M7350v1_en_gpl

kernel/arch/x86/ia32/Makefile

@@ -0,0 +1,14 @@
+#
+# Makefile for the ia32 kernel emulation subsystem.
+#
+
+obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o
+obj-$(CONFIG_IA32_EMULATION) += nosyscall.o syscall_ia32.o
+
+sysv-$(CONFIG_SYSVIPC) := ipc32.o
+obj-$(CONFIG_IA32_EMULATION) += $(sysv-y)
+
+obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
+
+audit-class-$(CONFIG_AUDIT) := audit.o
+obj-$(CONFIG_IA32_EMULATION) += $(audit-class-y)

kernel/arch/x86/ia32/audit.c

@@ -0,0 +1,42 @@
+#include <asm/unistd_32.h>
+
+unsigned ia32_dir_class[] = {
+#include <asm-generic/audit_dir_write.h>
+~0U
+};
+
+unsigned ia32_chattr_class[] = {
+#include <asm-generic/audit_change_attr.h>
+~0U
+};
+
+unsigned ia32_write_class[] = {
+#include <asm-generic/audit_write.h>
+~0U
+};
+
+unsigned ia32_read_class[] = {
+#include <asm-generic/audit_read.h>
+~0U
+};
+
+unsigned ia32_signal_class[] = {
+#include <asm-generic/audit_signal.h>
+~0U
+};
+
+int ia32_classify_syscall(unsigned syscall)
+{
+	switch (syscall) {
+	case __NR_open:
+		return 2;
+	case __NR_openat:
+		return 3;
+	case __NR_socketcall:
+		return 4;
+	case __NR_execve:
+		return 5;
+	default:
+		return 1;
+	}
+}

