aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/devicetree/bindings/virtio/mmio.txt17
-rw-r--r--Documentation/filesystems/Locking1
-rw-r--r--Documentation/filesystems/ext3.txt8
-rw-r--r--Documentation/filesystems/ext4.txt41
-rw-r--r--Documentation/virtual/uml/UserModeLinux-HOWTO.txt532
-rw-r--r--MAINTAINERS1
-rw-r--r--arch/s390/hypfs/inode.c6
-rw-r--r--arch/um/Kconfig.char114
-rw-r--r--arch/um/Kconfig.rest23
-rw-r--r--arch/um/Kconfig.um6
-rw-r--r--arch/um/Makefile49
-rw-r--r--arch/um/Makefile-x86_6426
-rw-r--r--arch/um/drivers/chan.h (renamed from arch/um/include/shared/chan_kern.h)6
-rw-r--r--arch/um/drivers/chan_kern.c12
-rw-r--r--arch/um/drivers/chan_user.c9
-rw-r--r--arch/um/drivers/chan_user.h (renamed from arch/um/include/shared/chan_user.h)0
-rw-r--r--arch/um/drivers/cow_sys.h1
-rw-r--r--arch/um/drivers/daemon_user.c1
-rw-r--r--arch/um/drivers/fd.c2
-rw-r--r--arch/um/drivers/harddog_user.c1
-rw-r--r--arch/um/drivers/line.c2
-rw-r--r--arch/um/drivers/line.h (renamed from arch/um/include/shared/line.h)0
-rw-r--r--arch/um/drivers/mconsole.h (renamed from arch/um/include/shared/mconsole.h)0
-rw-r--r--arch/um/drivers/mconsole_kern.h (renamed from arch/um/include/shared/mconsole_kern.h)0
-rw-r--r--arch/um/drivers/mconsole_user.c2
-rw-r--r--arch/um/drivers/net_user.c2
-rw-r--r--arch/um/drivers/pcap_user.c2
-rw-r--r--arch/um/drivers/port_user.c2
-rw-r--r--arch/um/drivers/pty.c2
-rw-r--r--arch/um/drivers/slip_user.c2
-rw-r--r--arch/um/drivers/slirp_user.c2
-rw-r--r--arch/um/drivers/ssl.c4
-rw-r--r--arch/um/drivers/stdio_console.c3
-rw-r--r--arch/um/drivers/tty.c2
-rw-r--r--arch/um/drivers/ubd_kern.c33
-rw-r--r--arch/um/drivers/ubd_user.c1
-rw-r--r--arch/um/drivers/ubd_user.h (renamed from arch/um/include/shared/ubd_user.h)0
-rw-r--r--arch/um/drivers/umcast_user.c2
-rw-r--r--arch/um/drivers/vde_user.c2
-rw-r--r--arch/um/drivers/xterm.c2
-rw-r--r--arch/um/include/asm/Kbuild3
-rw-r--r--arch/um/include/asm/bug.h6
-rw-r--r--arch/um/include/asm/checksum.h6
-rw-r--r--arch/um/include/asm/cputime.h6
-rw-r--r--arch/um/include/asm/device.h7
-rw-r--r--arch/um/include/asm/emergency-restart.h6
-rw-r--r--arch/um/include/asm/ftrace.h1
-rw-r--r--arch/um/include/asm/futex.h6
-rw-r--r--arch/um/include/asm/hardirq.h1
-rw-r--r--arch/um/include/asm/hw_irq.h7
-rw-r--r--arch/um/include/asm/irq_regs.h1
-rw-r--r--arch/um/include/asm/irqflags.h38
-rw-r--r--arch/um/include/asm/kdebug.h1
-rw-r--r--arch/um/include/asm/mmu.h22
-rw-r--r--arch/um/include/asm/mmu_context.h7
-rw-r--r--arch/um/include/asm/page.h2
-rw-r--r--arch/um/include/asm/page_offset.h1
-rw-r--r--arch/um/include/asm/pda.h21
-rw-r--r--arch/um/include/asm/percpu.h6
-rw-r--r--arch/um/include/asm/ptrace-generic.h7
-rw-r--r--arch/um/include/asm/sections.h7
-rw-r--r--arch/um/include/asm/system.h47
-rw-r--r--arch/um/include/asm/topology.h6
-rw-r--r--arch/um/include/asm/uaccess.h89
-rw-r--r--arch/um/include/asm/xor.h6
-rw-r--r--arch/um/include/shared/as-layout.h2
-rw-r--r--arch/um/include/shared/common-offsets.h1
-rw-r--r--arch/um/include/shared/initrd.h12
-rw-r--r--arch/um/include/shared/kern.h18
-rw-r--r--arch/um/include/shared/kern_util.h1
-rw-r--r--arch/um/include/shared/ldt.h37
-rw-r--r--arch/um/include/shared/mem_kern.h20
-rw-r--r--arch/um/include/shared/os.h13
-rw-r--r--arch/um/include/shared/process.h17
-rw-r--r--arch/um/include/shared/ptrace_user.h3
-rw-r--r--arch/um/include/shared/skas_ptregs.h6
-rw-r--r--arch/um/include/shared/syscall.h12
-rw-r--r--arch/um/include/shared/task.h9
-rw-r--r--arch/um/include/shared/tlb.h15
-rw-r--r--arch/um/include/shared/um_malloc.h2
-rw-r--r--arch/um/include/shared/um_mmu.h24
-rw-r--r--arch/um/include/shared/um_uaccess.h97
-rw-r--r--arch/um/include/shared/user.h7
-rw-r--r--arch/um/kernel/Makefile2
-rw-r--r--arch/um/kernel/exec.c18
-rw-r--r--arch/um/kernel/gmon_syms.c15
-rw-r--r--arch/um/kernel/initrd.c4
-rw-r--r--arch/um/kernel/irq.c1
-rw-r--r--arch/um/kernel/ksyms.c38
-rw-r--r--arch/um/kernel/mem.c2
-rw-r--r--arch/um/kernel/physmem.c21
-rw-r--r--arch/um/kernel/process.c4
-rw-r--r--arch/um/kernel/signal.c1
-rw-r--r--arch/um/kernel/skas/clone.c1
-rw-r--r--arch/um/kernel/skas/uaccess.c6
-rw-r--r--arch/um/kernel/tlb.c5
-rw-r--r--arch/um/kernel/trap.c3
-rw-r--r--arch/um/kernel/uaccess.c33
-rw-r--r--arch/um/kernel/um_arch.c2
-rw-r--r--arch/um/os-Linux/Makefile6
-rw-r--r--arch/um/os-Linux/aio.c2
-rw-r--r--arch/um/os-Linux/drivers/ethertap_user.c2
-rw-r--r--arch/um/os-Linux/drivers/tuntap_user.c2
-rw-r--r--arch/um/os-Linux/elf_aux.c1
-rw-r--r--arch/um/os-Linux/file.c2
-rw-r--r--arch/um/os-Linux/helper.c2
-rw-r--r--arch/um/os-Linux/internal.h1
-rw-r--r--arch/um/os-Linux/irq.c3
-rw-r--r--arch/um/os-Linux/main.c1
-rw-r--r--arch/um/os-Linux/mem.c2
-rw-r--r--arch/um/os-Linux/process.c23
-rw-r--r--arch/um/os-Linux/sigio.c3
-rw-r--r--arch/um/os-Linux/signal.c72
-rw-r--r--arch/um/os-Linux/skas/mem.c2
-rw-r--r--arch/um/os-Linux/skas/process.c21
-rw-r--r--arch/um/os-Linux/start_up.c10
-rw-r--r--arch/um/os-Linux/sys-i386/signal.c13
-rw-r--r--arch/um/os-Linux/sys-x86_64/Makefile10
-rw-r--r--arch/um/os-Linux/sys-x86_64/registers.c52
-rw-r--r--arch/um/os-Linux/sys-x86_64/signal.c16
-rw-r--r--arch/um/os-Linux/sys-x86_64/task_size.c5
-rw-r--r--arch/um/os-Linux/time.c4
-rw-r--r--arch/um/os-Linux/tls.c35
-rw-r--r--arch/um/os-Linux/tty.c2
-rw-r--r--arch/um/os-Linux/uaccess.c32
-rw-r--r--arch/um/os-Linux/umid.c2
-rw-r--r--arch/um/os-Linux/util.c2
-rw-r--r--arch/um/scripts/Makefile.rules7
-rw-r--r--arch/um/sys-i386/Makefile24
-rw-r--r--arch/um/sys-i386/asm/elf.h125
-rw-r--r--arch/um/sys-i386/asm/module.h13
-rw-r--r--arch/um/sys-i386/atomic64_cx8_32.S225
-rw-r--r--arch/um/sys-i386/bug.c21
-rw-r--r--arch/um/sys-i386/ksyms.c5
-rw-r--r--arch/um/sys-i386/shared/sysdep/barrier.h9
-rw-r--r--arch/um/sys-i386/shared/sysdep/host_ldt.h34
-rw-r--r--arch/um/sys-i386/shared/sysdep/ptrace_user.h50
-rw-r--r--arch/um/sys-i386/shared/sysdep/sc.h44
-rw-r--r--arch/um/sys-i386/shared/sysdep/sigcontext.h26
-rw-r--r--arch/um/sys-i386/shared/sysdep/vm-flags.h14
-rw-r--r--arch/um/sys-i386/stub_segv.c17
-rw-r--r--arch/um/sys-i386/user-offsets.c53
-rw-r--r--arch/um/sys-x86_64/Makefile27
-rw-r--r--arch/um/sys-x86_64/asm/archparam.h16
-rw-r--r--arch/um/sys-x86_64/asm/module.h20
-rw-r--r--arch/um/sys-x86_64/delay.c60
-rw-r--r--arch/um/sys-x86_64/fault.c28
-rw-r--r--arch/um/sys-x86_64/ptrace_user.c22
-rw-r--r--arch/um/sys-x86_64/shared/sysdep/barrier.h7
-rw-r--r--arch/um/sys-x86_64/shared/sysdep/host_ldt.h38
-rw-r--r--arch/um/sys-x86_64/shared/sysdep/kernel-offsets.h23
-rw-r--r--arch/um/sys-x86_64/shared/sysdep/ptrace_user.h77
-rw-r--r--arch/um/sys-x86_64/shared/sysdep/sc.h45
-rw-r--r--arch/um/sys-x86_64/shared/sysdep/sigcontext.h27
-rw-r--r--arch/um/sys-x86_64/shared/sysdep/skas_ptrace.h22
-rw-r--r--arch/um/sys-x86_64/shared/sysdep/system.h132
-rw-r--r--arch/um/sys-x86_64/shared/sysdep/tls.h29
-rw-r--r--arch/um/sys-x86_64/signal.c290
-rw-r--r--arch/x86/Makefile.um (renamed from arch/um/Makefile-i386)37
-rw-r--r--arch/x86/um/Kconfig (renamed from arch/um/Kconfig.x86)0
-rw-r--r--arch/x86/um/Makefile45
-rw-r--r--arch/x86/um/asm/apic.h (renamed from arch/um/include/asm/apic.h)0
-rw-r--r--arch/x86/um/asm/arch_hweight.h (renamed from arch/um/include/asm/arch_hweight.h)0
-rw-r--r--arch/x86/um/asm/archparam.h (renamed from arch/um/sys-i386/asm/archparam.h)8
-rw-r--r--arch/x86/um/asm/checksum.h10
-rw-r--r--arch/x86/um/asm/checksum_32.h (renamed from arch/um/sys-i386/shared/sysdep/checksum.h)2
-rw-r--r--arch/x86/um/asm/checksum_64.h (renamed from arch/um/sys-x86_64/shared/sysdep/checksum.h)0
-rw-r--r--arch/x86/um/asm/desc.h (renamed from arch/um/include/asm/desc.h)0
-rw-r--r--arch/x86/um/asm/elf.h (renamed from arch/um/sys-x86_64/asm/elf.h)145
-rw-r--r--arch/x86/um/asm/irq_vectors.h (renamed from arch/um/include/asm/irq_vectors.h)0
-rw-r--r--arch/x86/um/asm/mm_context.h72
-rw-r--r--arch/x86/um/asm/module.h23
-rw-r--r--arch/x86/um/asm/processor.h22
-rw-r--r--arch/x86/um/asm/processor_32.h (renamed from arch/um/sys-i386/asm/processor.h)18
-rw-r--r--arch/x86/um/asm/processor_64.h (renamed from arch/um/sys-x86_64/asm/processor.h)11
-rw-r--r--arch/x86/um/asm/ptrace.h5
-rw-r--r--arch/x86/um/asm/ptrace_32.h (renamed from arch/um/sys-i386/asm/ptrace.h)0
-rw-r--r--arch/x86/um/asm/ptrace_64.h (renamed from arch/um/sys-x86_64/asm/ptrace.h)2
-rw-r--r--arch/x86/um/asm/required-features.h (renamed from arch/um/include/asm/required-features.h)0
-rw-r--r--arch/x86/um/asm/segment.h (renamed from arch/um/include/asm/segment.h)0
-rw-r--r--arch/x86/um/asm/system.h (renamed from arch/um/sys-i386/shared/sysdep/system.h)3
-rw-r--r--arch/x86/um/asm/vm-flags.h (renamed from arch/um/sys-x86_64/shared/sysdep/vm-flags.h)14
-rw-r--r--arch/x86/um/bug.c (renamed from arch/um/sys-x86_64/bug.c)0
-rw-r--r--arch/x86/um/bugs_32.c (renamed from arch/um/sys-i386/bugs.c)6
-rw-r--r--arch/x86/um/bugs_64.c (renamed from arch/um/sys-x86_64/bugs.c)0
-rw-r--r--arch/x86/um/checksum_32.S (renamed from arch/um/sys-i386/checksum.S)0
-rw-r--r--arch/x86/um/delay.c (renamed from arch/um/sys-i386/delay.c)0
-rw-r--r--arch/x86/um/elfcore.c (renamed from arch/um/sys-i386/elfcore.c)0
-rw-r--r--arch/x86/um/fault.c (renamed from arch/um/sys-i386/fault.c)0
-rw-r--r--arch/x86/um/ksyms.c (renamed from arch/um/sys-x86_64/ksyms.c)2
-rw-r--r--arch/x86/um/ldt.c (renamed from arch/um/sys-i386/ldt.c)36
-rw-r--r--arch/x86/um/mem_32.c (renamed from arch/um/sys-i386/mem.c)0
-rw-r--r--arch/x86/um/mem_64.c (renamed from arch/um/sys-x86_64/mem.c)0
-rw-r--r--arch/x86/um/os-Linux/Makefile (renamed from arch/um/os-Linux/sys-i386/Makefile)5
-rw-r--r--arch/x86/um/os-Linux/mcontext.c31
-rw-r--r--arch/x86/um/os-Linux/prctl.c (renamed from arch/um/os-Linux/sys-x86_64/prctl.c)0
-rw-r--r--arch/x86/um/os-Linux/registers.c (renamed from arch/um/os-Linux/sys-i386/registers.c)62
-rw-r--r--arch/x86/um/os-Linux/task_size.c (renamed from arch/um/os-Linux/sys-i386/task_size.c)13
-rw-r--r--arch/x86/um/os-Linux/tls.c (renamed from arch/um/os-Linux/sys-i386/tls.c)35
-rw-r--r--arch/x86/um/ptrace_32.c (renamed from arch/um/sys-i386/ptrace.c)69
-rw-r--r--arch/x86/um/ptrace_64.c (renamed from arch/um/sys-x86_64/ptrace.c)103
-rw-r--r--arch/x86/um/ptrace_user.c (renamed from arch/um/sys-i386/ptrace_user.c)2
-rw-r--r--arch/x86/um/setjmp_32.S (renamed from arch/um/sys-i386/setjmp.S)0
-rw-r--r--arch/x86/um/setjmp_64.S (renamed from arch/um/sys-x86_64/setjmp.S)0
-rw-r--r--arch/x86/um/shared/sysdep/archsetjmp.h5
-rw-r--r--arch/x86/um/shared/sysdep/archsetjmp_32.h (renamed from arch/um/sys-i386/shared/sysdep/archsetjmp.h)0
-rw-r--r--arch/x86/um/shared/sysdep/archsetjmp_64.h (renamed from arch/um/sys-x86_64/shared/sysdep/archsetjmp.h)0
-rw-r--r--arch/x86/um/shared/sysdep/faultinfo.h5
-rw-r--r--arch/x86/um/shared/sysdep/faultinfo_32.h (renamed from arch/um/sys-i386/shared/sysdep/faultinfo.h)6
-rw-r--r--arch/x86/um/shared/sysdep/faultinfo_64.h (renamed from arch/um/sys-x86_64/shared/sysdep/faultinfo.h)6
-rw-r--r--arch/x86/um/shared/sysdep/kernel-offsets.h (renamed from arch/um/sys-i386/shared/sysdep/kernel-offsets.h)0
-rw-r--r--arch/x86/um/shared/sysdep/mcontext.h31
-rw-r--r--arch/x86/um/shared/sysdep/ptrace.h5
-rw-r--r--arch/x86/um/shared/sysdep/ptrace_32.h (renamed from arch/um/sys-i386/shared/sysdep/ptrace.h)75
-rw-r--r--arch/x86/um/shared/sysdep/ptrace_64.h (renamed from arch/um/sys-x86_64/shared/sysdep/ptrace.h)103
-rw-r--r--arch/x86/um/shared/sysdep/ptrace_user.h27
-rw-r--r--arch/x86/um/shared/sysdep/skas_ptrace.h (renamed from arch/um/sys-i386/shared/sysdep/skas_ptrace.h)4
-rw-r--r--arch/x86/um/shared/sysdep/stub.h14
-rw-r--r--arch/x86/um/shared/sysdep/stub_32.h (renamed from arch/um/sys-i386/shared/sysdep/stub.h)8
-rw-r--r--arch/x86/um/shared/sysdep/stub_64.h (renamed from arch/um/sys-x86_64/shared/sysdep/stub.h)8
-rw-r--r--arch/x86/um/shared/sysdep/syscalls.h5
-rw-r--r--arch/x86/um/shared/sysdep/syscalls_32.h (renamed from arch/um/sys-i386/shared/sysdep/syscalls.h)0
-rw-r--r--arch/x86/um/shared/sysdep/syscalls_64.h (renamed from arch/um/sys-x86_64/shared/sysdep/syscalls.h)1
-rw-r--r--arch/x86/um/shared/sysdep/tls.h (renamed from arch/um/sys-i386/shared/sysdep/tls.h)9
-rw-r--r--arch/x86/um/signal.c (renamed from arch/um/sys-i386/signal.c)304
-rw-r--r--arch/x86/um/stub_32.S (renamed from arch/um/sys-i386/stub.S)0
-rw-r--r--arch/x86/um/stub_64.S (renamed from arch/um/sys-x86_64/stub.S)0
-rw-r--r--arch/x86/um/stub_segv.c (renamed from arch/um/sys-x86_64/stub_segv.c)11
-rw-r--r--arch/x86/um/sys_call_table_32.S (renamed from arch/um/sys-i386/sys_call_table.S)4
-rw-r--r--arch/x86/um/sys_call_table_64.c (renamed from arch/um/sys-x86_64/syscall_table.c)3
-rw-r--r--arch/x86/um/syscalls_32.c (renamed from arch/um/sys-i386/syscalls.c)0
-rw-r--r--arch/x86/um/syscalls_64.c (renamed from arch/um/sys-x86_64/syscalls.c)0
-rw-r--r--arch/x86/um/sysrq_32.c (renamed from arch/um/sys-i386/sysrq.c)0
-rw-r--r--arch/x86/um/sysrq_64.c (renamed from arch/um/sys-x86_64/sysrq.c)2
-rw-r--r--arch/x86/um/tls_32.c (renamed from arch/um/sys-i386/tls.c)0
-rw-r--r--arch/x86/um/tls_64.c (renamed from arch/um/sys-x86_64/tls.c)0
-rw-r--r--arch/x86/um/user-offsets.c (renamed from arch/um/sys-x86_64/user-offsets.c)51
-rw-r--r--arch/x86/um/vdso/Makefile (renamed from arch/um/sys-x86_64/vdso/Makefile)4
-rw-r--r--arch/x86/um/vdso/checkundef.sh (renamed from arch/um/sys-x86_64/vdso/checkundef.sh)0
-rw-r--r--arch/x86/um/vdso/um_vdso.c (renamed from arch/um/sys-x86_64/vdso/um_vdso.c)0
-rw-r--r--arch/x86/um/vdso/vdso-layout.lds.S (renamed from arch/um/sys-x86_64/vdso/vdso-layout.lds.S)0
-rw-r--r--arch/x86/um/vdso/vdso-note.S (renamed from arch/um/sys-x86_64/vdso/vdso-note.S)0
-rw-r--r--arch/x86/um/vdso/vdso.S (renamed from arch/um/sys-x86_64/vdso/vdso.S)2
-rw-r--r--arch/x86/um/vdso/vdso.lds.S (renamed from arch/um/sys-x86_64/vdso/vdso.lds.S)0
-rw-r--r--arch/x86/um/vdso/vma.c (renamed from arch/um/sys-x86_64/vdso/vma.c)2
-rw-r--r--drivers/block/virtio_blk.c30
-rw-r--r--drivers/char/Kconfig6
-rw-r--r--drivers/char/hw_random/Kconfig15
-rw-r--r--drivers/char/ttyprintk.c2
-rw-r--r--drivers/char/virtio_console.c120
-rw-r--r--drivers/input/Kconfig2
-rw-r--r--drivers/isdn/Kconfig2
-rw-r--r--drivers/mtd/mtdchar.c2
-rw-r--r--drivers/net/virtio_net.c14
-rw-r--r--drivers/net/wireless/ath/Kconfig2
-rw-r--r--drivers/net/wireless/rtlwifi/Kconfig4
-rw-r--r--drivers/power/Kconfig1
-rw-r--r--drivers/rtc/Kconfig2
-rw-r--r--drivers/staging/pohmelfs/inode.c2
-rw-r--r--drivers/tty/Kconfig2
-rw-r--r--drivers/virtio/Kconfig11
-rw-r--r--drivers/virtio/Makefile1
-rw-r--r--drivers/virtio/virtio_mmio.c479
-rw-r--r--drivers/virtio/virtio_pci.c10
-rw-r--r--drivers/watchdog/Kconfig6
-rw-r--r--fs/9p/vfs_inode.c4
-rw-r--r--fs/9p/vfs_inode_dotl.c4
-rw-r--r--fs/adfs/inode.c2
-rw-r--r--fs/affs/amigaffs.c4
-rw-r--r--fs/affs/inode.c8
-rw-r--r--fs/affs/namei.c6
-rw-r--r--fs/afs/fsclient.c2
-rw-r--r--fs/afs/inode.c4
-rw-r--r--fs/autofs4/inode.c2
-rw-r--r--fs/befs/linuxvfs.c2
-rw-r--r--fs/bfs/dir.c2
-rw-r--r--fs/bfs/inode.c2
-rw-r--r--fs/binfmt_misc.c2
-rw-r--r--fs/btrfs/delayed-inode.c2
-rw-r--r--fs/btrfs/disk-io.c2
-rw-r--r--fs/btrfs/inode.c4
-rw-r--r--fs/btrfs/tree-log.c2
-rw-r--r--fs/ceph/caps.c2
-rw-r--r--fs/ceph/inode.c2
-rw-r--r--fs/cifs/inode.c6
-rw-r--r--fs/cifs/link.c2
-rw-r--r--fs/coda/coda_linux.c2
-rw-r--r--fs/coda/dir.c2
-rw-r--r--fs/dcache.c40
-rw-r--r--fs/devpts/inode.c4
-rw-r--r--fs/ecryptfs/inode.c12
-rw-r--r--fs/efs/inode.c2
-rw-r--r--fs/exofs/inode.c2
-rw-r--r--fs/ext2/balloc.c2
-rw-r--r--fs/ext2/ialloc.c2
-rw-r--r--fs/ext2/inode.c2
-rw-r--r--fs/ext2/super.c8
-rw-r--r--fs/ext3/balloc.c17
-rw-r--r--fs/ext3/fsync.c10
-rw-r--r--fs/ext3/ialloc.c47
-rw-r--r--fs/ext3/inode.c2
-rw-r--r--fs/ext3/ioctl.c24
-rw-r--r--fs/ext3/namei.c6
-rw-r--r--fs/ext3/super.c12
-rw-r--r--fs/ext4/balloc.c345
-rw-r--r--fs/ext4/ext4.h141
-rw-r--r--fs/ext4/ext4_extents.h2
-rw-r--r--fs/ext4/ext4_jbd2.c8
-rw-r--r--fs/ext4/extents.c1168
-rw-r--r--fs/ext4/file.c4
-rw-r--r--fs/ext4/fsync.c10
-rw-r--r--fs/ext4/ialloc.c206
-rw-r--r--fs/ext4/indirect.c20
-rw-r--r--fs/ext4/inode.c514
-rw-r--r--fs/ext4/ioctl.c65
-rw-r--r--fs/ext4/mballoc.c331
-rw-r--r--fs/ext4/mballoc.h11
-rw-r--r--fs/ext4/migrate.c111
-rw-r--r--fs/ext4/mmp.c10
-rw-r--r--fs/ext4/move_extent.c1
-rw-r--r--fs/ext4/namei.c29
-rw-r--r--fs/ext4/page-io.c66
-rw-r--r--fs/ext4/resize.c10
-rw-r--r--fs/ext4/super.c263
-rw-r--r--fs/ext4/xattr.c12
-rw-r--r--fs/fat/inode.c4
-rw-r--r--fs/fat/namei_msdos.c2
-rw-r--r--fs/fat/namei_vfat.c2
-rw-r--r--fs/freevxfs/vxfs_inode.c2
-rw-r--r--fs/fuse/control.c2
-rw-r--r--fs/fuse/inode.c2
-rw-r--r--fs/gfs2/glops.c2
-rw-r--r--fs/hfs/dir.c4
-rw-r--r--fs/hfs/inode.c4
-rw-r--r--fs/hfsplus/dir.c4
-rw-r--r--fs/hfsplus/inode.c10
-rw-r--r--fs/hostfs/hostfs_kern.c2
-rw-r--r--fs/hostfs/hostfs_user.c1
-rw-r--r--fs/hpfs/dir.c2
-rw-r--r--fs/hpfs/inode.c10
-rw-r--r--fs/hpfs/namei.c8
-rw-r--r--fs/hppfs/hppfs.c2
-rw-r--r--fs/hugetlbfs/inode.c2
-rw-r--r--fs/inode.c2
-rw-r--r--fs/isofs/inode.c4
-rw-r--r--fs/isofs/rock.c4
-rw-r--r--fs/jbd/journal.c8
-rw-r--r--fs/jbd2/commit.c26
-rw-r--r--fs/jbd2/journal.c44
-rw-r--r--fs/jbd2/recovery.c28
-rw-r--r--fs/jbd2/transaction.c68
-rw-r--r--fs/jffs2/dir.c6
-rw-r--r--fs/jffs2/fs.c6
-rw-r--r--fs/jfs/jfs_imap.c6
-rw-r--r--fs/jfs/jfs_inode.c2
-rw-r--r--fs/jfs/namei.c12
-rw-r--r--fs/jfs/super.c1
-rw-r--r--fs/libfs.c6
-rw-r--r--fs/logfs/dir.c8
-rw-r--r--fs/logfs/inode.c3
-rw-r--r--fs/logfs/readwrite.c2
-rw-r--r--fs/minix/inode.c4
-rw-r--r--fs/namei.c18
-rw-r--r--fs/ncpfs/inode.c2
-rw-r--r--fs/nfs/inode.c6
-rw-r--r--fs/nilfs2/inode.c4
-rw-r--r--fs/nilfs2/namei.c2
-rw-r--r--fs/ntfs/inode.c8
-rw-r--r--fs/ocfs2/dir.c4
-rw-r--r--fs/ocfs2/dlmglue.c2
-rw-r--r--fs/ocfs2/inode.c4
-rw-r--r--fs/ocfs2/namei.c18
-rw-r--r--fs/openpromfs/inode.c4
-rw-r--r--fs/proc/base.c12
-rw-r--r--fs/proc/generic.c2
-rw-r--r--fs/proc/inode.c2
-rw-r--r--fs/proc/proc_sysctl.c2
-rw-r--r--fs/qnx4/inode.c2
-rw-r--r--fs/quota/quota.c7
-rw-r--r--fs/reiserfs/inode.c10
-rw-r--r--fs/reiserfs/namei.c16
-rw-r--r--fs/romfs/super.c2
-rw-r--r--fs/squashfs/inode.c18
-rw-r--r--fs/stack.c2
-rw-r--r--fs/stat.c5
-rw-r--r--fs/super.c9
-rw-r--r--fs/sysfs/inode.c2
-rw-r--r--fs/sysv/inode.c2
-rw-r--r--fs/ubifs/super.c2
-rw-r--r--fs/ubifs/xattr.c4
-rw-r--r--fs/udf/balloc.c14
-rw-r--r--fs/udf/directory.c8
-rw-r--r--fs/udf/inode.c56
-rw-r--r--fs/udf/lowlevel.c2
-rw-r--r--fs/udf/misc.c19
-rw-r--r--fs/udf/namei.c20
-rw-r--r--fs/udf/partition.c19
-rw-r--r--fs/udf/super.c280
-rw-r--r--fs/udf/truncate.c22
-rw-r--r--fs/udf/udf_sb.h5
-rw-r--r--fs/udf/udfdecl.h35
-rw-r--r--fs/udf/udftime.c3
-rw-r--r--fs/udf/unicode.c6
-rw-r--r--fs/ufs/ialloc.c2
-rw-r--r--fs/ufs/inode.c4
-rw-r--r--fs/xfs/xfs_iops.c2
-rw-r--r--include/linux/dcache.h8
-rw-r--r--include/linux/ext2_fs.h4
-rw-r--r--include/linux/ext3_fs.h6
-rw-r--r--include/linux/ext3_fs_sb.h4
-rw-r--r--include/linux/fs.h41
-rw-r--r--include/linux/jbd.h64
-rw-r--r--include/linux/jbd2.h69
-rw-r--r--include/linux/jbd_common.h68
-rw-r--r--include/linux/namei.h1
-rw-r--r--include/linux/virtio.h4
-rw-r--r--include/linux/virtio_config.h3
-rw-r--r--include/linux/virtio_mmio.h111
-rw-r--r--include/linux/virtio_ring.h6
-rw-r--r--include/trace/events/ext4.h480
-rw-r--r--mm/shmem.c2
-rw-r--r--security/integrity/ima/Kconfig2
-rw-r--r--sound/Kconfig2
423 files changed, 5866 insertions, 5301 deletions
diff --git a/Documentation/devicetree/bindings/virtio/mmio.txt b/Documentation/devicetree/bindings/virtio/mmio.txt
new file mode 100644
index 000000000000..5069c1b8e193
--- /dev/null
+++ b/Documentation/devicetree/bindings/virtio/mmio.txt
@@ -0,0 +1,17 @@
+* virtio memory mapped device
+
+See http://ozlabs.org/~rusty/virtio-spec/ for more details.
