Merge branch 'for-linus-4.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml

Pull UML updates from Richard Weinberger:
 "This contains beside of random fixes/cleanups two bigger changes:

   - seccomp support by Mickaël Salaün

   - IRQ rework by Anton Ivanov"

* 'for-linus-4.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml:
  um: Use race-free temporary file creation
  um: Do not set unsecure permission for temporary file
  um: Fix build error and kconfig for i386
  um: Add seccomp support
  um: Add full asm/syscall.h support
  selftests/seccomp: Remove the need for HAVE_ARCH_TRACEHOOK
  um: Fix ptrace GETREGS/SETREGS bugs
  um: link with -lpthread
  um: Update UBD to use pread/pwrite family of functions
  um: Do not change hard IRQ flags in soft IRQ processing
  um: Prevent IRQ handler reentrancy
  uml: flush stdout before forking
  uml: fix hostfs mknod()

Documentation/features/seccomp/seccomp-filter/arch-support.txt

@@ -33,7 +33,7 @@
     |          sh: | TODO |
     |       sparc: | TODO |
     |        tile: |  ok  |
-    |          um: | TODO |
+    |          um: |  ok  |
     |   unicore32: | TODO |
     |         x86: |  ok  |
     |      xtensa: | TODO |

arch/um/Kconfig.common

@@ -2,6 +2,7 @@ config UML
 	bool
 	default y
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_UID16
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select GENERIC_IRQ_SHOW

arch/um/Kconfig.um

@@ -104,3 +104,19 @@ config PGTABLE_LEVELS
 	int
 	default 3 if 3_LEVEL_PGTABLES
 	default 2
+
+config SECCOMP
+	def_bool y
+	prompt "Enable seccomp to safely compute untrusted bytecode"
+	---help---
+	  This kernel feature is useful for number crunching applications
+	  that may need to compute untrusted bytecode during their
+	  execution. By using pipes or other transports made available to
+	  the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in
+	  their own address space using seccomp. Once seccomp is
+	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
+	  and the task is only allowed to execute a few safe syscalls
+	  defined by each seccomp mode.
+
+	  If unsure, say Y.

arch/um/drivers/ubd_kern.c

@@ -535,11 +535,7 @@ static int read_cow_bitmap(int fd, void *buf, int offset, int len)
 {
 	int err;
 
-	err = os_seek_file(fd, offset);
-	if (err < 0)
-		return err;
-
-	err = os_read_file(fd, buf, len);
+	err = os_pread_file(fd, buf, len, offset);
 	if (err < 0)
 		return err;
 
@@ -1377,14 +1373,8 @@ static int update_bitmap(struct io_thread_req *req)
 	if(req->cow_offset == -1)
 		return 0;
 
-	n = os_seek_file(req->fds[1], req->cow_offset);
-	if(n < 0){
-		printk("do_io - bitmap lseek failed : err = %d\n", -n);
-		return 1;
-	}
-
-	n = os_write_file(req->fds[1], &req->bitmap_words,
-			  sizeof(req->bitmap_words));
+	n = os_pwrite_file(req->fds[1], &req->bitmap_words,
+			  sizeof(req->bitmap_words), req->cow_offset);
 	if(n != sizeof(req->bitmap_words)){
 		printk("do_io - bitmap update failed, err = %d fd = %d\n", -n,
 		       req->fds[1]);
@@ -1399,7 +1389,6 @@ static void do_io(struct io_thread_req *req)
 	char *buf;
 	unsigned long len;
 	int n, nsectors, start, end, bit;
-	int err;
 	__u64 off;
 
 	if (req->op == UBD_FLUSH) {
@@ -1428,18 +1417,12 @@ static void do_io(struct io_thread_req *req)
 		len = (end - start) * req->sectorsize;
 		buf = &req->buffer[start * req->sectorsize];
 