kernel/arch/x86/ia32/ia32_aout.c

@@ -0,0 +1,514 @@
+/*
+ *  a.out loader for x86-64
+ *
+ *  Copyright (C) 1991, 1992, 1996  Linus Torvalds
+ *  Hacked together by Andi Kleen
+ */
+
+#include <linux/module.h>
+
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/a.out.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/fcntl.h>
+#include <linux/ptrace.h>
+#include <linux/user.h>
+#include <linux/binfmts.h>
+#include <linux/personality.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/cacheflush.h>
+#include <asm/user32.h>
+#include <asm/ia32.h>
+
+#undef WARN_OLD
+#undef CORE_DUMP /* definitely broken */
+
+static int load_aout_binary(struct linux_binprm *, struct pt_regs *regs);
+static int load_aout_library(struct file *);
+
+#ifdef CORE_DUMP
+static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
+			  unsigned long limit);
+
+/*
+ * fill in the user structure for a core dump..
+ */
+static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
+{
+	u32 fs, gs;
+
+/* changed the size calculations - should hopefully work better. lbt */
+	dump->magic = CMAGIC;
+	dump->start_code = 0;
+	dump->start_stack = regs->sp & ~(PAGE_SIZE - 1);
+	dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
+	dump->u_dsize = ((unsigned long)
+			 (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
+	dump->u_dsize -= dump->u_tsize;
+	dump->u_ssize = 0;
+	dump->u_debugreg[0] = current->thread.debugreg0;
+	dump->u_debugreg[1] = current->thread.debugreg1;
+	dump->u_debugreg[2] = current->thread.debugreg2;
+	dump->u_debugreg[3] = current->thread.debugreg3;
+	dump->u_debugreg[4] = 0;
+	dump->u_debugreg[5] = 0;
+	dump->u_debugreg[6] = current->thread.debugreg6;
+	dump->u_debugreg[7] = current->thread.debugreg7;
+
+	if (dump->start_stack < 0xc0000000) {
+		unsigned long tmp;
+
+		tmp = (unsigned long) (0xc0000000 - dump->start_stack);
+		dump->u_ssize = tmp >> PAGE_SHIFT;
+	}
+
+	dump->regs.bx = regs->bx;
+	dump->regs.cx = regs->cx;
+	dump->regs.dx = regs->dx;
+	dump->regs.si = regs->si;
+	dump->regs.di = regs->di;
+	dump->regs.bp = regs->bp;
+	dump->regs.ax = regs->ax;
+	dump->regs.ds = current->thread.ds;
+	dump->regs.es = current->thread.es;
+	savesegment(fs, fs);
+	dump->regs.fs = fs;
+	savesegment(gs, gs);
+	dump->regs.gs = gs;
+	dump->regs.orig_ax = regs->orig_ax;
+	dump->regs.ip = regs->ip;
+	dump->regs.cs = regs->cs;
+	dump->regs.flags = regs->flags;
+	dump->regs.sp = regs->sp;
+	dump->regs.ss = regs->ss;
+
+#if 1 /* FIXME */
+	dump->u_fpvalid = 0;
+#else
+	dump->u_fpvalid = dump_fpu(regs, &dump->i387);
+#endif
+}
+
+#endif
+
+static struct linux_binfmt aout_format = {
+	.module		= THIS_MODULE,
+	.load_binary	= load_aout_binary,
+	.load_shlib	= load_aout_library,
+#ifdef CORE_DUMP
+	.core_dump	= aout_core_dump,
+#endif
+	.min_coredump	= PAGE_SIZE
+};
+
+static void set_brk(unsigned long start, unsigned long end)
+{
+	start = PAGE_ALIGN(start);
+	end = PAGE_ALIGN(end);
+	if (end <= start)
+		return;
+	vm_brk(start, end - start);
+}
+
+#ifdef CORE_DUMP
+/*
+ * These are the only things you should do on a core-file: use only these
+ * macros to write out all the necessary info.
+ */
+
+#include <linux/coredump.h>
+
+#define DUMP_WRITE(addr, nr)			     \
+	if (!dump_write(file, (void *)(addr), (nr))) \
+		goto end_coredump;
+
+#define DUMP_SEEK(offset)		\
+	if (!dump_seek(file, offset))	\
+		goto end_coredump;
+
+#define START_DATA()	(u.u_tsize << PAGE_SHIFT)
+#define START_STACK(u)	(u.start_stack)
+
+/*
+ * Routine writes a core dump image in the current directory.
+ * Currently only a stub-function.
+ *
+ * Note that setuid/setgid files won't make a core-dump if the uid/gid
+ * changed due to the set[u|g]id. It's enforced by the "current->mm->dumpable"
+ * field, which also makes sure the core-dumps won't be recursive if the
+ * dumping of the process results in another error..
+ */
+
+static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
+			  unsigned long limit)
+{
+	mm_segment_t fs;
+	int has_dumped = 0;
+	unsigned long dump_start, dump_size;
+	struct user32 dump;
+
+	fs = get_fs();
+	set_fs(KERNEL_DS);
+	has_dumped = 1;
+	current->flags |= PF_DUMPCORE;
+	strncpy(dump.u_comm, current->comm, sizeof(current->comm));
+	dump.u_ar0 = offsetof(struct user32, regs);
+	dump.signal = signr;
+	dump_thread32(regs, &dump);
+
+	/*
+	 * If the size of the dump file exceeds the rlimit, then see
+	 * what would happen if we wrote the stack, but not the data
+	 * area.
+	 */
+	if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > limit)
+		dump.u_dsize = 0;
+
+	/* Make sure we have enough room to write the stack and data areas. */
+	if ((dump.u_ssize + 1) * PAGE_SIZE > limit)
+		dump.u_ssize = 0;
+
+	/* make sure we actually have a data and stack area to dump */
+	set_fs(USER_DS);
+	if (!access_ok(VERIFY_READ, (void *) (unsigned long)START_DATA(dump),
+		       dump.u_dsize << PAGE_SHIFT))
+		dump.u_dsize = 0;
+	if (!access_ok(VERIFY_READ, (void *) (unsigned long)START_STACK(dump),
+		       dump.u_ssize << PAGE_SHIFT))
+		dump.u_ssize = 0;
+
+	set_fs(KERNEL_DS);
+	/* struct user */
+	DUMP_WRITE(&dump, sizeof(dump));
+	/* Now dump all of the user data.  Include malloced stuff as well */
+	DUMP_SEEK(PAGE_SIZE);
+	/* now we start writing out the user space info */
+	set_fs(USER_DS);
+	/* Dump the data area */
+	if (dump.u_dsize != 0) {
+		dump_start = START_DATA(dump);
+		dump_size = dump.u_dsize << PAGE_SHIFT;
+		DUMP_WRITE(dump_start, dump_size);
+	}
+	/* Now prepare to dump the stack area */
+	if (dump.u_ssize != 0) {
+		dump_start = START_STACK(dump);
+		dump_size = dump.u_ssize << PAGE_SHIFT;
+		DUMP_WRITE(dump_start, dump_size);
+	}
+end_coredump:
+	set_fs(fs);
+	return has_dumped;
+}
+#endif
+
+/*
+ * create_aout_tables() parses the env- and arg-strings in new user
+ * memory and creates the pointer tables from them, and puts their
+ * addresses on the "stack", returning the new stack pointer value.
+ */
+static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm)
+{
+	u32 __user *argv, *envp, *sp;
+	int argc = bprm->argc, envc = bprm->envc;
+
+	sp = (u32 __user *) ((-(unsigned long)sizeof(u32)) & (unsigned long) p);
+	sp -= envc+1;
+	envp = sp;
+	sp -= argc+1;
+	argv = sp;
+	put_user((unsigned long) envp, --sp);
+	put_user((unsigned long) argv, --sp);
+	put_user(argc, --sp);
+	current->mm->arg_start = (unsigned long) p;
+	while (argc-- > 0) {
+		char c;
+
+		put_user((u32)(unsigned long)p, argv++);
+		do {
+			get_user(c, p++);
+		} while (c);
+	}
+	put_user(0, argv);
+	current->mm->arg_end = current->mm->env_start = (unsigned long) p;
+	while (envc-- > 0) {
+		char c;
+
+		put_user((u32)(unsigned long)p, envp++);
+		do {
+			get_user(c, p++);
+		} while (c);
+	}
+	put_user(0, envp);
+	current->mm->env_end = (unsigned long) p;
+	return sp;
+}
+
+/*
+ * These are the functions used to load a.out style executables and shared
+ * libraries.  There is no binary dependent code anywhere else.
+ */
+static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
+{
+	unsigned long error, fd_offset, rlim;
+	struct exec ex;
+	int retval;
+
+	ex = *((struct exec *) bprm->buf);		/* exec-header */
+	if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC &&
+	     N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) ||
+	    N_TRSIZE(ex) || N_DRSIZE(ex) ||
+	    i_size_read(bprm->file->f_path.dentry->d_inode) <
+	    ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
+		return -ENOEXEC;
+	}
+
+	fd_offset = N_TXTOFF(ex);
+
+	/* Check initial limits. This avoids letting people circumvent
+	 * size limits imposed on them by creating programs with large
+	 * arrays in the data or bss.
+	 */
+	rlim = rlimit(RLIMIT_DATA);
+	if (rlim >= RLIM_INFINITY)
+		rlim = ~0;
+	if (ex.a_data + ex.a_bss > rlim)
+		return -ENOMEM;
+
+	/* Flush all traces of the currently running executable */
+	retval = flush_old_exec(bprm);
+	if (retval)
+		return retval;
+
+	/* OK, This is the point of no return */
+	set_personality(PER_LINUX);
+	set_personality_ia32(false);
+
+	setup_new_exec(bprm);
+
+	regs->cs = __USER32_CS;
+	regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
+		regs->r13 = regs->r14 = regs->r15 = 0;
+
+	current->mm->end_code = ex.a_text +
+		(current->mm->start_code = N_TXTADDR(ex));
+	current->mm->end_data = ex.a_data +
+		(current->mm->start_data = N_DATADDR(ex));
+	current->mm->brk = ex.a_bss +
+		(current->mm->start_brk = N_BSSADDR(ex));
+	current->mm->free_area_cache = TASK_UNMAPPED_BASE;
+	current->mm->cached_hole_size = 0;
+
+	retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
+	if (retval < 0) {
+		/* Someone check-me: is this error path enough? */
+		send_sig(SIGKILL, current, 0);
+		return retval;
+	}
+
+	install_exec_creds(bprm);
+
+	if (N_MAGIC(ex) == OMAGIC) {
+		unsigned long text_addr, map_size;
+		loff_t pos;
+
+		text_addr = N_TXTADDR(ex);
+
+		pos = 32;
+		map_size = ex.a_text+ex.a_data;
+
+		error = vm_brk(text_addr & PAGE_MASK, map_size);
+
+		if (error != (text_addr & PAGE_MASK)) {
+			send_sig(SIGKILL, current, 0);
+			return error;
+		}
+
+		error = bprm->file->f_op->read(bprm->file,
+			 (char __user *)text_addr,
+			  ex.a_text+ex.a_data, &pos);
+		if ((signed long)error < 0) {
+			send_sig(SIGKILL, current, 0);
+			return error;
+		}
+
+		flush_icache_range(text_addr, text_addr+ex.a_text+ex.a_data);
+	} else {
+#ifdef WARN_OLD
+		static unsigned long error_time, error_time2;
+		if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
+		    (N_MAGIC(ex) != NMAGIC) &&
+				time_after(jiffies, error_time2 + 5*HZ)) {
+			printk(KERN_NOTICE "executable not page aligned\n");
+			error_time2 = jiffies;
+		}
+
+		if ((fd_offset & ~PAGE_MASK) != 0 &&
+			    time_after(jiffies, error_time + 5*HZ)) {
+			printk(KERN_WARNING
+			       "fd_offset is not page aligned. Please convert "
+			       "program: %s\n",
+			       bprm->file->f_path.dentry->d_name.name);
+			error_time = jiffies;
+		}
+#endif
+
+		if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) {
+			loff_t pos = fd_offset;
+
+			vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
+			bprm->file->f_op->read(bprm->file,
+					(char __user *)N_TXTADDR(ex),
+					ex.a_text+ex.a_data, &pos);
+			flush_icache_range((unsigned long) N_TXTADDR(ex),
+					   (unsigned long) N_TXTADDR(ex) +
+					   ex.a_text+ex.a_data);
+			goto beyond_if;
+		}
+
+		error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
+				PROT_READ | PROT_EXEC,
+				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
+				MAP_EXECUTABLE | MAP_32BIT,
+				fd_offset);
+
+		if (error != N_TXTADDR(ex)) {
+			send_sig(SIGKILL, current, 0);
+			return error;
+		}
+
+		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
+				PROT_READ | PROT_WRITE | PROT_EXEC,
+				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
+				MAP_EXECUTABLE | MAP_32BIT,
+				fd_offset + ex.a_text);
+		if (error != N_DATADDR(ex)) {
+			send_sig(SIGKILL, current, 0);
+			return error;
+		}
+	}
+beyond_if:
+	set_binfmt(&aout_format);
+
+	set_brk(current->mm->start_brk, current->mm->brk);
+
+	current->mm->start_stack =
+		(unsigned long)create_aout_tables((char __user *)bprm->p, bprm);
+	/* start thread */
+	loadsegment(fs, 0);
+	loadsegment(ds, __USER32_DS);
+	loadsegment(es, __USER32_DS);
+	load_gs_index(0);
+	(regs)->ip = ex.a_entry;
+	(regs)->sp = current->mm->start_stack;
+	(regs)->flags = 0x200;
+	(regs)->cs = __USER32_CS;
+	(regs)->ss = __USER32_DS;
+	regs->r8 = regs->r9 = regs->r10 = regs->r11 =
+	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
+	set_fs(USER_DS);
+	return 0;
+}
+
+static int load_aout_library(struct file *file)
+{
+	struct inode *inode;
+	unsigned long bss, start_addr, len, error;
+	int retval;
+	struct exec ex;
+
+	inode = file->f_path.dentry->d_inode;
+
+	retval = -ENOEXEC;
+	error = kernel_read(file, 0, (char *) &ex, sizeof(ex));
+	if (error != sizeof(ex))
+		goto out;
+
+	/* We come in here for the regular a.out style of shared libraries */
+	if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) ||
+	    N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) ||
+	    i_size_read(inode) <
+	    ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
+		goto out;
+	}
+
+	if (N_FLAGS(ex))
+		goto out;
+
+	/* For  QMAGIC, the starting address is 0x20 into the page.  We mask
+	   this off to get the starting address for the page */
+
+	start_addr =  ex.a_entry & 0xfffff000;
+
+	if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) {
+		loff_t pos = N_TXTOFF(ex);
+
+#ifdef WARN_OLD
+		static unsigned long error_time;
+		if (time_after(jiffies, error_time + 5*HZ)) {
+			printk(KERN_WARNING
+			       "N_TXTOFF is not page aligned. Please convert "
+			       "library: %s\n",
+			       file->f_path.dentry->d_name.name);
+			error_time = jiffies;
+		}
+#endif
+		vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
+
+		file->f_op->read(file, (char __user *)start_addr,
+			ex.a_text + ex.a_data, &pos);
+		flush_icache_range((unsigned long) start_addr,
+				   (unsigned long) start_addr + ex.a_text +
+				   ex.a_data);
+
+		retval = 0;
+		goto out;
+	}
+	/* Now use mmap to map the library into memory. */
+	error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
+			PROT_READ | PROT_WRITE | PROT_EXEC,
+			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT,
+			N_TXTOFF(ex));
+	retval = error;
+	if (error != start_addr)
+		goto out;
+
+	len = PAGE_ALIGN(ex.a_text + ex.a_data);
+	bss = ex.a_text + ex.a_data + ex.a_bss;
+	if (bss > len) {
+		error = vm_brk(start_addr + len, bss - len);
+		retval = error;
+		if (error != start_addr + len)
+			goto out;
+	}
+	retval = 0;
+out:
+	return retval;
+}
+
+static int __init init_aout_binfmt(void)
+{
+	register_binfmt(&aout_format);
+	return 0;
+}
+
+static void __exit exit_aout_binfmt(void)
+{
+	unregister_binfmt(&aout_format);
+}
+
+module_init(init_aout_binfmt);
+module_exit(exit_aout_binfmt);
+MODULE_LICENSE("GPL");