+
+Required properties:
+
+- compatible: "virtio,mmio" compatibility string
+- reg: control registers base address and size including configuration space
+- interrupts: interrupt generated by the device
+
+Example:
+
+ virtio_block@3000 {
+ compatible = "virtio,mmio";
+ reg = <0x3000 0x100>;
+ interrupts = <41>;
+ }
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 653380793a6c..d819ba16a0c7 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -29,6 +29,7 @@ d_hash no no no maybe
d_compare: yes no no maybe
d_delete: no yes no no
d_release: no no yes no
+d_prune: no yes no no
d_iput: no no yes no
d_dname: no no no no
d_automount: no no yes no
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 22f3a0eda1d2..b100adc38adb 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -73,14 +73,6 @@ nobarrier (*) This also requires an IO stack which can support
also be used to enable or disable barriers, for
consistency with other ext3 mount options.
-orlov (*) This enables the new Orlov block allocator. It is
- enabled by default.
-
-oldalloc This disables the Orlov block allocator and enables
- the old block allocator. Orlov should have better
- performance - we'd like to get some feedback if it's
- the contrary for you.
-
user_xattr Enables Extended User Attributes. Additionally, you
need to have extended attribute support enabled in the
kernel configuration (CONFIG_EXT3_FS_XATTR). See the
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 232a575a0c48..4917cf24a5e0 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -160,7 +160,9 @@ noload if the filesystem was not unmounted cleanly,
lead to any number of problems.
data=journal All data are committed into the journal prior to being
- written into the main file system.
+ written into the main file system. Enabling
+ this mode will disable delayed allocation and
+ O_DIRECT support.
data=ordered (*) All data are forced directly out to the main file
system prior to its metadata being committed to the
@@ -201,30 +203,19 @@ inode_readahead_blks=n This tuning parameter controls the maximum
table readahead algorithm will pre-read into
the buffer cache. The default value is 32 blocks.
-orlov (*) This enables the new Orlov block allocator. It is
- enabled by default.
-
-oldalloc This disables the Orlov block allocator and enables
- the old block allocator. Orlov should have better
- performance - we'd like to get some feedback if it's
- the contrary for you.
-
-user_xattr Enables Extended User Attributes. Additionally, you
- need to have extended attribute support enabled in the
- kernel configuration (CONFIG_EXT4_FS_XATTR). See the
- attr(5) manual page and http://acl.bestbits.at/ to
- learn more about extended attributes.
-
-nouser_xattr Disables Extended User Attributes.
-
-acl Enables POSIX Access Control Lists support.
- Additionally, you need to have ACL support enabled in
- the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL).
- See the acl(5) manual page and http://acl.bestbits.at/
- for more information.
+nouser_xattr Disables Extended User Attributes. If you have extended
+ attribute support enabled in the kernel configuration
+ (CONFIG_EXT4_FS_XATTR), extended attribute support
+ is enabled by default on mount. See the attr(5) manual
+ page and http://acl.bestbits.at/ for more information
+ about extended attributes.
noacl This option disables POSIX Access Control List
- support.
+ support. If ACL support is enabled in the kernel
+ configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is
+ enabled by default on mount. See the acl(5) manual
+ page and http://acl.bestbits.at/ for more information
+ about acl.
bsddf (*) Make 'df' act like BSD.
minixdf Make 'df' act like Minix.
@@ -419,8 +410,8 @@ written to the journal first, and then to its final location.
In the event of a crash, the journal can be replayed, bringing both data and
metadata into a consistent state. This mode is the slowest except when data
needs to be read from and written to disk at the same time where it
-outperforms all others modes. Currently ext4 does not have delayed
-allocation support if this data journalling mode is selected.
+outperforms all others modes. Enabling this mode will disable delayed
+allocation and O_DIRECT support.
/proc entries
=============
diff --git a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
index 5d0fc8bfcdb9..77dfecf4e2d6 100644
--- a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
+++ b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
@@ -134,13 +134,13 @@
______________________________________________________________________
- 11.. IInnttrroodduuccttiioonn
+ 1. Introduction
Welcome to User Mode Linux. It's going to be fun.
- 11..11.. HHooww iiss UUsseerr MMooddee LLiinnuuxx DDiiffffeerreenntt??
+ 1.1. How is User Mode Linux Different?
Normally, the Linux Kernel talks straight to your hardware (video
card, keyboard, hard drives, etc), and any programs which run ask the
@@ -181,7 +181,7 @@
- 11..22.. WWhhyy WWoouulldd II WWaanntt UUsseerr MMooddee LLiinnuuxx??
+ 1.2. Why Would I Want User Mode Linux?
1. If User Mode Linux crashes, your host kernel is still fine.
@@ -206,12 +206,12 @@
- 22.. CCoommppiilliinngg tthhee kkeerrnneell aanndd mmoodduulleess
+ 2. Compiling the kernel and modules
- 22..11.. CCoommppiilliinngg tthhee kkeerrnneell
+ 2.1. Compiling the kernel
Compiling the user mode kernel is just like compiling any other
@@ -322,7 +322,7 @@
bug fixes and enhancements that have gone into subsequent releases.
- 22..22.. CCoommppiilliinngg aanndd iinnssttaalllliinngg kkeerrnneell mmoodduulleess
+ 2.2. Compiling and installing kernel modules
UML modules are built in the same way as the native kernel (with the
exception of the 'ARCH=um' that you always need for UML):
@@ -386,19 +386,19 @@
- 22..33.. CCoommppiilliinngg aanndd iinnssttaalllliinngg uummll__uuttiilliittiieess
+ 2.3. Compiling and installing uml_utilities
Many features of the UML kernel require a user-space helper program,
so a uml_utilities package is distributed separately from the kernel
patch which provides these helpers. Included within this is:
- +o port-helper - Used by consoles which connect to xterms or ports
+ o port-helper - Used by consoles which connect to xterms or ports
- +o tunctl - Configuration tool to create and delete tap devices
+ o tunctl - Configuration tool to create and delete tap devices
- +o uml_net - Setuid binary for automatic tap device configuration
+ o uml_net - Setuid binary for automatic tap device configuration
- +o uml_switch - User-space virtual switch required for daemon
+ o uml_switch - User-space virtual switch required for daemon
transport
The uml_utilities tree is compiled with:
@@ -423,11 +423,11 @@
- 33.. RRuunnnniinngg UUMMLL aanndd llooggggiinngg iinn
+ 3. Running UML and logging in
- 33..11.. RRuunnnniinngg UUMMLL
+ 3.1. Running UML
It runs on 2.2.15 or later, and all 2.4 kernels.
@@ -454,7 +454,7 @@
- 33..22.. LLooggggiinngg iinn
+ 3.2. Logging in
@@ -468,7 +468,7 @@
There are a couple of other ways to log in:
- +o On a virtual console
+ o On a virtual console
@@ -480,7 +480,7 @@
- +o Over the serial line
+ o Over the serial line
In the boot output, find a line that looks like:
@@ -503,7 +503,7 @@
- +o Over the net
+ o Over the net
If the network is running, then you can telnet to the virtual
@@ -514,13 +514,13 @@
down and the process will exit.
- 33..33.. EExxaammpplleess
+ 3.3. Examples
Here are some examples of UML in action:
- +o A login session <http://user-mode-linux.sourceforge.net/login.html>
+ o A login session <http://user-mode-linux.sourceforge.net/login.html>
- +o A virtual network <http://user-mode-linux.sourceforge.net/net.html>
+ o A virtual network <http://user-mode-linux.sourceforge.net/net.html>
@@ -528,12 +528,12 @@
- 44.. UUMMLL oonn 22GG//22GG hhoossttss
+ 4. UML on 2G/2G hosts
- 44..11.. IInnttrroodduuccttiioonn
+ 4.1. Introduction
Most Linux machines are configured so that the kernel occupies the
@@ -546,7 +546,7 @@
- 44..22.. TThhee pprroobblleemm
+ 4.2. The problem
The prebuilt UML binaries on this site will not run on 2G/2G hosts
@@ -558,7 +558,7 @@
- 44..33.. TThhee ssoolluuttiioonn
+ 4.3. The solution
The fix for this is to rebuild UML from source after enabling
@@ -576,7 +576,7 @@
- 55.. SSeettttiinngg uupp sseerriiaall lliinneess aanndd ccoonnssoolleess
+ 5. Setting up serial lines and consoles
It is possible to attach UML serial lines and consoles to many types
@@ -586,12 +586,12 @@
You can attach them to host ptys, ttys, file descriptors, and ports.
This allows you to do things like
- +o have a UML console appear on an unused host console,
+ o have a UML console appear on an unused host console,
- +o hook two virtual machines together by having one attach to a pty
+ o hook two virtual machines together by having one attach to a pty
and having the other attach to the corresponding tty
- +o make a virtual machine accessible from the net by attaching a
+ o make a virtual machine accessible from the net by attaching a
console to a port on the host.
@@ -599,7 +599,7 @@
- 55..11.. SSppeecciiffyyiinngg tthhee ddeevviiccee
+ 5.1. Specifying the device
Devices are specified with "con" or "ssl" (console or serial line,
respectively), optionally with a device number if you are talking
@@ -626,13 +626,13 @@
- 55..22.. SSppeecciiffyyiinngg tthhee cchhaannnneell
+ 5.2. Specifying the channel
There are a number of different types of channels to attach a UML
device to, each with a different way of specifying exactly what to
attach to.
- +o pseudo-terminals - device=pty pts terminals - device=pts
+ o pseudo-terminals - device=pty pts terminals - device=pts
This will cause UML to allocate a free host pseudo-terminal for the
@@ -640,20 +640,20 @@
log. You access it by attaching a terminal program to the
corresponding tty:
- +o screen /dev/pts/n
+ o screen /dev/pts/n
- +o screen /dev/ttyxx
+ o screen /dev/ttyxx
- +o minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
+ o minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
devices
- +o kermit - start it up, 'open' the device, then 'connect'
+ o kermit - start it up, 'open' the device, then 'connect'
- +o terminals - device=tty:tty device file
+ o terminals - device=tty:tty device file
This will make UML attach the device to the specified tty (i.e
@@ -672,7 +672,7 @@
- +o xterms - device=xterm
+ o xterms - device=xterm
UML will run an xterm and the device will be attached to it.
@@ -681,7 +681,7 @@
- +o Port - device=port:port number
+ o Port - device=port:port number
This will attach the UML devices to the specified host port.
@@ -725,7 +725,7 @@
- +o already-existing file descriptors - device=file descriptor
+ o already-existing file descriptors - device=file descriptor
If you set up a file descriptor on the UML command line, you can
@@ -743,7 +743,7 @@
- +o Nothing - device=null
+ o Nothing - device=null
This allows the device to be opened, in contrast to 'none', but
@@ -754,7 +754,7 @@
- +o None - device=none
+ o None - device=none
This causes the device to disappear.
@@ -770,7 +770,7 @@
- will cause serial line 3 to accept input on the host's /dev/tty3 and
+ will cause serial line 3 to accept input on the host's /dev/tty2 and
display output on an xterm. That's a silly example - the most common
use of this syntax is to reattach the main console to stdin and stdout
as shown above.
@@ -785,7 +785,7 @@
- 55..33.. EExxaammpplleess
+ 5.3. Examples
There are a number of interesting things you can do with this
capability.
@@ -838,7 +838,7 @@
prompt of the other virtual machine.
- 66.. SSeettttiinngg uupp tthhee nneettwwoorrkk
+ 6. Setting up the network
@@ -858,19 +858,19 @@
There are currently five transport types available for a UML virtual
machine to exchange packets with other hosts:
- +o ethertap
+ o ethertap
- +o TUN/TAP
+ o TUN/TAP
- +o Multicast
+ o Multicast
- +o a switch daemon
+ o a switch daemon
- +o slip
+ o slip
- +o slirp
+ o slirp
- +o pcap
+ o pcap
The TUN/TAP, ethertap, slip, and slirp transports allow a UML
instance to exchange packets with the host. They may be directed
@@ -893,28 +893,28 @@
With so many host transports, which one should you use? Here's when
you should use each one:
- +o ethertap - if you want access to the host networking and it is
+ o ethertap - if you want access to the host networking and it is
running 2.2
- +o TUN/TAP - if you want access to the host networking and it is
+ o TUN/TAP - if you want access to the host networking and it is
running 2.4. Also, the TUN/TAP transport is able to use a
preconfigured device, allowing it to avoid using the setuid uml_net
helper, which is a security advantage.
- +o Multicast - if you want a purely virtual network and you don't want
+ o Multicast - if you want a purely virtual network and you don't want
to set up anything but the UML
- +o a switch daemon - if you want a purely virtual network and you
+ o a switch daemon - if you want a purely virtual network and you
don't mind running the daemon in order to get somewhat better
performance
- +o slip - there is no particular reason to run the slip backend unless
+ o slip - there is no particular reason to run the slip backend unless
ethertap and TUN/TAP are just not available for some reason
- +o slirp - if you don't have root access on the host to setup
+ o slirp - if you don't have root access on the host to setup
networking, or if you don't want to allocate an IP to your UML
- +o pcap - not much use for actual network connectivity, but great for
+ o pcap - not much use for actual network connectivity, but great for
monitoring traffic on the host
Ethertap is available on 2.4 and works fine. TUN/TAP is preferred
@@ -926,7 +926,7 @@
exploit the helper's root privileges.
- 66..11.. GGeenneerraall sseettuupp
+ 6.1. General setup
First, you must have the virtual network enabled in your UML. If are
running a prebuilt kernel from this site, everything is already
@@ -995,7 +995,7 @@
- 66..22.. UUsseerrssppaaccee ddaaeemmoonnss
+ 6.2. Userspace daemons
You will likely need the setuid helper, or the switch daemon, or both.
They are both installed with the RPM and deb, so if you've installed
@@ -1011,7 +1011,7 @@
- 66..33.. SSppeecciiffyyiinngg eetthheerrnneett aaddddrreesssseess
+ 6.3. Specifying ethernet addresses
Below, you will see that the TUN/TAP, ethertap, and daemon interfaces
allow you to specify hardware addresses for the virtual ethernet
@@ -1023,11 +1023,11 @@
sufficient to guarantee a unique hardware address for the device. A
couple of exceptions are:
- +o Another set of virtual ethernet devices are on the same network and
+ o Another set of virtual ethernet devices are on the same network and
they are assigned hardware addresses using a different scheme which
may conflict with the UML IP address-based scheme
- +o You aren't going to use the device for IP networking, so you don't
+ o You aren't going to use the device for IP networking, so you don't
assign the device an IP address
If you let the driver provide the hardware address, you should make
@@ -1049,7 +1049,7 @@
- 66..44.. UUMMLL iinntteerrffaaccee sseettuupp
+ 6.4. UML interface setup
Once the network devices have been described on the command line, you
should boot UML and log in.
@@ -1131,7 +1131,7 @@
- 66..55.. MMuullttiiccaasstt
+ 6.5. Multicast
The simplest way to set up a virtual network between multiple UMLs is
to use the mcast transport. This was written by Harald Welte and is
@@ -1194,7 +1194,7 @@
- 66..66.. TTUUNN//TTAAPP wwiitthh tthhee uummll__nneett hheellppeerr
+ 6.6. TUN/TAP with the uml_net helper
TUN/TAP is the preferred mechanism on 2.4 to exchange packets with the
host. The TUN/TAP backend has been in UML since 2.4.9-3um.
@@ -1247,10 +1247,10 @@
There are a couple potential problems with running the TUN/TAP
transport on a 2.4 host kernel
- +o TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host
+ o TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host
kernel or use the ethertap transport.
- +o With an upgraded kernel, TUN/TAP may fail with
+ o With an upgraded kernel, TUN/TAP may fail with
File descriptor in bad state
@@ -1269,7 +1269,7 @@
- 66..77.. TTUUNN//TTAAPP wwiitthh aa pprreeccoonnffiigguurreedd ttaapp ddeevviiccee
+ 6.7. TUN/TAP with a preconfigured tap device
If you prefer not to have UML use uml_net (which is somewhat
insecure), with UML 2.4.17-11, you can set up a TUN/TAP device
@@ -1277,7 +1277,7 @@
there is no need for root assistance. Setting up the device is done
as follows:
- +o Create the device with tunctl (available from the UML utilities
+ o Create the device with tunctl (available from the UML utilities
tarball)
@@ -1291,7 +1291,7 @@
where uid is the user id or username that UML will be run as. This
will tell you what device was created.
- +o Configure the device IP (change IP addresses and device name to
+ o Configure the device IP (change IP addresses and device name to
suit)
@@ -1303,7 +1303,7 @@
- +o Set up routing and arping if desired - this is my recipe, there are
+ o Set up routing and arping if desired - this is my recipe, there are
other ways of doing the same thing
@@ -1338,7 +1338,7 @@
utility which reads the information from a config file and sets up
devices at boot time.
- +o Rather than using up two IPs and ARPing for one of them, you can
+ o Rather than using up two IPs and ARPing for one of them, you can
also provide direct access to your LAN by the UML by using a
bridge.
@@ -1417,7 +1417,7 @@
Note that 'br0' should be setup using ifconfig with the existing IP
address of eth0, as eth0 no longer has its own IP.
- +o
+ o
Also, the /dev/net/tun device must be writable by the user running
@@ -1438,11 +1438,11 @@
devices and chgrp /dev/net/tun to that group with mode 664 or 660.
- +o Once the device is set up, run UML with 'eth0=tuntap,device name'
+ o Once the device is set up, run UML with 'eth0=tuntap,device name'
(i.e. 'eth0=tuntap,tap0') on the command line (or do it with the
mconsole config command).
- +o Bring the eth device up in UML and you're in business.
+ o Bring the eth device up in UML and you're in business.
If you don't want that tap device any more, you can make it non-
persistent with
@@ -1465,7 +1465,7 @@
- 66..88.. EEtthheerrttaapp
+ 6.8. Ethertap
Ethertap is the general mechanism on 2.2 for userspace processes to
exchange packets with the kernel.
@@ -1561,9 +1561,9 @@
- 66..99.. TThhee sswwiittcchh ddaaeemmoonn
+ 6.9. The switch daemon
- NNoottee: This is the daemon formerly known as uml_router, but which was
+ Note: This is the daemon formerly known as uml_router, but which was
renamed so the network weenies of the world would stop growling at me.
@@ -1649,7 +1649,7 @@
- 66..1100.. SSlliipp
+ 6.10. Slip
Slip is another, less general, mechanism for a process to communicate
with the host networking. In contrast to the ethertap interface,
@@ -1681,7 +1681,7 @@
- 66..1111.. SSlliirrpp
+ 6.11. Slirp
slirp uses an external program, usually /usr/bin/slirp, to provide IP
only networking connectivity through the host. This is similar to IP
@@ -1737,7 +1737,7 @@
- 66..1122.. ppccaapp
+ 6.12. pcap
The pcap transport is attached to a UML ethernet device on the command
line or with uml_mconsole with the following syntax:
@@ -1777,7 +1777,7 @@
- 66..1133.. SSeettttiinngg uupp tthhee hhoosstt yyoouurrsseellff
+ 6.13. Setting up the host yourself
If you don't specify an address for the host side of the ethertap or
slip device, UML won't do any setup on the host. So this is what is
@@ -1785,7 +1785,7 @@
192.168.0.251 and a UML-side IP of 192.168.0.250 - adjust to suit your
own network):
- +o The device needs to be configured with its IP address. Tap devices
+ o The device needs to be configured with its IP address. Tap devices
are also configured with an mtu of 1484. Slip devices are
configured with a point-to-point address pointing at the UML ip
address.
@@ -1805,7 +1805,7 @@
- +o If a tap device is being set up, a route is set to the UML IP.
+ o If a tap device is being set up, a route is set to the UML IP.
UML# route add -host 192.168.0.250 gw 192.168.0.251
@@ -1814,7 +1814,7 @@
- +o To allow other hosts on your network to see the virtual machine,
+ o To allow other hosts on your network to see the virtual machine,
proxy arp is set up for it.
@@ -1824,7 +1824,7 @@
- +o Finally, the host is set up to route packets.
+ o Finally, the host is set up to route packets.
host# echo 1 > /proc/sys/net/ipv4/ip_forward
@@ -1838,12 +1838,12 @@
- 77.. SShhaarriinngg FFiilleessyysstteemmss bbeettwweeeenn VViirrttuuaall MMaacchhiinneess
+ 7. Sharing Filesystems between Virtual Machines
- 77..11.. AA wwaarrnniinngg
+ 7.1. A warning
Don't attempt to share filesystems simply by booting two UMLs from the
same file. That's the same thing as booting two physical machines
@@ -1851,7 +1851,7 @@
- 77..22.. UUssiinngg llaayyeerreedd bblloocckk ddeevviicceess
+ 7.2. Using layered block devices
The way to share a filesystem between two virtual machines is to use
the copy-on-write (COW) layering capability of the ubd block driver.
@@ -1896,7 +1896,7 @@
- 77..33.. NNoottee!!
+ 7.3. Note!
When checking the size of the COW file in order to see the gobs of
space that you're saving, make sure you use 'ls -ls' to see the actual
@@ -1926,7 +1926,7 @@
- 77..44.. AAnnootthheerr wwaarrnniinngg
+ 7.4. Another warning
Once a filesystem is being used as a readonly backing file for a COW
file, do not boot directly from it or modify it in any way. Doing so
@@ -1952,7 +1952,7 @@
- 77..55.. uummll__mmoooo :: MMeerrggiinngg aa CCOOWW ffiillee wwiitthh iittss bbaacckkiinngg ffiillee
+ 7.5. uml_moo : Merging a COW file with its backing file
Depending on how you use UML and COW devices, it may be advisable to
merge the changes in the COW file into the backing file every once in
@@ -2001,7 +2001,7 @@
- 88.. CCrreeaattiinngg ffiilleessyysstteemmss
+ 8. Creating filesystems
You may want to create and mount new UML filesystems, either because
@@ -2015,7 +2015,7 @@
should be easy to translate to the filesystem of your choice.
- 88..11.. CCrreeaattee tthhee ffiilleessyysstteemm ffiillee
+ 8.1. Create the filesystem file
dd is your friend. All you need to do is tell dd to create an empty
file of the appropriate size. I usually make it sparse to save time
@@ -2032,7 +2032,7 @@
- 88..22.. AAssssiiggnn tthhee ffiillee ttoo aa UUMMLL ddeevviiccee
+ 8.2. Assign the file to a UML device
Add an argument like the following to the UML command line:
@@ -2045,7 +2045,7 @@
- 88..33.. CCrreeaattiinngg aanndd mmoouunnttiinngg tthhee ffiilleessyysstteemm
+ 8.3. Creating and mounting the filesystem
Make sure that the filesystem is available, either by being built into
the kernel, or available as a module, then boot up UML and log in. If
@@ -2096,7 +2096,7 @@
- 99.. HHoosstt ffiillee aacccceessss
+ 9. Host file access
If you want to access files on the host machine from inside UML, you
@@ -2112,7 +2112,7 @@
files contained in it just as you would on the host.
- 99..11.. UUssiinngg hhoossttffss
+ 9.1. Using hostfs
To begin with, make sure that hostfs is available inside the virtual
machine with
@@ -2151,7 +2151,7 @@
- 99..22.. hhoossttffss aass tthhee rroooott ffiilleessyysstteemm
+ 9.2. hostfs as the root filesystem
It's possible to boot from a directory hierarchy on the host using
hostfs rather than using the standard filesystem in a file.
@@ -2194,20 +2194,20 @@
UML should then boot as it does normally.
- 99..33.. BBuuiillddiinngg hhoossttffss
+ 9.3. Building hostfs
If you need to build hostfs because it's not in your kernel, you have
two choices:
- +o Compiling hostfs into the kernel:
+ o Compiling hostfs into the kernel:
Reconfigure the kernel and set the 'Host filesystem' option under
- +o Compiling hostfs as a module:
+ o Compiling hostfs as a module:
Reconfigure the kernel and set the 'Host filesystem' option under
@@ -2228,7 +2228,7 @@
- 1100.. TThhee MMaannaaggeemmeenntt CCoonnssoollee
+ 10. The Management Console
@@ -2240,15 +2240,15 @@
There are a number of things you can do with the mconsole interface:
- +o get the kernel version
+ o get the kernel version
- +o add and remove devices
+ o add and remove devices
- +o halt or reboot the machine
+ o halt or reboot the machine
- +o Send SysRq commands
+ o Send SysRq commands
- +o Pause and resume the UML
+ o Pause and resume the UML
You need the mconsole client (uml_mconsole) which is present in CVS
@@ -2300,28 +2300,28 @@
You'll get a prompt, at which you can run one of these commands:
- +o version
+ o version
- +o halt
+ o halt
- +o reboot
+ o reboot
- +o config
+ o config
- +o remove
+ o remove
- +o sysrq
+ o sysrq
- +o help
+ o help
- +o cad
+ o cad
- +o stop
+ o stop
- +o go
+ o go
- 1100..11.. vveerrssiioonn
+ 10.1. version
This takes no arguments. It prints the UML version.
@@ -2342,7 +2342,7 @@
- 1100..22.. hhaalltt aanndd rreebboooott
+ 10.2. halt and reboot
These take no arguments. They shut the machine down immediately, with
no syncing of disks and no clean shutdown of userspace. So, they are
@@ -2357,7 +2357,7 @@
- 1100..33.. ccoonnffiigg
+ 10.3. config
"config" adds a new device to the virtual machine. Currently the ubd
and network drivers support this. It takes one argument, which is the
@@ -2378,7 +2378,7 @@
- 1100..44.. rreemmoovvee
+ 10.4. remove
"remove" deletes a device from the system. Its argument is just the
name of the device to be removed. The device must be idle in whatever
@@ -2397,7 +2397,7 @@
- 1100..55.. ssyyssrrqq
+ 10.5. sysrq
This takes one argument, which is a single letter. It calls the
generic kernel's SysRq driver, which does whatever is called for by
@@ -2407,14 +2407,14 @@
- 1100..66.. hheellpp
+ 10.6. help
"help" returns a string listing the valid commands and what each one
does.
- 1100..77.. ccaadd
+ 10.7. cad
This invokes the Ctl-Alt-Del action on init. What exactly this ends
up doing is up to /etc/inittab. Normally, it reboots the machine.
