VM_EXEC for write faults! */
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+			goto out;
+	}
+
+	do {
+		vm_fault_t fault;
+
+		fault = handle_mm_fault(vma, address, flags, NULL);
+
+		if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+			goto out_nosemaphore;
+
+		/* The fault is fully completed (including releasing mmap lock) */
+		if (fault & VM_FAULT_COMPLETED)
+			return 0;
+
+		if (unlikely(fault & VM_FAULT_ERROR)) {
+			if (fault & VM_FAULT_OOM) {
+				goto out_of_memory;
+			} else if (fault & VM_FAULT_SIGSEGV) {
+				goto out;
+			} else if (fault & VM_FAULT_SIGBUS) {
+				err = -EACCES;
+				goto out;
+			}
+			BUG();
+		}
+		if (fault & VM_FAULT_RETRY) {
+			flags |= FAULT_FLAG_TRIED;
+
+			goto retry;
+		}
+
+		pmd = pmd_off(mm, address);
+		pte = pte_offset_kernel(pmd, address);
+	} while (!pte_present(*pte));
+	err = 0;
+	/*
+	 * The below warning was added in place of
+	 *	pte_mkyoung(); if (is_write) pte_mkdirty();
+	 * If it's triggered, we'd see normally a hang here (a clean pte is
+	 * marked read-only to emulate the dirty bit).
+	 * However, the generic code can mark a PTE writable but clean on a
+	 * concurrent read fault, triggering this harmlessly. So comment it out.
+	 */
+#if 0
+	WARN_ON(!pte_young(*pte) || (is_write && !pte_dirty(*pte)));
+#endif
+
+out:
+	mmap_read_unlock(mm);
+out_nosemaphore:
+	return err;
+
+out_of_memory:
+	/*
+	 * We ran out of memory, call the OOM killer, and return the userspace
+	 * (which will retry the fault, or kill us if we got oom-killed).
+	 */
+	mmap_read_unlock(mm);
+	if (!is_user)
+		goto out_nosemaphore;
+	pagefault_out_of_memory();
+	return 0;
+}
+
+static void show_segv_info(struct uml_pt_regs *regs)
+{
+	struct task_struct *tsk = current;
+	struct faultinfo *fi = UPT_FAULTINFO(regs);
+
+	if (!unhandled_signal(tsk, SIGSEGV))
+		return;
+
+	if (!printk_ratelimit())
+		return;
+
+	printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x",
+		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
+		tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
+		(void *)UPT_IP(regs), (void *)UPT_SP(regs),
+		fi->error_code);
+
+	print_vma_addr(KERN_CONT " in ", UPT_IP(regs));
+	printk(KERN_CONT "\n");
+}
+
+static void bad_segv(struct faultinfo fi, unsigned long ip)
+{
+	current->thread.arch.faultinfo = fi;
+	force_sig_fault(SIGSEGV, SEGV_ACCERR, (void __user *) FAULT_ADDRESS(fi));
+}
+
+void fatal_sigsegv(void)
+{
+	force_fatal_sig(SIGSEGV);
+	do_signal(&current->thread.regs);
+	/*
+	 * This is to tell gcc that we're not returning - do_signal
+	 * can, in general, return, but in this case, it's not, since
+	 * we just got a fatal SIGSEGV queued.
+	 */
+	os_dump_core();
+}
+
+/**
+ * segv_handler() - the SIGSEGV handler
+ * @sig:	the signal number
+ * @unused_si:	the signal info struct; unused in this handler
+ * @regs:	the ptrace register information
+ * @mc:		the mcontext of the signal
+ *
+ * The handler first extracts the faultinfo from the UML ptrace regs struct.
+ * If the userfault did not happen in an UML userspace process, bad_segv is called.
+ * Otherwise the signal did happen in a cloned userspace process, handle it.
+ */
+void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+		  void *mc)
+{
+	struct faultinfo * fi = UPT_FAULTINFO(regs);
+
+	if (UPT_IS_USER(regs) && !SEGV_IS_FIXABLE(fi)) {
+		show_segv_info(regs);
+		bad_segv(*fi, UPT_IP(regs));
+		return;
+	}
+	segv(*fi, UPT_IP(regs), UPT_IS_USER(regs), regs, mc);
+}
+
+/*
+ * We give a *copy* of the faultinfo in the regs to segv.