kernel/arch/x86/ia32/ia32_signal.c

@@ -0,0 +1,562 @@
+/*
+ *  linux/arch/x86_64/ia32/ia32_signal.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
+ *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
+ *  2000-12-*   x86-64 compatibility mode signal handling by Andi Kleen
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/personality.h>
+#include <linux/compat.h>
+#include <linux/binfmts.h>
+#include <asm/ucontext.h>
+#include <asm/uaccess.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
+#include <asm/ptrace.h>
+#include <asm/ia32_unistd.h>
+#include <asm/user32.h>
+#include <asm/sigcontext32.h>
+#include <asm/proto.h>
+#include <asm/vdso.h>
+#include <asm/sigframe.h>
+#include <asm/sighandling.h>
+#include <asm/sys_ia32.h>
+
+#define FIX_EFLAGS	__FIX_EFLAGS
+
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+{
+	int err = 0;
+	bool ia32 = is_ia32_task();
+
+	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
+		return -EFAULT;
+
+	put_user_try {
+		/* If you change siginfo_t structure, please make sure that
+		   this code is fixed accordingly.
+		   It should never copy any pad contained in the structure
+		   to avoid security leaks, but must copy the generic
+		   3 ints plus the relevant union member.  */
+		put_user_ex(from->si_signo, &to->si_signo);
+		put_user_ex(from->si_errno, &to->si_errno);
+		put_user_ex((short)from->si_code, &to->si_code);
+
+		if (from->si_code < 0) {
+			put_user_ex(from->si_pid, &to->si_pid);
+			put_user_ex(from->si_uid, &to->si_uid);
+			put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr);
+		} else {
+			/*
+			 * First 32bits of unions are always present:
+			 * si_pid === si_band === si_tid === si_addr(LS half)
+			 */
+			put_user_ex(from->_sifields._pad[0],
+					  &to->_sifields._pad[0]);
+			switch (from->si_code >> 16) {
+			case __SI_FAULT >> 16:
+				break;
+			case __SI_CHLD >> 16:
+				if (ia32) {
+					put_user_ex(from->si_utime, &to->si_utime);
+					put_user_ex(from->si_stime, &to->si_stime);
+				} else {
+					put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime);
+					put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime);
+				}
+				put_user_ex(from->si_status, &to->si_status);
+				/* FALL THROUGH */
+			default:
+			case __SI_KILL >> 16:
+				put_user_ex(from->si_uid, &to->si_uid);
+				break;
+			case __SI_POLL >> 16:
+				put_user_ex(from->si_fd, &to->si_fd);
+				break;
+			case __SI_TIMER >> 16:
+				put_user_ex(from->si_overrun, &to->si_overrun);
+				put_user_ex(ptr_to_compat(from->si_ptr),
+					    &to->si_ptr);
+				break;
+				 /* This is not generated by the kernel as of now.  */
+			case __SI_RT >> 16:
+			case __SI_MESGQ >> 16:
+				put_user_ex(from->si_uid, &to->si_uid);
+				put_user_ex(from->si_int, &to->si_int);
+				break;
+			}
+		}
+	} put_user_catch(err);
+
+	return err;
+}
+
+int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
+{
+	int err = 0;
+	u32 ptr32;
+
+	if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
+		return -EFAULT;
+
+	get_user_try {
+		get_user_ex(to->si_signo, &from->si_signo);
+		get_user_ex(to->si_errno, &from->si_errno);
+		get_user_ex(to->si_code, &from->si_code);
+
+		get_user_ex(to->si_pid, &from->si_pid);
+		get_user_ex(to->si_uid, &from->si_uid);
+		get_user_ex(ptr32, &from->si_ptr);
+		to->si_ptr = compat_ptr(ptr32);
+	} get_user_catch(err);
+
+	return err;
+}
+
+asmlinkage long sys32_sigsuspend(int history0, int history1, old_sigset_t mask)
+{
+	sigset_t blocked;
+
+	current->saved_sigmask = current->blocked;
+
+	mask &= _BLOCKABLE;
+	siginitset(&blocked, mask);
+	set_current_blocked(&blocked);
+
+	current->state = TASK_INTERRUPTIBLE;
+	schedule();
+
+	set_restore_sigmask();
+	return -ERESTARTNOHAND;
+}
+
+asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
+				  stack_ia32_t __user *uoss_ptr,
+				  struct pt_regs *regs)
+{
+	stack_t uss, uoss;
+	int ret, err = 0;
+	mm_segment_t seg;
+
+	if (uss_ptr) {
+		u32 ptr;
+
+		memset(&uss, 0, sizeof(stack_t));
+		if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t)))
+			return -EFAULT;
+
+		get_user_try {
+			get_user_ex(ptr, &uss_ptr->ss_sp);
+			get_user_ex(uss.ss_flags, &uss_ptr->ss_flags);
+			get_user_ex(uss.ss_size, &uss_ptr->ss_size);
+		} get_user_catch(err);
+
+		if (err)
+			return -EFAULT;
+		uss.ss_sp = compat_ptr(ptr);
+	}
+	seg = get_fs();
+	set_fs(KERNEL_DS);
+	ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp);
+	set_fs(seg);
+	if (ret >= 0 && uoss_ptr)  {
+		if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)))
+			return -EFAULT;
+
+		put_user_try {
+			put_user_ex(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp);
+			put_user_ex(uoss.ss_flags, &uoss_ptr->ss_flags);
+			put_user_ex(uoss.ss_size, &uoss_ptr->ss_size);
+		} put_user_catch(err);
+
+		if (err)
+			ret = -EFAULT;
+	}
+	return ret;
+}
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+#define loadsegment_gs(v)	load_gs_index(v)
+#define loadsegment_fs(v)	loadsegment(fs, v)
+#define loadsegment_ds(v)	loadsegment(ds, v)
+#define loadsegment_es(v)	loadsegment(es, v)
+
+#define get_user_seg(seg)	({ unsigned int v; savesegment(seg, v); v; })
+#define set_user_seg(seg, v)	loadsegment_##seg(v)
+
+#define COPY(x)			{		\
+	get_user_ex(regs->x, &sc->x);		\
+}
+
+#define GET_SEG(seg)		({			\
+	unsigned short tmp;				\
+	get_user_ex(tmp, &sc->seg);			\
+	tmp;						\
+})
+
+#define COPY_SEG_CPL3(seg)	do {			\
+	regs->seg = GET_SEG(seg) | 3;			\
+} while (0)
+
+#define RELOAD_SEG(seg)		{		\
+	unsigned int pre = GET_SEG(seg);	\
+	unsigned int cur = get_user_seg(seg);	\
+	pre |= 3;				\
+	if (pre != cur)				\
+		set_user_seg(seg, pre);		\
+}
+
+static int ia32_restore_sigcontext(struct pt_regs *regs,
+				   struct sigcontext_ia32 __user *sc,
+				   unsigned int *pax)
+{
+	unsigned int tmpflags, err = 0;
+	void __user *buf;
+	u32 tmp;
+
+	/* Always make any pending restarted system calls return -EINTR */
+	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+	get_user_try {
+		/*
+		 * Reload fs and gs if they have changed in the signal
+		 * handler.  This does not handle long fs/gs base changes in
+		 * the handler, but does not clobber them at least in the
+		 * normal case.
+		 */
+		RELOAD_SEG(gs);
+		RELOAD_SEG(fs);
+		RELOAD_SEG(ds);
+		RELOAD_SEG(es);
+
+		COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
+		COPY(dx); COPY(cx); COPY(ip);
+		/* Don't touch extended registers */
+
+		COPY_SEG_CPL3(cs);
+		COPY_SEG_CPL3(ss);
+
+		get_user_ex(tmpflags, &sc->flags);
+		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
+		/* disable syscall checks */
+		regs->orig_ax = -1;
+
+		get_user_ex(tmp, &sc->fpstate);
+		buf = compat_ptr(tmp);
+		err |= restore_i387_xstate_ia32(buf);
+
+		get_user_ex(*pax, &sc->ax);
+	} get_user_catch(err);
+
+	return err;
+}
+
+asmlinkage long sys32_sigreturn(struct pt_regs *regs)
+{
+	struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
+	sigset_t set;
+	unsigned int ax;
+
+	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+		goto badframe;
+	if (__get_user(set.sig[0], &frame->sc.oldmask)
+	    || (_COMPAT_NSIG_WORDS > 1
+		&& __copy_from_user((((char *) &set.sig) + 4),
+				    &frame->extramask,
+				    sizeof(frame->extramask))))
+		goto badframe;
+
+	sigdelsetmask(&set, ~_BLOCKABLE);
+	set_current_blocked(&set);
+
+	if (ia32_restore_sigcontext(regs, &frame->sc, &ax))
+		goto badframe;
+	return ax;
+
+badframe:
+	signal_fault(regs, frame, "32bit sigreturn");
+	return 0;
+}
+
+asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs)
+{
+	struct rt_sigframe_ia32 __user *frame;
+	sigset_t set;
+	unsigned int ax;
+	struct pt_regs tregs;
+
+	frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
+
+	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+		goto badframe;
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+
+	sigdelsetmask(&set, ~_BLOCKABLE);
+	set_current_blocked(&set);
+
+	if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+		goto badframe;
+
+	tregs = *regs;
+	if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT)
+		goto badframe;
+
+	return ax;
+
+badframe:
+	signal_fault(regs, frame, "32bit rt sigreturn");
+	return 0;
+}
+
+/*
+ * Set up a signal frame.
+ */
+
+static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
+				 void __user *fpstate,
+				 struct pt_regs *regs, unsigned int mask)
+{
+	int err = 0;
+
+	put_user_try {
+		put_user_ex(get_user_seg(gs), (unsigned int __user *)&sc->gs);
+		put_user_ex(get_user_seg(fs), (unsigned int __user *)&sc->fs);
+		put_user_ex(get_user_seg(ds), (unsigned int __user *)&sc->ds);
+		put_user_ex(get_user_seg(es), (unsigned int __user *)&sc->es);
+
+		put_user_ex(regs->di, &sc->di);
+		put_user_ex(regs->si, &sc->si);
+		put_user_ex(regs->bp, &sc->bp);
+		put_user_ex(regs->sp, &sc->sp);
+		put_user_ex(regs->bx, &sc->bx);
+		put_user_ex(regs->dx, &sc->dx);
+		put_user_ex(regs->cx, &sc->cx);
+		put_user_ex(regs->ax, &sc->ax);
+		put_user_ex(current->thread.trap_nr, &sc->trapno);
+		put_user_ex(current->thread.error_code, &sc->err);
+		put_user_ex(regs->ip, &sc->ip);
+		put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
+		put_user_ex(regs->flags, &sc->flags);
+		put_user_ex(regs->sp, &sc->sp_at_signal);
+		put_user_ex(regs->ss, (unsigned int __user *)&sc->ss);
+
+		put_user_ex(ptr_to_compat(fpstate), &sc->fpstate);
+
+		/* non-iBCS2 extensions.. */
+		put_user_ex(mask, &sc->oldmask);
+		put_user_ex(current->thread.cr2, &sc->cr2);
+	} put_user_catch(err);
+
+	return err;
+}
+
+/*
+ * Determine which stack to use..
+ */
+static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
+				 size_t frame_size,
+				 void **fpstate)
+{
+	unsigned long sp;
+
+	/* Default to using normal stack */
+	sp = regs->sp;
+
+	/* This is the X/Open sanctioned signal stack switching.  */
+	if (ka->sa.sa_flags & SA_ONSTACK) {
+		if (sas_ss_flags(sp) == 0)
+			sp = current->sas_ss_sp + current->sas_ss_size;
+	}
+
+	/* This is the legacy signal stack switching. */
+	else if ((regs->ss & 0xffff) != __USER32_DS &&
+		!(ka->sa.sa_flags & SA_RESTORER) &&
+		 ka->sa.sa_restorer)
+		sp = (unsigned long) ka->sa.sa_restorer;
+
+	if (used_math()) {
+		sp = sp - sig_xstate_ia32_size;
+		*fpstate = (struct _fpstate_ia32 *) sp;
+		if (save_i387_xstate_ia32(*fpstate) < 0)
+			return (void __user *) -1L;
+	}
+
+	sp -= frame_size;
+	/* Align the stack pointer according to the i386 ABI,
+	 * i.e. so that on function entry ((sp + 4) & 15) == 0. */
+	sp = ((sp + 4) & -16ul) - 4;
+	return (void __user *) sp;
+}
+
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+		     compat_sigset_t *set, struct pt_regs *regs)
+{
+	struct sigframe_ia32 __user *frame;
+	void __user *restorer;
+	int err = 0;
+	void __user *fpstate = NULL;
+
+	/* copy_to_user optimizes that into a single 8 byte store */
+	static const struct {
+		u16 poplmovl;
+		u32 val;
+		u16 int80;
+	} __attribute__((packed)) code = {
+		0xb858,		 /* popl %eax ; movl $...,%eax */
+		__NR_ia32_sigreturn,
+		0x80cd,		/* int $0x80 */
+	};
+
+	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+		return -EFAULT;
+
+	if (__put_user(sig, &frame->sig))
+		return -EFAULT;
+
+	if (ia32_setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]))
+		return -EFAULT;
+
+	if (_COMPAT_NSIG_WORDS > 1) {
+		if (__copy_to_user(frame->extramask, &set->sig[1],
+				   sizeof(frame->extramask)))
+			return -EFAULT;
+	}
+
+	if (ka->sa.sa_flags & SA_RESTORER) {
+		restorer = ka->sa.sa_restorer;
+	} else {
+		/* Return stub is in 32bit vsyscall page */
+		if (current->mm->context.vdso)
+			restorer = VDSO32_SYMBOL(current->mm->context.vdso,
+						 sigreturn);
+		else
+			restorer = &frame->retcode;
+	}
+
+	put_user_try {
+		put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
+
+		/*
+		 * These are actually not used anymore, but left because some
+		 * gdb versions depend on them as a marker.
+		 */
+		put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+	} put_user_catch(err);
+
+	if (err)
+		return -EFAULT;
+
+	/* Set up registers for signal handler */
+	regs->sp = (unsigned long) frame;
+	regs->ip = (unsigned long) ka->sa.sa_handler;
+
+	/* Make -mregparm=3 work */
+	regs->ax = sig;
+	regs->dx = 0;
+	regs->cx = 0;
+
+	loadsegment(ds, __USER32_DS);
+	loadsegment(es, __USER32_DS);
+
+	regs->cs = __USER32_CS;
+	regs->ss = __USER32_DS;
+
+	return 0;
+}
+
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+			compat_sigset_t *set, struct pt_regs *regs)
+{
+	struct rt_sigframe_ia32 __user *frame;
+	void __user *restorer;
+	int err = 0;
+	void __user *fpstate = NULL;
+
+	/* __copy_to_user optimizes that into a single 8 byte store */
+	static const struct {
+		u8 movl;
+		u32 val;
+		u16 int80;
+		u8  pad;
+	} __attribute__((packed)) code = {
+		0xb8,
+		__NR_ia32_rt_sigreturn,
+		0x80cd,
+		0,
+	};
+
+	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+		return -EFAULT;
+
+	put_user_try {
+		put_user_ex(sig, &frame->sig);
+		put_user_ex(ptr_to_compat(&frame->info), &frame->pinfo);
+		put_user_ex(ptr_to_compat(&frame->uc), &frame->puc);
+		err |= copy_siginfo_to_user32(&frame->info, info);
+
+		/* Create the ucontext.  */
+		if (cpu_has_xsave)
+			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+		else
+			put_user_ex(0, &frame->uc.uc_flags);
+		put_user_ex(0, &frame->uc.uc_link);
+		put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+		put_user_ex(sas_ss_flags(regs->sp),
+			    &frame->uc.uc_stack.ss_flags);
+		put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+		err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+					     regs, set->sig[0]);
+		err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+		if (ka->sa.sa_flags & SA_RESTORER)
+			restorer = ka->sa.sa_restorer;
+		else
+			restorer = VDSO32_SYMBOL(current->mm->context.vdso,
+						 rt_sigreturn);
+		put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
+
+		/*
+		 * Not actually used anymore, but left because some gdb
+		 * versions need it.
+		 */
+		put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+	} put_user_catch(err);
+
+	if (err)
+		return -EFAULT;
+
+	/* Set up registers for signal handler */
+	regs->sp = (unsigned long) frame;
+	regs->ip = (unsigned long) ka->sa.sa_handler;
+
+	/* Make -mregparm=3 work */
+	regs->ax = sig;
+	regs->dx = (unsigned long) &frame->info;
+	regs->cx = (unsigned long) &frame->uc;
+
+	loadsegment(ds, __USER32_DS);
+	loadsegment(es, __USER32_DS);
+
+	regs->cs = __USER32_CS;
+	regs->ss = __USER32_DS;
+
+	return 0;
+}