@@ -2432,7 +2432,7 @@
- 1100..88.. ssttoopp
+ 10.8. stop
This puts the UML in a loop reading mconsole requests until a 'go'
mconsole command is received. This is very useful for making backups
@@ -2448,7 +2448,7 @@
- 1100..99.. ggoo
+ 10.9. go
This resumes a UML after being paused by a 'stop' command. Note that
when the UML has resumed, TCP connections may have timed out and if
@@ -2462,10 +2462,10 @@
- 1111.. KKeerrnneell ddeebbuuggggiinngg
+ 11. Kernel debugging
- NNoottee:: The interface that makes debugging, as described here, possible
+ Note: The interface that makes debugging, as described here, possible
is present in 2.4.0-test6 kernels and later.
@@ -2485,7 +2485,7 @@
- 1111..11.. SSttaarrttiinngg tthhee kkeerrnneell uunnddeerr ggddbb
+ 11.1. Starting the kernel under gdb
You can have the kernel running under the control of gdb from the
beginning by putting 'debug' on the command line. You will get an
@@ -2498,7 +2498,7 @@
There is a transcript of a debugging session here <debug-
session.html> , with breakpoints being set in the scheduler and in an
interrupt handler.
- 1111..22.. EExxaammiinniinngg sslleeeeppiinngg pprroocceesssseess
+ 11.2. Examining sleeping processes
Not every bug is evident in the currently running process. Sometimes,
processes hang in the kernel when they shouldn't because they've
@@ -2516,7 +2516,7 @@
Now what you do is this:
- +o detach from the current thread
+ o detach from the current thread
(UML gdb) det
@@ -2525,7 +2525,7 @@
- +o attach to the thread you are interested in
+ o attach to the thread you are interested in
(UML gdb) att <host pid>
@@ -2534,7 +2534,7 @@
- +o look at its stack and anything else of interest
+ o look at its stack and anything else of interest
(UML gdb) bt
@@ -2545,7 +2545,7 @@
Note that you can't do anything at this point that requires that a
process execute, e.g. calling a function
- +o when you're done looking at that process, reattach to the current
+ o when you're done looking at that process, reattach to the current
thread and continue it
@@ -2569,12 +2569,12 @@
- 1111..33.. RRuunnnniinngg dddddd oonn UUMMLL
+ 11.3. Running ddd on UML
ddd works on UML, but requires a special kludge. The process goes
like this:
- +o Start ddd
+ o Start ddd
host% ddd linux
@@ -2583,14 +2583,14 @@
- +o With ps, get the pid of the gdb that ddd started. You can ask the
+ o With ps, get the pid of the gdb that ddd started. You can ask the
gdb to tell you, but for some reason that confuses things and
causes a hang.
- +o run UML with 'debug=parent gdb-pid=<pid>' added to the command line
+ o run UML with 'debug=parent gdb-pid=<pid>' added to the command line
- it will just sit there after you hit return
- +o type 'att 1' to the ddd gdb and you will see something like
+ o type 'att 1' to the ddd gdb and you will see something like
0xa013dc51 in __kill ()
@@ -2602,12 +2602,12 @@
- +o At this point, type 'c', UML will boot up, and you can use ddd just
+ o At this point, type 'c', UML will boot up, and you can use ddd just
as you do on any other process.
- 1111..44.. DDeebbuuggggiinngg mmoodduulleess
+ 11.4. Debugging modules
gdb has support for debugging code which is dynamically loaded into
the process. This support is what is needed to debug kernel modules
@@ -2823,7 +2823,7 @@
- 1111..55.. AAttttaacchhiinngg ggddbb ttoo tthhee kkeerrnneell
+ 11.5. Attaching gdb to the kernel
If you don't have the kernel running under gdb, you can attach gdb to
it later by sending the tracing thread a SIGUSR1. The first line of
@@ -2857,7 +2857,7 @@
- 1111..66.. UUssiinngg aalltteerrnnaattee ddeebbuuggggeerrss
+ 11.6. Using alternate debuggers
UML has support for attaching to an already running debugger rather
than starting gdb itself. This is present in CVS as of 17 Apr 2001.
@@ -2886,7 +2886,7 @@
An example of an alternate debugger is strace. You can strace the
actual kernel as follows:
- +o Run the following in a shell
+ o Run the following in a shell
host%
@@ -2894,10 +2894,10 @@
- +o Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
+ o Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
by the previous command
- +o Hit return in the shell, and UML will start running, and strace
+ o Hit return in the shell, and UML will start running, and strace
output will start accumulating in the output file.
Note that this is different from running
@@ -2917,9 +2917,9 @@
- 1122.. KKeerrnneell ddeebbuuggggiinngg eexxaammpplleess
+ 12. Kernel debugging examples
- 1122..11.. TThhee ccaassee ooff tthhee hhuunngg ffsscckk
+ 12.1. The case of the hung fsck
When booting up the kernel, fsck failed, and dropped me into a shell
to fix things up. I ran fsck -y, which hung:
@@ -3154,9 +3154,9 @@
The interesting things here are :
- +o There are two segfaults on this stack (frames 9 and 14)
+ o There are two segfaults on this stack (frames 9 and 14)
- +o The first faulting address (frame 11) is 0x50000800
+ o The first faulting address (frame 11) is 0x50000800
(gdb) p (void *)1342179328
$16 = (void *) 0x50000800
@@ -3399,7 +3399,7 @@
on will be somewhat clearer.
- 1122..22.. EEppiissooddee 22:: TThhee ccaassee ooff tthhee hhuunngg ffsscckk
+ 12.2. Episode 2: The case of the hung fsck
After setting a trap in the SEGV handler for accesses to the signal
thread's stack, I reran the kernel.
@@ -3788,12 +3788,12 @@
- 1133.. WWhhaatt ttoo ddoo wwhheenn UUMMLL ddooeessnn''tt wwoorrkk
+ 13. What to do when UML doesn't work
- 1133..11.. SSttrraannggee ccoommppiillaattiioonn eerrrroorrss wwhheenn yyoouu bbuuiilldd ffrroomm ssoouurrccee
+ 13.1. Strange compilation errors when you build from source
As of test11, it is necessary to have "ARCH=um" in the environment or
on the make command line for all steps in building UML, including
@@ -3824,8 +3824,8 @@
- 1133..33.. AA vvaarriieettyy ooff ppaanniiccss aanndd hhaannggss wwiitthh //ttmmpp oonn aa rreeiisseerrffss ffiilleessyyss--
- tteemm
+ 13.3. A variety of panics and hangs with /tmp on a reiserfs filesys-
+ tem
I saw this on reiserfs 3.5.21 and it seems to be fixed in 3.5.27.
Panics preceded by
@@ -3842,8 +3842,8 @@
- 1133..44.. TThhee ccoommppiillee ffaaiillss wwiitthh eerrrroorrss aabboouutt ccoonnfflliiccttiinngg ttyyppeess ffoorr
- ''ooppeenn'',, ''dduupp'',, aanndd ''wwaaiittppiidd''
+ 13.4. The compile fails with errors about conflicting types for
+ 'open', 'dup', and 'waitpid'
This happens when you build in /usr/src/linux. The UML build makes
the include/asm link point to include/asm-um. /usr/include/asm points
@@ -3854,14 +3854,14 @@
- 1133..55.. UUMMLL ddooeessnn''tt wwoorrkk wwhheenn //ttmmpp iiss aann NNFFSS ffiilleessyysstteemm
+ 13.5. UML doesn't work when /tmp is an NFS filesystem
This seems to be a similar situation with the ReiserFS problem above.
Some versions of NFS seems not to handle mmap correctly, which UML
depends on. The workaround is have /tmp be a non-NFS directory.
- 1133..66.. UUMMLL hhaannggss oonn bboooott wwhheenn ccoommppiilleedd wwiitthh ggpprrooff ssuuppppoorrtt
+ 13.6. UML hangs on boot when compiled with gprof support
If you build UML with gprof support and, early in the boot, it does
this
@@ -3878,7 +3878,7 @@
- 1133..77.. ssyyssllooggdd ddiieess wwiitthh aa SSIIGGTTEERRMM oonn ssttaarrttuupp
+ 13.7. syslogd dies with a SIGTERM on startup
The exact boot error depends on the distribution that you're booting,
but Debian produces this:
@@ -3897,17 +3897,17 @@
- 1133..88.. TTUUNN//TTAAPP nneettwwoorrkkiinngg ddooeessnn''tt wwoorrkk oonn aa 22..44 hhoosstt
+ 13.8. TUN/TAP networking doesn't work on a 2.4 host
There are a couple of problems which were
<http://www.geocrawler.com/lists/3/SourceForge/597/0/> name="pointed
out"> by Tim Robinson <timro at trkr dot net>
- +o It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
+ o It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
The fix is to upgrade to something more recent and then read the
next item.
- +o If you see
+ o If you see
File descriptor in bad state
@@ -3921,8 +3921,8 @@
- 1133..99.. YYoouu ccaann nneettwwoorrkk ttoo tthhee hhoosstt bbuutt nnoott ttoo ootthheerr mmaacchhiinneess oonn tthhee
- nneett
+ 13.9. You can network to the host but not to other machines on the
+ net
If you can connect to the host, and the host can connect to UML, but
you cannot connect to any other machines, then you may need to enable
@@ -3972,7 +3972,7 @@
- 1133..1100.. II hhaavvee nnoo rroooott aanndd II wwaanntt ttoo ssccrreeaamm
+ 13.10. I have no root and I want to scream
Thanks to Birgit Wahlich for telling me about this strange one. It
turns out that there's a limit of six environment variables on the
@@ -3987,7 +3987,7 @@
- 1133..1111.. UUMMLL bbuuiilldd ccoonnfflliicctt bbeettwweeeenn ppttrraaccee..hh aanndd uuccoonntteexxtt..hh
+ 13.11. UML build conflict between ptrace.h and ucontext.h
On some older systems, /usr/include/asm/ptrace.h and
/usr/include/sys/ucontext.h define the same names. So, when they're
@@ -4007,7 +4007,7 @@
- 1133..1122.. TThhee UUMMLL BBooggooMMiippss iiss eexxaaccttllyy hhaallff tthhee hhoosstt''ss BBooggooMMiippss
+ 13.12. The UML BogoMips is exactly half the host's BogoMips
On i386 kernels, there are two ways of running the loop that is used
to calculate the BogoMips rating, using the TSC if it's there or using
@@ -4019,7 +4019,7 @@
- 1133..1133.. WWhheenn yyoouu rruunn UUMMLL,, iitt iimmmmeeddiiaatteellyy sseeggffaauullttss
+ 13.13. When you run UML, it immediately segfaults
If the host is configured with the 2G/2G address space split, that's
why. See ``UML on 2G/2G hosts'' for the details on getting UML to
@@ -4027,7 +4027,7 @@
- 1133..1144.. xxtteerrmmss aappppeeaarr,, tthheenn iimmmmeeddiiaatteellyy ddiissaappppeeaarr
+ 13.14. xterms appear, then immediately disappear
If you're running an up to date kernel with an old release of
uml_utilities, the port-helper program will not work properly, so
@@ -4039,7 +4039,7 @@
- 1133..1155.. AAnnyy ootthheerr ppaanniicc,, hhaanngg,, oorr ssttrraannggee bbeehhaavviioorr
+ 13.15. Any other panic, hang, or strange behavior
If you're seeing truly strange behavior, such as hangs or panics that
happen in random places, or you try running the debugger to see what's
@@ -4059,7 +4059,7 @@
If you want to be super-helpful, read ``Diagnosing Problems'' and
follow the instructions contained therein.
- 1144.. DDiiaaggnnoossiinngg PPrroobblleemmss
+ 14. Diagnosing Problems
If you get UML to crash, hang, or otherwise misbehave, you should
@@ -4078,7 +4078,7 @@
``Kernel debugging'' UML first.
- 1144..11.. CCaassee 11 :: NNoorrmmaall kkeerrnneell ppaanniiccss
+ 14.1. Case 1 : Normal kernel panics
The most common case is for a normal thread to panic. To debug this,
you will need to run it under the debugger (add 'debug' to the command
@@ -4128,7 +4128,7 @@
to get that information from the faulting ip.
- 1144..22.. CCaassee 22 :: TTrraacciinngg tthhrreeaadd ppaanniiccss
+ 14.2. Case 2 : Tracing thread panics
The less common and more painful case is when the tracing thread
panics. In this case, the kernel debugger will be useless because it
@@ -4161,7 +4161,7 @@
backtrace in and wait for our crack debugging team to fix the problem.
- 1144..33.. CCaassee 33 :: TTrraacciinngg tthhrreeaadd ppaanniiccss ccaauusseedd bbyy ootthheerr tthhrreeaaddss
+ 14.3. Case 3 : Tracing thread panics caused by other threads
However, there are cases where the misbehavior of another thread
caused the problem. The most common panic of this type is:
@@ -4227,7 +4227,7 @@
- 1144..44.. CCaassee 44 :: HHaannggss
+ 14.4. Case 4 : Hangs
Hangs seem to be fairly rare, but they sometimes happen. When a hang
happens, we need a backtrace from the offending process. Run the
@@ -4257,7 +4257,7 @@
- 1155.. TThhaannkkss
+ 15. Thanks
A number of people have helped this project in various ways, and this
@@ -4274,20 +4274,20 @@
bookkeeping lapses and I forget about contributions.
- 1155..11.. CCooddee aanndd DDooccuummeennttaattiioonn
+ 15.1. Code and Documentation
Rusty Russell <rusty at linuxcare.com.au> -
- +o wrote the HOWTO <http://user-mode-
+ o wrote the HOWTO <http://user-mode-
linux.sourceforge.net/UserModeLinux-HOWTO.html>
- +o prodded me into making this project official and putting it on
+ o prodded me into making this project official and putting it on
SourceForge
- +o came up with the way cool UML logo <http://user-mode-
+ o came up with the way cool UML logo <http://user-mode-
linux.sourceforge.net/uml-small.png>
- +o redid the config process
+ o redid the config process
Peter Moulder <reiter at netspace.net.au> - Fixed my config and build
@@ -4296,18 +4296,18 @@
Bill Stearns <wstearns at pobox.com> -
- +o HOWTO updates
+ o HOWTO updates
- +o lots of bug reports
+ o lots of bug reports
- +o lots of testing
+ o lots of testing
- +o dedicated a box (uml.ists.dartmouth.edu) to support UML development
+ o dedicated a box (uml.ists.dartmouth.edu) to support UML development
- +o wrote the mkrootfs script, which allows bootable filesystems of
+ o wrote the mkrootfs script, which allows bootable filesystems of
RPM-based distributions to be cranked out
- +o cranked out a large number of filesystems with said script
+ o cranked out a large number of filesystems with said script
Jim Leu <jleu at mindspring.com> - Wrote the virtual ethernet driver
@@ -4375,176 +4375,176 @@
David Coulson <http://davidcoulson.net> -
- +o Set up the usermodelinux.org <http://usermodelinux.org> site,
+ o Set up the usermodelinux.org <http://usermodelinux.org> site,
which is a great way of keeping the UML user community on top of
UML goings-on.
- +o Site documentation and updates
+ o Site documentation and updates
- +o Nifty little UML management daemon UMLd
+ o Nifty little UML management daemon UMLd
<http://uml.openconsultancy.com/umld/>
- +o Lots of testing and bug reports
+ o Lots of testing and bug reports
- 1155..22.. FFlluusshhiinngg oouutt bbuuggss
+ 15.2. Flushing out bugs
- +o Yuri Pudgorodsky
+ o Yuri Pudgorodsky
- +o Gerald Britton
+ o Gerald Britton
- +o Ian Wehrman
+ o Ian Wehrman
- +o Gord Lamb
+ o Gord Lamb
- +o Eugene Koontz
+ o Eugene Koontz
- +o John H. Hartman
+ o John H. Hartman
- +o Anders Karlsson
+ o Anders Karlsson
- +o Daniel Phillips
+ o Daniel Phillips
- +o John Fremlin
+ o John Fremlin
- +o Rainer Burgstaller
+ o Rainer Burgstaller
- +o James Stevenson
+ o James Stevenson
- +o Matt Clay
+ o Matt Clay
- +o Cliff Jefferies
+ o Cliff Jefferies
- +o Geoff Hoff
+ o Geoff Hoff
- +o Lennert Buytenhek
+ o Lennert Buytenhek
- +o Al Viro
+ o Al Viro
- +o Frank Klingenhoefer
+ o Frank Klingenhoefer
- +o Livio Baldini Soares
+ o Livio Baldini Soares
- +o Jon Burgess
+ o Jon Burgess
- +o Petru Paler
+ o Petru Paler
- +o Paul
+ o Paul
- +o Chris Reahard
+ o Chris Reahard
- +o Sverker Nilsson
+ o Sverker Nilsson
- +o Gong Su
+ o Gong Su
- +o johan verrept
+ o johan verrept
- +o Bjorn Eriksson
+ o Bjorn Eriksson
- +o Lorenzo Allegrucci
+ o Lorenzo Allegrucci
- +o Muli Ben-Yehuda
+ o Muli Ben-Yehuda
- +o David Mansfield
+ o David Mansfield
- +o Howard Goff
+ o Howard Goff
- +o Mike Anderson
+ o Mike Anderson
- +o John Byrne
+ o John Byrne
- +o Sapan J. Batia
+ o Sapan J. Batia
- +o Iris Huang
+ o Iris Huang
- +o Jan Hudec
+ o Jan Hudec
- +o Voluspa
+ o Voluspa
- 1155..33.. BBuugglleettss aanndd cclleeaann--uuppss
+ 15.3. Buglets and clean-ups
- +o Dave Zarzycki
+ o Dave Zarzycki
- +o Adam Lazur
+ o Adam Lazur
- +o Boria Feigin
+ o Boria Feigin
- +o Brian J. Murrell
+ o Brian J. Murrell
- +o JS
+ o JS
- +o Roman Zippel
+ o Roman Zippel
- +o Wil Cooley
+ o Wil Cooley
- +o Ayelet Shemesh
+ o Ayelet Shemesh
- +o Will Dyson
+ o Will Dyson
- +o Sverker Nilsson
+ o Sverker Nilsson
- +o dvorak
+ o dvorak
- +o v.naga srinivas
+ o v.naga srinivas
- +o Shlomi Fish
+ o Shlomi Fish
- +o Roger Binns
+ o Roger Binns
- +o johan verrept
+ o johan verrept
- +o MrChuoi
+ o MrChuoi
- +o Peter Cleve
+ o Peter Cleve
- +o Vincent Guffens
+ o Vincent Guffens
- +o Nathan Scott
+ o Nathan Scott
- +o Patrick Caulfield
+ o Patrick Caulfield
- +o jbearce
+ o jbearce
- +o Catalin Marinas
+ o Catalin Marinas
- +o Shane Spencer
+ o Shane Spencer
- +o Zou Min
+ o Zou Min
- +o Ryan Boder
+ o Ryan Boder
- +o Lorenzo Colitti
+ o Lorenzo Colitti
- +o Gwendal Grignou
+ o Gwendal Grignou
- +o Andre' Breiler
+ o Andre' Breiler
- +o Tsutomu Yasuda
+ o Tsutomu Yasuda
- 1155..44.. CCaassee SSttuuddiieess
+ 15.4. Case Studies
- +o Jon Wright
+ o Jon Wright
- +o William McEwan
+ o William McEwan
- +o Michael Richardson
+ o Michael Richardson
- 1155..55.. OOtthheerr ccoonnttrriibbuuttiioonnss
+ 15.5. Other contributions
Bill Carr <Bill.Carr at compaq.com> made the Red Hat mkrootfs script
diff --git a/MAINTAINERS b/MAINTAINERS
index c406f9ba1923..479beaa39131 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6683,7 +6683,6 @@ F: drivers/net/ethernet/8390/ne-h8300.c
UDF FILESYSTEM
M: Jan Kara <jack@suse.cz>
-W: http://linux-udf.sourceforge.net
S: Maintained
F: Documentation/filesystems/udf.txt
F: fs/udf/
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 6fe874fc5f8e..481f4f76f664 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -108,9 +108,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, int mode)
ret->i_gid = hypfs_info->gid;
ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME;
if (mode & S_IFDIR)
- ret->i_nlink = 2;
- else
- ret->i_nlink = 1;
+ set_nlink(ret, 2);
}
return ret;
}
@@ -361,7 +359,7 @@ static struct dentry *hypfs_create_file(struct super_block *sb,
} else if (mode & S_IFDIR) {
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
- parent->d_inode->i_nlink++;
+ inc_nlink(parent->d_inode);
} else
BUG();
inode->i_private = data;
diff --git a/arch/um/Kconfig.char b/arch/um/Kconfig.char
index 70dabd1e0652..b9d7c4276682 100644
--- a/arch/um/Kconfig.char
+++ b/arch/um/Kconfig.char
@@ -1,5 +1,4 @@
-
-menu "Character Devices"
+menu "UML Character Devices"
config STDERR_CONSOLE
bool "stderr console"
@@ -105,92 +104,6 @@ config SSL_CHAN
this if you expect the UML that you build to be run in environments
which don't have a set of /dev/pty* devices.
-config UNIX98_PTYS
- bool "Unix98 PTY support"
- help
- A pseudo terminal (PTY) is a software device consisting of two
- halves: a master and a slave. The slave device behaves identical to
- a physical terminal; the master device is used by a process to
- read data from and write data to the slave, thereby emulating a
- terminal. Typical programs for the master side are telnet servers
- and xterms.
-
- Linux has traditionally used the BSD-like names /dev/ptyxx for
- masters and /dev/ttyxx for slaves of pseudo terminals. This scheme
- has a number of problems. The GNU C library glibc 2.1 and later,
- however, supports the Unix98 naming standard: in order to acquire a
- pseudo terminal, a process opens /dev/ptmx; the number of the pseudo
- terminal is then made available to the process and the pseudo
- terminal slave can be accessed as /dev/pts/<number>. What was
- traditionally /dev/ttyp2 will then be /dev/pts/2, for example.
-
- All modern Linux systems use the Unix98 ptys. Say Y unless
- you're on an embedded system and want to conserve memory.
-
-config LEGACY_PTYS
- bool "Legacy (BSD) PTY support"
- default y
- help
- A pseudo terminal (PTY) is a software device consisting of two
- halves: a master and a slave. The slave device behaves identical to
- a physical terminal; the master device is used by a process to
- read data from and write data to the slave, thereby emulating a
- terminal. Typical programs for the master side are telnet servers
- and xterms.
-
- Linux has traditionally used the BSD-like names /dev/ptyxx
- for masters and /dev/ttyxx for slaves of pseudo
- terminals. This scheme has a number of problems, including
- security. This option enables these legacy devices; on most
- systems, it is safe to say N.
-
-config RAW_DRIVER
- tristate "RAW driver (/dev/raw/rawN)"
- depends on BLOCK
- help
- The raw driver permits block devices to be bound to /dev/raw/rawN.
- Once bound, I/O against /dev/raw/rawN uses efficient zero-copy I/O.
- See the raw(8) manpage for more details.
-
- Applications should preferably open the device (eg /dev/hda1)
- with the O_DIRECT flag.
-
-config MAX_RAW_DEVS
- int "Maximum number of RAW devices to support (1-8192)"
- depends on RAW_DRIVER
- default "256"
- help
- The maximum number of RAW devices that are supported.
- Default is 256. Increase this number in case you need lots of
- raw devices.
-
-config LEGACY_PTY_COUNT
- int "Maximum number of legacy PTY in use"
- depends on LEGACY_PTYS
- default "256"
- help
- The maximum number of legacy PTYs that can be used at any one time.
- The default is 256, and should be more than enough. Embedded
- systems may want to reduce this to save memory.
-
- When not in use, each legacy PTY occupies 12 bytes on 32-bit
- architectures and 24 bytes on 64-bit architectures.
-
-config WATCHDOG
- bool "Watchdog Timer Support"
-
-config WATCHDOG_NOWAYOUT
- bool "Disable watchdog shutdown on close"
- depends on WATCHDOG
-
-config SOFT_WATCHDOG
- tristate "Software Watchdog"
- depends on WATCHDOG
-
-config UML_WATCHDOG
- tristate "UML watchdog"
- depends on WATCHDOG
-
config UML_SOUND
tristate "Sound support"
help
@@ -211,29 +124,4 @@ config HOSTAUDIO
tristate
default UML_SOUND
-#It is selected elsewhere, so kconfig would warn without this.
-config HW_RANDOM
- tristate
- default n
-
-config UML_RANDOM
- tristate "Hardware random number generator"
- help
- This option enables UML's "hardware" random number generator. It
- attaches itself to the host's /dev/random, supplying as much entropy
- as the host has, rather than the small amount the UML gets from its
- own drivers. It registers itself as a standard hardware random number
- generator, major 10, minor 183, and the canonical device name is
- /dev/hwrng.
- The way to make use of this is to install the rng-tools package
- (check your distro, or download from
- http://sourceforge.net/projects/gkernel/). rngd periodically reads
- /dev/hwrng and injects the entropy into /dev/random.
-
-config MMAPPER
- tristate "iomem emulation driver"
- help
- This driver allows a host file to be used as emulated IO memory inside
- UML.
-
endmenu
diff --git a/arch/um/Kconfig.rest b/arch/um/Kconfig.rest
index 0ccad0ff6d6e..567eb5fc21df 100644
--- a/arch/um/Kconfig.rest
+++ b/arch/um/Kconfig.rest
@@ -2,20 +2,14 @@ source "init/Kconfig"
source "kernel/Kconfig.freezer"
-source "drivers/block/Kconfig"
-
source "arch/um/Kconfig.char"
-source "drivers/base/Kconfig"
+source "drivers/Kconfig"
source "net/Kconfig"
source "arch/um/Kconfig.net"
-source "drivers/net/Kconfig"
-
-source "drivers/connector/Kconfig"
-
source "fs/Kconfig"
source "security/Kconfig"
@@ -24,19 +18,4 @@ source "crypto/Kconfig"
source "lib/Kconfig"
-source "drivers/scsi/Kconfig"
-
-source "drivers/md/Kconfig"
-
-if BROKEN
- source "drivers/mtd/Kconfig"
-endif
-
-source "drivers/leds/Kconfig"
-
-#This is just to shut up some Kconfig warnings, so no prompt.
-config INPUT
- tristate
- default n
-
source "arch/um/Kconfig.debug"
diff --git a/arch/um/Kconfig.um b/arch/um/Kconfig.um
index b5e675e370c6..70fd690964e4 100644
--- a/arch/um/Kconfig.um
+++ b/arch/um/Kconfig.um
@@ -148,5 +148,11 @@ config KERNEL_STACK_ORDER
be 1 << order pages. The default is OK unless you're running Valgrind
on UML, in which case, set this to 3.
+config MMAPPER
+ tristate "iomem emulation driver"
+ help
+ This driver allows a host file to be used as emulated IO memory inside
+ UML.