-		err = os_seek_file(req->fds[bit], off);
-		if(err < 0){
-			printk("do_io - lseek failed : err = %d\n", -err);
-			req->error = 1;
-			return;
-		}
 		if(req->op == UBD_READ){
 			n = 0;
 			do {
 				buf = &buf[n];
 				len -= n;
-				n = os_read_file(req->fds[bit], buf, len);
+				n = os_pread_file(req->fds[bit], buf, len, off);
 				if (n < 0) {
 					printk("do_io - read failed, err = %d "
 					       "fd = %d\n", -n, req->fds[bit]);
@@ -1449,7 +1432,7 @@ static void do_io(struct io_thread_req *req)
 			} while((n < len) && (n != 0));
 			if (n < len) memset(&buf[n], 0, len - n);
 		} else {
-			n = os_write_file(req->fds[bit], buf, len);
+			n = os_pwrite_file(req->fds[bit], buf, len, off);
 			if(n != len){
 				printk("do_io - write failed err = %d "
 				       "fd = %d\n", -n, req->fds[bit]);

arch/um/include/asm/hardirq.h

@@ -0,0 +1,23 @@
+#ifndef __ASM_UM_HARDIRQ_H
+#define __ASM_UM_HARDIRQ_H
+
+#include <linux/cache.h>
+#include <linux/threads.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+} ____cacheline_aligned irq_cpustat_t;
+
+#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+#include <linux/irq.h>
+
+#ifndef ack_bad_irq
+static inline void ack_bad_irq(unsigned int irq)
+{
+	printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
+}
+#endif
+
+#define __ARCH_IRQ_EXIT_IRQS_DISABLED 1
+
+#endif /* __ASM_UM_HARDIRQ_H */

arch/um/include/asm/syscall-generic.h

@@ -0,0 +1,138 @@
+/*
+ * Access to user system call parameters and results
+ *
+ * See asm-generic/syscall.h for function descriptions.
+ *
+ * Copyright (C) 2015 Mickaël Salaün <mic@digikod.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __UM_SYSCALL_GENERIC_H
+#define __UM_SYSCALL_GENERIC_H
+
+#include <asm/ptrace.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <sysdep/ptrace.h>
+
+static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
+{
+
+	return PT_REGS_SYSCALL_NR(regs);
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	/* do nothing */
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	const long error = regs_return_value(regs);
+
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs_return_value(regs);
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	PT_REGS_SET_SYSCALL_RETURN(regs, (long) error ?: val);
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	const struct uml_pt_regs *r = &regs->regs;
+
+	switch (i) {
+	case 0:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG1(r);
+	case 1:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG2(r);
+	case 2:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG3(r);
+	case 3:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG4(r);
+	case 4:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG5(r);
+	case 5:
+		if (!n--)
+			break;
+		*args++ = UPT_SYSCALL_ARG6(r);
+	case 6:
+		if (!n--)
+			break;
+	default:
+		BUG();
+		break;
+	}
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	struct uml_pt_regs *r = &regs->regs;
+
+	switch (i) {
+	case 0:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG1(r) = *args++;
+	case 1:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG2(r) = *args++;
+	case 2:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG3(r) = *args++;
+	case 3:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG4(r) = *args++;
+	case 4:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG5(r) = *args++;
+	case 5:
+		if (!n--)
+			break;
+		UPT_SYSCALL_ARG6(r) = *args++;
+	case 6:
+		if (!n--)
+			break;
+	default:
+		BUG();
+		break;
+	}
+}
+
+/* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */
+
+#endif	/* __UM_SYSCALL_GENERIC_H */

arch/um/include/asm/thread_info.h

@@ -62,11 +62,13 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_AUDIT	6
 #define TIF_RESTORE_SIGMASK	7
 #define TIF_NOTIFY_RESUME	8
+#define TIF_SECCOMP		9	/* secure computing */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_MEMDIE		(1 << TIF_MEMDIE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 
 #endif