kernel/arch/x86/ia32/ia32entry.S

@@ -0,0 +1,493 @@
+/*
+ * Compatibility mode system call entry point for x86-64. 
+ * 		
+ * Copyright 2000-2002 Andi Kleen, SuSE Labs.
+ */		 
+
+#include <asm/dwarf2.h>
+#include <asm/calling.h>
+#include <asm/asm-offsets.h>
+#include <asm/current.h>
+#include <asm/errno.h>
+#include <asm/ia32_unistd.h>	
+#include <asm/thread_info.h>	
+#include <asm/segment.h>
+#include <asm/irqflags.h>
+#include <linux/linkage.h>
+#include <linux/err.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE	   0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+#define sysexit_audit ia32_ret_from_sys_call
+#define sysretl_audit ia32_ret_from_sys_call
+#endif
+
+	.section .entry.text, "ax"
+
+	.macro IA32_ARG_FIXUP noebp=0
+	movl	%edi,%r8d
+	.if \noebp
+	.else
+	movl	%ebp,%r9d
+	.endif
+	xchg	%ecx,%esi
+	movl	%ebx,%edi
+	movl	%edx,%edx	/* zero extension */
+	.endm 
+
+	/* clobbers %eax */	
+	.macro  CLEAR_RREGS offset=0, _r9=rax
+	xorl 	%eax,%eax
+	movq	%rax,\offset+R11(%rsp)
+	movq	%rax,\offset+R10(%rsp)
+	movq	%\_r9,\offset+R9(%rsp)
+	movq	%rax,\offset+R8(%rsp)
+	.endm
+
+	/*
+	 * Reload arg registers from stack in case ptrace changed them.
+	 * We don't reload %eax because syscall_trace_enter() returned
+	 * the %rax value we should see.  Instead, we just truncate that
+	 * value to 32 bits again as we did on entry from user mode.
+	 * If it's a new value set by user_regset during entry tracing,
+	 * this matches the normal truncation of the user-mode value.
+	 * If it's -1 to make us punt the syscall, then (u32)-1 is still
+	 * an appropriately invalid value.
+	 */
+	.macro LOAD_ARGS32 offset, _r9=0
+	.if \_r9
+	movl \offset+16(%rsp),%r9d
+	.endif
+	movl \offset+40(%rsp),%ecx
+	movl \offset+48(%rsp),%edx
+	movl \offset+56(%rsp),%esi
+	movl \offset+64(%rsp),%edi
+	movl %eax,%eax			/* zero extension */
+	.endm
+	
+	.macro CFI_STARTPROC32 simple
+	CFI_STARTPROC	\simple
+	CFI_UNDEFINED	r8
+	CFI_UNDEFINED	r9
+	CFI_UNDEFINED	r10
+	CFI_UNDEFINED	r11
+	CFI_UNDEFINED	r12
+	CFI_UNDEFINED	r13
+	CFI_UNDEFINED	r14
+	CFI_UNDEFINED	r15
+	.endm
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret32)
+	swapgs
+	sysretl
+ENDPROC(native_usergs_sysret32)
+
+ENTRY(native_irq_enable_sysexit)
+	swapgs
+	sti
+	sysexit
+ENDPROC(native_irq_enable_sysexit)
+#endif
+
+/*
+ * 32bit SYSENTER instruction entry.
+ *
+ * Arguments:
+ * %eax	System call number.
+ * %ebx Arg1
+ * %ecx Arg2
+ * %edx Arg3
+ * %esi Arg4
+ * %edi Arg5
+ * %ebp user stack
+ * 0(%ebp) Arg6	
+ * 	
+ * Interrupts off.
+ *	
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below.	Set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */ 	
+ENTRY(ia32_sysenter_target)
+	CFI_STARTPROC32	simple
+	CFI_SIGNAL_FRAME
+	CFI_DEF_CFA	rsp,0
+	CFI_REGISTER	rsp,rbp
+	SWAPGS_UNSAFE_STACK
+	movq	PER_CPU_VAR(kernel_stack), %rsp
+	addq	$(KERNEL_STACK_OFFSET),%rsp
+	/*
+	 * No need to follow this irqs on/off section: the syscall
+	 * disabled irqs, here we enable it straight after entry:
+	 */
+	ENABLE_INTERRUPTS(CLBR_NONE)
+ 	movl	%ebp,%ebp		/* zero extension */
+	pushq_cfi $__USER32_DS
+	/*CFI_REL_OFFSET ss,0*/
+	pushq_cfi %rbp
+	CFI_REL_OFFSET rsp,0
+	pushfq_cfi
+	/*CFI_REL_OFFSET rflags,0*/
+	movl	TI_sysenter_return+THREAD_INFO(%rsp,3*8-KERNEL_STACK_OFFSET),%r10d
+	CFI_REGISTER rip,r10
+	pushq_cfi $__USER32_CS
+	/*CFI_REL_OFFSET cs,0*/
+	movl	%eax, %eax
+	pushq_cfi %r10
+	CFI_REL_OFFSET rip,0
+	pushq_cfi %rax
+	cld
+	SAVE_ARGS 0,1,0
+ 	/* no need to do an access_ok check here because rbp has been
+ 	   32bit zero extended */ 
+1:	movl	(%rbp),%ebp
+ 	.section __ex_table,"a"
+ 	.quad 1b,ia32_badarg
+ 	.previous	
+	orl     $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	testl   $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	CFI_REMEMBER_STATE
+	jnz  sysenter_tracesys
+	cmpq	$(IA32_NR_syscalls-1),%rax
+	ja	ia32_badsys
+sysenter_do_call:
+	IA32_ARG_FIXUP
+sysenter_dispatch:
+	call	*ia32_sys_call_table(,%rax,8)
+	movq	%rax,RAX-ARGOFFSET(%rsp)
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	testl	$_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jnz	sysexit_audit
+sysexit_from_sys_call:
+	andl    $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	/* clear IF, that popfq doesn't enable interrupts early */
+	andl  $~0x200,EFLAGS-R11(%rsp) 
+	movl	RIP-R11(%rsp),%edx		/* User %eip */
+	CFI_REGISTER rip,rdx
+	RESTORE_ARGS 0,24,0,0,0,0
+	xorq	%r8,%r8
+	xorq	%r9,%r9
+	xorq	%r10,%r10
+	xorq	%r11,%r11
+	popfq_cfi
+	/*CFI_RESTORE rflags*/
+	popq_cfi %rcx				/* User %esp */
+	CFI_REGISTER rsp,rcx
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS_SYSEXIT32
+
+#ifdef CONFIG_AUDITSYSCALL
+	.macro auditsys_entry_common
+	movl %esi,%r9d			/* 6th arg: 4th syscall arg */
+	movl %edx,%r8d			/* 5th arg: 3rd syscall arg */
+	/* (already in %ecx)		   4th arg: 2nd syscall arg */
+	movl %ebx,%edx			/* 3rd arg: 1st syscall arg */
+	movl %eax,%esi			/* 2nd arg: syscall number */
+	movl $AUDIT_ARCH_I386,%edi	/* 1st arg: audit arch */
+	call __audit_syscall_entry
+	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall number */
+	cmpq $(IA32_NR_syscalls-1),%rax
+	ja ia32_badsys
+	movl %ebx,%edi			/* reload 1st syscall arg */
+	movl RCX-ARGOFFSET(%rsp),%esi	/* reload 2nd syscall arg */
+	movl RDX-ARGOFFSET(%rsp),%edx	/* reload 3rd syscall arg */
+	movl RSI-ARGOFFSET(%rsp),%ecx	/* reload 4th syscall arg */
+	movl RDI-ARGOFFSET(%rsp),%r8d	/* reload 5th syscall arg */
+	.endm
+
+	.macro auditsys_exit exit
+	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jnz ia32_ret_from_sys_call
+	TRACE_IRQS_ON
+	sti
+	movl %eax,%esi		/* second arg, syscall return value */
+	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
+	jbe 1f
+	movslq %eax, %rsi	/* if error sign extend to 64 bits */
+1:	setbe %al		/* 1 if error, 0 if not */
+	movzbl %al,%edi		/* zero-extend that into %edi */
+	call __audit_syscall_exit
+	movq RAX-ARGOFFSET(%rsp),%rax	/* reload syscall return value */
+	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
+	cli
+	TRACE_IRQS_OFF
+	testl %edi,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jz \exit
+	CLEAR_RREGS -ARGOFFSET
+	jmp int_with_check
+	.endm
+
+sysenter_auditsys:
+	CFI_RESTORE_STATE
+	auditsys_entry_common
+	movl %ebp,%r9d			/* reload 6th syscall arg */
+	jmp sysenter_dispatch
+
+sysexit_audit:
+	auditsys_exit sysexit_from_sys_call
+#endif
+
+sysenter_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jz	sysenter_auditsys
+#endif
+	SAVE_REST
+	CLEAR_RREGS
+	movq	$-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
+	movq	%rsp,%rdi        /* &pt_regs -> arg1 */
+	call	syscall_trace_enter
+	LOAD_ARGS32 ARGOFFSET  /* reload args from stack in case ptrace changed it */
+	RESTORE_REST
+	cmpq	$(IA32_NR_syscalls-1),%rax