+
config NO_DMA
def_bool y
diff --git a/arch/um/Makefile b/arch/um/Makefile
index c0f712cc7c5f..7730af6ec13f 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -20,15 +20,27 @@ core-y += $(ARCH_DIR)/kernel/ \
MODE_INCLUDE += -I$(srctree)/$(ARCH_DIR)/include/shared/skas
+HEADER_ARCH := $(SUBARCH)
+
+# Additional ARCH settings for x86
+ifeq ($(SUBARCH),i386)
+ HEADER_ARCH := x86
+endif
+ifeq ($(SUBARCH),x86_64)
+ HEADER_ARCH := x86
+endif
+
+HOST_DIR := arch/$(HEADER_ARCH)
+
include $(srctree)/$(ARCH_DIR)/Makefile-skas
+include $(srctree)/$(HOST_DIR)/Makefile.um
+
+core-y += $(HOST_DIR)/um/
SHARED_HEADERS := $(ARCH_DIR)/include/shared
ARCH_INCLUDE := -I$(srctree)/$(SHARED_HEADERS)
-ARCH_INCLUDE += -I$(srctree)/$(ARCH_DIR)/sys-$(SUBARCH)/shared
-ifneq ($(KBUILD_SRC),)
-ARCH_INCLUDE += -I$(SHARED_HEADERS)
-endif
-KBUILD_CPPFLAGS += -I$(srctree)/$(ARCH_DIR)/sys-$(SUBARCH)
+ARCH_INCLUDE += -I$(srctree)/$(HOST_DIR)/um/shared
+KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/um
# -Dvmap=kernel_vmap prevents anything from referencing the libpcap.o symbol so
# named - it's a common symbol in libpcap, so we get a binary which crashes.
@@ -47,14 +59,12 @@ KBUILD_AFLAGS += $(ARCH_INCLUDE)
USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -D__KERNEL__,,\
$(patsubst -I%,,$(KBUILD_CFLAGS)))) $(ARCH_INCLUDE) $(MODE_INCLUDE) \
- $(filter -I%,$(CFLAGS)) -D_FILE_OFFSET_BITS=64
-
-include $(srctree)/$(ARCH_DIR)/Makefile-$(SUBARCH)
+ $(filter -I%,$(CFLAGS)) -D_FILE_OFFSET_BITS=64 -idirafter include
#This will adjust *FLAGS accordingly to the platform.
include $(srctree)/$(ARCH_DIR)/Makefile-os-$(OS)
-KBUILD_CPPFLAGS += -I$(srctree)/arch/$(HEADER_ARCH)/include
+KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/include
# -Derrno=kernel_errno - This turns all kernel references to errno into
# kernel_errno to separate them from the libc errno. This allows -fno-common
@@ -84,10 +94,9 @@ define archhelp
echo ' find in the kernel root.'
endef
-KBUILD_KCONFIG := arch/um/Kconfig.$(HEADER_ARCH)
+KBUILD_KCONFIG := $(HOST_DIR)/um/Kconfig
-archprepare: $(SHARED_HEADERS)/user_constants.h
-archprepare: $(SHARED_HEADERS)/kern_constants.h
+archprepare: include/generated/user_constants.h
LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib
@@ -118,9 +127,7 @@ endef
# When cleaning we don't include .config, so we don't include
# TT or skas makefiles and don't clean skas_ptregs.h.
-CLEAN_FILES += linux x.i gmon.out \
- $(SHARED_HEADERS)/user_constants.h \
- $(SHARED_HEADERS)/kern_constants.h
+CLEAN_FILES += linux x.i gmon.out
archclean:
@find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \
@@ -128,8 +135,8 @@ archclean:
# Generated files
-$(ARCH_DIR)/sys-$(SUBARCH)/user-offsets.s: FORCE
- $(Q)$(MAKE) $(build)=$(ARCH_DIR)/sys-$(SUBARCH) $@
+$(HOST_DIR)/um/user-offsets.s: FORCE
+ $(Q)$(MAKE) $(build)=$(HOST_DIR)/um $@
define filechk_gen-asm-offsets
(set -e; \
@@ -144,11 +151,7 @@ define filechk_gen-asm-offsets
echo ""; )
endef
-$(SHARED_HEADERS)/user_constants.h: $(ARCH_DIR)/sys-$(SUBARCH)/user-offsets.s
+include/generated/user_constants.h: $(HOST_DIR)/um/user-offsets.s
$(call filechk,gen-asm-offsets)
-$(SHARED_HEADERS)/kern_constants.h:
- $(Q)mkdir -p $(dir $@)
- $(Q)echo '#include "../../../../include/generated/asm-offsets.h"' >$@
-
-export SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS HEADER_ARCH DEV_NULL_PATH
+export SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS DEV_NULL_PATH
diff --git a/arch/um/Makefile-x86_64 b/arch/um/Makefile-x86_64
deleted file mode 100644
index a9cd7e77a7ab..000000000000
--- a/arch/um/Makefile-x86_64
+++ /dev/null
@@ -1,26 +0,0 @@
-# Copyright 2003 - 2004 Pathscale, Inc
-# Released under the GPL
-
-core-y += arch/um/sys-x86_64/ arch/x86/crypto/
-START := 0x60000000
-
-_extra_flags_ = -fno-builtin -m64
-
-KBUILD_CFLAGS += $(_extra_flags_)
-
-CHECKFLAGS += -m64 -D__x86_64__
-KBUILD_AFLAGS += -m64
-LDFLAGS += -m elf_x86_64
-KBUILD_CPPFLAGS += -m64
-
-ELF_ARCH := i386:x86-64
-ELF_FORMAT := elf64-x86-64
-HEADER_ARCH := x86
-
-# Not on all 64-bit distros /lib is a symlink to /lib64. PLD is an example.
-
-LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib64
-LINK-y += -m64
-
-# Do unit-at-a-time unconditionally on x86_64, following the host
-KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
diff --git a/arch/um/include/shared/chan_kern.h b/arch/um/drivers/chan.h
index 1e651457e049..8df0fd9024dc 100644
--- a/arch/um/include/shared/chan_kern.h
+++ b/arch/um/drivers/chan.h
@@ -6,9 +6,9 @@
#ifndef __CHAN_KERN_H__
#define __CHAN_KERN_H__
-#include "linux/tty.h"
-#include "linux/list.h"
-#include "linux/console.h"
+#include <linux/tty.h>
+#include <linux/list.h>
+#include <linux/console.h>
#include "chan_user.h"
#include "line.h"
diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c
index d4191fe1cede..420e2c800799 100644
--- a/arch/um/drivers/chan_kern.c
+++ b/arch/um/drivers/chan_kern.c
@@ -6,7 +6,7 @@
#include <linux/slab.h>
#include <linux/tty.h>
#include <linux/tty_flip.h>
-#include "chan_kern.h"
+#include "chan.h"
#include "os.h"
#ifdef CONFIG_NOCONFIG_CHAN
@@ -358,11 +358,11 @@ int chan_window_size(struct list_head *chans, unsigned short *rows_out,
return 0;
}
-static void free_one_chan(struct chan *chan, int delay_free_irq)
+static void free_one_chan(struct chan *chan)
{
list_del(&chan->list);
- close_one_chan(chan, delay_free_irq);
+ close_one_chan(chan, 0);
if (chan->ops->free != NULL)
(*chan->ops->free)(chan->data);
@@ -372,14 +372,14 @@ static void free_one_chan(struct chan *chan, int delay_free_irq)
kfree(chan);
}
-static void free_chan(struct list_head *chans, int delay_free_irq)
+static void free_chan(struct list_head *chans)
{
struct list_head *ele, *next;
struct chan *chan;
list_for_each_safe(ele, next, chans) {
chan = list_entry(ele, struct chan, list);
- free_one_chan(chan, delay_free_irq);
+ free_one_chan(chan);
}
}
@@ -547,7 +547,7 @@ int parse_chan_pair(char *str, struct line *line, int device,
char *in, *out;
if (!list_empty(chans)) {
- free_chan(chans, 0);
+ free_chan(chans);
INIT_LIST_HEAD(chans);
}
diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c
index cfeb3f4a44af..f180813ce2c7 100644
--- a/arch/um/drivers/chan_user.c
+++ b/arch/um/drivers/chan_user.c
@@ -11,10 +11,8 @@
#include <termios.h>
#include <sys/ioctl.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
void generic_close(int fd, void *unused)
{
@@ -283,7 +281,12 @@ void register_winch(int fd, struct tty_struct *tty)
return;
pid = tcgetpgrp(fd);
- if (!is_skas_winch(pid, fd, tty) && (pid == -1)) {
+ if (is_skas_winch(pid, fd, tty)) {
+ register_winch_irq(-1, fd, -1, tty, 0);
+ return;
+ }
+
+ if (pid == -1) {
thread = winch_tramp(fd, tty, &thread_fd, &stack);
if (thread < 0)
return;
diff --git a/arch/um/include/shared/chan_user.h b/arch/um/drivers/chan_user.h
index 9b9ced85b703..9b9ced85b703 100644
--- a/arch/um/include/shared/chan_user.h
+++ b/arch/um/drivers/chan_user.h
diff --git a/arch/um/drivers/cow_sys.h b/arch/um/drivers/cow_sys.h
index f5701fd2ef90..7f2ed0b8824a 100644
--- a/arch/um/drivers/cow_sys.h
+++ b/arch/um/drivers/cow_sys.h
@@ -3,7 +3,6 @@
#include "kern_util.h"
#include "os.h"
-#include "user.h"
#include "um_malloc.h"
static inline void *cow_malloc(int size)
diff --git a/arch/um/drivers/daemon_user.c b/arch/um/drivers/daemon_user.c
index f8e85e0bdace..a4fd7bc14af7 100644
--- a/arch/um/drivers/daemon_user.c
+++ b/arch/um/drivers/daemon_user.c
@@ -17,7 +17,6 @@
#include "net_user.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
enum request_type { REQ_NEW_CONTROL };
diff --git a/arch/um/drivers/fd.c b/arch/um/drivers/fd.c
index f5a981a16240..5b81d2574415 100644
--- a/arch/um/drivers/fd.c
+++ b/arch/um/drivers/fd.c
@@ -9,10 +9,8 @@
#include <errno.h>
#include <termios.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
struct fd_chan {
int fd;
diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c
index 84dce3fc590c..0345d6206d40 100644
--- a/arch/um/drivers/harddog_user.c
+++ b/arch/um/drivers/harddog_user.c
@@ -7,7 +7,6 @@
#include <unistd.h>
#include <errno.h>
#include "os.h"
-#include "user.h"
struct dog_data {
int stdin;
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index 364c8a15c4c3..c1cf2206b84b 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -7,7 +7,7 @@
#include "linux/kd.h"
#include "linux/sched.h"
#include "linux/slab.h"
-#include "chan_kern.h"
+#include "chan.h"
#include "irq_kern.h"
#include "irq_user.h"
#include "kern_util.h"
diff --git a/arch/um/include/shared/line.h b/arch/um/drivers/line.h
index 63df3ca02ac2..63df3ca02ac2 100644
--- a/arch/um/include/shared/line.h
+++ b/arch/um/drivers/line.h
diff --git a/arch/um/include/shared/mconsole.h b/arch/um/drivers/mconsole.h
index c139ae1d6826..c139ae1d6826 100644
--- a/arch/um/include/shared/mconsole.h
+++ b/arch/um/drivers/mconsole.h
diff --git a/arch/um/include/shared/mconsole_kern.h b/arch/um/drivers/mconsole_kern.h
index d2fe07e78958..d2fe07e78958 100644
--- a/arch/um/include/shared/mconsole_kern.h
+++ b/arch/um/drivers/mconsole_kern.h
diff --git a/arch/um/drivers/mconsole_user.c b/arch/um/drivers/mconsole_user.c
index f8cf4c8bedef..99209826adb1 100644
--- a/arch/um/drivers/mconsole_user.c
+++ b/arch/um/drivers/mconsole_user.c
@@ -10,9 +10,7 @@
#include <sys/socket.h>
#include <sys/uio.h>
#include <sys/un.h>
-#include "kern_constants.h"
#include "mconsole.h"
-#include "user.h"
static struct mconsole_command commands[] = {
/*
diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c
index 520118888f16..05090c37fa84 100644
--- a/arch/um/drivers/net_user.c
+++ b/arch/um/drivers/net_user.c
@@ -12,10 +12,8 @@
#include <sys/socket.h>
#include <sys/wait.h>
#include "net_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
int tap_open_common(void *dev, char *gate_addr)
{
diff --git a/arch/um/drivers/pcap_user.c b/arch/um/drivers/pcap_user.c
index 5f903587d69e..702a75b190ee 100644
--- a/arch/um/drivers/pcap_user.c
+++ b/arch/um/drivers/pcap_user.c
@@ -9,9 +9,7 @@
#include <asm/types.h>
#include "net_user.h"
#include "pcap_user.h"
-#include "kern_constants.h"
#include "um_malloc.h"
-#include "user.h"
#define PCAP_FD(p) (*(int *)(p))
diff --git a/arch/um/drivers/port_user.c b/arch/um/drivers/port_user.c
index b49bf56a56aa..7b010b76ddf0 100644
--- a/arch/um/drivers/port_user.c
+++ b/arch/um/drivers/port_user.c
@@ -10,11 +10,9 @@
#include <unistd.h>
#include <netinet/in.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "port.h"
#include "um_malloc.h"
-#include "user.h"
struct port_chan {
int raw;
diff --git a/arch/um/drivers/pty.c b/arch/um/drivers/pty.c
index 1113911dcb2b..cff2b75d31fd 100644
--- a/arch/um/drivers/pty.c
+++ b/arch/um/drivers/pty.c
@@ -12,10 +12,8 @@
#include <termios.h>
#include <sys/stat.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
struct pty_chan {
void (*announce)(char *dev_name, int dev);
diff --git a/arch/um/drivers/slip_user.c b/arch/um/drivers/slip_user.c
index cbacfc4e63e6..932b4d69bec2 100644
--- a/arch/um/drivers/slip_user.c
+++ b/arch/um/drivers/slip_user.c
@@ -11,12 +11,10 @@
#include <string.h>
#include <sys/termios.h>
#include <sys/wait.h>
-#include "kern_constants.h"
#include "net_user.h"
#include "os.h"
#include "slip.h"
#include "um_malloc.h"
-#include "user.h"
static int slip_user_init(void *data, void *dev)
{
diff --git a/arch/um/drivers/slirp_user.c b/arch/um/drivers/slirp_user.c
index a0ada8fec72a..db4adb639ff8 100644
--- a/arch/um/drivers/slirp_user.c
+++ b/arch/um/drivers/slirp_user.c
@@ -7,11 +7,9 @@
#include <errno.h>
#include <string.h>
#include <sys/wait.h>
-#include "kern_constants.h"
#include "net_user.h"
#include "os.h"
#include "slirp.h"
-#include "user.h"
static int slirp_user_init(void *data, void *dev)
{
diff --git a/arch/um/drivers/ssl.c b/arch/um/drivers/ssl.c
index f1786e64607f..9d8c20af6f80 100644
--- a/arch/um/drivers/ssl.c
+++ b/arch/um/drivers/ssl.c
@@ -12,10 +12,8 @@
#include "linux/console.h"
#include "asm/termbits.h"
#include "asm/irq.h"
-#include "line.h"
#include "ssl.h"
-#include "chan_kern.h"
-#include "kern.h"
+#include "chan.h"
#include "init.h"
#include "irq_user.h"
#include "mconsole_kern.h"
diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c
index 49266f6108c4..088776f01908 100644
--- a/arch/um/drivers/stdio_console.c
+++ b/arch/um/drivers/stdio_console.c
@@ -20,8 +20,7 @@
#include "asm/current.h"
#include "asm/irq.h"
#include "stdio_console.h"
-#include "line.h"
-#include "chan_kern.h"
+#include "chan.h"
#include "irq_user.h"
#include "mconsole_kern.h"
#include "init.h"
diff --git a/arch/um/drivers/tty.c b/arch/um/drivers/tty.c
index 495858a090e4..a97391f9ec54 100644
--- a/arch/um/drivers/tty.c
+++ b/arch/um/drivers/tty.c
@@ -7,10 +7,8 @@
#include <fcntl.h>
#include <termios.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
struct tty_chan {
char *dev;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 620f5b70957d..944453a3ec99 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -46,7 +46,6 @@
#include "asm/tlbflush.h"
#include "mem_user.h"
#include "kern_util.h"
-#include "kern.h"
#include "mconsole_kern.h"
#include "init.h"
#include "irq_user.h"
@@ -54,7 +53,6 @@
#include "ubd_user.h"
#include "os.h"
#include "mem.h"
-#include "mem_kern.h"
#include "cow.h"
enum ubd_req { UBD_READ, UBD_WRITE };
@@ -513,8 +511,37 @@ __uml_exitcall(kill_io_thread);
static inline int ubd_file_size(struct ubd *ubd_dev, __u64 *size_out)
{
char *file;
+ int fd;
+ int err;
+
+ __u32 version;
+ __u32 align;
+ char *backing_file;
+ time_t mtime;
+ unsigned long long size;
+ int sector_size;
+ int bitmap_offset;
+
+ if (ubd_dev->file && ubd_dev->cow.file) {
+ file = ubd_dev->cow.file;
+
+ goto out;
+ }
- file = ubd_dev->cow.file ? ubd_dev->cow.file : ubd_dev->file;
+ fd = os_open_file(ubd_dev->file, global_openflags, 0);
+ if (fd < 0)
+ return fd;
+
+ err = read_cow_header(file_reader, &fd, &version, &backing_file, \
+ &mtime, &size, &sector_size, &align, &bitmap_offset);
+ os_close_file(fd);
+
+ if(err == -EINVAL)
+ file = ubd_dev->file;
+ else
+ file = backing_file;
+
+out:
return os_file_size(file, size_out);
}
diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c
index b591bb9c41dd..007b94d97726 100644
--- a/arch/um/drivers/ubd_user.c
+++ b/arch/um/drivers/ubd_user.c
@@ -16,7 +16,6 @@
#include <sys/mman.h>
#include <sys/param.h>
#include "asm/types.h"
-#include "user.h"
#include "ubd_user.h"
#include "os.h"
#include "cow.h"
diff --git a/arch/um/include/shared/ubd_user.h b/arch/um/drivers/ubd_user.h
index 3845051f1b10..3845051f1b10 100644
--- a/arch/um/include/shared/ubd_user.h
+++ b/arch/um/drivers/ubd_user.h
diff --git a/arch/um/drivers/umcast_user.c b/arch/um/drivers/umcast_user.c
index 59c56fd6f52a..010fa2d849ec 100644
--- a/arch/um/drivers/umcast_user.c
+++ b/arch/um/drivers/umcast_user.c
@@ -15,11 +15,9 @@
#include <unistd.h>
#include <errno.h>
#include <netinet/in.h>
-#include "kern_constants.h"
#include "umcast.h"
#include "net_user.h"
#include "um_malloc.h"
-#include "user.h"
static struct sockaddr_in *new_addr(char *addr, unsigned short port)
{
diff --git a/arch/um/drivers/vde_user.c b/arch/um/drivers/vde_user.c
index c5c43253e6ce..b8c286748d3d 100644
--- a/arch/um/drivers/vde_user.c
+++ b/arch/um/drivers/vde_user.c
@@ -6,10 +6,8 @@
#include <stddef.h>
#include <errno.h>
#include <libvdeplug.h>
-#include "kern_constants.h"
#include "net_user.h"
#include "um_malloc.h"
-#include "user.h"
#include "vde.h"
static int vde_user_init(void *data, void *dev)
diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c
index 2e1de5728604..969110e56487 100644
--- a/arch/um/drivers/xterm.c
+++ b/arch/um/drivers/xterm.c
@@ -11,10 +11,8 @@
#include <string.h>
#include <termios.h>
#include "chan_user.h"
-#include "kern_constants.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
#include "xterm.h"
struct xterm_chan {
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
new file mode 100644
index 000000000000..451f4517b334
--- /dev/null
+++ b/arch/um/include/asm/Kbuild
@@ -0,0 +1,3 @@
+generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
+generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
+generic-y += ftrace.h
diff --git a/arch/um/include/asm/bug.h b/arch/um/include/asm/bug.h
deleted file mode 100644
index 9e33b864c359..000000000000
--- a/arch/um/include/asm/bug.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_BUG_H
-#define __UM_BUG_H
-
-#include <asm-generic/bug.h>
-
-#endif
diff --git a/arch/um/include/asm/checksum.h b/arch/um/include/asm/checksum.h
deleted file mode 100644
index 5b501361e361..000000000000
--- a/arch/um/include/asm/checksum.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_CHECKSUM_H
-#define __UM_CHECKSUM_H
-
-#include "sysdep/checksum.h"
-
-#endif
diff --git a/arch/um/include/asm/cputime.h b/arch/um/include/asm/cputime.h
deleted file mode 100644
index c84acbadfa2f..000000000000
--- a/arch/um/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_CPUTIME_H
-#define __UM_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __UM_CPUTIME_H */
diff --git a/arch/um/include/asm/device.h b/arch/um/include/asm/device.h
deleted file mode 100644
index d8f9872b0e2d..000000000000
--- a/arch/um/include/asm/device.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-#include <asm-generic/device.h>
-
diff --git a/arch/um/include/asm/emergency-restart.h b/arch/um/include/asm/emergency-restart.h
deleted file mode 100644
index 108d8c48e42e..000000000000
--- a/arch/um/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/um/include/asm/ftrace.h b/arch/um/include/asm/ftrace.h
deleted file mode 100644
index 40a8c178f10d..000000000000
--- a/arch/um/include/asm/ftrace.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/um/include/asm/futex.h b/arch/um/include/asm/futex.h
deleted file mode 100644
index 6a332a9f099c..000000000000
--- a/arch/um/include/asm/futex.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_FUTEX_H
-#define _ASM_FUTEX_H
-
-#include <asm-generic/futex.h>
-
-#endif
diff --git a/arch/um/include/asm/hardirq.h b/arch/um/include/asm/hardirq.h
deleted file mode 100644
index fb3c05a0cbbf..000000000000
--- a/arch/um/include/asm/hardirq.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/hardirq.h>
diff --git a/arch/um/include/asm/hw_irq.h b/arch/um/include/asm/hw_irq.h
deleted file mode 100644
index 1cf84cf5f21a..000000000000
--- a/arch/um/include/asm/hw_irq.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ASM_UM_HW_IRQ_H
-#define _ASM_UM_HW_IRQ_H
-
-#include "asm/irq.h"
-#include "asm/archparam.h"
-
-#endif
diff --git a/arch/um/include/asm/irq_regs.h b/arch/um/include/asm/irq_regs.h
deleted file mode 100644
index 3dd9c0b70270..000000000000
--- a/arch/um/include/asm/irq_regs.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/um/include/asm/irqflags.h b/arch/um/include/asm/irqflags.h
index 659b9abdfdba..c780d8a16773 100644
--- a/arch/um/include/asm/irqflags.h
+++ b/arch/um/include/asm/irqflags.h
@@ -1,6 +1,42 @@
#ifndef __UM_IRQFLAGS_H
#define __UM_IRQFLAGS_H
-/* Empty for now */
+extern int get_signals(void);
+extern int set_signals(int enable);
+extern void block_signals(void);
+extern void unblock_signals(void);
+
+static inline unsigned long arch_local_save_flags(void)
+{
+ return get_signals();
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+ set_signals(flags);
+}
+
+static inline void arch_local_irq_enable(void)
+{
+ unblock_signals();
+}
+
+static inline void arch_local_irq_disable(void)
+{
+ block_signals();
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+ unsigned long flags;
+ flags = arch_local_save_flags();
+ arch_local_irq_disable();
+ return flags;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+ return arch_local_save_flags() == 0;
+}
#endif
diff --git a/arch/um/include/asm/kdebug.h b/arch/um/include/asm/kdebug.h
deleted file mode 100644
index 6ece1b037665..000000000000
--- a/arch/um/include/asm/kdebug.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/kdebug.h>
diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h
index cf259de51531..30509b9f37fd 100644
--- a/arch/um/include/asm/mmu.h
+++ b/arch/um/include/asm/mmu.h
@@ -1,12 +1,24 @@
/*
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*/
-#ifndef __MMU_H
-#define __MMU_H
+#ifndef __ARCH_UM_MMU_H
+#define __ARCH_UM_MMU_H
-#include "um_mmu.h"
+#include "mm_id.h"
+#include <asm/mm_context.h>
-#endif
+typedef struct mm_context {
+ struct mm_id id;
+ struct uml_arch_mm_context arch;
+ struct page **stub_pages;
+} mm_context_t;
+
+extern void __switch_mm(struct mm_id * mm_idp);
+/* Avoid tangled inclusion with asm/ldt.h */
+extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm);
+extern void free_ldt(struct mm_context *mm);
+
+#endif
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index 34d813011b7a..591b3d8d7614 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -6,15 +6,12 @@
#ifndef __UM_MMU_CONTEXT_H
#define __UM_MMU_CONTEXT_H
-#include "linux/sched.h"
-#include "um_mmu.h"
+#include <linux/sched.h>
+#include <asm/mmu.h>
extern void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm);
extern void arch_exit_mmap(struct mm_struct *mm);
-#define get_mmu_context(task) do ; while(0)
-#define activate_context(tsk) do ; while(0)
-
#define deactivate_mm(tsk,mm) do { } while (0)
extern void force_flush_all(void);
diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h
index 4cc9b6cf480a..7cfc3cedce84 100644
--- a/arch/um/include/asm/page.h
+++ b/arch/um/include/asm/page.h
@@ -19,7 +19,7 @@
struct page;
#include <linux/types.h>
-#include <sysdep/vm-flags.h>
+#include <asm/vm-flags.h>
/*
* These are used to make use of C type-checking..
diff --git a/arch/um/include/asm/page_offset.h b/arch/um/include/asm/page_offset.h
deleted file mode 100644
index 1c168dfbf359..000000000000
--- a/arch/um/include/asm/page_offset.h
+++ /dev/null
@@ -1 +0,0 @@
-#define PAGE_OFFSET_RAW (uml_physmem)
diff --git a/arch/um/include/asm/pda.h b/arch/um/include/asm/pda.h
deleted file mode 100644
index ddcd774fc2a0..000000000000
--- a/arch/um/include/asm/pda.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_PDA_X86_64_H
-#define __UM_PDA_X86_64_H
-
-/* XXX */
-struct foo {
- unsigned int __softirq_pending;
- unsigned int __nmi_count;
-};
-
-extern struct foo me;
-
-#define read_pda(me) (&me)
-
-#endif
-
diff --git a/arch/um/include/asm/percpu.h b/arch/um/include/asm/percpu.h
deleted file mode 100644
index efe7508d8abd..000000000000
--- a/arch/um/include/asm/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_PERCPU_H
-#define __UM_PERCPU_H
-
-#include <asm-generic/percpu.h>
-
-#endif /* __UM_PERCPU_H */
diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h
index 1a7d2757fe05..f605d3c4844c 100644
--- a/arch/um/include/asm/ptrace-generic.h
+++ b/arch/um/include/asm/ptrace-generic.h
@@ -23,17 +23,10 @@ struct pt_regs {
#define PT_REGS_IP(r) UPT_IP(&(r)->regs)
#define PT_REGS_SP(r) UPT_SP(&(r)->regs)
-#define PT_REG(r, reg) UPT_REG(&(r)->regs, reg)
-#define PT_REGS_SET(r, reg, val) UPT_SET(&(r)->regs, reg, val)
-
-#define PT_REGS_SET_SYSCALL_RETURN(r, res) \
- UPT_SET_SYSCALL_RETURN(&(r)->regs, res)
#define PT_REGS_RESTART_SYSCALL(r) UPT_RESTART_SYSCALL(&(r)->regs)
#define PT_REGS_SYSCALL_NR(r) UPT_SYSCALL_NR(&(r)->regs)
-#define PT_REGS_SC(r) UPT_SC(&(r)->regs)
-
#define instruction_pointer(regs) PT_REGS_IP(regs)
struct task_struct;
diff --git a/arch/um/include/asm/sections.h b/arch/um/include/asm/sections.h
deleted file mode 100644
index 6b0231eefea8..000000000000
--- a/arch/um/include/asm/sections.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _UM_SECTIONS_H
-#define _UM_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/arch/um/include/asm/system.h b/arch/um/include/asm/system.h
deleted file mode 100644
index 68a90ecd1450..000000000000
--- a/arch/um/include/asm/system.h
+++ /dev/null
@@ -1,47 +0,0 @@
-#ifndef __UM_SYSTEM_GENERIC_H
-#define __UM_SYSTEM_GENERIC_H
-
-#include "sysdep/system.h"
-
-extern int get_signals(void);
-extern int set_signals(int enable);
-extern void block_signals(void);
-extern void unblock_signals(void);
-
-static inline unsigned long arch_local_save_flags(void)
-{
- return get_signals();
-}
-
-static inline void arch_local_irq_restore(unsigned long flags)
-{
- set_signals(flags);
-}
-
-static inline void arch_local_irq_enable(void)
-{
- unblock_signals();
-}
-
-static inline void arch_local_irq_disable(void)
-{
- block_signals();
-}
-
-static inline unsigned long arch_local_irq_save(void)
-{
- unsigned long flags;
- flags = arch_local_save_flags();
- arch_local_irq_disable();
- return flags;
-}
-
-static inline bool arch_irqs_disabled(void)
-{
- return arch_local_save_flags() == 0;
-}
-
-extern void *_switch_to(void *prev, void *next, void *last);
-#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
-
-#endif
diff --git a/arch/um/include/asm/topology.h b/arch/um/include/asm/topology.h
deleted file mode 100644
index 0905e4f21d42..000000000000
--- a/arch/um/include/asm/topology.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_UM_TOPOLOGY_H
-#define _ASM_UM_TOPOLOGY_H
-
-#include <asm-generic/topology.h>
-
-#endif
diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h
index b9a895d6fa1d..3f22fbf7ca1d 100644
--- a/arch/um/include/asm/uaccess.h
+++ b/arch/um/include/asm/uaccess.h
@@ -6,15 +6,15 @@
#ifndef __UM_UACCESS_H
#define __UM_UACCESS_H
-#include <asm/errno.h>
-#include <asm/processor.h>
-
/* thread_info has a mm_segment_t in it, so put the definition up here */
typedef struct {
unsigned long seg;
} mm_segment_t;
-#include "linux/thread_info.h"
+#include <linux/thread_info.h>
+#include <linux/errno.h>
+#include <asm/processor.h>
+#include <asm/elf.h>
#define VERIFY_READ 0
#define VERIFY_WRITE 1
@@ -38,7 +38,86 @@ typedef struct {
#define segment_eq(a, b) ((a).seg == (b).seg)
-#include "um_uaccess.h"
+#define __under_task_size(addr, size) \
+ (((unsigned long) (addr) < TASK_SIZE) && \
+ (((unsigned long) (addr) + (size)) < TASK_SIZE))
+
+#define __access_ok_vsyscall(type, addr, size) \
+ ((type == VERIFY_READ) && \
+ ((unsigned long) (addr) >= FIXADDR_USER_START) && \
+ ((unsigned long) (addr) + (size) <= FIXADDR_USER_END) && \
+ ((unsigned long) (addr) + (size) >= (unsigned long)(addr)))
+
+#define __addr_range_nowrap(addr, size) \
+ ((unsigned long) (addr) <= ((unsigned long) (addr) + (size)))
+
+#define access_ok(type, addr, size) \
+ (__addr_range_nowrap(addr, size) && \
+ (__under_task_size(addr, size) || \
+ __access_ok_vsyscall(type, addr, size) || \
+ segment_eq(get_fs(), KERNEL_DS)))
+
+extern int copy_from_user(void *to, const void __user *from, int n);
+extern int copy_to_user(void __user *to, const void *from, int n);
+
+/*
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst: Destination address, in kernel space. This buffer must be at
+ * least @count bytes long.