+ * This must be done, since nesting SEGVs could overwrite
+ * the info in the regs. A pointer to the info then would
+ * give us bad data!
+ */
+unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
+		   struct uml_pt_regs *regs, void *mc)
+{
+	int si_code;
+	int err;
+	int is_write = FAULT_WRITE(fi);
+	unsigned long address = FAULT_ADDRESS(fi);
+
+	if (!is_user && regs)
+		current->thread.segv_regs = container_of(regs, struct pt_regs, regs);
+
+	if (!is_user && address >= start_vm && address < end_vm) {
+		/*
+		 * Kernel has pending updates from set_ptes that were not
+		 * flushed yet. Syncing them should fix the pagefault (if not
+		 * we'll get here again and panic).
+		 */
+		err = um_tlb_sync(&init_mm);
+		if (err == -ENOMEM)
+			report_enomem();
+		if (err)
+			panic("Failed to sync kernel TLBs: %d", err);
+		goto out;
+	}
+	else if (current->pagefault_disabled) {
+		if (!mc) {
+			show_regs(container_of(regs, struct pt_regs, regs));
+			panic("Segfault with pagefaults disabled but no mcontext");
+		}
+		if (!current->thread.segv_continue) {
+			show_regs(container_of(regs, struct pt_regs, regs));
+			panic("Segfault without recovery target");
+		}
+		mc_set_rip(mc, current->thread.segv_continue);
+		current->thread.segv_continue = NULL;
+		goto out;
+	}
+	else if (current->mm == NULL) {
+		show_regs(container_of(regs, struct pt_regs, regs));
+		panic("Segfault with no mm");
+	}
+	else if (!is_user && address > PAGE_SIZE && address < TASK_SIZE) {
+		show_regs(container_of(regs, struct pt_regs, regs));
+		panic("Kernel tried to access user memory at addr 0x%lx, ip 0x%lx",
+		       address, ip);
+	}
+
+	if (SEGV_IS_FIXABLE(&fi))
+		err = handle_page_fault(address, ip, is_write, is_user,
+					&si_code);
+	else {
+		err = -EFAULT;
+		/*
+		 * A thread accessed NULL, we get a fault, but CR2 is invalid.
+		 * This code is used in __do_copy_from_user() of TT mode.
+		 * XXX tt mode is gone, so maybe this isn't needed any more
+		 */
+		address = 0;
+	}
+
+	if (!err)
+		goto out;
+	else if (!is_user && arch_fixup(ip, regs))
+		goto out;
+
+	if (!is_user) {
+		show_regs(container_of(regs, struct pt_regs, regs));
+		panic("Kernel mode fault at addr 0x%lx, ip 0x%lx",
+		      address, ip);
+	}
+
+	show_segv_info(regs);
+
+	if (err == -EACCES) {
+		current->thread.arch.faultinfo = fi;
+		force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
+	} else {
+		BUG_ON(err != -EFAULT);
+		current->thread.arch.faultinfo = fi;
+		force_sig_fault(SIGSEGV, si_code, (void __user *) address);
+	}
+
+out:
+	if (regs)
+		current->thread.segv_regs = NULL;
+
+	return 0;
+}
+
+void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs,
+		  void *mc)
+{
+	int code, err;
+	if (!UPT_IS_USER(regs)) {
+		if (sig == SIGBUS)
+			printk(KERN_ERR "Bus error - the host /dev/shm or /tmp "
+			       "mount likely just ran out of space\n");
+		panic("Kernel mode signal %d", sig);
+	}
+
+	arch_examine_signal(sig, regs);
+
+	/* Is the signal layout for the signal known?
+	 * Signal data must be scrubbed to prevent information leaks.