+	ja	int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
+	jmp	sysenter_do_call
+	CFI_ENDPROC
+ENDPROC(ia32_sysenter_target)
+
+/*
+ * 32bit SYSCALL instruction entry.
+ *
+ * Arguments:
+ * %eax	System call number.
+ * %ebx Arg1
+ * %ecx return EIP 
+ * %edx Arg3
+ * %esi Arg4
+ * %edi Arg5
+ * %ebp Arg2    [note: not saved in the stack frame, should not be touched]
+ * %esp user stack 
+ * 0(%esp) Arg6
+ * 	
+ * Interrupts off.
+ *	
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below.	Set up a complete hardware stack frame to share code
+ * with the int 0x80 path.	
+ */ 	
+ENTRY(ia32_cstar_target)
+	CFI_STARTPROC32	simple
+	CFI_SIGNAL_FRAME
+	CFI_DEF_CFA	rsp,KERNEL_STACK_OFFSET
+	CFI_REGISTER	rip,rcx
+	/*CFI_REGISTER	rflags,r11*/
+	SWAPGS_UNSAFE_STACK
+	movl	%esp,%r8d
+	CFI_REGISTER	rsp,r8
+	movq	PER_CPU_VAR(kernel_stack),%rsp
+	/*
+	 * No need to follow this irqs on/off section: the syscall
+	 * disabled irqs and here we enable it straight after entry:
+	 */
+	ENABLE_INTERRUPTS(CLBR_NONE)
+	SAVE_ARGS 8,0,0
+	movl 	%eax,%eax	/* zero extension */
+	movq	%rax,ORIG_RAX-ARGOFFSET(%rsp)
+	movq	%rcx,RIP-ARGOFFSET(%rsp)
+	CFI_REL_OFFSET rip,RIP-ARGOFFSET
+	movq	%rbp,RCX-ARGOFFSET(%rsp) /* this lies slightly to ptrace */
+	movl	%ebp,%ecx
+	movq	$__USER32_CS,CS-ARGOFFSET(%rsp)
+	movq	$__USER32_DS,SS-ARGOFFSET(%rsp)
+	movq	%r11,EFLAGS-ARGOFFSET(%rsp)
+	/*CFI_REL_OFFSET rflags,EFLAGS-ARGOFFSET*/
+	movq	%r8,RSP-ARGOFFSET(%rsp)	
+	CFI_REL_OFFSET rsp,RSP-ARGOFFSET
+	/* no need to do an access_ok check here because r8 has been
+	   32bit zero extended */ 
+	/* hardware stack frame is complete now */	
+1:	movl	(%r8),%r9d
+	.section __ex_table,"a"
+	.quad 1b,ia32_badarg
+	.previous	
+	orl     $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	testl   $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	CFI_REMEMBER_STATE
+	jnz   cstar_tracesys
+	cmpq $IA32_NR_syscalls-1,%rax
+	ja  ia32_badsys
+cstar_do_call:
+	IA32_ARG_FIXUP 1
+cstar_dispatch:
+	call *ia32_sys_call_table(,%rax,8)
+	movq %rax,RAX-ARGOFFSET(%rsp)
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jnz sysretl_audit
+sysretl_from_sys_call:
+	andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	RESTORE_ARGS 0,-ARG_SKIP,0,0,0
+	movl RIP-ARGOFFSET(%rsp),%ecx
+	CFI_REGISTER rip,rcx
+	movl EFLAGS-ARGOFFSET(%rsp),%r11d	
+	/*CFI_REGISTER rflags,r11*/
+	xorq	%r10,%r10
+	xorq	%r9,%r9
+	xorq	%r8,%r8
+	TRACE_IRQS_ON
+	movl RSP-ARGOFFSET(%rsp),%esp
+	CFI_RESTORE rsp
+	USERGS_SYSRET32
+	
+#ifdef CONFIG_AUDITSYSCALL
+cstar_auditsys:
+	CFI_RESTORE_STATE
+	movl %r9d,R9-ARGOFFSET(%rsp)	/* register to be clobbered by call */
+	auditsys_entry_common
+	movl R9-ARGOFFSET(%rsp),%r9d	/* reload 6th syscall arg */
+	jmp cstar_dispatch
+
+sysretl_audit:
+	auditsys_exit sysretl_from_sys_call
+#endif
+
+cstar_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jz cstar_auditsys
+#endif
+	xchgl %r9d,%ebp
+	SAVE_REST
+	CLEAR_RREGS 0, r9
+	movq $-ENOSYS,RAX(%rsp)	/* ptrace can change this for a bad syscall */
+	movq %rsp,%rdi        /* &pt_regs -> arg1 */
+	call syscall_trace_enter
+	LOAD_ARGS32 ARGOFFSET, 1  /* reload args from stack in case ptrace changed it */
+	RESTORE_REST
+	xchgl %ebp,%r9d
+	cmpq $(IA32_NR_syscalls-1),%rax
+	ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
+	jmp cstar_do_call
+END(ia32_cstar_target)
+				
+ia32_badarg:
+	movq $-EFAULT,%rax
+	jmp ia32_sysret
+	CFI_ENDPROC
+
+/* 
+ * Emulated IA32 system calls via int 0x80. 
+ *
+ * Arguments:	 
+ * %eax	System call number.
+ * %ebx Arg1
+ * %ecx Arg2
+ * %edx Arg3
+ * %esi Arg4
+ * %edi Arg5
+ * %ebp Arg6    [note: not saved in the stack frame, should not be touched]
+ *
+ * Notes:
+ * Uses the same stack frame as the x86-64 version.	
+ * All registers except %eax must be saved (but ptrace may violate that)
+ * Arguments are zero extended. For system calls that want sign extension and
+ * take long arguments a wrapper is needed. Most calls can just be called
+ * directly.
+ * Assumes it is only called from user space and entered with interrupts off.	
+ */ 				
+
+ENTRY(ia32_syscall)
+	CFI_STARTPROC32	simple
+	CFI_SIGNAL_FRAME
+	CFI_DEF_CFA	rsp,SS+8-RIP
+	/*CFI_REL_OFFSET	ss,SS-RIP*/
+	CFI_REL_OFFSET	rsp,RSP-RIP
+	/*CFI_REL_OFFSET	rflags,EFLAGS-RIP*/
+	/*CFI_REL_OFFSET	cs,CS-RIP*/
+	CFI_REL_OFFSET	rip,RIP-RIP
+	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	SWAPGS
+	/*
+	 * No need to follow this irqs on/off section: the syscall
+	 * disabled irqs and here we enable it straight after entry:
+	 */
+	ENABLE_INTERRUPTS(CLBR_NONE)
+	movl %eax,%eax
+	pushq_cfi %rax
+	cld
+	/* note the registers are not zero extended to the sf.
+	   this could be a problem. */
+	SAVE_ARGS 0,1,0
+	orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jnz ia32_tracesys
+	cmpq $(IA32_NR_syscalls-1),%rax
+	ja ia32_badsys
+ia32_do_call:
+	IA32_ARG_FIXUP
+	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
+ia32_sysret:
+	movq %rax,RAX-ARGOFFSET(%rsp)
+ia32_ret_from_sys_call:
+	CLEAR_RREGS -ARGOFFSET
+	jmp int_ret_from_sys_call 
+
+ia32_tracesys:			 
+	SAVE_REST
+	CLEAR_RREGS
+	movq $-ENOSYS,RAX(%rsp)	/* ptrace can change this for a bad syscall */
+	movq %rsp,%rdi        /* &pt_regs -> arg1 */
+	call syscall_trace_enter
+	LOAD_ARGS32 ARGOFFSET  /* reload args from stack in case ptrace changed it */
+	RESTORE_REST
+	cmpq $(IA32_NR_syscalls-1),%rax
+	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
+	jmp ia32_do_call
+END(ia32_syscall)
+
+ia32_badsys:
+	movq $0,ORIG_RAX-ARGOFFSET(%rsp)
+	movq $-ENOSYS,%rax
+	jmp ia32_sysret
+
+	CFI_ENDPROC
+	
+	.macro PTREGSCALL label, func, arg
+	ALIGN
+GLOBAL(\label)
+	leaq \func(%rip),%rax
+	leaq -ARGOFFSET+8(%rsp),\arg	/* 8 for return address */
+	jmp  ia32_ptregs_common	
+	.endm
+
+	CFI_STARTPROC32
+
+	PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi
+	PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi
+	PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx
+	PTREGSCALL stub32_execve, sys32_execve, %rcx
+	PTREGSCALL stub32_fork, sys_fork, %rdi
+	PTREGSCALL stub32_clone, sys32_clone, %rdx
+	PTREGSCALL stub32_vfork, sys_vfork, %rdi
+	PTREGSCALL stub32_iopl, sys_iopl, %rsi
+
+	ALIGN
+ia32_ptregs_common:
+	popq %r11
+	CFI_ENDPROC
+	CFI_STARTPROC32	simple
+	CFI_SIGNAL_FRAME
+	CFI_DEF_CFA	rsp,SS+8-ARGOFFSET
+	CFI_REL_OFFSET	rax,RAX-ARGOFFSET
+	CFI_REL_OFFSET	rcx,RCX-ARGOFFSET
+	CFI_REL_OFFSET	rdx,RDX-ARGOFFSET
+	CFI_REL_OFFSET	rsi,RSI-ARGOFFSET
+	CFI_REL_OFFSET	rdi,RDI-ARGOFFSET
+	CFI_REL_OFFSET	rip,RIP-ARGOFFSET
+/*	CFI_REL_OFFSET	cs,CS-ARGOFFSET*/
+/*	CFI_REL_OFFSET	rflags,EFLAGS-ARGOFFSET*/
+	CFI_REL_OFFSET	rsp,RSP-ARGOFFSET
+/*	CFI_REL_OFFSET	ss,SS-ARGOFFSET*/
+	SAVE_REST
+	call *%rax
+	RESTORE_REST
+	jmp  ia32_sysret	/* misbalances the return cache */
+	CFI_ENDPROC
+END(ia32_ptregs_common)