arch/um/include/shared/os.h

@@ -146,6 +146,8 @@ extern int os_read_file(int fd, void *buf, int len);
 extern int os_write_file(int fd, const void *buf, int count);
 extern int os_sync_file(int fd);
 extern int os_file_size(const char *file, unsigned long long *size_out);
+extern int os_pread_file(int fd, void *buf, int len, unsigned long long offset);
+extern int os_pwrite_file(int fd, const void *buf, int count, unsigned long long offset);
 extern int os_file_modtime(const char *file, unsigned long *modtime);
 extern int os_pipe(int *fd, int stream, int close_on_exec);
 extern int os_set_fd_async(int fd);
@@ -282,7 +284,6 @@ extern void initial_thread_cb_skas(void (*proc)(void *),
 				 void *arg);
 extern void halt_skas(void);
 extern void reboot_skas(void);
-extern int get_syscall(struct uml_pt_regs *regs);
 
 /* irq.c */
 extern int os_waiting_for_events(struct irq_fd *active_fds);

arch/um/kernel/skas/syscall.c

@@ -5,31 +5,38 @@
 
 #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 <sysdep/syscalls.h>
-#include <os.h>
 
 void handle_syscall(struct uml_pt_regs *r)
 {
 	struct pt_regs *regs = container_of(r, struct pt_regs, regs);
-	long result;
 	int syscall;
 
-	if (syscall_trace_enter(regs)) {
-		result = -ENOSYS;
+	/* Initialize the syscall number and default return value. */
+	UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
+	PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS);
+
+	/* Do the secure computing check first; failures should be fast. */
+	if (secure_computing() == -1)
+		return;
+
+	if (syscall_trace_enter(regs))
 		goto out;
-	}
 
-	syscall = get_syscall(r);
+	/* Update the syscall number after orig_ax has potentially been updated
+	 * with ptrace.
+	 */
+	UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
+	syscall = UPT_SYSCALL_NR(r);
 
-	if ((syscall > __NR_syscall_max) || syscall < 0)
-		result = -ENOSYS;
-	else
-		result = EXECUTE_SYSCALL(syscall, regs);
+	if (syscall >= 0 && syscall <= __NR_syscall_max)
+		PT_REGS_SET_SYSCALL_RETURN(regs,
+				EXECUTE_SYSCALL(syscall, regs));
 
 out:
-	PT_REGS_SET_SYSCALL_RETURN(regs, result);
-
 	syscall_trace_leave(regs);
 }

arch/um/os-Linux/file.c

@@ -264,6 +264,15 @@ int os_read_file(int fd, void *buf, int len)
 	return n;
 }
 
+int os_pread_file(int fd, void *buf, int len, unsigned long long offset)
+{
+	int n = pread(fd, buf, len, offset);
+
+	if (n < 0)
+		return -errno;
+	return n;
+}
+
 int os_write_file(int fd, const void *buf, int len)
 {
 	int n = write(fd, (void *) buf, len);
@@ -282,6 +291,16 @@ int os_sync_file(int fd)
 	return n;
 }
 
+int os_pwrite_file(int fd, const void *buf, int len, unsigned long long offset)
+{
+	int n = pwrite(fd, (void *) buf, len, offset);
+
+	if (n < 0)
+		return -errno;
+	return n;
+}
+
+
 int os_file_size(const char *file, unsigned long long *size_out)
 {
 	struct uml_stat buf;

arch/um/os-Linux/mem.c

@@ -106,6 +106,17 @@ static int __init make_tempfile(const char *template)
 		}
 	}
 
+#ifdef O_TMPFILE
+	fd = open(tempdir, O_CLOEXEC | O_RDWR | O_EXCL | O_TMPFILE, 0700);
+	/*
+	 * If the running system does not support O_TMPFILE flag then retry
+	 * without it.
+	 */
+	if (fd != -1 || (errno != EINVAL && errno != EISDIR &&
+			errno != EOPNOTSUPP))
+		return fd;
+#endif
+
 	tempname = malloc(strlen(tempdir) + strlen(template) + 1);
 	if (tempname == NULL)
 		return -1;
@@ -142,12 +153,6 @@ static int __init create_tmp_file(unsigned long long len)
 	if (fd < 0)
 		exit(1);
 