+	 */
+	code = si->si_code;
+	err = si->si_errno;
+	if ((err == 0) && (siginfo_layout(sig, code) == SIL_FAULT)) {
+		struct faultinfo *fi = UPT_FAULTINFO(regs);
+		current->thread.arch.faultinfo = *fi;
+		force_sig_fault(sig, code, (void __user *)FAULT_ADDRESS(*fi));
+	} else {
+		printk(KERN_ERR "Attempted to relay unknown signal %d (si_code = %d) with errno %d\n",
+		       sig, code, err);
+		force_sig(sig);
+	}
+}
+
+void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+	   void *mc)
+{
+	do_IRQ(WINCH_IRQ, regs);
+}

linux-7.2.3/arch/um/kernel/um_arch.c

@@ -0,0 +1,551 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/ctype.h>
+#include <linux/module.h>
+#include <linux/panic_notifier.h>
+#include <linux/seq_file.h>
+#include <linux/string.h>
+#include <linux/string_choices.h>
+#include <linux/utsname.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/kmsg_dump.h>
+#include <linux/suspend.h>
+#include <linux/random.h>
+#include <linux/smp-internal.h>
+
+#include <asm/processor.h>
+#include <asm/cpufeature.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/text-patching.h>
+#include <as-layout.h>
+#include <arch.h>
+#include <init.h>
+#include <kern.h>
+#include <kern_util.h>
+#include <mem_user.h>
+#include <os.h>
+
+#include "um_arch.h"
+
+#define DEFAULT_COMMAND_LINE_ROOT "root=98:0"
+#define DEFAULT_COMMAND_LINE_CONSOLE "console=tty0"
+
+/* Changed in add_arg and setup_arch, which run before SMP is started */
+static char __initdata command_line[COMMAND_LINE_SIZE] = { 0 };
+
+static void __init add_arg(char *arg)
+{
+	if (strlen(command_line) + strlen(arg) + 1 > COMMAND_LINE_SIZE) {
+		os_warn("add_arg: Too many command line arguments!\n");
+		exit(1);
+	}
+	if (strlen(command_line) > 0)
+		strcat(command_line, " ");
+	strcat(command_line, arg);
+}
+
+/*
+ * These fields are initialized at boot time and not changed.
+ */
+struct cpuinfo_um boot_cpu_data = {
+	.loops_per_jiffy	= 0,
+	.cache_alignment	= L1_CACHE_BYTES,
+	.x86_capability		= { 0 }
+};
+
+EXPORT_SYMBOL(boot_cpu_data);
+
+
+/* Changed in setup_arch, which is called in early boot */
+static char host_info[(__NEW_UTS_LEN + 1) * 5];
+
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+	int i = 0;
+
+#if IS_ENABLED(CONFIG_SMP)
+	i = (uintptr_t) v - 1;
+	if (!cpu_online(i))
+		return 0;
+#endif
+
+	seq_printf(m, "processor\t: %d\n", i);
+	seq_printf(m, "vendor_id\t: User Mode Linux\n");
+	seq_printf(m, "model name\t: UML\n");
+	seq_printf(m, "mode\t\t: skas\n");
+	seq_printf(m, "host\t\t: %s\n", host_info);
+	seq_printf(m, "fpu\t\t: %s\n", str_yes_no(cpu_has(&boot_cpu_data, X86_FEATURE_FPU)));
+	seq_printf(m, "flags\t\t:");
+	for (i = 0; i < 32*NCAPINTS; i++)
+		if (cpu_has(&boot_cpu_data, i) && (x86_cap_flags[i] != NULL))
+			seq_printf(m, " %s", x86_cap_flags[i]);
+	seq_printf(m, "\n");
+	seq_printf(m, "cache_alignment\t: %d\n", boot_cpu_data.cache_alignment);
+	seq_printf(m, "bogomips\t: %lu.%02lu\n",
+		   loops_per_jiffy/(500000/HZ),
+		   (loops_per_jiffy/(5000/HZ)) % 100);
+
+	return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	if (*pos < nr_cpu_ids)
+		return (void *)(uintptr_t)(*pos + 1);
+	return NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	++*pos;
+	return c_start(m, pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+const struct seq_operations cpuinfo_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= show_cpuinfo,
+};
+
+/* Set in linux_main */
+unsigned long uml_physmem;
+EXPORT_SYMBOL(uml_physmem);
+
+unsigned long uml_reserved; /* Also modified in mem_init */
+unsigned long start_vm;
+unsigned long end_vm;
+
+/* Set in early boot */
+static int have_root __initdata;
+static int have_console __initdata;
+
+/* Set in uml_mem_setup and modified in linux_main */
+unsigned long long physmem_size = 64 * 1024 * 1024;
+EXPORT_SYMBOL(physmem_size);
+
+static const char *usage_string =