kernel/arch/x86/ia32/ipc32.c

@@ -0,0 +1,54 @@
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/syscalls.h>
+#include <linux/time.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/ipc.h>
+#include <linux/compat.h>
+#include <asm/sys_ia32.h>
+
+asmlinkage long sys32_ipc(u32 call, int first, int second, int third,
+			  compat_uptr_t ptr, u32 fifth)
+{
+	int version;
+
+	version = call >> 16; /* hack for backward compatibility */
+	call &= 0xffff;
+
+	switch (call) {
+	case SEMOP:
+		/* struct sembuf is the same on 32 and 64bit :)) */
+		return sys_semtimedop(first, compat_ptr(ptr), second, NULL);
+	case SEMTIMEDOP:
+		return compat_sys_semtimedop(first, compat_ptr(ptr), second,
+						compat_ptr(fifth));
+	case SEMGET:
+		return sys_semget(first, second, third);
+	case SEMCTL:
+		return compat_sys_semctl(first, second, third, compat_ptr(ptr));
+
+	case MSGSND:
+		return compat_sys_msgsnd(first, second, third, compat_ptr(ptr));
+	case MSGRCV:
+		return compat_sys_msgrcv(first, second, fifth, third,
+					 version, compat_ptr(ptr));
+	case MSGGET:
+		return sys_msgget((key_t) first, second);
+	case MSGCTL:
+		return compat_sys_msgctl(first, second, compat_ptr(ptr));
+
+	case SHMAT:
+		return compat_sys_shmat(first, second, third, version,
+					compat_ptr(ptr));
+	case SHMDT:
+		return sys_shmdt(compat_ptr(ptr));
+	case SHMGET:
+		return sys_shmget(first, (unsigned)second, third);
+	case SHMCTL:
+		return compat_sys_shmctl(first, second, compat_ptr(ptr));
+	}
+	return -ENOSYS;
+}