+ * @src: Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+
+extern int strncpy_from_user(char *dst, const char __user *src, int count);
+
+/*
+ * __clear_user: - Zero a block of memory in user space, with less checking.
+ * @to: Destination address, in user space.
+ * @n: Number of bytes to zero.
+ *
+ * Zero a block of memory in user space. Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+extern int __clear_user(void __user *mem, int len);
+
+/*
+ * clear_user: - Zero a block of memory in user space.
+ * @to: Destination address, in user space.
+ * @n: Number of bytes to zero.
+ *
+ * Zero a block of memory in user space.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+extern int clear_user(void __user *mem, int len);
+
+/*
+ * strlen_user: - Get the size of a string in user space.
+ * @str: The string to measure.
+ * @n: The maximum valid length
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * On exception, returns 0.
+ * If the string is too long, returns a value greater than @n.
+ */
+extern int strnlen_user(const void __user *str, int len);
#define __copy_from_user(to, from, n) copy_from_user(to, from, n)
diff --git a/arch/um/include/asm/xor.h b/arch/um/include/asm/xor.h
deleted file mode 100644
index a19db3e17241..000000000000
--- a/arch/um/include/asm/xor.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_XOR_H
-#define __UM_XOR_H
-
-#include "asm-generic/xor.h"
-
-#endif
diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h
index a92b678503cf..896e16602176 100644
--- a/arch/um/include/shared/as-layout.h
+++ b/arch/um/include/shared/as-layout.h
@@ -6,7 +6,7 @@
#ifndef __START_H__
#define __START_H__
-#include "kern_constants.h"
+#include <generated/asm-offsets.h>
/*
* Stolen from linux/const.h, which can't be directly included since
diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h
index 72009c7e3210..d7fe563aa7e7 100644
--- a/arch/um/include/shared/common-offsets.h
+++ b/arch/um/include/shared/common-offsets.h
@@ -2,7 +2,6 @@
DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE);
-OFFSET(HOST_TASK_REGS, task_struct, thread.regs);
OFFSET(HOST_TASK_PID, task_struct, pid);
DEFINE(UM_KERN_PAGE_SIZE, PAGE_SIZE);
diff --git a/arch/um/include/shared/initrd.h b/arch/um/include/shared/initrd.h
deleted file mode 100644
index 22673bcc273d..000000000000
--- a/arch/um/include/shared/initrd.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * Copyright (C) 2000 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __INITRD_USER_H__
-#define __INITRD_USER_H__
-
-extern int load_initrd(char *filename, void *buf, int size);
-
-#endif
-
diff --git a/arch/um/include/shared/kern.h b/arch/um/include/shared/kern.h
index 4ce3fc650e57..6cd01240bbf0 100644
--- a/arch/um/include/shared/kern.h
+++ b/arch/um/include/shared/kern.h
@@ -13,28 +13,10 @@
* includes.
*/
-extern int errno;
-
-extern int clone(int (*proc)(void *), void *sp, int flags, void *data);
-extern int sleep(int);
extern int printf(const char *fmt, ...);
-extern char *strerror(int errnum);
-extern char *ptsname(int __fd);
-extern int munmap(void *, int);
extern void *sbrk(int increment);
-extern void *malloc(int size);
-extern void perror(char *err);
-extern int kill(int pid, int sig);
-extern int getuid(void);
-extern int getgid(void);
extern int pause(void);
-extern int write(int, const void *, int);
extern void exit(int);
-extern int close(int);
-extern int read(unsigned int, char *, int);
-extern int pipe(int *);
-extern int sched_yield(void);
-extern int ptrace(int op, int pid, long addr, long data);
#endif
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index 3c341222d252..0f1483852460 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -21,7 +21,6 @@ extern unsigned long alloc_stack(int order, int atomic);
extern void free_stack(unsigned long stack, int order);
extern int do_signal(void);
-extern void copy_sc(struct uml_pt_regs *regs, void *from);
extern void interrupt_end(void);
extern void relay_signal(int sig, struct uml_pt_regs *regs);
diff --git a/arch/um/include/shared/ldt.h b/arch/um/include/shared/ldt.h
deleted file mode 100644
index a7f999a58774..000000000000
--- a/arch/um/include/shared/ldt.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright (C) 2004 Fujitsu Siemens Computers GmbH
- * Licensed under the GPL
- *
- * Author: Bodo Stroesser <bstroesser@fujitsu-siemens.com>
- */
-
-#ifndef __ASM_LDT_H
-#define __ASM_LDT_H
-
-#include <linux/mutex.h>
-#include <sysdep/host_ldt.h>
-
-extern void ldt_host_info(void);
-
-#define LDT_PAGES_MAX \
- ((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE)
-#define LDT_ENTRIES_PER_PAGE \
- (PAGE_SIZE/LDT_ENTRY_SIZE)
-#define LDT_DIRECT_ENTRIES \
- ((LDT_PAGES_MAX*sizeof(void *))/LDT_ENTRY_SIZE)
-
-struct ldt_entry {
- __u32 a;
- __u32 b;
-};
-
-typedef struct uml_ldt {
- int entry_count;
- struct mutex lock;
- union {
- struct ldt_entry * pages[LDT_PAGES_MAX];
- struct ldt_entry entries[LDT_DIRECT_ENTRIES];
- } u;
-} uml_ldt_t;
-
-#endif
diff --git a/arch/um/include/shared/mem_kern.h b/arch/um/include/shared/mem_kern.h
deleted file mode 100644
index 69be0fd0ce4b..000000000000
--- a/arch/um/include/shared/mem_kern.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (C) 2003 Jeff Dike (jdike@addtoit.com)
- * Licensed under the GPL
- */
-
-#ifndef __MEM_KERN_H__
-#define __MEM_KERN_H__
-
-#include "linux/list.h"
-#include "linux/types.h"
-
-struct remapper {
- struct list_head list;
- int (*proc)(int, unsigned long, int, __u64);
-};
-
-extern void register_remapper(struct remapper *info);
-
-#endif
-
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 83c7c2ecd614..89b686c1a3ea 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -10,7 +10,6 @@
#include "irq_user.h"
#include "longjmp.h"
#include "mm_id.h"
-#include "sysdep/tls.h"
#define CATCH_EINTR(expr) while ((errno = 0, ((expr) < 0)) && (errno == EINTR))
@@ -203,12 +202,6 @@ extern int os_drop_memory(void *addr, int length);
extern int can_drop_memory(void);
extern void os_flush_stdout(void);
-/* uaccess.c */
-extern unsigned long __do_user_copy(void *to, const void *from, int n,
- void **fault_addr, jmp_buf **fault_catcher,
- void (*op)(void *to, const void *from,
- int n), int *faulted_out);
-
/* execvp.c */
extern int execvp_noalloc(char *buf, const char *file, char *const argv[]);
/* helper.c */
@@ -218,10 +211,6 @@ extern int run_helper_thread(int (*proc)(void *), void *arg,
extern int helper_wait(int pid);
-/* tls.c */
-extern int os_set_thread_area(user_desc_t *info, int pid);
-extern int os_get_thread_area(user_desc_t *info, int pid);
-
/* umid.c */
extern int umid_file_name(char *name, char *buf, int len);
extern int set_umid(char *name);
@@ -231,7 +220,7 @@ extern char *get_umid(void);
extern void timer_init(void);
extern void set_sigstack(void *sig_stack, int size);
extern void remove_sigstack(void);
-extern void set_handler(int sig, void (*handler)(int), int flags, ...);
+extern void set_handler(int sig);
extern int change_sig(int signal, int on);
extern void block_signals(void);
extern void unblock_signals(void);
diff --git a/arch/um/include/shared/process.h b/arch/um/include/shared/process.h
deleted file mode 100644
index bb873a51262e..000000000000
--- a/arch/um/include/shared/process.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Copyright (C) 2000 - 2008 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __PROCESS_H__
-#define __PROCESS_H__
-
-#include <signal.h>
-
-/* Copied from linux/compiler-gcc.h since we can't include it directly */
-#define barrier() __asm__ __volatile__("": : :"memory")
-
-extern void sig_handler(int sig, struct sigcontext *sc);
-extern void alarm_handler(int sig, struct sigcontext *sc);
-
-#endif
diff --git a/arch/um/include/shared/ptrace_user.h b/arch/um/include/shared/ptrace_user.h
index 7fd8539bc19a..56b2f284b108 100644
--- a/arch/um/include/shared/ptrace_user.h
+++ b/arch/um/include/shared/ptrace_user.h
@@ -6,7 +6,8 @@
#ifndef __PTRACE_USER_H__
#define __PTRACE_USER_H__
-#include "sysdep/ptrace_user.h"
+#include <sys/ptrace.h>
+#include <sysdep/ptrace_user.h>
extern int ptrace_getregs(long pid, unsigned long *regs_out);
extern int ptrace_setregs(long pid, unsigned long *regs_in);
diff --git a/arch/um/include/shared/skas_ptregs.h b/arch/um/include/shared/skas_ptregs.h
deleted file mode 100644
index 73db19e9c077..000000000000
--- a/arch/um/include/shared/skas_ptregs.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __SKAS_PT_REGS_
-#define __SKAS_PT_REGS_
-
-#include <user_constants.h>
-
-#endif
diff --git a/arch/um/include/shared/syscall.h b/arch/um/include/shared/syscall.h
deleted file mode 100644
index dda1df901a08..000000000000
--- a/arch/um/include/shared/syscall.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __SYSCALL_USER_H
-#define __SYSCALL_USER_H
-
-extern int record_syscall_start(int syscall);
-extern void record_syscall_end(int index, long result);
-
-#endif
diff --git a/arch/um/include/shared/task.h b/arch/um/include/shared/task.h
deleted file mode 100644
index 3fe726b3cf48..000000000000
--- a/arch/um/include/shared/task.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __TASK_H
-#define __TASK_H
-
-#include <kern_constants.h>
-
-#define TASK_REGS(task) ((struct uml_pt_regs *) &(((char *) (task))[HOST_TASK_REGS]))
-#define TASK_PID(task) *((int *) &(((char *) (task))[HOST_TASK_PID]))
-
-#endif
diff --git a/arch/um/include/shared/tlb.h b/arch/um/include/shared/tlb.h
deleted file mode 100644
index ecd2265b301b..000000000000
--- a/arch/um/include/shared/tlb.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __TLB_H__
-#define __TLB_H__
-
-#include "um_mmu.h"
-
-extern void force_flush_all(void);
-extern int flush_tlb_kernel_range_common(unsigned long start,
- unsigned long end);
-
-#endif
diff --git a/arch/um/include/shared/um_malloc.h b/arch/um/include/shared/um_malloc.h
index c554d706d106..6395fef6b69b 100644
--- a/arch/um/include/shared/um_malloc.h
+++ b/arch/um/include/shared/um_malloc.h
@@ -6,7 +6,7 @@
#ifndef __UM_MALLOC_H__
#define __UM_MALLOC_H__
-#include "kern_constants.h"
+#include <generated/asm-offsets.h>
extern void *uml_kmalloc(int size, int flags);
extern void kfree(const void *ptr);
diff --git a/arch/um/include/shared/um_mmu.h b/arch/um/include/shared/um_mmu.h
deleted file mode 100644
index b1a7e47d1027..000000000000
--- a/arch/um/include/shared/um_mmu.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __ARCH_UM_MMU_H
-#define __ARCH_UM_MMU_H
-
-#include "mm_id.h"
-#include "ldt.h"
-
-typedef struct mm_context {
- struct mm_id id;
- struct uml_ldt ldt;
- struct page **stub_pages;
-} mm_context_t;
-
-extern void __switch_mm(struct mm_id * mm_idp);
-
-/* Avoid tangled inclusion with asm/ldt.h */
-extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm);
-extern void free_ldt(struct mm_context *mm);
-
-#endif
diff --git a/arch/um/include/shared/um_uaccess.h b/arch/um/include/shared/um_uaccess.h
deleted file mode 100644
index 45c04999d670..000000000000
--- a/arch/um/include/shared/um_uaccess.h
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __ARCH_UM_UACCESS_H
-#define __ARCH_UM_UACCESS_H
-
-#include <asm/elf.h>
-#include <asm/fixmap.h>
-#include "sysdep/archsetjmp.h"
-
-#define __under_task_size(addr, size) \
- (((unsigned long) (addr) < TASK_SIZE) && \
- (((unsigned long) (addr) + (size)) < TASK_SIZE))
-
-#define __access_ok_vsyscall(type, addr, size) \
- ((type == VERIFY_READ) && \
- ((unsigned long) (addr) >= FIXADDR_USER_START) && \
- ((unsigned long) (addr) + (size) <= FIXADDR_USER_END) && \
- ((unsigned long) (addr) + (size) >= (unsigned long)(addr)))
-
-#define __addr_range_nowrap(addr, size) \
- ((unsigned long) (addr) <= ((unsigned long) (addr) + (size)))
-
-#define access_ok(type, addr, size) \
- (__addr_range_nowrap(addr, size) && \
- (__under_task_size(addr, size) || \
- __access_ok_vsyscall(type, addr, size) || \
- segment_eq(get_fs(), KERNEL_DS)))
-
-extern int copy_from_user(void *to, const void __user *from, int n);
-extern int copy_to_user(void __user *to, const void *from, int n);
-
-extern int __do_copy_to_user(void *to, const void *from, int n,
- void **fault_addr, jmp_buf **fault_catcher);
-
-/*
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst: Destination address, in kernel space. This buffer must be at
- * least @count bytes long.
- * @src: Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-
-extern int strncpy_from_user(char *dst, const char __user *src, int count);
-
-/*
- * __clear_user: - Zero a block of memory in user space, with less checking.
- * @to: Destination address, in user space.
- * @n: Number of bytes to zero.
- *
- * Zero a block of memory in user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be cleared.
- * On success, this will be zero.
- */
-extern int __clear_user(void __user *mem, int len);
-
-/*
- * clear_user: - Zero a block of memory in user space.
- * @to: Destination address, in user space.
- * @n: Number of bytes to zero.
- *
- * Zero a block of memory in user space.
- *
- * Returns number of bytes that could not be cleared.
- * On success, this will be zero.
- */
-extern int clear_user(void __user *mem, int len);
-
-/*
- * strlen_user: - Get the size of a string in user space.
- * @str: The string to measure.
- * @n: The maximum valid length
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- * If the string is too long, returns a value greater than @n.
- */
-extern int strnlen_user(const void __user *str, int len);
-
-#endif
diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h
index 293f7c794faa..4fa82c055aab 100644
--- a/arch/um/include/shared/user.h
+++ b/arch/um/include/shared/user.h
@@ -6,7 +6,7 @@
#ifndef __USER_H__
#define __USER_H__
-#include "kern_constants.h"
+#include <generated/asm-offsets.h>
/*
* The usual definition - copied here because the kernel provides its own,
@@ -36,10 +36,11 @@ static inline int printk(const char *fmt, ...)
}
#endif
-extern void schedule(void);
extern int in_aton(char *str);
-extern int open_gdb_chan(void);
extern size_t strlcpy(char *, const char *, size_t);
extern size_t strlcat(char *, const char *, size_t);
+/* Copied from linux/compiler-gcc.h since we can't include it directly */
+#define barrier() __asm__ __volatile__("": : :"memory")
+
#endif
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index c4491c15afb2..bc494741b1f3 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -11,7 +11,7 @@ clean-files :=
obj-y = config.o exec.o exitcode.o init_task.o irq.o ksyms.o mem.o \
physmem.o process.o ptrace.o reboot.o sigio.o \
- signal.o smp.o syscall.o sysrq.o time.o tlb.o trap.o uaccess.o \
+ signal.o smp.o syscall.o sysrq.o time.o tlb.o trap.o \
um_arch.o umid.o skas/
obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 939a4a67f0fd..6cade9366364 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -3,14 +3,15 @@
* Licensed under the GPL
*/
-#include "linux/stddef.h"
-#include "linux/fs.h"
-#include "linux/ptrace.h"
-#include "linux/sched.h"
-#include "linux/slab.h"
-#include "asm/current.h"
-#include "asm/processor.h"
-#include "asm/uaccess.h"
+#include <linux/stddef.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <asm/current.h>
+#include <asm/processor.h>
+#include <asm/uaccess.h>
#include "as-layout.h"
#include "mem_user.h"
#include "skas.h"
@@ -41,6 +42,7 @@ void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp)
PT_REGS_IP(regs) = eip;
PT_REGS_SP(regs) = esp;
}
+EXPORT_SYMBOL(start_thread);
static long execve1(const char *file,
const char __user *const __user *argv,
diff --git a/arch/um/kernel/gmon_syms.c b/arch/um/kernel/gmon_syms.c
index 72eccd2a4113..e9bcf247bcee 100644
--- a/arch/um/kernel/gmon_syms.c
+++ b/arch/um/kernel/gmon_syms.c
@@ -7,18 +7,3 @@
extern void __bb_init_func(void *) __attribute__((weak));
EXPORT_SYMBOL(__bb_init_func);
-
-/*
- * This is defined (and referred to in profiling stub code) only by some GCC
- * versions in libgcov.
- *
- * Since SuSE backported the fix, we cannot handle it depending on GCC version.
- * So, unconditionally export it. But also give it a weak declaration, which
- * will be overridden by any other one.
- */
-
-extern void __gcov_init(void *) __attribute__((weak));
-EXPORT_SYMBOL(__gcov_init);
-
-extern void __gcov_merge_add(void *) __attribute__((weak));
-EXPORT_SYMBOL(__gcov_merge_add);
diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c
index d386c75c88eb..10cc18f729fd 100644
--- a/arch/um/kernel/initrd.c
+++ b/arch/um/kernel/initrd.c
@@ -7,12 +7,12 @@
#include "linux/bootmem.h"
#include "linux/initrd.h"
#include "asm/types.h"
-#include "initrd.h"
#include "init.h"
#include "os.h"
/* Changed by uml_initrd_setup, which is a setup */
static char *initrd __initdata = NULL;
+static int load_initrd(char *filename, void *buf, int size);
static int __init read_initrd(void)
{
@@ -62,7 +62,7 @@ __uml_setup("initrd=", uml_initrd_setup,
" name of the file containing the image.\n\n"
);
-int load_initrd(char *filename, void *buf, int size)
+static int load_initrd(char *filename, void *buf, int size)
{
int fd, n;
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 9e485c770308..71b8c947e5ef 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -258,6 +258,7 @@ void deactivate_fd(int fd, int irqnum)
ignore_sigio_fd(fd);
}
+EXPORT_SYMBOL(deactivate_fd);
/*
* Called just before shutdown in order to provide a clean exec
diff --git a/arch/um/kernel/ksyms.c b/arch/um/kernel/ksyms.c
index 0ae0dfcfbffb..e17bea0b22e1 100644
--- a/arch/um/kernel/ksyms.c
+++ b/arch/um/kernel/ksyms.c
@@ -3,33 +3,11 @@
* Licensed under the GPL
*/
-#include "linux/module.h"
-#include "linux/syscalls.h"
-#include "asm/tlbflush.h"
-#include "asm/uaccess.h"
-#include "as-layout.h"
-#include "kern_util.h"
-#include "mem_user.h"
+#include <linux/module.h>
#include "os.h"
-EXPORT_SYMBOL(uml_physmem);
EXPORT_SYMBOL(set_signals);
EXPORT_SYMBOL(get_signals);
-EXPORT_SYMBOL(kernel_thread);
-EXPORT_SYMBOL(sys_waitpid);
-EXPORT_SYMBOL(flush_tlb_range);
-
-EXPORT_SYMBOL(high_physmem);
-EXPORT_SYMBOL(empty_zero_page);
-EXPORT_SYMBOL(handle_page_fault);
-EXPORT_SYMBOL(find_iomem);
-
-EXPORT_SYMBOL(strnlen_user);
-EXPORT_SYMBOL(strncpy_from_user);
-EXPORT_SYMBOL(copy_to_user);
-EXPORT_SYMBOL(copy_from_user);
-EXPORT_SYMBOL(clear_user);
-EXPORT_SYMBOL(uml_strdup);
EXPORT_SYMBOL(os_stat_fd);
EXPORT_SYMBOL(os_stat_file);
@@ -57,24 +35,10 @@ EXPORT_SYMBOL(os_connect_socket);
EXPORT_SYMBOL(os_accept_connection);
EXPORT_SYMBOL(os_rcv_fd);
EXPORT_SYMBOL(run_helper);
-EXPORT_SYMBOL(start_thread);
EXPORT_SYMBOL(os_major);
EXPORT_SYMBOL(os_minor);
EXPORT_SYMBOL(os_makedev);
EXPORT_SYMBOL(add_sigio_fd);
EXPORT_SYMBOL(ignore_sigio_fd);
-EXPORT_SYMBOL(deactivate_fd);
EXPORT_SYMBOL(sigio_broken);
-
-#ifdef CONFIG_SMP
-
-/* required for SMP */
-
-extern void __write_lock_failed(rwlock_t *rw);
-EXPORT_SYMBOL(__write_lock_failed);
-
-extern void __read_lock_failed(rwlock_t *rw);
-EXPORT_SYMBOL(__read_lock_failed);
-
-#endif
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 8137ccc9635b..ebb86b218445 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -4,6 +4,7 @@
*/
#include <linux/stddef.h>
+#include <linux/module.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/mm.h>
@@ -20,6 +21,7 @@
/* allocated in paging_init, zeroed in mem_init, and unchanged thereafter */
unsigned long *empty_zero_page = NULL;
+EXPORT_SYMBOL(empty_zero_page);
/* allocated in paging_init and unchanged thereafter */
static unsigned long *empty_bad_page = NULL;
diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c
index a1a9090254c2..f116db15d402 100644
--- a/arch/um/kernel/physmem.c
+++ b/arch/um/kernel/physmem.c
@@ -3,20 +3,22 @@
* Licensed under the GPL
*/
-#include "linux/bootmem.h"
-#include "linux/mm.h"
-#include "linux/pfn.h"
-#include "asm/page.h"
-#include "as-layout.h"
-#include "init.h"
-#include "kern.h"
-#include "mem_user.h"
-#include "os.h"
+#include <linux/module.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/pfn.h>
+#include <asm/page.h>
+#include <as-layout.h>
+#include <init.h>
+#include <kern.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);
extern unsigned long long physmem_size;
@@ -184,6 +186,7 @@ unsigned long find_iomem(char *driver, unsigned long *len_out)
return 0;
}
+EXPORT_SYMBOL(find_iomem);
static int setup_iomem(void)
{
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 21c1ae7c3d75..c5338351aecd 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -20,12 +20,12 @@
#include <linux/threads.h>
#include <asm/current.h>
#include <asm/pgtable.h>
+#include <asm/mmu_context.h>
#include <asm/uaccess.h>
#include "as-layout.h"
#include "kern_util.h"
#include "os.h"
#include "skas.h"
-#include "tlb.h"
/*
* This is a per-cpu array. A processor only modifies its entry and it only
@@ -78,6 +78,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
&current->thread.regs, 0, NULL, NULL);
return pid;
}
+EXPORT_SYMBOL(kernel_thread);
static inline void set_current(struct task_struct *task)
{
@@ -286,6 +287,7 @@ char *uml_strdup(const char *string)
{
return kstrdup(string, GFP_KERNEL);
}
+EXPORT_SYMBOL(uml_strdup);
int copy_to_user_proc(void __user *to, void *from, int size)
{
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index b5c094c4ade4..e8b889d3bce7 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -11,7 +11,6 @@
#include <asm/unistd.h>
#include "frame_kern.h"
#include "kern_util.h"
-#include <sysdep/sigcontext.h>
EXPORT_SYMBOL(block_signals);
EXPORT_SYMBOL(unblock_signals);
diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c
index 2c8583c1a344..e1fd066a3525 100644
--- a/arch/um/kernel/skas/clone.c
+++ b/arch/um/kernel/skas/clone.c
@@ -8,7 +8,6 @@
#include <asm/unistd.h>
#include <sys/time.h>
#include "as-layout.h"
-#include "kern_constants.h"
#include "ptrace_user.h"
#include "stub-data.h"
#include "sysdep/stub.h"
diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c
index 696634214dc6..9fefd924fb49 100644
--- a/arch/um/kernel/skas/uaccess.c
+++ b/arch/um/kernel/skas/uaccess.c
@@ -6,6 +6,7 @@
#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>
@@ -149,6 +150,7 @@ int copy_from_user(void *to, const void __user *from, int n)
buffer_op((unsigned long) from, n, 0, copy_chunk_from_user, &to):
n;
}
+EXPORT_SYMBOL(copy_from_user);
static int copy_chunk_to_user(unsigned long to, int len, void *arg)
{
@@ -170,6 +172,7 @@ int copy_to_user(void __user *to, const void *from, int n)
buffer_op((unsigned long) to, n, 1, copy_chunk_to_user, &from) :
n;
}
+EXPORT_SYMBOL(copy_to_user);
static int strncpy_chunk_from_user(unsigned long from, int len, void *arg)
{
@@ -204,6 +207,7 @@ int strncpy_from_user(char *dst, const char __user *src, int count)
return -EFAULT;
return strnlen(dst, count);
}
+EXPORT_SYMBOL(strncpy_from_user);
static int clear_chunk(unsigned long addr, int len, void *unused)
{
@@ -226,6 +230,7 @@ int clear_user(void __user *mem, int len)
return access_ok(VERIFY_WRITE, mem, len) ?
buffer_op((unsigned long) mem, len, 1, clear_chunk, NULL) : len;
}
+EXPORT_SYMBOL(clear_user);
static int strnlen_chunk(unsigned long str, int len, void *arg)
{
@@ -251,3 +256,4 @@ int strnlen_user(const void __user *str, int len)
return count + 1;
return -EFAULT;
}
+EXPORT_SYMBOL(strnlen_user);
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index d175d0566af0..7f3d4d86431a 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -4,6 +4,7 @@
*/
#include <linux/mm.h>
+#include <linux/module.h>
#include <linux/sched.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
@@ -11,7 +12,6 @@
#include "mem_user.h"
#include "os.h"
#include "skas.h"
-#include "tlb.h"
struct host_vm_change {
struct host_vm_op {
@@ -287,7 +287,7 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
}
}
-int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
+static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
{
struct mm_struct *mm;
pgd_t *pgd;
@@ -499,6 +499,7 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
flush_tlb_kernel_range_common(start, end);
else fix_range(vma->vm_mm, start, end, 0);
}
+EXPORT_SYMBOL(flush_tlb_range);
void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end)
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 8c7b8823d1f0..dafc94715950 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -6,6 +6,7 @@
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/hardirq.h>
+#include <linux/module.h>
#include <asm/current.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
@@ -14,7 +15,6 @@
#include "kern_util.h"
#include "os.h"
#include "skas.h"
-#include "sysdep/sigcontext.h"
/*
* Note this is constrained to return 0, -EFAULT, -EACCESS, -ENOMEM by
@@ -112,6 +112,7 @@ out_of_memory:
pagefault_out_of_memory();
return 0;
}
+EXPORT_SYMBOL(handle_page_fault);
static void show_segv_info(struct uml_pt_regs *regs)
{
diff --git a/arch/um/kernel/uaccess.c b/arch/um/kernel/uaccess.c
deleted file mode 100644
index dd33f040c526..000000000000
--- a/arch/um/kernel/uaccess.c
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * Copyright (C) 2001 Chris Emerson (cemerson@chiark.greenend.org.uk)
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-/*
- * These are here rather than tt/uaccess.c because skas mode needs them in
- * order to do SIGBUS recovery when a tmpfs mount runs out of room.