+"User Mode Linux v%s\n"
+"	available at http://user-mode-linux.sourceforge.net/\n\n";
+
+static int __init uml_version_setup(char *line, int *add)
+{
+	/* Explicitly use printf() to show version in stdout */
+	printf("%s\n", init_utsname()->release);
+	exit(0);
+
+	return 0;
+}
+
+__uml_setup("--version", uml_version_setup,
+"--version\n"
+"    Prints the version number of the kernel.\n\n"
+);
+
+static int __init uml_root_setup(char *line, int *add)
+{
+	have_root = 1;
+	return 0;
+}
+
+__uml_setup("root=", uml_root_setup,
+"root=<file containing the root fs>\n"
+"    This is actually used by the generic kernel in exactly the same\n"
+"    way as in any other kernel. If you configure a number of block\n"
+"    devices and want to boot off something other than ubd0, you \n"
+"    would use something like:\n"
+"        root=/dev/ubd5\n\n"
+);
+
+static int __init uml_console_setup(char *line, int *add)
+{
+	have_console = 1;
+	return 0;
+}
+
+__uml_setup("console=", uml_console_setup,
+"console=<preferred console>\n"
+"    Specify the preferred console output driver\n\n"
+);
+
+static int __init Usage(char *line, int *add)
+{
+	const char **p;
+
+	printf(usage_string, init_utsname()->release);
+	p = &__uml_help_start;
+	/* Explicitly use printf() to show help in stdout */
+	while (p < &__uml_help_end) {
+		printf("%s", *p);
+		p++;
+	}
+	exit(0);
+	return 0;
+}
+
+__uml_setup("--help", Usage,
+"--help\n"
+"    Prints this message.\n\n"
+);
+
+static void __init uml_checksetup(char *line, int *add)
+{
+	struct uml_param *p;
+
+	p = &__uml_setup_start;
+	while (p < &__uml_setup_end) {
+		size_t n;
+
+		n = strlen(p->str);
+		if (!strncmp(line, p->str, n) && p->setup_func(line + n, add))
+			return;
+		p++;
+	}
+}
+
+static void __init uml_postsetup(void)
+{
+	initcall_t *p;
+
+	p = &__uml_postsetup_start;
+	while (p < &__uml_postsetup_end) {
+		(*p)();
+		p++;
+	}
+	return;
+}
+
+static int panic_exit(struct notifier_block *self, unsigned long unused1,
+		      void *unused2)
+{
+	kmsg_dump(KMSG_DUMP_PANIC);
+	bust_spinlocks(1);
+	bust_spinlocks(0);
+	uml_exitcode = 1;
+	os_dump_core();
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block panic_exit_notifier = {
+	.notifier_call	= panic_exit,
+	.priority	= INT_MAX - 1, /* run as 2nd notifier, won't return */
+};
+
+void uml_finishsetup(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list,
+				       &panic_exit_notifier);
+
+	uml_postsetup();
+
+	new_thread_handler();
+}
+
+/* Set during early boot */
+unsigned long stub_start;
+unsigned long task_size;
+EXPORT_SYMBOL(task_size);
+
+unsigned long brk_start;
+
+#define MIN_VMALLOC (32 * 1024 * 1024)
+
+static void __init parse_host_cpu_flags(char *line)
+{
+	int i;
+	for (i = 0; i < 32*NCAPINTS; i++) {
+		if ((x86_cap_flags[i] != NULL) && strstr(line, x86_cap_flags[i]))
+			set_cpu_cap(&boot_cpu_data, i);
+	}
+}
+
+static void __init parse_cache_line(char *line)
+{
+	long res;
+	char *to_parse = strstr(line, ":");
+	if (to_parse) {
+		to_parse++;
+		while (*to_parse != 0 && isspace(*to_parse)) {
+			to_parse++;
+		}
+		if (kstrtoul(to_parse, 10, &res) == 0 && is_power_of_2(res))
+			boot_cpu_data.cache_alignment = res;
+		else
+			boot_cpu_data.cache_alignment = L1_CACHE_BYTES;
+	}
+}
+
+static unsigned long __init get_top_address(char **envp)
+{
+	unsigned long top_addr = (unsigned long) &top_addr;
+	int i;
+
+	/* The earliest variable should be after the program name in ELF */
+	for (i = 0; envp[i]; i++) {
+		if ((unsigned long) envp[i] > top_addr)
+			top_addr = (unsigned long) envp[i];
+	}
+
+	return PAGE_ALIGN(top_addr + 1);
+}
+
+int __init linux_main(int argc, char **argv, char **envp)
+{
+	unsigned long avail, diff;
+	unsigned long virtmem_size, max_physmem;
+	unsigned long host_task_size;
+	unsigned long stack;
+	unsigned int i;
+	int add;
+
+	for (i = 1; i < argc; i++) {