kernel/arch/x86/ia32/nosyscall.c

@@ -0,0 +1,7 @@
+#include <linux/kernel.h>
+#include <linux/errno.h>
+
+long compat_ni_syscall(void)
+{
+	return -ENOSYS;
+}

kernel/arch/x86/ia32/sys_ia32.c

@@ -0,0 +1,516 @@
+/*
+ * sys_ia32.c: Conversion between 32bit and 64bit native syscalls. Based on
+ *             sys_sparc32
+ *
+ * Copyright (C) 2000		VA Linux Co
+ * Copyright (C) 2000		Don Dugger <n0ano@valinux.com>
+ * Copyright (C) 1999		Arun Sharma <arun.sharma@intel.com>
+ * Copyright (C) 1997,1998	Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ * Copyright (C) 1997		David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 2000		Hewlett-Packard Co.
+ * Copyright (C) 2000		David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 2000,2001,2002	Andi Kleen, SuSE Labs (x86-64 port)
+ *
+ * These routines maintain argument size conversion between 32bit and 64bit
+ * environment. In 2.5 most of this should be moved to a generic directory.
+ *
+ * This file assumes that there is a hole at the end of user address space.
+ *
+ * Some of the functions are LE specific currently. These are
+ * hopefully all marked.  This should be fixed.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/signal.h>
+#include <linux/syscalls.h>
+#include <linux/times.h>
+#include <linux/utsname.h>
+#include <linux/mm.h>
+#include <linux/uio.h>
+#include <linux/poll.h>
+#include <linux/personality.h>
+#include <linux/stat.h>
+#include <linux/rwsem.h>
+#include <linux/compat.h>
+#include <linux/vfs.h>
+#include <linux/ptrace.h>
+#include <linux/highuid.h>
+#include <linux/sysctl.h>
+#include <linux/slab.h>
+#include <asm/mman.h>
+#include <asm/types.h>
+#include <asm/uaccess.h>
+#include <linux/atomic.h>
+#include <asm/vgtod.h>
+#include <asm/sys_ia32.h>
+
+#define AA(__x)		((unsigned long)(__x))
+
+
+asmlinkage long sys32_truncate64(const char __user *filename,
+				 unsigned long offset_low,
+				 unsigned long offset_high)
+{
+       return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low);
+}
+
+asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low,
+				  unsigned long offset_high)
+{
+       return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low);
+}
+
+/*
+ * Another set for IA32/LFS -- x86_64 struct stat is different due to
+ * support for 64bit inode numbers.
+ */
+static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
+{
+	typeof(ubuf->st_uid) uid = 0;
+	typeof(ubuf->st_gid) gid = 0;
+	SET_UID(uid, stat->uid);
+	SET_GID(gid, stat->gid);
+	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(struct stat64)) ||
+	    __put_user(huge_encode_dev(stat->dev), &ubuf->st_dev) ||
+	    __put_user(stat->ino, &ubuf->__st_ino) ||
+	    __put_user(stat->ino, &ubuf->st_ino) ||
+	    __put_user(stat->mode, &ubuf->st_mode) ||
+	    __put_user(stat->nlink, &ubuf->st_nlink) ||
+	    __put_user(uid, &ubuf->st_uid) ||
+	    __put_user(gid, &ubuf->st_gid) ||
+	    __put_user(huge_encode_dev(stat->rdev), &ubuf->st_rdev) ||
+	    __put_user(stat->size, &ubuf->st_size) ||
+	    __put_user(stat->atime.tv_sec, &ubuf->st_atime) ||
+	    __put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec) ||
+	    __put_user(stat->mtime.tv_sec, &ubuf->st_mtime) ||
+	    __put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec) ||
+	    __put_user(stat->ctime.tv_sec, &ubuf->st_ctime) ||
+	    __put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec) ||
+	    __put_user(stat->blksize, &ubuf->st_blksize) ||
+	    __put_user(stat->blocks, &ubuf->st_blocks))
+		return -EFAULT;
+	return 0;
+}
+
+asmlinkage long sys32_stat64(const char __user *filename,
+			     struct stat64 __user *statbuf)
+{
+	struct kstat stat;
+	int ret = vfs_stat(filename, &stat);
+
+	if (!ret)
+		ret = cp_stat64(statbuf, &stat);
+	return ret;
+}
+
+asmlinkage long sys32_lstat64(const char __user *filename,
+			      struct stat64 __user *statbuf)
+{
+	struct kstat stat;
+	int ret = vfs_lstat(filename, &stat);
+	if (!ret)
+		ret = cp_stat64(statbuf, &stat);
+	return ret;
+}
+
+asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
+{
+	struct kstat stat;
+	int ret = vfs_fstat(fd, &stat);
+	if (!ret)
+		ret = cp_stat64(statbuf, &stat);
+	return ret;
+}
+
+asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename,
+			      struct stat64 __user *statbuf, int flag)
+{
+	struct kstat stat;
+	int error;
+
+	error = vfs_fstatat(dfd, filename, &stat, flag);
+	if (error)
+		return error;
+	return cp_stat64(statbuf, &stat);
+}
+
+/*
+ * Linux/i386 didn't use to be able to handle more than
+ * 4 system call parameters, so these system calls used a memory
+ * block for parameter passing..
+ */
+
+struct mmap_arg_struct32 {
+	unsigned int addr;
+	unsigned int len;
+	unsigned int prot;
+	unsigned int flags;
+	unsigned int fd;
+	unsigned int offset;
+};
+
+asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg)
+{
+	struct mmap_arg_struct32 a;
+
+	if (copy_from_user(&a, arg, sizeof(a)))
+		return -EFAULT;
+
+	if (a.offset & ~PAGE_MASK)
+		return -EINVAL;
+
+	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
+			       a.offset>>PAGE_SHIFT);
+}
+
+asmlinkage long sys32_mprotect(unsigned long start, size_t len,
+			       unsigned long prot)
+{
+	return sys_mprotect(start, len, prot);
+}
+
+asmlinkage long sys32_rt_sigaction(int sig, struct sigaction32 __user *act,
+				   struct sigaction32 __user *oact,
+				   unsigned int sigsetsize)
+{
+	struct k_sigaction new_ka, old_ka;
+	int ret;
+	compat_sigset_t set32;
+
+	/* XXX: Don't preclude handling different sized sigset_t's.  */
+	if (sigsetsize != sizeof(compat_sigset_t))
+		return -EINVAL;
+
+	if (act) {
+		compat_uptr_t handler, restorer;
+
+		if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
+		    __get_user(handler, &act->sa_handler) ||
+		    __get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
+		    __get_user(restorer, &act->sa_restorer) ||
+		    __copy_from_user(&set32, &act->sa_mask,
+				     sizeof(compat_sigset_t)))
+			return -EFAULT;
+		new_ka.sa.sa_handler = compat_ptr(handler);
+		new_ka.sa.sa_restorer = compat_ptr(restorer);
+
+		/*
+		 * FIXME: here we rely on _COMPAT_NSIG_WORS to be >=
+		 * than _NSIG_WORDS << 1
+		 */
+		switch (_NSIG_WORDS) {
+		case 4: new_ka.sa.sa_mask.sig[3] = set32.sig[6]
+				| (((long)set32.sig[7]) << 32);
+		case 3: new_ka.sa.sa_mask.sig[2] = set32.sig[4]
+				| (((long)set32.sig[5]) << 32);
+		case 2: new_ka.sa.sa_mask.sig[1] = set32.sig[2]
+				| (((long)set32.sig[3]) << 32);
+		case 1: new_ka.sa.sa_mask.sig[0] = set32.sig[0]
+				| (((long)set32.sig[1]) << 32);
+		}
+	}
+
+	ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
+
+	if (!ret && oact) {
+		/*
+		 * FIXME: here we rely on _COMPAT_NSIG_WORS to be >=
+		 * than _NSIG_WORDS << 1
+		 */
+		switch (_NSIG_WORDS) {
+		case 4:
+			set32.sig[7] = (old_ka.sa.sa_mask.sig[3] >> 32);
+			set32.sig[6] = old_ka.sa.sa_mask.sig[3];
+		case 3:
+			set32.sig[5] = (old_ka.sa.sa_mask.sig[2] >> 32);
+			set32.sig[4] = old_ka.sa.sa_mask.sig[2];
+		case 2:
+			set32.sig[3] = (old_ka.sa.sa_mask.sig[1] >> 32);
+			set32.sig[2] = old_ka.sa.sa_mask.sig[1];
+		case 1:
+			set32.sig[1] = (old_ka.sa.sa_mask.sig[0] >> 32);
+			set32.sig[0] = old_ka.sa.sa_mask.sig[0];
+		}
+		if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
+		    __put_user(ptr_to_compat(old_ka.sa.sa_handler),
+			       &oact->sa_handler) ||
+		    __put_user(ptr_to_compat(old_ka.sa.sa_restorer),
+			       &oact->sa_restorer) ||
+		    __put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
+		    __copy_to_user(&oact->sa_mask, &set32,
+				   sizeof(compat_sigset_t)))
+			return -EFAULT;
+	}
+
+	return ret;
+}
+
+asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act,