- */
-
-#include <linux/string.h>
-#include "os.h"
-
-static void __do_copy(void *to, const void *from, int n)
-{
- memcpy(to, from, n);
-}
-
-
-int __do_copy_to_user(void *to, const void *from, int n,
- void **fault_addr, jmp_buf **fault_catcher)
-{
- unsigned long fault;
- int faulted;
-
- fault = __do_user_copy(to, from, n, fault_addr, fault_catcher,
- __do_copy, &faulted);
- if (!faulted)
- return 0;
- else
- return n - (fault - (unsigned long) to);
-}
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 8d84250324b3..ba00eae45aad 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -102,6 +102,8 @@ const struct seq_operations cpuinfo_op = {
/* 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;
diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile
index b33f4dfe7ae5..dd764101e488 100644
--- a/arch/um/os-Linux/Makefile
+++ b/arch/um/os-Linux/Makefile
@@ -4,14 +4,14 @@
#
obj-y = aio.o execvp.o file.o helper.o irq.o main.o mem.o process.o \
- registers.o sigio.o signal.o start_up.o time.o tty.o uaccess.o \
- umid.o tls.o user_syms.o util.o drivers/ sys-$(SUBARCH)/ skas/
+ registers.o sigio.o signal.o start_up.o time.o tty.o \
+ umid.o user_syms.o util.o drivers/ skas/
obj-$(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) += elf_aux.o
USER_OBJS := $(user-objs-y) aio.o elf_aux.o execvp.o file.o helper.o irq.o \
main.o mem.o process.o registers.o sigio.o signal.o start_up.o time.o \
- tty.o tls.o uaccess.o umid.o util.o
+ tty.o umid.o util.o
CFLAGS_user_syms.o += -DSUBARCH_$(SUBARCH)
diff --git a/arch/um/os-Linux/aio.c b/arch/um/os-Linux/aio.c
index 57e3d46c989c..c5d039e1ff3b 100644
--- a/arch/um/os-Linux/aio.c
+++ b/arch/um/os-Linux/aio.c
@@ -11,10 +11,8 @@
#include <asm/unistd.h>
#include "aio.h"
#include "init.h"
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
-#include "user.h"
struct aio_thread_req {
enum aio_type type;
diff --git a/arch/um/os-Linux/drivers/ethertap_user.c b/arch/um/os-Linux/drivers/ethertap_user.c
index cc72cb2c1af6..db3d6481375a 100644
--- a/arch/um/os-Linux/drivers/ethertap_user.c
+++ b/arch/um/os-Linux/drivers/ethertap_user.c
@@ -13,11 +13,9 @@
#include <sys/socket.h>
#include <sys/wait.h>
#include "etap.h"
-#include "kern_constants.h"
#include "os.h"
#include "net_user.h"
#include "um_malloc.h"
-#include "user.h"
#define MAX_PACKET ETH_MAX_PACKET
diff --git a/arch/um/os-Linux/drivers/tuntap_user.c b/arch/um/os-Linux/drivers/tuntap_user.c
index 2448be03fd7a..a2aacffdd907 100644
--- a/arch/um/os-Linux/drivers/tuntap_user.c
+++ b/arch/um/os-Linux/drivers/tuntap_user.c
@@ -13,11 +13,9 @@
#include <sys/socket.h>
#include <sys/wait.h>
#include <sys/uio.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
#include "tuntap.h"
-#include "user.h"
static int tuntap_user_init(void *data, void *dev)
{
diff --git a/arch/um/os-Linux/elf_aux.c b/arch/um/os-Linux/elf_aux.c
index 953323799381..d895271ad6f7 100644
--- a/arch/um/os-Linux/elf_aux.c
+++ b/arch/um/os-Linux/elf_aux.c
@@ -12,7 +12,6 @@
#include "init.h"
#include "elf_user.h"
#include "mem_user.h"
-#include <kern_constants.h>
typedef Elf32_auxv_t elf_auxv_t;
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index 140e587bc0ad..b049a63bb74b 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -13,9 +13,7 @@
#include <sys/socket.h>
#include <sys/stat.h>
#include <sys/un.h>
-#include "kern_constants.h"
#include "os.h"
-#include "user.h"
static void copy_stat(struct uml_stat *dst, const struct stat64 *src)
{
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index feff22d64672..cf26c4a9a43a 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -10,11 +10,9 @@
#include <linux/limits.h>
#include <sys/socket.h>
#include <sys/wait.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
#include "um_malloc.h"
-#include "user.h"
struct helper_data {
void (*pre_exec)(void*);
diff --git a/arch/um/os-Linux/internal.h b/arch/um/os-Linux/internal.h
new file mode 100644
index 000000000000..2c3c3ecd8c01
--- /dev/null
+++ b/arch/um/os-Linux/internal.h
@@ -0,0 +1 @@
+void alarm_handler(int, mcontext_t *);
diff --git a/arch/um/os-Linux/irq.c b/arch/um/os-Linux/irq.c
index 0348b975e81c..9a49908b576c 100644
--- a/arch/um/os-Linux/irq.c
+++ b/arch/um/os-Linux/irq.c
@@ -9,11 +9,8 @@
#include <signal.h>
#include <string.h>
#include "irq_user.h"
-#include "kern_constants.h"
#include "os.h"
-#include "process.h"
#include "um_malloc.h"
-#include "user.h"
/*
* Locked by irq_lock in arch/um/kernel/irq.c. Changed by os_create_pollfd
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index 8471b817d94f..7a86dd516eb1 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -12,7 +12,6 @@
#include <sys/resource.h>
#include "as-layout.h"
#include "init.h"
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
#include "um_malloc.h"
diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c
index 62878cf1d33f..8e421e1d6d36 100644
--- a/arch/um/os-Linux/mem.c
+++ b/arch/um/os-Linux/mem.c
@@ -14,9 +14,7 @@
#include <sys/mman.h>
#include <sys/param.h>
#include "init.h"
-#include "kern_constants.h"
#include "os.h"
-#include "user.h"
/* Modified by which_tmpdir, which is called during early boot */
static char *default_tmpdir = "/tmp";
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index 0c45dc8efb05..307f173e7f82 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -13,12 +13,9 @@
#include <sys/wait.h>
#include <asm/unistd.h>
#include "init.h"
-#include "kern_constants.h"
#include "longjmp.h"
#include "os.h"
-#include "process.h"
#include "skas_ptrace.h"
-#include "user.h"
#define ARBITRARY_ADDR -1
#define FAILURE_PID -1
@@ -237,21 +234,13 @@ out:
void init_new_thread_signals(void)
{
- set_handler(SIGSEGV, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
- set_handler(SIGTRAP, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
- set_handler(SIGFPE, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
- set_handler(SIGILL, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
- set_handler(SIGBUS, (__sighandler_t) sig_handler, SA_ONSTACK,
- SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
+ set_handler(SIGSEGV);
+ set_handler(SIGTRAP);
+ set_handler(SIGFPE);
+ set_handler(SIGILL);
+ set_handler(SIGBUS);
signal(SIGHUP, SIG_IGN);
-
- set_handler(SIGIO, (__sighandler_t) sig_handler,
- SA_ONSTACK | SA_RESTART, SIGUSR1, SIGIO, SIGWINCH, SIGALRM,
- SIGVTALRM, -1);
+ set_handler(SIGIO);
signal(SIGWINCH, SIG_IGN);
signal(SIGTERM, SIG_DFL);
}
diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c
index 63d299df152b..3c161218c671 100644
--- a/arch/um/os-Linux/sigio.c
+++ b/arch/um/os-Linux/sigio.c
@@ -11,14 +11,11 @@
#include <sched.h>
#include <signal.h>
#include <string.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "init.h"
#include "os.h"
-#include "process.h"
#include "sigio.h"
#include "um_malloc.h"
-#include "user.h"
/*
* Protected by sigio_lock(), also used by sigio_cleanup, which is an
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 6ae180703a63..2d22f1fcd8e2 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -12,13 +12,7 @@
#include "as-layout.h"
#include "kern_util.h"
#include "os.h"
-#include "process.h"
-#include "sysdep/barrier.h"
-#include "sysdep/sigcontext.h"
-#include "user.h"
-
-/* Copied from linux/compiler-gcc.h since we can't include it directly */
-#define barrier() __asm__ __volatile__("": : :"memory")
+#include "sysdep/mcontext.h"
void (*sig_info[NSIG])(int, struct uml_pt_regs *) = {
[SIGTRAP] = relay_signal,
@@ -30,7 +24,7 @@ void (*sig_info[NSIG])(int, struct uml_pt_regs *) = {
[SIGIO] = sigio_handler,
[SIGVTALRM] = timer_handler };
-static void sig_handler_common(int sig, struct sigcontext *sc)
+static void sig_handler_common(int sig, mcontext_t *mc)
{
struct uml_pt_regs r;
int save_errno = errno;
@@ -38,8 +32,8 @@ static void sig_handler_common(int sig, struct sigcontext *sc)
r.is_user = 0;
if (sig == SIGSEGV) {
/* For segfaults, we want the data from the sigcontext. */
- copy_sc(&r, sc);
- GET_FAULTINFO_FROM_SC(r.faultinfo, sc);
+ get_regs_from_mc(&r, mc);
+ GET_FAULTINFO_FROM_MC(r.faultinfo, mc);
}
/* enable signals if sig isn't IRQ signal */
@@ -66,7 +60,7 @@ static void sig_handler_common(int sig, struct sigcontext *sc)
static int signals_enabled;
static unsigned int signals_pending;
-void sig_handler(int sig, struct sigcontext *sc)
+void sig_handler(int sig, mcontext_t *mc)
{
int enabled;
@@ -78,23 +72,23 @@ void sig_handler(int sig, struct sigcontext *sc)
block_signals();
- sig_handler_common(sig, sc);
+ sig_handler_common(sig, mc);
set_signals(enabled);
}
-static void real_alarm_handler(struct sigcontext *sc)
+static void real_alarm_handler(mcontext_t *mc)
{
struct uml_pt_regs regs;
- if (sc != NULL)
- copy_sc(&regs, sc);
+ if (mc != NULL)
+ get_regs_from_mc(&regs, mc);
regs.is_user = 0;
unblock_signals();
timer_handler(SIGVTALRM, &regs);
}
-void alarm_handler(int sig, struct sigcontext *sc)
+void alarm_handler(int sig, mcontext_t *mc)
{
int enabled;
@@ -106,14 +100,13 @@ void alarm_handler(int sig, struct sigcontext *sc)
block_signals();
- real_alarm_handler(sc);
+ real_alarm_handler(mc);
set_signals(enabled);
}
void timer_init(void)
{
- set_handler(SIGVTALRM, (__sighandler_t) alarm_handler,
- SA_ONSTACK | SA_RESTART, SIGUSR1, SIGIO, SIGWINCH, -1);
+ set_handler(SIGVTALRM);
}
void set_sigstack(void *sig_stack, int size)
@@ -126,10 +119,23 @@ void set_sigstack(void *sig_stack, int size)
panic("enabling signal stack failed, errno = %d\n", errno);
}
-static void (*handlers[_NSIG])(int sig, struct sigcontext *sc);
+static void (*handlers[_NSIG])(int sig, mcontext_t *mc) = {
+ [SIGSEGV] = sig_handler,
+ [SIGBUS] = sig_handler,
+ [SIGILL] = sig_handler,
+ [SIGFPE] = sig_handler,
+ [SIGTRAP] = sig_handler,
+
+ [SIGIO] = sig_handler,
+ [SIGWINCH] = sig_handler,
+ [SIGVTALRM] = alarm_handler
+};
+
-void handle_signal(int sig, struct sigcontext *sc)
+static void hard_handler(int sig, siginfo_t *info, void *p)
{
+ struct ucontext *uc = p;
+ mcontext_t *mc = &uc->uc_mcontext;
unsigned long pending = 1UL << sig;
do {
@@ -155,7 +161,7 @@ void handle_signal(int sig, struct sigcontext *sc)
while ((sig = ffs(pending)) != 0){
sig--;
pending &= ~(1 << sig);
- (*handlers[sig])(sig, sc);
+ (*handlers[sig])(sig, mc);
}
/*
@@ -169,28 +175,26 @@ void handle_signal(int sig, struct sigcontext *sc)
} while (pending);
}
-extern void hard_handler(int sig);
-
-void set_handler(int sig, void (*handler)(int), int flags, ...)
+void set_handler(int sig)
{
struct sigaction action;
- va_list ap;
+ int flags = SA_SIGINFO | SA_ONSTACK;
sigset_t sig_mask;
- int mask;
- handlers[sig] = (void (*)(int, struct sigcontext *)) handler;
- action.sa_handler = hard_handler;
+ action.sa_sigaction = hard_handler;
+ /* block irq ones */
sigemptyset(&action.sa_mask);
-
- va_start(ap, flags);
- while ((mask = va_arg(ap, int)) != -1)
- sigaddset(&action.sa_mask, mask);
- va_end(ap);
+ sigaddset(&action.sa_mask, SIGVTALRM);
+ sigaddset(&action.sa_mask, SIGIO);
+ sigaddset(&action.sa_mask, SIGWINCH);
if (sig == SIGSEGV)
flags |= SA_NODEFER;
+ if (sigismember(&action.sa_mask, sig))
+ flags |= SA_RESTART; /* if it's an irq signal */
+
action.sa_flags = flags;
action.sa_restorer = NULL;
if (sigaction(sig, &action, NULL) < 0)
diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c
index e771398be5f3..c0afff7af4bd 100644
--- a/arch/um/os-Linux/skas/mem.c
+++ b/arch/um/os-Linux/skas/mem.c
@@ -9,7 +9,6 @@
#include <string.h>
#include <sys/mman.h>
#include "init.h"
-#include "kern_constants.h"
#include "as-layout.h"
#include "mm_id.h"
#include "os.h"
@@ -17,7 +16,6 @@
#include "ptrace_user.h"
#include "registers.h"
#include "skas.h"
-#include "user.h"
#include "sysdep/ptrace.h"
#include "sysdep/stub.h"
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index dee0e8cf8ad0..cd65727854eb 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -9,31 +9,23 @@
#include <errno.h>
#include <string.h>
#include <sys/mman.h>
-#include <sys/ptrace.h>
#include <sys/wait.h>
#include <asm/unistd.h>
#include "as-layout.h"
-#include "chan_user.h"
-#include "kern_constants.h"
+#include "init.h"
#include "kern_util.h"
#include "mem.h"
#include "os.h"
-#include "process.h"
#include "proc_mm.h"
#include "ptrace_user.h"
#include "registers.h"
#include "skas.h"
#include "skas_ptrace.h"
-#include "user.h"
#include "sysdep/stub.h"
int is_skas_winch(int pid, int fd, void *data)
{
- if (pid != getpgrp())
- return 0;
-
- register_winch_irq(-1, fd, -1, data, 0);
- return 1;
+ return pid == getpgrp();
}
static int ptrace_dump_regs(int pid)
@@ -169,7 +161,7 @@ static void handle_trap(int pid, struct uml_pt_regs *regs,
if (!local_using_sysemu)
{
- err = ptrace(PTRACE_POKEUSR, pid, PT_SYSCALL_NR_OFFSET,
+ err = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET,
__NR_getpid);
if (err < 0) {
printk(UM_KERN_ERR "handle_trap - nullifying syscall "
@@ -257,8 +249,8 @@ static int userspace_tramp(void *stack)
set_sigstack((void *) STUB_DATA, UM_KERN_PAGE_SIZE);
sigemptyset(&sa.sa_mask);
- sa.sa_flags = SA_ONSTACK | SA_NODEFER;
- sa.sa_handler = (void *) v;
+ sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
+ sa.sa_sigaction = (void *) v;
sa.sa_restorer = NULL;
if (sigaction(SIGSEGV, &sa, NULL) < 0) {
printk(UM_KERN_ERR "userspace_tramp - setting SIGSEGV "
@@ -661,8 +653,7 @@ int start_idle_thread(void *stack, jmp_buf *switch_buf)
{
int n;
- set_handler(SIGWINCH, (__sighandler_t) sig_handler,
- SA_ONSTACK | SA_RESTART, SIGUSR1, SIGIO, SIGVTALRM, -1);
+ set_handler(SIGWINCH);
/*
* Can't use UML_SETJMP or UML_LONGJMP here because they save
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index 02ee9adff54a..425162e22af5 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -13,12 +13,10 @@
#include <signal.h>
#include <string.h>
#include <sys/mman.h>
-#include <sys/ptrace.h>
#include <sys/stat.h>
#include <sys/wait.h>
#include <asm/unistd.h>
#include "init.h"
-#include "kern_constants.h"
#include "os.h"
#include "mem_user.h"
#include "ptrace_user.h"
@@ -225,7 +223,7 @@ static void __init check_sysemu(void)
goto fail;
}
- n = ptrace(PTRACE_POKEUSR, pid, PT_SYSCALL_RET_OFFSET, os_getpid());
+ n = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_RET_OFFSET, os_getpid());
if (n < 0) {
non_fatal("check_sysemu : failed to modify system call "
"return");
@@ -261,7 +259,7 @@ static void __init check_sysemu(void)
"doesn't singlestep");
goto fail;
}
- n = ptrace(PTRACE_POKEUSR, pid, PT_SYSCALL_RET_OFFSET,
+ n = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_RET_OFFSET,
os_getpid());
if (n < 0)
fatal_perror("check_sysemu : failed to modify "
@@ -317,10 +315,10 @@ static void __init check_ptrace(void)
fatal("check_ptrace : expected (SIGTRAP|0x80), "
"got status = %d", status);
- syscall = ptrace(PTRACE_PEEKUSR, pid, PT_SYSCALL_NR_OFFSET,
+ syscall = ptrace(PTRACE_PEEKUSER, pid, PT_SYSCALL_NR_OFFSET,
0);
if (syscall == __NR_getpid) {
- n = ptrace(PTRACE_POKEUSR, pid, PT_SYSCALL_NR_OFFSET,
+ n = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET,
__NR_getppid);
if (n < 0)
fatal_perror("check_ptrace : failed to modify "
diff --git a/arch/um/os-Linux/sys-i386/signal.c b/arch/um/os-Linux/sys-i386/signal.c
deleted file mode 100644
index f311609f93da..000000000000
--- a/arch/um/os-Linux/sys-i386/signal.c
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- * Copyright (C) 2006 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <signal.h>
-
-extern void handle_signal(int sig, struct sigcontext *sc);
-
-void hard_handler(int sig)
-{
- handle_signal(sig, (struct sigcontext *) (&sig + 1));
-}
diff --git a/arch/um/os-Linux/sys-x86_64/Makefile b/arch/um/os-Linux/sys-x86_64/Makefile
deleted file mode 100644
index a44a47f8f57b..000000000000
--- a/arch/um/os-Linux/sys-x86_64/Makefile
+++ /dev/null
@@ -1,10 +0,0 @@
-#
-# Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
-# Licensed under the GPL
-#
-
-obj-y = registers.o prctl.o signal.o task_size.o
-
-USER_OBJS := $(obj-y)
-
-include arch/um/scripts/Makefile.rules
diff --git a/arch/um/os-Linux/sys-x86_64/registers.c b/arch/um/os-Linux/sys-x86_64/registers.c
deleted file mode 100644
index 594d97ad02b3..000000000000
--- a/arch/um/os-Linux/sys-x86_64/registers.c
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright (C) 2006 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <errno.h>
-#include <sys/ptrace.h>
-#define __FRAME_OFFSETS
-#include <asm/ptrace.h>
-#include "kern_constants.h"
-#include "longjmp.h"
-#include "user.h"
-
-int save_fp_registers(int pid, unsigned long *fp_regs)
-{
- if (ptrace(PTRACE_GETFPREGS, pid, 0, fp_regs) < 0)
- return -errno;
- return 0;
-}
-
-int restore_fp_registers(int pid, unsigned long *fp_regs)
-{
- if (ptrace(PTRACE_SETFPREGS, pid, 0, fp_regs) < 0)
- return -errno;
- return 0;
-}
-
-unsigned long get_thread_reg(int reg, jmp_buf *buf)
-{
- switch (reg) {
- case RIP:
- return buf[0]->__rip;
- case RSP:
- return buf[0]->__rsp;
- case RBP:
- return buf[0]->__rbp;
- default:
- printk(UM_KERN_ERR "get_thread_regs - unknown register %d\n",
- reg);
- return 0;
- }
-}
-
-int get_fp_registers(int pid, unsigned long *regs)
-{
- return save_fp_registers(pid, regs);
-}
-
-int put_fp_registers(int pid, unsigned long *regs)
-{
- return restore_fp_registers(pid, regs);
-}
diff --git a/arch/um/os-Linux/sys-x86_64/signal.c b/arch/um/os-Linux/sys-x86_64/signal.c
deleted file mode 100644
index 82a388822cd3..000000000000
--- a/arch/um/os-Linux/sys-x86_64/signal.c
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * Copyright (C) 2006 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <signal.h>
-
-extern void handle_signal(int sig, struct sigcontext *sc);
-
-void hard_handler(int sig)
-{
- struct ucontext *uc;
- asm("movq %%rdx, %0" : "=r" (uc));
-
- handle_signal(sig, (struct sigcontext *) &uc->uc_mcontext);
-}
diff --git a/arch/um/os-Linux/sys-x86_64/task_size.c b/arch/um/os-Linux/sys-x86_64/task_size.c
deleted file mode 100644
index 26a0dd1f349c..000000000000
--- a/arch/um/os-Linux/sys-x86_64/task_size.c
+++ /dev/null
@@ -1,5 +0,0 @@
-unsigned long os_get_top_address(unsigned long shift)
-{
- /* The old value of CONFIG_TOP_ADDR */
- return 0x7fc0000000;
-}
diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c
index 6e3359d6a839..910499d76a67 100644
--- a/arch/um/os-Linux/time.c
+++ b/arch/um/os-Linux/time.c
@@ -8,11 +8,9 @@
#include <signal.h>
#include <time.h>
#include <sys/time.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
-#include "process.h"
-#include "user.h"
+#include "internal.h"
int set_interval(void)
{
diff --git a/arch/um/os-Linux/tls.c b/arch/um/os-Linux/tls.c
deleted file mode 100644
index 73277801ef14..000000000000
--- a/arch/um/os-Linux/tls.c
+++ /dev/null
@@ -1,35 +0,0 @@
-#include <errno.h>
-#include <sys/ptrace.h>
-#include "sysdep/tls.h"
-
-/* TLS support - we basically rely on the host's one.*/
-
-#ifndef PTRACE_GET_THREAD_AREA
-#define PTRACE_GET_THREAD_AREA 25
-#endif
-
-#ifndef PTRACE_SET_THREAD_AREA
-#define PTRACE_SET_THREAD_AREA 26
-#endif
-
-int os_set_thread_area(user_desc_t *info, int pid)
-{
- int ret;
-
- ret = ptrace(PTRACE_SET_THREAD_AREA, pid, info->entry_number,
- (unsigned long) info);
- if (ret < 0)
- ret = -errno;
- return ret;
-}
-
-int os_get_thread_area(user_desc_t *info, int pid)
-{
- int ret;
-
- ret = ptrace(PTRACE_GET_THREAD_AREA, pid, info->entry_number,
- (unsigned long) info);
- if (ret < 0)
- ret = -errno;
- return ret;
-}
diff --git a/arch/um/os-Linux/tty.c b/arch/um/os-Linux/tty.c
index b09ff66a77ee..dd12b99dcb59 100644
--- a/arch/um/os-Linux/tty.c
+++ b/arch/um/os-Linux/tty.c
@@ -7,10 +7,8 @@
#include <unistd.h>
#include <errno.h>
#include <fcntl.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "os.h"
-#include "user.h"
struct grantpt_info {
int fd;
diff --git a/arch/um/os-Linux/uaccess.c b/arch/um/os-Linux/uaccess.c
deleted file mode 100644
index 087ed74ffca5..000000000000
--- a/arch/um/os-Linux/uaccess.c
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * Copyright (C) 2001 Chris Emerson (cemerson@chiark.greenend.org.uk)
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <stddef.h>
-#include "longjmp.h"
-
-unsigned long __do_user_copy(void *to, const void *from, int n,
- void **fault_addr, jmp_buf **fault_catcher,
- void (*op)(void *to, const void *from,
- int n), int *faulted_out)
-{
- unsigned long *faddrp = (unsigned long *) fault_addr, ret;
-
- jmp_buf jbuf;
- *fault_catcher = &jbuf;
- if (UML_SETJMP(&jbuf) == 0) {
- (*op)(to, from, n);
- ret = 0;
- *faulted_out = 0;
- }
- else {
- ret = *faddrp;
- *faulted_out = 1;
- }
- *fault_addr = NULL;
- *fault_catcher = NULL;
- return ret;
-}
-
diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c
index a27defb81884..4832eb519f8d 100644
--- a/arch/um/os-Linux/umid.c
+++ b/arch/um/os-Linux/umid.c
@@ -13,9 +13,7 @@
#include <unistd.h>
#include <sys/stat.h>
#include "init.h"
-#include "kern_constants.h"
#include "os.h"
-#include "user.h"
#define UML_DIR "~/.uml/"
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index 5803b1887672..9e3b43bb84c9 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -13,9 +13,7 @@
#include <wait.h>
#include <sys/mman.h>
#include <sys/utsname.h>
-#include "kern_constants.h"
#include "os.h"
-#include "user.h"
void stack_protections(unsigned long address)
{
diff --git a/arch/um/scripts/Makefile.rules b/arch/um/scripts/Makefile.rules
index 61107b68e05b..2eb2843b0634 100644
--- a/arch/um/scripts/Makefile.rules
+++ b/arch/um/scripts/Makefile.rules
@@ -8,7 +8,7 @@ USER_OBJS += $(filter %_user.o,$(obj-y) $(obj-m) $(USER_SINGLE_OBJS))
USER_OBJS := $(foreach file,$(USER_OBJS),$(obj)/$(file))
$(USER_OBJS:.o=.%): \
- c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) $(CFLAGS_$(basetarget).o)
+ c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) -include user.h $(CFLAGS_$(basetarget).o)
$(USER_OBJS) : CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ \
-Dunix -D__unix__ -D__$(SUBARCH)__ $(CF)
@@ -25,8 +25,3 @@ $(UNPROFILE_OBJS) : CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ \
define unprofile
$(patsubst -pg,,$(patsubst -fprofile-arcs -ftest-coverage,,$(1)))
endef
-
-ifdef subarch-obj-y
-obj-y += subarch.o
-subarch-y = $(addprefix ../../$(HEADER_ARCH)/,$(subarch-obj-y))
-endif
diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile
deleted file mode 100644
index 3923cfb87649..000000000000
--- a/arch/um/sys-i386/Makefile
+++ /dev/null
@@ -1,24 +0,0 @@
-#
-# Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
-#
-
-obj-y = bug.o bugs.o checksum.o delay.o fault.o ksyms.o ldt.o ptrace.o \
- ptrace_user.o setjmp.o signal.o stub.o stub_segv.o syscalls.o sysrq.o \
- sys_call_table.o tls.o atomic64_cx8_32.o mem.o
-
-obj-$(CONFIG_BINFMT_ELF) += elfcore.o
-
-subarch-obj-y = lib/string_32.o
-subarch-obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += lib/rwsem.o
-subarch-obj-$(CONFIG_HIGHMEM) += mm/highmem_32.o
-subarch-obj-$(CONFIG_MODULES) += kernel/module.o
-
-USER_OBJS := bugs.o ptrace_user.o fault.o
-
-USER_OBJS += user-offsets.s
-extra-y += user-offsets.s
-
-UNPROFILE_OBJS := stub_segv.o
-CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING)
-
-include arch/um/scripts/Makefile.rules
diff --git a/arch/um/sys-i386/asm/elf.h b/arch/um/sys-i386/asm/elf.h
deleted file mode 100644
index 42305551d204..000000000000
--- a/arch/um/sys-i386/asm/elf.h
+++ /dev/null
@@ -1,125 +0,0 @@
-/*
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-#ifndef __UM_ELF_I386_H
-#define __UM_ELF_I386_H
-
-#include <asm/user.h>
-#include "skas.h"
-
-#define R_386_NONE 0
-#define R_386_32 1
-#define R_386_PC32 2
-#define R_386_GOT32 3
-#define R_386_PLT32 4
-#define R_386_COPY 5
-#define R_386_GLOB_DAT 6
-#define R_386_JMP_SLOT 7
-#define R_386_RELATIVE 8
-#define R_386_GOTOFF 9
-#define R_386_GOTPC 10
-#define R_386_NUM 11
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_i387_struct elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) \
- (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
-
-#define ELF_CLASS ELFCLASS32
-#define ELF_DATA ELFDATA2LSB
-#define ELF_ARCH EM_386
-
-#define ELF_PLAT_INIT(regs, load_addr) do { \
- PT_REGS_EBX(regs) = 0; \
- PT_REGS_ECX(regs) = 0; \
- PT_REGS_EDX(regs) = 0; \
- PT_REGS_ESI(regs) = 0; \
- PT_REGS_EDI(regs) = 0; \
- PT_REGS_EBP(regs) = 0; \
- PT_REGS_EAX(regs) = 0; \
-} while (0)
-
-#define ELF_EXEC_PAGESIZE 4096
-
-#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
-
-/* Shamelessly stolen from include/asm-i386/elf.h */
-
-#define ELF_CORE_COPY_REGS(pr_reg, regs) do { \
- pr_reg[0] = PT_REGS_EBX(regs); \
- pr_reg[1] = PT_REGS_ECX(regs); \
- pr_reg[2] = PT_REGS_EDX(regs); \
- pr_reg[3] = PT_REGS_ESI(regs); \
- pr_reg[4] = PT_REGS_EDI(regs); \
- pr_reg[5] = PT_REGS_EBP(regs); \
- pr_reg[6] = PT_REGS_EAX(regs); \
- pr_reg[7] = PT_REGS_DS(regs); \
- pr_reg[8] = PT_REGS_ES(regs); \
- /* fake once used fs and gs selectors? */ \
- pr_reg[9] = PT_REGS_DS(regs); \
- pr_reg[10] = PT_REGS_DS(regs); \
- pr_reg[11] = PT_REGS_SYSCALL_NR(regs); \
- pr_reg[12] = PT_REGS_IP(regs); \
- pr_reg[13] = PT_REGS_CS(regs); \
- pr_reg[14] = PT_REGS_EFLAGS(regs); \
- pr_reg[15] = PT_REGS_SP(regs); \
- pr_reg[16] = PT_REGS_SS(regs); \
-} while (0);
-
-#define task_pt_regs(t) (&(t)->thread.regs)
-
-struct task_struct;
-
-extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
-
-#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
-
-extern long elf_aux_hwcap;
-#define ELF_HWCAP (elf_aux_hwcap)
-
-extern char * elf_aux_platform;
-#define ELF_PLATFORM (elf_aux_platform)
-
-#define SET_PERSONALITY(ex) do { } while (0)
-
-extern unsigned long vsyscall_ehdr;
-extern unsigned long vsyscall_end;
-extern unsigned long __kernel_vsyscall;
-
-#define VSYSCALL_BASE vsyscall_ehdr
-#define VSYSCALL_END vsyscall_end
-
-/*
- * This is the range that is readable by user mode, and things
- * acting like user mode such as get_user_pages.