-	err = fchmod(fd, 0777);
-	if (err < 0) {
-		perror("fchmod");
-		exit(1);
-	}
-
 	/*
 	 * Seek to len - 1 because writing a character there will
 	 * increase the file size by one byte, to the desired length.

arch/um/os-Linux/signal.c

@@ -62,6 +62,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
 
 static int signals_enabled;
 static unsigned int signals_pending;
+static unsigned int signals_active = 0;
 
 void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
 {
@@ -101,7 +102,12 @@ void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc)
 
 	block_signals();
 
+	signals_active |= SIGALRM_MASK;
+
 	timer_real_alarm_handler(mc);
+
+	signals_active &= ~SIGALRM_MASK;
+
 	set_signals(enabled);
 }
 
@@ -286,8 +292,16 @@ void unblock_signals(void)
 		if (save_pending & SIGIO_MASK)
 			sig_handler_common(SIGIO, NULL, NULL);
 
-		if (save_pending & SIGALRM_MASK)
+		/* Do not reenter the handler */
+
+		if ((save_pending & SIGALRM_MASK) && (!(signals_active & SIGALRM_MASK)))
 			timer_real_alarm_handler(NULL);
+
+		/* Rerun the loop only if there is still pending SIGIO and not in TIMER handler */
+
+		if (!(signals_pending & SIGIO_MASK) && (signals_active & SIGALRM_MASK))
+			return;
+
 	}
 }
 

arch/um/os-Linux/skas/process.c

@@ -172,13 +172,6 @@ static void handle_trap(int pid, struct uml_pt_regs *regs,
 	handle_syscall(regs);
 }
 
-int get_syscall(struct uml_pt_regs *regs)
-{
-	UPT_SYSCALL_NR(regs) = PT_SYSCALL_NR(regs->gp);
-
-	return UPT_SYSCALL_NR(regs);
-}
-
 extern char __syscall_stub_start[];
 
 static int userspace_tramp(void *stack)

arch/um/os-Linux/start_up.c

@@ -94,6 +94,8 @@ static int start_ptraced_child(void)
 {
 	int pid, n, status;
 
+	fflush(stdout);
+
 	pid = fork();
 	if (pid == 0)
 		ptrace_child();

arch/x86/um/Makefile

@@ -17,7 +17,7 @@ obj-y = bug.o bugs_$(BITS).o delay.o fault.o ksyms.o ldt.o \
 ifeq ($(CONFIG_X86_32),y)
 
 obj-y += checksum_32.o
-obj-$(CONFIG_BINFMT_ELF) += elfcore.o
+obj-$(CONFIG_ELF_CORE) += elfcore.o
 
 subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
 subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o

arch/x86/um/asm/syscall.h

@@ -1,6 +1,7 @@
 #ifndef __UM_ASM_SYSCALL_H
 #define __UM_ASM_SYSCALL_H
 
+#include <asm/syscall-generic.h>
 #include <uapi/linux/audit.h>
 
 typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,

arch/x86/um/ptrace_32.c

@@ -68,6 +68,7 @@ static const int reg_offsets[] = {
 	[EFL] = HOST_EFLAGS,
 	[UESP] = HOST_SP,
 	[SS] = HOST_SS,
+	[ORIG_EAX] = HOST_ORIG_AX,
 };
 
 int putreg(struct task_struct *child, int regno, unsigned long value)
@@ -83,6 +84,7 @@ int putreg(struct task_struct *child, int regno, unsigned long value)
 	case EAX:
 	case EIP:
 	case UESP:
+	case ORIG_EAX:
 		break;
 	case FS:
 		if (value && (value & 3) != 3)
@@ -108,9 +110,6 @@ int putreg(struct task_struct *child, int regno, unsigned long value)
 		value &= FLAG_MASK;
 		child->thread.regs.regs.gp[HOST_EFLAGS] |= value;
 		return 0;
-	case ORIG_EAX:
-		child->thread.regs.regs.syscall = value;
-		return 0;
 	default :
 		panic("Bad register in putreg() : %d\n", regno);
 	}
@@ -143,8 +142,6 @@ unsigned long getreg(struct task_struct *child, int regno)
 