+		if ((i == 1) && (argv[i][0] == ' '))
+			continue;
+		add = 1;
+		uml_checksetup(argv[i], &add);
+		if (add)
+			add_arg(argv[i]);
+	}
+	if (have_root == 0)
+		add_arg(DEFAULT_COMMAND_LINE_ROOT);
+
+	if (have_console == 0)
+		add_arg(DEFAULT_COMMAND_LINE_CONSOLE);
+
+	host_task_size = get_top_address(envp);
+	/* reserve a few pages for the stubs */
+	stub_start = host_task_size - STUB_SIZE;
+	host_task_size = stub_start;
+
+	/* Limit TASK_SIZE to what is addressable by the page table */
+	task_size = host_task_size;
+	if (task_size > (unsigned long long) PTRS_PER_PGD * PGDIR_SIZE)
+		task_size = PTRS_PER_PGD * PGDIR_SIZE;
+
+	/*
+	 * TASK_SIZE needs to be PGDIR_SIZE aligned or else exit_mmap craps
+	 * out
+	 */
+	task_size = task_size & PGDIR_MASK;
+
+	/* OS sanity checks that need to happen before the kernel runs */
+	os_early_checks();
+
+	get_host_cpu_features(parse_host_cpu_flags, parse_cache_line);
+
+	brk_start = (unsigned long) sbrk(0);
+
+	/*
+	 * Increase physical memory size for exec-shield users
+	 * so they actually get what they asked for. This should
+	 * add zero for non-exec shield users
+	 */
+	diff = PAGE_ALIGN(brk_start) - PAGE_ALIGN((unsigned long) &_end);
+	if (diff > 1024 * 1024) {
+		os_info("Adding %ld bytes to physical memory to account for "
+			"exec-shield gap\n", diff);
+		physmem_size += diff;
+	}
+
+	uml_physmem = (unsigned long) __binary_start & PAGE_MASK;
+
+	/* Reserve up to 4M after the current brk */
+	uml_reserved = ROUND_4M(brk_start) + (1 << 22);
+
+	setup_machinename(init_utsname()->machine);
+
+	physmem_size = PAGE_ALIGN(physmem_size);
+	max_physmem = TASK_SIZE - uml_physmem - MIN_VMALLOC;
+	if (physmem_size > max_physmem) {
+		physmem_size = max_physmem;
+		os_info("Physical memory size shrunk to %llu bytes\n",
+			physmem_size);
+	}
+
+	high_physmem = uml_physmem + physmem_size;
+
+	start_vm = VMALLOC_START;
+
+	virtmem_size = physmem_size;
+	stack = (unsigned long) argv;
+	stack &= ~(1024 * 1024 - 1);
+	avail = stack - start_vm;
+	if (physmem_size > avail)
+		virtmem_size = avail;
+	end_vm = start_vm + virtmem_size;
+
+	if (virtmem_size < physmem_size)
+		os_info("Kernel virtual memory size shrunk to %lu bytes\n",
+			virtmem_size);
+
+	arch_task_struct_size = sizeof(struct task_struct) + host_fp_size;
+
+	os_flush_stdout();
+
+	return start_uml();
+}
+
+int __init __weak read_initrd(void)
+{
+	return 0;
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+	u8 rng_seed[32];
+
+	stack_protections((unsigned long) init_task.stack);
+	setup_physmem(uml_physmem, uml_reserved, physmem_size);
+	uml_dtb_init();
+	read_initrd();
+
+	strscpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
+	*cmdline_p = command_line;
+	setup_hostinfo(host_info, sizeof host_info);
+	prefill_possible_map();
+
+	if (os_getrandom(rng_seed, sizeof(rng_seed), 0) == sizeof(rng_seed)) {
+		add_bootloader_randomness(rng_seed, sizeof(rng_seed));
+		memzero_explicit(rng_seed, sizeof(rng_seed));
+	}
+}
+
+void __init arch_cpu_finalize_init(void)
+{
+	arch_check_bugs();
+	os_check_bugs();
+}
+
+void apply_seal_endbr(s32 *start, s32 *end)
+{
+}
+
+void apply_retpolines(s32 *start, s32 *end)
+{
+}
+
+void apply_returns(s32 *start, s32 *end)
+{
+}
+
+void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+		   s32 *start_cfi, s32 *end_cfi)
+{
+}
+
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
+{
+}
+
+#if IS_ENABLED(CONFIG_SMP)
+void alternatives_smp_module_add(struct module *mod, char *name,
+				 void *locks, void *locks_end,
+				 void *text,  void *text_end)
+{
+}
+
+void alternatives_smp_module_del(struct module *mod)
+{
+}
+#endif
+
+void *text_poke(void *addr, const void *opcode, size_t len)
+{
+	/*
+	 * In UML, the only reference to this function is in
+	 * apply_relocate_add(), which shouldn't ever actually call this
+	 * because UML doesn't have live patching.