- */
-#define FIXADDR_USER_START VSYSCALL_BASE
-#define FIXADDR_USER_END VSYSCALL_END
-
-#define __HAVE_ARCH_GATE_AREA 1
-
-/*
- * Architecture-neutral AT_ values in 0-17, leave some room
- * for more of them, start the x86-specific ones at 32.
- */
-#define AT_SYSINFO 32
-#define AT_SYSINFO_EHDR 33
-
-#define ARCH_DLINFO \
-do { \
- if ( vsyscall_ehdr ) { \
- NEW_AUX_ENT(AT_SYSINFO, __kernel_vsyscall); \
- NEW_AUX_ENT(AT_SYSINFO_EHDR, vsyscall_ehdr); \
- } \
-} while (0)
-
-#endif
diff --git a/arch/um/sys-i386/asm/module.h b/arch/um/sys-i386/asm/module.h
deleted file mode 100644
index 5ead4a0b2e35..000000000000
--- a/arch/um/sys-i386/asm/module.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __UM_MODULE_I386_H
-#define __UM_MODULE_I386_H
-
-/* UML is simple */
-struct mod_arch_specific
-{
-};
-
-#define Elf_Shdr Elf32_Shdr
-#define Elf_Sym Elf32_Sym
-#define Elf_Ehdr Elf32_Ehdr
-
-#endif
diff --git a/arch/um/sys-i386/atomic64_cx8_32.S b/arch/um/sys-i386/atomic64_cx8_32.S
deleted file mode 100644
index 1e901d3d4a95..000000000000
--- a/arch/um/sys-i386/atomic64_cx8_32.S
+++ /dev/null
@@ -1,225 +0,0 @@
-/*
- * atomic64_t for 586+
- *
- * Copied from arch/x86/lib/atomic64_cx8_32.S
- *
- * Copyright © 2010 Luca Barbieri
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- */
-
-#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
-
-.macro SAVE reg
- pushl_cfi %\reg
- CFI_REL_OFFSET \reg, 0
-.endm
-
-.macro RESTORE reg
- popl_cfi %\reg
- CFI_RESTORE \reg
-.endm
-
-.macro read64 reg
- movl %ebx, %eax
- movl %ecx, %edx
-/* we need LOCK_PREFIX since otherwise cmpxchg8b always does the write */
- LOCK_PREFIX
- cmpxchg8b (\reg)
-.endm
-
-ENTRY(atomic64_read_cx8)
- CFI_STARTPROC
-
- read64 %ecx
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_read_cx8)
-
-ENTRY(atomic64_set_cx8)
- CFI_STARTPROC
-
-1:
-/* we don't need LOCK_PREFIX since aligned 64-bit writes
- * are atomic on 586 and newer */
- cmpxchg8b (%esi)
- jne 1b
-
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_set_cx8)
-
-ENTRY(atomic64_xchg_cx8)
- CFI_STARTPROC
-
- movl %ebx, %eax
- movl %ecx, %edx
-1:
- LOCK_PREFIX
- cmpxchg8b (%esi)
- jne 1b
-
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_xchg_cx8)
-
-.macro addsub_return func ins insc
-ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- SAVE ebp
- SAVE ebx
- SAVE esi
- SAVE edi
-
- movl %eax, %esi
- movl %edx, %edi
- movl %ecx, %ebp
-
- read64 %ebp
-1:
- movl %eax, %ebx
- movl %edx, %ecx
- \ins\()l %esi, %ebx
- \insc\()l %edi, %ecx
- LOCK_PREFIX
- cmpxchg8b (%ebp)
- jne 1b
-
-10:
- movl %ebx, %eax
- movl %ecx, %edx
- RESTORE edi
- RESTORE esi
- RESTORE ebx
- RESTORE ebp
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_\func\()_return_cx8)
-.endm
-
-addsub_return add add adc
-addsub_return sub sub sbb
-
-.macro incdec_return func ins insc
-ENTRY(atomic64_\func\()_return_cx8)
- CFI_STARTPROC
- SAVE ebx
-
- read64 %esi
-1:
- movl %eax, %ebx
- movl %edx, %ecx
- \ins\()l $1, %ebx
- \insc\()l $0, %ecx
- LOCK_PREFIX
- cmpxchg8b (%esi)
- jne 1b
-
-10:
- movl %ebx, %eax
- movl %ecx, %edx
- RESTORE ebx
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_\func\()_return_cx8)
-.endm
-
-incdec_return inc add adc
-incdec_return dec sub sbb
-
-ENTRY(atomic64_dec_if_positive_cx8)
- CFI_STARTPROC
- SAVE ebx
-
- read64 %esi
-1:
- movl %eax, %ebx
- movl %edx, %ecx
- subl $1, %ebx
- sbb $0, %ecx
- js 2f
- LOCK_PREFIX
- cmpxchg8b (%esi)
- jne 1b
-
-2:
- movl %ebx, %eax
- movl %ecx, %edx
- RESTORE ebx
- ret
- CFI_ENDPROC
-ENDPROC(atomic64_dec_if_positive_cx8)
-
-ENTRY(atomic64_add_unless_cx8)
- CFI_STARTPROC
- SAVE ebp
- SAVE ebx
-/* these just push these two parameters on the stack */
- SAVE edi
- SAVE esi
-
- movl %ecx, %ebp
- movl %eax, %esi
- movl %edx, %edi
-
- read64 %ebp
-1:
- cmpl %eax, 0(%esp)
- je 4f
-2:
- movl %eax, %ebx
- movl %edx, %ecx
- addl %esi, %ebx
- adcl %edi, %ecx
- LOCK_PREFIX
- cmpxchg8b (%ebp)
- jne 1b
-
- movl $1, %eax
-3:
- addl $8, %esp
- CFI_ADJUST_CFA_OFFSET -8
- RESTORE ebx
- RESTORE ebp
- ret
-4:
- cmpl %edx, 4(%esp)
- jne 2b
- xorl %eax, %eax
- jmp 3b
- CFI_ENDPROC
-ENDPROC(atomic64_add_unless_cx8)
-
-ENTRY(atomic64_inc_not_zero_cx8)
- CFI_STARTPROC
- SAVE ebx
-
- read64 %esi
-1:
- testl %eax, %eax
- je 4f
-2:
- movl %eax, %ebx
- movl %edx, %ecx
- addl $1, %ebx
- adcl $0, %ecx
- LOCK_PREFIX
- cmpxchg8b (%esi)
- jne 1b
-
- movl $1, %eax
-3:
- RESTORE ebx
- ret
-4:
- testl %edx, %edx
- jne 2b
- jmp 3b
- CFI_ENDPROC
-ENDPROC(atomic64_inc_not_zero_cx8)
diff --git a/arch/um/sys-i386/bug.c b/arch/um/sys-i386/bug.c
deleted file mode 100644
index 8d4f273f1219..000000000000
--- a/arch/um/sys-i386/bug.c
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright (C) 2006 Jeff Dike (jdike@addtoit.com)
- * Licensed under the GPL V2
- */
-
-#include <linux/uaccess.h>
-#include <asm/errno.h>
-
-/* Mostly copied from i386/x86_86 - eliminated the eip < PAGE_OFFSET because
- * that's not relevant in skas mode.
- */
-
-int is_valid_bugaddr(unsigned long eip)
-{
- unsigned short ud2;
-
- if (probe_kernel_address((unsigned short __user *)eip, ud2))
- return 0;
-
- return ud2 == 0x0b0f;
-}
diff --git a/arch/um/sys-i386/ksyms.c b/arch/um/sys-i386/ksyms.c
deleted file mode 100644
index bfbefd30db8f..000000000000
--- a/arch/um/sys-i386/ksyms.c
+++ /dev/null
@@ -1,5 +0,0 @@
-#include "linux/module.h"
-#include "asm/checksum.h"
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_partial);
diff --git a/arch/um/sys-i386/shared/sysdep/barrier.h b/arch/um/sys-i386/shared/sysdep/barrier.h
deleted file mode 100644
index b58d52c5b2f4..000000000000
--- a/arch/um/sys-i386/shared/sysdep/barrier.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __SYSDEP_I386_BARRIER_H
-#define __SYSDEP_I386_BARRIER_H
-
-/* Copied from include/asm-i386 for use by userspace. i386 has the option
- * of using mfence, but I'm just using this, which works everywhere, for now.
- */
-#define mb() asm volatile("lock; addl $0,0(%esp)")
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/host_ldt.h b/arch/um/sys-i386/shared/sysdep/host_ldt.h
deleted file mode 100644
index 0953cc4df652..000000000000
--- a/arch/um/sys-i386/shared/sysdep/host_ldt.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef __ASM_HOST_LDT_I386_H
-#define __ASM_HOST_LDT_I386_H
-
-#include <asm/ldt.h>
-
-/*
- * macros stolen from include/asm-i386/desc.h
- */
-#define LDT_entry_a(info) \
- ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
-
-#define LDT_entry_b(info) \
- (((info)->base_addr & 0xff000000) | \
- (((info)->base_addr & 0x00ff0000) >> 16) | \
- ((info)->limit & 0xf0000) | \
- (((info)->read_exec_only ^ 1) << 9) | \
- ((info)->contents << 10) | \
- (((info)->seg_not_present ^ 1) << 15) | \
- ((info)->seg_32bit << 22) | \
- ((info)->limit_in_pages << 23) | \
- ((info)->useable << 20) | \
- 0x7000)
-
-#define LDT_empty(info) (\
- (info)->base_addr == 0 && \
- (info)->limit == 0 && \
- (info)->contents == 0 && \
- (info)->read_exec_only == 1 && \
- (info)->seg_32bit == 0 && \
- (info)->limit_in_pages == 0 && \
- (info)->seg_not_present == 1 && \
- (info)->useable == 0 )
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/ptrace_user.h b/arch/um/sys-i386/shared/sysdep/ptrace_user.h
deleted file mode 100644
index ef56247e4143..000000000000
--- a/arch/um/sys-i386/shared/sysdep/ptrace_user.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_I386_PTRACE_USER_H__
-#define __SYSDEP_I386_PTRACE_USER_H__
-
-#include <sys/ptrace.h>
-#include <linux/ptrace.h>
-#include <asm/ptrace.h>
-#include "user_constants.h"
-
-#define PT_OFFSET(r) ((r) * sizeof(long))
-
-#define PT_SYSCALL_NR(regs) ((regs)[ORIG_EAX])
-#define PT_SYSCALL_NR_OFFSET PT_OFFSET(ORIG_EAX)
-
-#define PT_SYSCALL_ARG1_OFFSET PT_OFFSET(EBX)
-#define PT_SYSCALL_ARG2_OFFSET PT_OFFSET(ECX)
-#define PT_SYSCALL_ARG3_OFFSET PT_OFFSET(EDX)
-#define PT_SYSCALL_ARG4_OFFSET PT_OFFSET(ESI)
-#define PT_SYSCALL_ARG5_OFFSET PT_OFFSET(EDI)
-#define PT_SYSCALL_ARG6_OFFSET PT_OFFSET(EBP)
-
-#define PT_SYSCALL_RET_OFFSET PT_OFFSET(EAX)
-
-#define REGS_SYSCALL_NR EAX /* This is used before a system call */
-#define REGS_SYSCALL_ARG1 EBX
-#define REGS_SYSCALL_ARG2 ECX
-#define REGS_SYSCALL_ARG3 EDX
-#define REGS_SYSCALL_ARG4 ESI
-#define REGS_SYSCALL_ARG5 EDI
-#define REGS_SYSCALL_ARG6 EBP
-
-#define REGS_IP_INDEX EIP
-#define REGS_SP_INDEX UESP
-
-#define PT_IP_OFFSET PT_OFFSET(EIP)
-#define PT_IP(regs) ((regs)[EIP])
-#define PT_SP_OFFSET PT_OFFSET(UESP)
-#define PT_SP(regs) ((regs)[UESP])
-
-#define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE)
-
-#ifndef FRAME_SIZE
-#define FRAME_SIZE (17)
-#endif
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/sc.h b/arch/um/sys-i386/shared/sysdep/sc.h
deleted file mode 100644
index c57d1780ad37..000000000000
--- a/arch/um/sys-i386/shared/sysdep/sc.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef __SYSDEP_I386_SC_H
-#define __SYSDEP_I386_SC_H
-
-#include <user_constants.h>
-
-#define SC_OFFSET(sc, field) \
- *((unsigned long *) &(((char *) (sc))[HOST_##field]))
-#define SC_FP_OFFSET(sc, field) \
- *((unsigned long *) &(((char *) (SC_FPSTATE(sc)))[HOST_##field]))
-#define SC_FP_OFFSET_PTR(sc, field, type) \
- ((type *) &(((char *) (SC_FPSTATE(sc)))[HOST_##field]))
-
-#define SC_IP(sc) SC_OFFSET(sc, SC_IP)
-#define SC_SP(sc) SC_OFFSET(sc, SC_SP)
-#define SC_FS(sc) SC_OFFSET(sc, SC_FS)
-#define SC_GS(sc) SC_OFFSET(sc, SC_GS)
-#define SC_DS(sc) SC_OFFSET(sc, SC_DS)
-#define SC_ES(sc) SC_OFFSET(sc, SC_ES)
-#define SC_SS(sc) SC_OFFSET(sc, SC_SS)
-#define SC_CS(sc) SC_OFFSET(sc, SC_CS)
-#define SC_EFLAGS(sc) SC_OFFSET(sc, SC_EFLAGS)
-#define SC_EAX(sc) SC_OFFSET(sc, SC_EAX)
-#define SC_EBX(sc) SC_OFFSET(sc, SC_EBX)
-#define SC_ECX(sc) SC_OFFSET(sc, SC_ECX)
-#define SC_EDX(sc) SC_OFFSET(sc, SC_EDX)
-#define SC_EDI(sc) SC_OFFSET(sc, SC_EDI)
-#define SC_ESI(sc) SC_OFFSET(sc, SC_ESI)
-#define SC_EBP(sc) SC_OFFSET(sc, SC_EBP)
-#define SC_TRAPNO(sc) SC_OFFSET(sc, SC_TRAPNO)
-#define SC_ERR(sc) SC_OFFSET(sc, SC_ERR)
-#define SC_CR2(sc) SC_OFFSET(sc, SC_CR2)
-#define SC_FPSTATE(sc) SC_OFFSET(sc, SC_FPSTATE)
-#define SC_SIGMASK(sc) SC_OFFSET(sc, SC_SIGMASK)
-#define SC_FP_CW(sc) SC_FP_OFFSET(sc, SC_FP_CW)
-#define SC_FP_SW(sc) SC_FP_OFFSET(sc, SC_FP_SW)
-#define SC_FP_TAG(sc) SC_FP_OFFSET(sc, SC_FP_TAG)
-#define SC_FP_IPOFF(sc) SC_FP_OFFSET(sc, SC_FP_IPOFF)
-#define SC_FP_CSSEL(sc) SC_FP_OFFSET(sc, SC_FP_CSSEL)
-#define SC_FP_DATAOFF(sc) SC_FP_OFFSET(sc, SC_FP_DATAOFF)
-#define SC_FP_DATASEL(sc) SC_FP_OFFSET(sc, SC_FP_DATASEL)
-#define SC_FP_ST(sc) SC_FP_OFFSET_PTR(sc, SC_FP_ST, struct _fpstate)
-#define SC_FXSR_ENV(sc) SC_FP_OFFSET_PTR(sc, SC_FXSR_ENV, void)
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/sigcontext.h b/arch/um/sys-i386/shared/sysdep/sigcontext.h
deleted file mode 100644
index f583c87111a0..000000000000
--- a/arch/um/sys-i386/shared/sysdep/sigcontext.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __SYS_SIGCONTEXT_I386_H
-#define __SYS_SIGCONTEXT_I386_H
-
-#include "sysdep/sc.h"
-
-#define IP_RESTART_SYSCALL(ip) ((ip) -= 2)
-
-#define GET_FAULTINFO_FROM_SC(fi, sc) \
- { \
- (fi).cr2 = SC_CR2(sc); \
- (fi).error_code = SC_ERR(sc); \
- (fi).trap_no = SC_TRAPNO(sc); \
- }
-
-/* This is Page Fault */
-#define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14)
-
-/* SKAS3 has no trap_no on i386, but get_skas_faultinfo() sets it to 0. */
-#define SEGV_MAYBE_FIXABLE(fi) ((fi)->trap_no == 0 && ptrace_faultinfo)
-
-#endif
diff --git a/arch/um/sys-i386/shared/sysdep/vm-flags.h b/arch/um/sys-i386/shared/sysdep/vm-flags.h
deleted file mode 100644
index e0d24c568dbc..000000000000
--- a/arch/um/sys-i386/shared/sysdep/vm-flags.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * Copyright (C) 2004 Jeff Dike (jdike@addtoit.com)
- * Licensed under the GPL
- */
-
-#ifndef __VM_FLAGS_I386_H
-#define __VM_FLAGS_I386_H
-
-#define VM_DATA_DEFAULT_FLAGS \
- (VM_READ | VM_WRITE | \
- ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
- VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-#endif
diff --git a/arch/um/sys-i386/stub_segv.c b/arch/um/sys-i386/stub_segv.c
deleted file mode 100644
index 28ccf737a79f..000000000000
--- a/arch/um/sys-i386/stub_segv.c
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Copyright (C) 2004 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include "sysdep/stub.h"
-#include "sysdep/sigcontext.h"
-
-void __attribute__ ((__section__ (".__syscall_stub")))
-stub_segv_handler(int sig)
-{
- struct sigcontext *sc = (struct sigcontext *) (&sig + 1);
-
- GET_FAULTINFO_FROM_SC(*((struct faultinfo *) STUB_DATA), sc);
-
- trap_myself();
-}
diff --git a/arch/um/sys-i386/user-offsets.c b/arch/um/sys-i386/user-offsets.c
deleted file mode 100644
index 5f883bfe773f..000000000000
--- a/arch/um/sys-i386/user-offsets.c
+++ /dev/null
@@ -1,53 +0,0 @@
-#include <stdio.h>
-#include <stddef.h>
-#include <signal.h>
-#include <sys/poll.h>
-#include <sys/user.h>
-#include <sys/mman.h>
-#include <asm/ptrace.h>
-
-#define DEFINE(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define DEFINE_LONGS(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long)))
-
-#define OFFSET(sym, str, mem) \
- DEFINE(sym, offsetof(struct str, mem));
-
-void foo(void)
-{
- OFFSET(HOST_SC_TRAPNO, sigcontext, trapno);
- OFFSET(HOST_SC_ERR, sigcontext, err);
- OFFSET(HOST_SC_CR2, sigcontext, cr2);
-
- DEFINE_LONGS(HOST_FP_SIZE, sizeof(struct user_fpregs_struct));
- DEFINE_LONGS(HOST_FPX_SIZE, sizeof(struct user_fpxregs_struct));
-
- DEFINE(HOST_IP, EIP);
- DEFINE(HOST_SP, UESP);
- DEFINE(HOST_EFLAGS, EFL);
- DEFINE(HOST_EAX, EAX);
- DEFINE(HOST_EBX, EBX);
- DEFINE(HOST_ECX, ECX);
- DEFINE(HOST_EDX, EDX);
- DEFINE(HOST_ESI, ESI);
- DEFINE(HOST_EDI, EDI);
- DEFINE(HOST_EBP, EBP);
- DEFINE(HOST_CS, CS);
- DEFINE(HOST_SS, SS);
- DEFINE(HOST_DS, DS);
- DEFINE(HOST_FS, FS);
- DEFINE(HOST_ES, ES);
- DEFINE(HOST_GS, GS);
- DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct));
-
- /* XXX Duplicated between i386 and x86_64 */
- DEFINE(UM_POLLIN, POLLIN);
- DEFINE(UM_POLLPRI, POLLPRI);
- DEFINE(UM_POLLOUT, POLLOUT);
-
- DEFINE(UM_PROT_READ, PROT_READ);
- DEFINE(UM_PROT_WRITE, PROT_WRITE);
- DEFINE(UM_PROT_EXEC, PROT_EXEC);
-}
diff --git a/arch/um/sys-x86_64/Makefile b/arch/um/sys-x86_64/Makefile
deleted file mode 100644
index bd4d1d3ba919..000000000000
--- a/arch/um/sys-x86_64/Makefile
+++ /dev/null
@@ -1,27 +0,0 @@
-#
-# Copyright 2003 PathScale, Inc.
-#
-# Licensed under the GPL
-#
-
-obj-y = bug.o bugs.o delay.o fault.o ldt.o ptrace.o ptrace_user.o mem.o \
- setjmp.o signal.o stub.o stub_segv.o syscalls.o syscall_table.o \
- sysrq.o ksyms.o tls.o
-
-obj-y += vdso/
-
-subarch-obj-y = lib/csum-partial_64.o lib/memcpy_64.o lib/thunk_64.o \
- lib/rwsem.o
-subarch-obj-$(CONFIG_MODULES) += kernel/module.o
-
-ldt-y = ../sys-i386/ldt.o
-
-USER_OBJS := ptrace_user.o
-
-USER_OBJS += user-offsets.s
-extra-y += user-offsets.s
-
-UNPROFILE_OBJS := stub_segv.o
-CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING)
-
-include arch/um/scripts/Makefile.rules
diff --git a/arch/um/sys-x86_64/asm/archparam.h b/arch/um/sys-x86_64/asm/archparam.h
deleted file mode 100644
index 6c083663b8d9..000000000000
--- a/arch/um/sys-x86_64/asm/archparam.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_ARCHPARAM_X86_64_H
-#define __UM_ARCHPARAM_X86_64_H
-
-
-/* No user-accessible fixmap addresses, i.e. vsyscall */
-#define FIXADDR_USER_START 0
-#define FIXADDR_USER_END 0
-
-#endif
-
diff --git a/arch/um/sys-x86_64/asm/module.h b/arch/um/sys-x86_64/asm/module.h
deleted file mode 100644
index 8eb79c2d07d5..000000000000
--- a/arch/um/sys-x86_64/asm/module.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_MODULE_X86_64_H
-#define __UM_MODULE_X86_64_H
-
-/* UML is simple */
-struct mod_arch_specific
-{
-};
-
-#define Elf_Shdr Elf64_Shdr
-#define Elf_Sym Elf64_Sym
-#define Elf_Ehdr Elf64_Ehdr
-
-#endif
-
diff --git a/arch/um/sys-x86_64/delay.c b/arch/um/sys-x86_64/delay.c
deleted file mode 100644
index f3fe1a688f7e..000000000000
--- a/arch/um/sys-x86_64/delay.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * Copyright (C) 2011 Richard Weinberger <richrd@nod.at>
- * Mostly copied from arch/x86/lib/delay.c
- *
- * 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.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <asm/param.h>
-
-void __delay(unsigned long loops)
-{
- asm volatile(
- "test %0,%0\n"
- "jz 3f\n"
- "jmp 1f\n"
-
- ".align 16\n"
- "1: jmp 2f\n"
-
- ".align 16\n"
- "2: dec %0\n"
- " jnz 2b\n"
- "3: dec %0\n"
-
- : /* we don't need output */
- : "a" (loops)
- );
-}
-EXPORT_SYMBOL(__delay);
-
-inline void __const_udelay(unsigned long xloops)
-{
- int d0;
-
- xloops *= 4;
- asm("mull %%edx"
- : "=d" (xloops), "=&a" (d0)
- : "1" (xloops), "0"
- (loops_per_jiffy * (HZ/4)));
-
- __delay(++xloops);
-}
-EXPORT_SYMBOL(__const_udelay);
-
-void __udelay(unsigned long usecs)
-{
- __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
-}
-EXPORT_SYMBOL(__udelay);
-
-void __ndelay(unsigned long nsecs)
-{
- __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
-}
-EXPORT_SYMBOL(__ndelay);
diff --git a/arch/um/sys-x86_64/fault.c b/arch/um/sys-x86_64/fault.c
deleted file mode 100644
index ce85117fc64e..000000000000
--- a/arch/um/sys-x86_64/fault.c
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#include "sysdep/ptrace.h"
-
-/* These two are from asm-um/uaccess.h and linux/module.h, check them. */
-struct exception_table_entry
-{
- unsigned long insn;
- unsigned long fixup;
-};
-
-const struct exception_table_entry *search_exception_tables(unsigned long add);
-
-int arch_fixup(unsigned long address, struct uml_pt_regs *regs)
-{
- const struct exception_table_entry *fixup;
-
- fixup = search_exception_tables(address);
- if (fixup != 0) {
- UPT_IP(regs) = fixup->fixup;
- return 1;
- }
- return 0;
-}
diff --git a/arch/um/sys-x86_64/ptrace_user.c b/arch/um/sys-x86_64/ptrace_user.c
deleted file mode 100644
index c57a496d3f5b..000000000000
--- a/arch/um/sys-x86_64/ptrace_user.c
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#include <errno.h>
-#include "ptrace_user.h"
-
-int ptrace_getregs(long pid, unsigned long *regs_out)
-{
- if (ptrace(PTRACE_GETREGS, pid, 0, regs_out) < 0)
- return -errno;
- return(0);
-}
-
-int ptrace_setregs(long pid, unsigned long *regs_out)
-{
- if (ptrace(PTRACE_SETREGS, pid, 0, regs_out) < 0)
- return -errno;
- return(0);
-}
diff --git a/arch/um/sys-x86_64/shared/sysdep/barrier.h b/arch/um/sys-x86_64/shared/sysdep/barrier.h
deleted file mode 100644
index 7b610befdc8f..000000000000
--- a/arch/um/sys-x86_64/shared/sysdep/barrier.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __SYSDEP_X86_64_BARRIER_H
-#define __SYSDEP_X86_64_BARRIER_H
-
-/* Copied from include/asm-x86_64 for use by userspace. */
-#define mb() asm volatile("mfence":::"memory")
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/host_ldt.h b/arch/um/sys-x86_64/shared/sysdep/host_ldt.h
deleted file mode 100644
index e8b1be1e154f..000000000000
--- a/arch/um/sys-x86_64/shared/sysdep/host_ldt.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#ifndef __ASM_HOST_LDT_X86_64_H
-#define __ASM_HOST_LDT_X86_64_H
-
-#include <asm/ldt.h>
-
-/*
- * macros stolen from include/asm-x86_64/desc.h
- */
-#define LDT_entry_a(info) \
- ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
-
-/* Don't allow setting of the lm bit. It is useless anyways because
- * 64bit system calls require __USER_CS. */
-#define LDT_entry_b(info) \
- (((info)->base_addr & 0xff000000) | \
- (((info)->base_addr & 0x00ff0000) >> 16) | \
- ((info)->limit & 0xf0000) | \
- (((info)->read_exec_only ^ 1) << 9) | \
- ((info)->contents << 10) | \
- (((info)->seg_not_present ^ 1) << 15) | \
- ((info)->seg_32bit << 22) | \
- ((info)->limit_in_pages << 23) | \
- ((info)->useable << 20) | \
- /* ((info)->lm << 21) | */ \
- 0x7000)
-
-#define LDT_empty(info) (\
- (info)->base_addr == 0 && \
- (info)->limit == 0 && \
- (info)->contents == 0 && \
- (info)->read_exec_only == 1 && \
- (info)->seg_32bit == 0 && \
- (info)->limit_in_pages == 0 && \
- (info)->seg_not_present == 1 && \
- (info)->useable == 0 && \
- (info)->lm == 0)
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/kernel-offsets.h b/arch/um/sys-x86_64/shared/sysdep/kernel-offsets.h
deleted file mode 100644
index a307237b7964..000000000000
--- a/arch/um/sys-x86_64/shared/sysdep/kernel-offsets.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#include <linux/stddef.h>
-#include <linux/sched.h>
-#include <linux/time.h>
-#include <linux/elf.h>
-#include <linux/crypto.h>
-#include <asm/page.h>
-#include <asm/mman.h>
-
-#define DEFINE(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define DEFINE_STR1(x) #x
-#define DEFINE_STR(sym, val) asm volatile("\n->" #sym " " DEFINE_STR1(val) " " #val: : )
-
-#define BLANK() asm volatile("\n->" : : )
-
-#define OFFSET(sym, str, mem) \
- DEFINE(sym, offsetof(struct str, mem));
-
-void foo(void)
-{
-#include <common-offsets.h>
-}
diff --git a/arch/um/sys-x86_64/shared/sysdep/ptrace_user.h b/arch/um/sys-x86_64/shared/sysdep/ptrace_user.h
deleted file mode 100644
index 4dbccdb58f48..000000000000
--- a/arch/um/sys-x86_64/shared/sysdep/ptrace_user.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_X86_64_PTRACE_USER_H__
-#define __SYSDEP_X86_64_PTRACE_USER_H__
-
-#define __FRAME_OFFSETS
-#include <sys/ptrace.h>
-#include <linux/ptrace.h>
-#include <asm/ptrace.h>
-#undef __FRAME_OFFSETS
-#include "user_constants.h"
-
-#define PT_INDEX(off) ((off) / sizeof(unsigned long))
-
-#define PT_SYSCALL_NR(regs) ((regs)[PT_INDEX(ORIG_RAX)])
-#define PT_SYSCALL_NR_OFFSET (ORIG_RAX)
-
-#define PT_SYSCALL_ARG1(regs) (((unsigned long *) (regs))[PT_INDEX(RDI)])
-#define PT_SYSCALL_ARG1_OFFSET (RDI)
-
-#define PT_SYSCALL_ARG2(regs) (((unsigned long *) (regs))[PT_INDEX(RSI)])
-#define PT_SYSCALL_ARG2_OFFSET (RSI)
-
-#define PT_SYSCALL_ARG3(regs) (((unsigned long *) (regs))[PT_INDEX(RDX)])
-#define PT_SYSCALL_ARG3_OFFSET (RDX)
-
-#define PT_SYSCALL_ARG4(regs) (((unsigned long *) (regs))[PT_INDEX(RCX)])
-#define PT_SYSCALL_ARG4_OFFSET (RCX)
-
-#define PT_SYSCALL_ARG5(regs) (((unsigned long *) (regs))[PT_INDEX(R8)])
-#define PT_SYSCALL_ARG5_OFFSET (R8)
-
-#define PT_SYSCALL_ARG6(regs) (((unsigned long *) (regs))[PT_INDEX(R9)])
-#define PT_SYSCALL_ARG6_OFFSET (R9)
-
-#define PT_SYSCALL_RET_OFFSET (RAX)
-
-#define PT_IP_OFFSET (RIP)
-#define PT_IP(regs) ((regs)[PT_INDEX(RIP)])
-
-#define PT_SP_OFFSET (RSP)
-#define PT_SP(regs) ((regs)[PT_INDEX(RSP)])
-
-#define PT_ORIG_RAX_OFFSET (ORIG_RAX)
-#define PT_ORIG_RAX(regs) ((regs)[PT_INDEX(ORIG_RAX)])
-
-/*
- * x86_64 FC3 doesn't define this in /usr/include/linux/ptrace.h even though
- * it's defined in the kernel's include/linux/ptrace.h. Additionally, use the
- * 2.4 name and value for 2.4 host compatibility.