 	regno >>= 2;
 	switch (regno) {
-	case ORIG_EAX:
-		return child->thread.regs.regs.syscall;
 	case FS:
 	case GS:
 	case DS:
@@ -163,6 +160,7 @@ unsigned long getreg(struct task_struct *child, int regno)
 	case EDI:
 	case EBP:
 	case EFL:
+	case ORIG_EAX:
 		break;
 	default:
 		panic("Bad register in getreg() : %d\n", regno);

fs/hostfs/hostfs_kern.c

@@ -730,15 +730,13 @@ static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	init_special_inode(inode, mode, dev);
 	err = do_mknod(name, mode, MAJOR(dev), MINOR(dev));
-	if (!err)
+	if (err)
 		goto out_free;
 
 	err = read_name(inode, name);
 	__putname(name);
 	if (err)
 		goto out_put;
-	if (err)
-		goto out_put;
 
 	d_instantiate(dentry, inode);
 	return 0;

scripts/link-vmlinux.sh

@@ -62,7 +62,7 @@ vmlinux_link()
 			-Wl,--start-group                                    \
 				 ${KBUILD_VMLINUX_MAIN}                      \
 			-Wl,--end-group                                      \
-			-lutil -lrt ${1}
+			-lutil -lrt -lpthread ${1}
 		rm -f linux
 	fi
 }

tools/testing/selftests/seccomp/seccomp_bpf.c

@@ -1246,11 +1246,24 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 # error "Do not know how to find your architecture's registers and syscalls"
 #endif
 
+/* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
+ * architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux).
+ */
+#if defined(__x86_64__) || defined(__i386__)
+#define HAVE_GETREGS
+#endif
+
 /* Architecture-specific syscall fetching routine. */
 int get_syscall(struct __test_metadata *_metadata, pid_t tracee)
 {
-	struct iovec iov;
 	ARCH_REGS regs;
+#ifdef HAVE_GETREGS
+	EXPECT_EQ(0, ptrace(PTRACE_GETREGS, tracee, 0, &regs)) {
+		TH_LOG("PTRACE_GETREGS failed");
+		return -1;
+	}
+#else
+	struct iovec iov;
 
 	iov.iov_base = &regs;
 	iov.iov_len = sizeof(regs);
@@ -1258,6 +1271,7 @@ int get_syscall(struct __test_metadata *_metadata, pid_t tracee)
 		TH_LOG("PTRACE_GETREGSET failed");
 		return -1;
 	}
+#endif
 
 	return regs.SYSCALL_NUM;
 }
@@ -1266,13 +1280,16 @@ int get_syscall(struct __test_metadata *_metadata, pid_t tracee)
 void change_syscall(struct __test_metadata *_metadata,
 		    pid_t tracee, int syscall)
 {
-	struct iovec iov;
 	int ret;
 	ARCH_REGS regs;
-
+#ifdef HAVE_GETREGS
+	ret = ptrace(PTRACE_GETREGS, tracee, 0, &regs);
+#else
+	struct iovec iov;
 	iov.iov_base = &regs;
 	iov.iov_len = sizeof(regs);
 	ret = ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov);
+#endif
 	EXPECT_EQ(0, ret);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__powerpc__) || \
@@ -1312,9 +1329,13 @@ void change_syscall(struct __test_metadata *_metadata,
 	if (syscall == -1)
 		regs.SYSCALL_RET = 1;
 
+#ifdef HAVE_GETREGS
+	ret = ptrace(PTRACE_SETREGS, tracee, 0, &regs);
+#else
 	iov.iov_base = &regs;
 	iov.iov_len = sizeof(regs);
 	ret = ptrace(PTRACE_SETREGSET, tracee, NT_PRSTATUS, &iov);
+#endif
 	EXPECT_EQ(0, ret);
 }