+	 */
+	WARN_ON(1);
+
+	return memcpy(addr, opcode, len);
+}
+
+void *text_poke_copy(void *addr, const void *opcode, size_t len)
+{
+	return text_poke(addr, opcode, len);
+}
+
+void smp_text_poke_sync_each_cpu(void)
+{
+}
+
+void uml_pm_wake(void)
+{
+	pm_system_wakeup();
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int um_suspend_valid(suspend_state_t state)
+{
+	return state == PM_SUSPEND_MEM;
+}
+
+static int um_suspend_prepare(void)
+{
+	um_irqs_suspend();
+	return 0;
+}
+
+static int um_suspend_enter(suspend_state_t state)
+{
+	if (WARN_ON(state != PM_SUSPEND_MEM))
+		return -EINVAL;
+
+	/*
+	 * This is identical to the idle sleep, but we've just
+	 * (during suspend) turned off all interrupt sources
+	 * except for the ones we want, so now we can only wake
+	 * up on something we actually want to wake up on. All
+	 * timing has also been suspended.
+	 */
+	um_idle_sleep();
+	return 0;
+}
+
+static void um_suspend_finish(void)
+{
+	um_irqs_resume();
+}
+
+const struct platform_suspend_ops um_suspend_ops = {
+	.valid = um_suspend_valid,
+	.prepare = um_suspend_prepare,
+	.enter = um_suspend_enter,
+	.finish = um_suspend_finish,
+};
+
+static int init_pm_wake_signal(void)
+{
+	/*
+	 * In external time-travel mode we can't use signals to wake up
+	 * since that would mess with the scheduling. We'll have to do
+	 * some additional work to support wakeup on virtio devices or
+	 * similar, perhaps implementing a fake RTC controller that can
+	 * trigger wakeup (and request the appropriate scheduling from
+	 * the external scheduler when going to suspend.)
+	 */
+	if (time_travel_mode != TT_MODE_EXTERNAL)
+		register_pm_wake_signal();
+
+	suspend_set_ops(&um_suspend_ops);
+
+	return 0;
+}
+
+late_initcall(init_pm_wake_signal);
+#endif

linux-7.2.3/arch/um/kernel/um_arch.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __UML_ARCH_H__
+#define __UML_ARCH_H__
+
+extern void * __init uml_load_file(const char *filename, unsigned long long *size);
+
+#ifdef CONFIG_OF
+extern void __init uml_dtb_init(void);
+#else
+static inline void uml_dtb_init(void) { }
+#endif
+
+extern int __init read_initrd(void);
+
+#endif

linux-7.2.3/arch/um/kernel/umid.c

@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <asm/errno.h>
+#include <init.h>
+#include <kern.h>
+#include <os.h>
+
+/* Changed by set_umid_arg */
+static int umid_inited;
+
+static int __init set_umid_arg(char *name, int *add)
+{
+	int err;
+
+	if (umid_inited) {
+		os_warn("umid already set\n");
+		return 0;
+	}
+
+	*add = 0;
+	err = set_umid(name);
+	if (err == -EEXIST)
+		os_warn("umid '%s' already in use\n", name);
+	else if (!err)
+		umid_inited = 1;
+
+	return 0;
+}
+
+__uml_setup("umid=", set_umid_arg,
+"umid=<name>\n"
+"    This is used to assign a unique identity to this UML machine and\n"
+"    is used for naming the pid file and management console socket.\n\n"
+);
+

linux-7.2.3/arch/um/kernel/uml.lds.S

@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/vmlinux.lds.h>
+#include <asm/page.h>
+
+OUTPUT_FORMAT(ELF_FORMAT)
+OUTPUT_ARCH(ELF_ARCH)
+ENTRY(_start)
+jiffies = jiffies_64;
+
+VERSION {
+  {
+    local: *;
+  };
+}
+
+SECTIONS
+{
+  /* This must contain the right address - not quite the default ELF one.*/
+  PROVIDE (__executable_start = START);
+  /* Static binaries stick stuff here, like the sigreturn trampoline,
+   * invisibly to objdump.  So, just make __binary_start equal to the very
+   * beginning of the executable, and if there are unmapped pages after this,
+   * they are forever unusable.