+				struct old_sigaction32 __user *oact)
+{
+	struct k_sigaction new_ka, old_ka;
+	int ret;
+
+	if (act) {
+		compat_old_sigset_t mask;
+		compat_uptr_t handler, restorer;
+
+		if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
+		    __get_user(handler, &act->sa_handler) ||
+		    __get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
+		    __get_user(restorer, &act->sa_restorer) ||
+		    __get_user(mask, &act->sa_mask))
+			return -EFAULT;
+
+		new_ka.sa.sa_handler = compat_ptr(handler);
+		new_ka.sa.sa_restorer = compat_ptr(restorer);
+
+		siginitset(&new_ka.sa.sa_mask, mask);
+	}
+
+	ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
+
+	if (!ret && oact) {
+		if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
+		    __put_user(ptr_to_compat(old_ka.sa.sa_handler),
+			       &oact->sa_handler) ||
+		    __put_user(ptr_to_compat(old_ka.sa.sa_restorer),
+			       &oact->sa_restorer) ||
+		    __put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
+		    __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
+			return -EFAULT;
+	}
+
+	return ret;
+}
+
+asmlinkage long sys32_alarm(unsigned int seconds)
+{
+	return alarm_setitimer(seconds);
+}
+
+asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr,
+			      int options)
+{
+	return compat_sys_wait4(pid, stat_addr, options, NULL);
+}
+
+/* 32-bit timeval and related flotsam.  */
+
+asmlinkage long sys32_sysfs(int option, u32 arg1, u32 arg2)
+{
+	return sys_sysfs(option, arg1, arg2);
+}
+
+asmlinkage long sys32_sched_rr_get_interval(compat_pid_t pid,
+				    struct compat_timespec __user *interval)
+{
+	struct timespec t;
+	int ret;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(KERNEL_DS);
+	ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t);
+	set_fs(old_fs);
+	if (put_compat_timespec(&t, interval))
+		return -EFAULT;
+	return ret;
+}
+
+asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *set,
+				    compat_size_t sigsetsize)
+{
+	sigset_t s;
+	compat_sigset_t s32;
+	int ret;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(KERNEL_DS);
+	ret = sys_rt_sigpending((sigset_t __user *)&s, sigsetsize);
+	set_fs(old_fs);
+	if (!ret) {
+		switch (_NSIG_WORDS) {
+		case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3];
+		case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2];
+		case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1];
+		case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0];
+		}
+		if (copy_to_user(set, &s32, sizeof(compat_sigset_t)))
+			return -EFAULT;
+	}
+	return ret;
+}
+
+asmlinkage long sys32_rt_sigqueueinfo(int pid, int sig,
+				      compat_siginfo_t __user *uinfo)
+{
+	siginfo_t info;
+	int ret;
+	mm_segment_t old_fs = get_fs();
+
+	if (copy_siginfo_from_user32(&info, uinfo))
+		return -EFAULT;
+	set_fs(KERNEL_DS);
+	ret = sys_rt_sigqueueinfo(pid, sig, (siginfo_t __user *)&info);
+	set_fs(old_fs);
+	return ret;
+}
+
+/* warning: next two assume little endian */
+asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count,
+			    u32 poslo, u32 poshi)
+{
+	return sys_pread64(fd, ubuf, count,
+			 ((loff_t)AA(poshi) << 32) | AA(poslo));
+}
+
+asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf,
+			     u32 count, u32 poslo, u32 poshi)
+{
+	return sys_pwrite64(fd, ubuf, count,
+			  ((loff_t)AA(poshi) << 32) | AA(poslo));
+}
+
+
+asmlinkage long sys32_personality(unsigned long personality)
+{
+	int ret;
+
+	if (personality(current->personality) == PER_LINUX32 &&
+		personality == PER_LINUX)
+		personality = PER_LINUX32;
+	ret = sys_personality(personality);
+	if (ret == PER_LINUX32)
+		ret = PER_LINUX;
+	return ret;
+}
+
+asmlinkage long sys32_sendfile(int out_fd, int in_fd,
+			       compat_off_t __user *offset, s32 count)
+{
+	mm_segment_t old_fs = get_fs();
+	int ret;
+	off_t of;
+
+	if (offset && get_user(of, offset))
+		return -EFAULT;
+
+	set_fs(KERNEL_DS);
+	ret = sys_sendfile(out_fd, in_fd, offset ? (off_t __user *)&of : NULL,
+			   count);
+	set_fs(old_fs);
+
+	if (offset && put_user(of, offset))
+		return -EFAULT;
+	return ret;
+}
+
+asmlinkage long sys32_execve(const char __user *name, compat_uptr_t __user *argv,
+			     compat_uptr_t __user *envp, struct pt_regs *regs)
+{
+	long error;
+	char *filename;
+
+	filename = getname(name);
+	error = PTR_ERR(filename);
+	if (IS_ERR(filename))
+		return error;
+	error = compat_do_execve(filename, argv, envp, regs);
+	putname(filename);
+	return error;
+}
+
+asmlinkage long sys32_clone(unsigned int clone_flags, unsigned int newsp,
+			    struct pt_regs *regs)
+{
+	void __user *parent_tid = (void __user *)regs->dx;
+	void __user *child_tid = (void __user *)regs->di;
+
+	if (!newsp)
+		newsp = regs->sp;
+	return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
+}
+
+/*
+ * Some system calls that need sign extended arguments. This could be
+ * done by a generic wrapper.
+ */
+long sys32_lseek(unsigned int fd, int offset, unsigned int whence)
+{
+	return sys_lseek(fd, offset, whence);
+}
+
+long sys32_kill(int pid, int sig)
+{
+	return sys_kill(pid, sig);
+}
+
+long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
+			__u32 len_low, __u32 len_high, int advice)
+{
+	return sys_fadvise64_64(fd,
+			       (((u64)offset_high)<<32) | offset_low,
+			       (((u64)len_high)<<32) | len_low,
+				advice);
+}
+
+long sys32_vm86_warning(void)
+{
+	struct task_struct *me = current;
+	static char lastcomm[sizeof(me->comm)];
+
+	if (strncmp(lastcomm, me->comm, sizeof(lastcomm))) {
+		compat_printk(KERN_INFO
+			      "%s: vm86 mode not supported on 64 bit kernel\n",
+			      me->comm);
+		strncpy(lastcomm, me->comm, sizeof(lastcomm));
+	}
+	return -ENOSYS;
+}
+
+long sys32_lookup_dcookie(u32 addr_low, u32 addr_high,
+			  char __user *buf, size_t len)
+{
+	return sys_lookup_dcookie(((u64)addr_high << 32) | addr_low, buf, len);
+}
+
+asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi,
+				   size_t count)
+{
+	return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count);
+}
+
+asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi,
+				      unsigned n_low, unsigned n_hi,  int flags)
+{
+	return sys_sync_file_range(fd,
+				   ((u64)off_hi << 32) | off_low,
+				   ((u64)n_hi << 32) | n_low, flags);
+}
+
+asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi,
+				size_t len, int advice)
+{
+	return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
+				len, advice);
+}
+
+asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo,
+				unsigned offset_hi, unsigned len_lo,
+				unsigned len_hi)
+{
+	return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo,
+			     ((u64)len_hi << 32) | len_lo);
+}
+
+asmlinkage long sys32_fanotify_mark(int fanotify_fd, unsigned int flags,
+				    u32 mask_lo, u32 mask_hi,
+				    int fd, const char  __user *pathname)
+{
+	return sys_fanotify_mark(fanotify_fd, flags,
+				 ((u64)mask_hi << 32) | mask_lo,
+				 fd, pathname);
+}

kernel/arch/x86/ia32/syscall_ia32.c

@@ -0,0 +1,25 @@
+/* System call table for ia32 emulation. */
+
+#include <linux/linkage.h>
+#include <linux/sys.h>
+#include <linux/cache.h>
+#include <asm/asm-offsets.h>
+
+#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void compat(void) ;
+#include <asm/syscalls_32.h>
+#undef __SYSCALL_I386
+
+#define __SYSCALL_I386(nr, sym, compat) [nr] = compat,
+
+typedef void (*sys_call_ptr_t)(void);
+
+extern void compat_ni_syscall(void);
+
+const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = {
+	/*
+	 * Smells like a compiler bug -- it doesn't work
+	 * when the & below is removed.
+	 */
+	[0 ... __NR_ia32_syscall_max] = &compat_ni_syscall,
+#include <asm/syscalls_32.h>
+};