+   */
+  __binary_start = START;
+
+  . = START + SIZEOF_HEADERS;
+  . = ALIGN(PAGE_SIZE);
+
+  _text = .;
+  INIT_TEXT_SECTION(0)
+
+  .text      :
+  {
+    _stext = .;
+    TEXT_TEXT
+    SCHED_TEXT
+    LOCK_TEXT
+    IRQENTRY_TEXT
+    SOFTIRQENTRY_TEXT
+    *(.fixup)
+    /* .gnu.warning sections are handled specially by elf32.em.  */
+    *(.gnu.warning)
+    *(.gnu.linkonce.t*)
+  }
+
+  . = ALIGN(PAGE_SIZE);
+  .syscall_stub : {
+	__syscall_stub_start = .;
+	*(.__syscall_stub*)
+	__syscall_stub_end = .;
+  }
+
+  /*
+   * These are needed even in a static link, even if they wind up being empty.
+   * Newer glibc needs these __rel{,a}_iplt_{start,end} symbols.
+   */
+  .rel.plt : {
+	*(.rel.plt)
+	PROVIDE_HIDDEN(__rel_iplt_start = .);
+	*(.rel.iplt)
+	PROVIDE_HIDDEN(__rel_iplt_end = .);
+  }
+  .rela.plt : {
+	*(.rela.plt)
+	PROVIDE_HIDDEN(__rela_iplt_start = .);
+	*(.rela.iplt)
+	PROVIDE_HIDDEN(__rela_iplt_end = .);
+  }
+
+  #include <asm/common.lds.S>
+
+  __init_begin = .;
+  init.data : { INIT_DATA }
+  __init_end = .;
+
+  .data    :
+  {
+    INIT_TASK_DATA(KERNEL_STACK_SIZE)
+    DATA_DATA
+    *(.gnu.linkonce.d*)
+    CONSTRUCTORS
+  }
+  .data1   : { *(.data1) }
+  .ctors         :
+  {
+    *(.ctors)
+  }
+  .dtors         :
+  {
+    *(.dtors)
+  }
+
+  .got           : { *(.got.plt) *(.got) }
+  .eh_frame       : { KEEP (*(.eh_frame)) }
+  .dynamic       : { *(.dynamic) }
+  .tdata	  : { *(.tdata .tdata.* .gnu.linkonce.td.*) }
+  .tbss		  : { *(.tbss .tbss.* .gnu.linkonce.tb.*) *(.tcommon) }
+  /* We want the small data sections together, so single-instruction offsets
+     can access them all, and initialized data all before uninitialized, so
+     we can shorten the on-disk segment size.  */
+  .sdata     : { *(.sdata) }
+  _edata  =  .;
+  PROVIDE (edata = .);
+  . = ALIGN(PAGE_SIZE);
+  __bss_start = .;
+  PROVIDE(_bss_start = .);
+  SBSS(0)
+  BSS(0)
+   __bss_stop = .;
+  _end = .;
+  PROVIDE (end = .);
+
+  STABS_DEBUG
+  DWARF_DEBUG
+  MODINFO
+  ELF_DETAILS
+
+  DISCARDS
+}

linux-7.2.3/arch/um/kernel/vmlinux.lds.S

@@ -0,0 +1,8 @@
+#define RUNTIME_DISCARD_EXIT
+KERNEL_STACK_SIZE = 4096 * (1 << CONFIG_KERNEL_STACK_ORDER);
+
+#ifdef CONFIG_LD_SCRIPT_STATIC
+#include "uml.lds.S"
+#else
+#include "dyn.lds.S"
+#endif