- */
-#ifndef PTRACE_OLDSETOPTIONS
-#define PTRACE_OLDSETOPTIONS 21
-#endif
-
-/*
- * These are before the system call, so the system call number is RAX
- * rather than ORIG_RAX, and arg4 is R10 rather than RCX
- */
-#define REGS_SYSCALL_NR PT_INDEX(RAX)
-#define REGS_SYSCALL_ARG1 PT_INDEX(RDI)
-#define REGS_SYSCALL_ARG2 PT_INDEX(RSI)
-#define REGS_SYSCALL_ARG3 PT_INDEX(RDX)
-#define REGS_SYSCALL_ARG4 PT_INDEX(R10)
-#define REGS_SYSCALL_ARG5 PT_INDEX(R8)
-#define REGS_SYSCALL_ARG6 PT_INDEX(R9)
-
-#define REGS_IP_INDEX PT_INDEX(RIP)
-#define REGS_SP_INDEX PT_INDEX(RSP)
-
-#define FP_SIZE (HOST_FP_SIZE)
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/sc.h b/arch/um/sys-x86_64/shared/sysdep/sc.h
deleted file mode 100644
index 8aee45b07434..000000000000
--- a/arch/um/sys-x86_64/shared/sysdep/sc.h
+++ /dev/null
@@ -1,45 +0,0 @@
-#ifndef __SYSDEP_X86_64_SC_H
-#define __SYSDEP_X86_64_SC_H
-
-/* Copyright (C) 2003 - 2004 PathScale, Inc
- * Released under the GPL
- */
-
-#include <user_constants.h>
-
-#define SC_OFFSET(sc, field) \
- *((unsigned long *) &(((char *) (sc))[HOST_##field]))
-
-#define SC_RBX(sc) SC_OFFSET(sc, SC_RBX)
-#define SC_RCX(sc) SC_OFFSET(sc, SC_RCX)
-#define SC_RDX(sc) SC_OFFSET(sc, SC_RDX)
-#define SC_RSI(sc) SC_OFFSET(sc, SC_RSI)
-#define SC_RDI(sc) SC_OFFSET(sc, SC_RDI)
-#define SC_RBP(sc) SC_OFFSET(sc, SC_RBP)
-#define SC_RAX(sc) SC_OFFSET(sc, SC_RAX)
-#define SC_R8(sc) SC_OFFSET(sc, SC_R8)
-#define SC_R9(sc) SC_OFFSET(sc, SC_R9)
-#define SC_R10(sc) SC_OFFSET(sc, SC_R10)
-#define SC_R11(sc) SC_OFFSET(sc, SC_R11)
-#define SC_R12(sc) SC_OFFSET(sc, SC_R12)
-#define SC_R13(sc) SC_OFFSET(sc, SC_R13)
-#define SC_R14(sc) SC_OFFSET(sc, SC_R14)
-#define SC_R15(sc) SC_OFFSET(sc, SC_R15)
-#define SC_IP(sc) SC_OFFSET(sc, SC_IP)
-#define SC_SP(sc) SC_OFFSET(sc, SC_SP)
-#define SC_CR2(sc) SC_OFFSET(sc, SC_CR2)
-#define SC_ERR(sc) SC_OFFSET(sc, SC_ERR)
-#define SC_TRAPNO(sc) SC_OFFSET(sc, SC_TRAPNO)
-#define SC_CS(sc) SC_OFFSET(sc, SC_CS)
-#define SC_FS(sc) SC_OFFSET(sc, SC_FS)
-#define SC_GS(sc) SC_OFFSET(sc, SC_GS)
-#define SC_EFLAGS(sc) SC_OFFSET(sc, SC_EFLAGS)
-#define SC_SIGMASK(sc) SC_OFFSET(sc, SC_SIGMASK)
-#define SC_SS(sc) SC_OFFSET(sc, SC_SS)
-#if 0
-#define SC_ORIG_RAX(sc) SC_OFFSET(sc, SC_ORIG_RAX)
-#define SC_DS(sc) SC_OFFSET(sc, SC_DS)
-#define SC_ES(sc) SC_OFFSET(sc, SC_ES)
-#endif
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/sigcontext.h b/arch/um/sys-x86_64/shared/sysdep/sigcontext.h
deleted file mode 100644
index 0155133b1458..000000000000
--- a/arch/um/sys-x86_64/shared/sysdep/sigcontext.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_X86_64_SIGCONTEXT_H
-#define __SYSDEP_X86_64_SIGCONTEXT_H
-
-#include <sysdep/sc.h>
-
-#define IP_RESTART_SYSCALL(ip) ((ip) -= 2)
-
-#define GET_FAULTINFO_FROM_SC(fi, sc) \
- { \
- (fi).cr2 = SC_CR2(sc); \
- (fi).error_code = SC_ERR(sc); \
- (fi).trap_no = SC_TRAPNO(sc); \
- }
-
-/* This is Page Fault */
-#define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14)
-
-/* No broken SKAS API, which doesn't pass trap_no, here. */
-#define SEGV_MAYBE_FIXABLE(fi) 0
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/skas_ptrace.h b/arch/um/sys-x86_64/shared/sysdep/skas_ptrace.h
deleted file mode 100644
index 95db4be786e4..000000000000
--- a/arch/um/sys-x86_64/shared/sysdep/skas_ptrace.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_X86_64_SKAS_PTRACE_H
-#define __SYSDEP_X86_64_SKAS_PTRACE_H
-
-struct ptrace_faultinfo {
- int is_write;
- unsigned long addr;
-};
-
-struct ptrace_ldt {
- int func;
- void *ptr;
- unsigned long bytecount;
-};
-
-#define PTRACE_LDT 54
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/system.h b/arch/um/sys-x86_64/shared/sysdep/system.h
deleted file mode 100644
index d1b93c436200..000000000000
--- a/arch/um/sys-x86_64/shared/sysdep/system.h
+++ /dev/null
@@ -1,132 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_H_
-#define _ASM_X86_SYSTEM_H_
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
-# define AT_VECTOR_SIZE_ARCH 2
-#else
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-void default_idle(void);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() asm volatile("mfence":::"memory")
-#define rmb() asm volatile("lfence":::"memory")
-#define wmb() asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier. All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads. This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies. See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- * CPU 0 CPU 1
- *
- * b = 2;
- * memory_barrier();
- * p = &b; q = p;
- * read_barrier_depends();
- * d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends(). However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- * CPU 0 CPU 1
- *
- * a = 2;
- * memory_barrier();
- * b = 3; y = b;
- * read_barrier_depends();
- * x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b". Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends() do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb() mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb() rmb()
-#else
-# define smp_rmb() barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() wmb()
-#else
-# define smp_wmb() barrier()
-#endif
-#define smp_read_barrier_depends() read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb() barrier()
-#define smp_rmb() barrier()
-#define smp_wmb() barrier()
-#define smp_read_barrier_depends() do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static inline void rdtsc_barrier(void)
-{
- alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
- alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/tls.h b/arch/um/sys-x86_64/shared/sysdep/tls.h
deleted file mode 100644
index 18c000d0357a..000000000000
--- a/arch/um/sys-x86_64/shared/sysdep/tls.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef _SYSDEP_TLS_H
-#define _SYSDEP_TLS_H
-
-# ifndef __KERNEL__
-
-/* Change name to avoid conflicts with the original one from <asm/ldt.h>, which
- * may be named user_desc (but in 2.4 and in header matching its API was named
- * modify_ldt_ldt_s). */
-
-typedef struct um_dup_user_desc {
- unsigned int entry_number;
- unsigned int base_addr;
- unsigned int limit;
- unsigned int seg_32bit:1;
- unsigned int contents:2;
- unsigned int read_exec_only:1;
- unsigned int limit_in_pages:1;
- unsigned int seg_not_present:1;
- unsigned int useable:1;
- unsigned int lm:1;
-} user_desc_t;
-
-# else /* __KERNEL__ */
-
-# include <ldt.h>
-typedef struct user_desc user_desc_t;
-
-# endif /* __KERNEL__ */
-#endif /* _SYSDEP_TLS_H */
diff --git a/arch/um/sys-x86_64/signal.c b/arch/um/sys-x86_64/signal.c
deleted file mode 100644
index b6b65c7c7a7d..000000000000
--- a/arch/um/sys-x86_64/signal.c
+++ /dev/null
@@ -1,290 +0,0 @@
-/*
- * Copyright (C) 2003 PathScale, Inc.
- * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <linux/personality.h>
-#include <linux/ptrace.h>
-#include <linux/kernel.h>
-#include <asm/unistd.h>
-#include <asm/uaccess.h>
-#include <asm/ucontext.h>
-#include "frame_kern.h"
-#include "skas.h"
-
-void copy_sc(struct uml_pt_regs *regs, void *from)
-{
- struct sigcontext *sc = from;
-
-#define GETREG(regs, regno, sc, regname) \
- (regs)->gp[(regno) / sizeof(unsigned long)] = (sc)->regname
-
- GETREG(regs, R8, sc, r8);
- GETREG(regs, R9, sc, r9);
- GETREG(regs, R10, sc, r10);
- GETREG(regs, R11, sc, r11);
- GETREG(regs, R12, sc, r12);
- GETREG(regs, R13, sc, r13);
- GETREG(regs, R14, sc, r14);
- GETREG(regs, R15, sc, r15);
- GETREG(regs, RDI, sc, di);
- GETREG(regs, RSI, sc, si);
- GETREG(regs, RBP, sc, bp);
- GETREG(regs, RBX, sc, bx);
- GETREG(regs, RDX, sc, dx);
- GETREG(regs, RAX, sc, ax);
- GETREG(regs, RCX, sc, cx);
- GETREG(regs, RSP, sc, sp);
- GETREG(regs, RIP, sc, ip);
- GETREG(regs, EFLAGS, sc, flags);
- GETREG(regs, CS, sc, cs);
-
-#undef GETREG
-}
-
-static int copy_sc_from_user(struct pt_regs *regs,
- struct sigcontext __user *from,
- struct _fpstate __user *fpp)
-{
- struct user_i387_struct fp;
- int err = 0;
-
-#define GETREG(regs, regno, sc, regname) \
- __get_user((regs)->regs.gp[(regno) / sizeof(unsigned long)], \
- &(sc)->regname)
-
- err |= GETREG(regs, R8, from, r8);
- err |= GETREG(regs, R9, from, r9);
- err |= GETREG(regs, R10, from, r10);
- err |= GETREG(regs, R11, from, r11);
- err |= GETREG(regs, R12, from, r12);
- err |= GETREG(regs, R13, from, r13);
- err |= GETREG(regs, R14, from, r14);
- err |= GETREG(regs, R15, from, r15);
- err |= GETREG(regs, RDI, from, di);
- err |= GETREG(regs, RSI, from, si);
- err |= GETREG(regs, RBP, from, bp);
- err |= GETREG(regs, RBX, from, bx);
- err |= GETREG(regs, RDX, from, dx);
- err |= GETREG(regs, RAX, from, ax);
- err |= GETREG(regs, RCX, from, cx);
- err |= GETREG(regs, RSP, from, sp);
- err |= GETREG(regs, RIP, from, ip);
- err |= GETREG(regs, EFLAGS, from, flags);
- err |= GETREG(regs, CS, from, cs);
- if (err)
- return 1;
-
-#undef GETREG
-
- err = copy_from_user(&fp, fpp, sizeof(struct user_i387_struct));
- if (err)
- return 1;
-
- err = restore_fp_registers(userspace_pid[current_thread_info()->cpu],
- (unsigned long *) &fp);
- if (err < 0) {
- printk(KERN_ERR "copy_sc_from_user - "
- "restore_fp_registers failed, errno = %d\n",
- -err);
- return 1;
- }
-
- return 0;
-}
-
-static int copy_sc_to_user(struct sigcontext __user *to,
- struct _fpstate __user *to_fp, struct pt_regs *regs,
- unsigned long mask, unsigned long sp)
-{
- struct faultinfo * fi = &current->thread.arch.faultinfo;
- struct user_i387_struct fp;
- int err = 0;
-
- err |= __put_user(0, &to->gs);
- err |= __put_user(0, &to->fs);
-
-#define PUTREG(regs, regno, sc, regname) \
- __put_user((regs)->regs.gp[(regno) / sizeof(unsigned long)], \
- &(sc)->regname)
-
- err |= PUTREG(regs, RDI, to, di);
- err |= PUTREG(regs, RSI, to, si);
- err |= PUTREG(regs, RBP, to, bp);
- /*
- * Must use original RSP, which is passed in, rather than what's in
- * the pt_regs, because that's already been updated to point at the
- * signal frame.
- */
- err |= __put_user(sp, &to->sp);
- err |= PUTREG(regs, RBX, to, bx);
- err |= PUTREG(regs, RDX, to, dx);
- err |= PUTREG(regs, RCX, to, cx);
- err |= PUTREG(regs, RAX, to, ax);
- err |= PUTREG(regs, R8, to, r8);
- err |= PUTREG(regs, R9, to, r9);
- err |= PUTREG(regs, R10, to, r10);
- err |= PUTREG(regs, R11, to, r11);
- err |= PUTREG(regs, R12, to, r12);
- err |= PUTREG(regs, R13, to, r13);
- err |= PUTREG(regs, R14, to, r14);
- err |= PUTREG(regs, R15, to, r15);
- err |= PUTREG(regs, CS, to, cs); /* XXX x86_64 doesn't do this */
-
- err |= __put_user(fi->cr2, &to->cr2);
- err |= __put_user(fi->error_code, &to->err);
- err |= __put_user(fi->trap_no, &to->trapno);
-
- err |= PUTREG(regs, RIP, to, ip);
- err |= PUTREG(regs, EFLAGS, to, flags);
-#undef PUTREG
-
- err |= __put_user(mask, &to->oldmask);
- if (err)
- return 1;
-
- err = save_fp_registers(userspace_pid[current_thread_info()->cpu],
- (unsigned long *) &fp);
- if (err < 0) {
- printk(KERN_ERR "copy_sc_from_user - restore_fp_registers "
- "failed, errno = %d\n", -err);
- return 1;
- }
-
- if (copy_to_user(to_fp, &fp, sizeof(struct user_i387_struct)))
- return 1;
-
- return err;
-}
-
-struct rt_sigframe
-{
- char __user *pretcode;
- struct ucontext uc;
- struct siginfo info;
- struct _fpstate fpstate;
-};
-
-int setup_signal_stack_si(unsigned long stack_top, int sig,
- struct k_sigaction *ka, struct pt_regs * regs,
- siginfo_t *info, sigset_t *set)
-{
- struct rt_sigframe __user *frame;
- unsigned long save_sp = PT_REGS_RSP(regs);
- int err = 0;
- struct task_struct *me = current;
-
- frame = (struct rt_sigframe __user *)
- round_down(stack_top - sizeof(struct rt_sigframe), 16);
- /* Subtract 128 for a red zone and 8 for proper alignment */
- frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8);
-
- if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
- goto out;
-
- if (ka->sa.sa_flags & SA_SIGINFO) {
- err |= copy_siginfo_to_user(&frame->info, info);
- if (err)
- goto out;
- }
-
- /*
- * Update SP now because the page fault handler refuses to extend
- * the stack if the faulting address is too far below the current
- * SP, which frame now certainly is. If there's an error, the original
- * value is restored on the way out.
- * When writing the sigcontext to the stack, we have to write the
- * original value, so that's passed to copy_sc_to_user, which does
- * the right thing with it.
- */
- PT_REGS_RSP(regs) = (unsigned long) frame;
-
- /* Create the ucontext. */
- err |= __put_user(0, &frame->uc.uc_flags);
- err |= __put_user(0, &frame->uc.uc_link);
- err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- err |= __put_user(sas_ss_flags(save_sp),
- &frame->uc.uc_stack.ss_flags);
- err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs,
- set->sig[0], save_sp);
- err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate);
- if (sizeof(*set) == 16) {
- __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
- __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
- }
- else
- err |= __copy_to_user(&frame->uc.uc_sigmask, set,
- sizeof(*set));
-
- /*
- * Set up to return from userspace. If provided, use a stub
- * already in userspace.
- */
- /* x86-64 should always use SA_RESTORER. */
- if (ka->sa.sa_flags & SA_RESTORER)
- err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
- else
- /* could use a vstub here */
- goto restore_sp;
-
- if (err)
- goto restore_sp;
-
- /* Set up registers for signal handler */
- {
- struct exec_domain *ed = current_thread_info()->exec_domain;
- if (unlikely(ed && ed->signal_invmap && sig < 32))
- sig = ed->signal_invmap[sig];
- }
-
- PT_REGS_RDI(regs) = sig;
- /* In case the signal handler was declared without prototypes */
- PT_REGS_RAX(regs) = 0;
-
- /*
- * This also works for non SA_SIGINFO handlers because they expect the
- * next argument after the signal number on the stack.
- */
- PT_REGS_RSI(regs) = (unsigned long) &frame->info;
- PT_REGS_RDX(regs) = (unsigned long) &frame->uc;
- PT_REGS_RIP(regs) = (unsigned long) ka->sa.sa_handler;
- out:
- return err;
-
-restore_sp:
- PT_REGS_RSP(regs) = save_sp;
- return err;
-}
-
-long sys_rt_sigreturn(struct pt_regs *regs)
-{
- unsigned long sp = PT_REGS_SP(&current->thread.regs);
- struct rt_sigframe __user *frame =
- (struct rt_sigframe __user *)(sp - 8);
- struct ucontext __user *uc = &frame->uc;
- sigset_t set;
-
- if (copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
- goto segfault;
-
- sigdelsetmask(&set, ~_BLOCKABLE);
-
- spin_lock_irq(&current->sighand->siglock);
- current->blocked = set;
- recalc_sigpending();
- spin_unlock_irq(&current->sighand->siglock);
-
- if (copy_sc_from_user(&current->thread.regs, &uc->uc_mcontext,
- &frame->fpstate))
- goto segfault;
-
- /* Avoid ERESTART handling */
- PT_REGS_SYSCALL_NR(&current->thread.regs) = -1;
- return PT_REGS_SYSCALL_RET(&current->thread.regs);
-
- segfault:
- force_sig(SIGSEGV, current);
- return 0;
-}
diff --git a/arch/um/Makefile-i386 b/arch/x86/Makefile.um
index 302cbe504543..36ddec6a41c9 100644
--- a/arch/um/Makefile-i386
+++ b/arch/x86/Makefile.um
@@ -1,14 +1,11 @@
-core-y += arch/um/sys-i386/ arch/x86/crypto/
-
-TOP_ADDR := $(CONFIG_TOP_ADDR)
+core-y += arch/x86/crypto/
+ifeq ($(CONFIG_X86_32),y)
START := 0x8048000
LDFLAGS += -m elf_i386
-ELF_ARCH := $(SUBARCH)
-ELF_FORMAT := elf32-$(SUBARCH)
-OBJCOPYFLAGS := -O binary -R .note -R .comment -S
-HEADER_ARCH := x86
+ELF_ARCH := i386
+ELF_FORMAT := elf32-i386
CHECKFLAGS += -D__i386__
ifeq ("$(origin SUBARCH)", "command line")
@@ -16,9 +13,8 @@ ifneq ("$(shell uname -m | sed -e s/i.86/i386/)", "$(SUBARCH)")
KBUILD_CFLAGS += $(call cc-option,-m32)
KBUILD_AFLAGS += $(call cc-option,-m32)
LINK-y += $(call cc-option,-m32)
-UML_OBJCOPYFLAGS += -F $(ELF_FORMAT)
-export LDFLAGS HOSTCFLAGS HOSTLDFLAGS UML_OBJCOPYFLAGS
+export LDFLAGS
endif
endif
@@ -40,3 +36,26 @@ KBUILD_CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then \
else echo $(call cc-option,-funit-at-a-time); fi ;)
KBUILD_CFLAGS += $(cflags-y)
+
+else
+
+START := 0x60000000
+
+KBUILD_CFLAGS += -fno-builtin -m64
+
+CHECKFLAGS += -m64 -D__x86_64__
+KBUILD_AFLAGS += -m64
+LDFLAGS += -m elf_x86_64
+KBUILD_CPPFLAGS += -m64
+
+ELF_ARCH := i386:x86-64
+ELF_FORMAT := elf64-x86-64
+
+# Not on all 64-bit distros /lib is a symlink to /lib64. PLD is an example.
+
+LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib64
+LINK-y += -m64
+
+# Do unit-at-a-time unconditionally on x86_64, following the host
+KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
+endif
diff --git a/arch/um/Kconfig.x86 b/arch/x86/um/Kconfig
index 21bebe63df66..21bebe63df66 100644
--- a/arch/um/Kconfig.x86
+++ b/arch/x86/um/Kconfig
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
new file mode 100644
index 000000000000..8fb58400e415
--- /dev/null
+++ b/arch/x86/um/Makefile
@@ -0,0 +1,45 @@
+#
+# Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+#
+
+ifeq ($(CONFIG_X86_32),y)
+ BITS := 32
+else
+ BITS := 64
+endif
+
+obj-y = bug.o bugs_$(BITS).o delay.o fault.o ksyms.o ldt.o \
+ ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \
+ stub_$(BITS).o stub_segv.o syscalls_$(BITS).o \
+ sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \
+ mem_$(BITS).o subarch.o os-$(OS)/
+
+ifeq ($(CONFIG_X86_32),y)
+
+obj-y += checksum_32.o
+obj-$(CONFIG_BINFMT_ELF) += elfcore.o
+
+subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
+subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o
+subarch-$(CONFIG_HIGHMEM) += ../mm/highmem_32.o
+
+else
+
+obj-y += vdso/
+
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../lib/thunk_64.o \
+ ../lib/rwsem.o
+
+endif
+
+subarch-$(CONFIG_MODULES) += ../kernel/module.o
+
+USER_OBJS := bugs_$(BITS).o ptrace_user.o fault.o
+
+extra-y += user-offsets.s
+$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS)
+
+UNPROFILE_OBJS := stub_segv.o
+CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING)
+
+include arch/um/scripts/Makefile.rules
diff --git a/arch/um/include/asm/apic.h b/arch/x86/um/asm/apic.h
index 876dee84ab11..876dee84ab11 100644
--- a/arch/um/include/asm/apic.h
+++ b/arch/x86/um/asm/apic.h
diff --git a/arch/um/include/asm/arch_hweight.h b/arch/x86/um/asm/arch_hweight.h
index c656cf443f4a..c656cf443f4a 100644
--- a/arch/um/include/asm/arch_hweight.h
+++ b/arch/x86/um/asm/arch_hweight.h
diff --git a/arch/um/sys-i386/asm/archparam.h b/arch/x86/um/asm/archparam.h
index 2a18a884ca1b..c17cf68dda0f 100644
--- a/arch/um/sys-i386/asm/archparam.h
+++ b/arch/x86/um/asm/archparam.h
@@ -1,10 +1,13 @@
/*
* Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com)
+ * Copyright 2003 PathScale, Inc.
* Licensed under the GPL
*/
-#ifndef __UM_ARCHPARAM_I386_H
-#define __UM_ARCHPARAM_I386_H
+#ifndef __UM_ARCHPARAM_H
+#define __UM_ARCHPARAM_H
+
+#ifdef CONFIG_X86_32
#ifdef CONFIG_X86_PAE
#define LAST_PKMAP 512
@@ -14,3 +17,4 @@
#endif
+#endif
diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h
new file mode 100644
index 000000000000..b6efe2381b5d
--- /dev/null
+++ b/arch/x86/um/asm/checksum.h
@@ -0,0 +1,10 @@
+#ifndef __UM_CHECKSUM_H
+#define __UM_CHECKSUM_H
+
+#ifdef CONFIG_X86_32
+# include "checksum_32.h"
+#else
+# include "checksum_64.h"
+#endif
+
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/checksum.h b/arch/x86/um/asm/checksum_32.h
index ed47445f3905..caab74252e27 100644
--- a/arch/um/sys-i386/shared/sysdep/checksum.h
+++ b/arch/x86/um/asm/checksum_32.h
@@ -1,4 +1,4 @@
-/*
+/*
* Licensed under the GPL
*/
diff --git a/arch/um/sys-x86_64/shared/sysdep/checksum.h b/arch/x86/um/asm/checksum_64.h
index a5be9031ea85..a5be9031ea85 100644
--- a/arch/um/sys-x86_64/shared/sysdep/checksum.h
+++ b/arch/x86/um/asm/checksum_64.h
diff --git a/arch/um/include/asm/desc.h b/arch/x86/um/asm/desc.h
index 4ec34a51b62c..4ec34a51b62c 100644
--- a/arch/um/include/asm/desc.h
+++ b/arch/x86/um/asm/desc.h
diff --git a/arch/um/sys-x86_64/asm/elf.h b/arch/x86/um/asm/elf.h
index 11a2bfb38859..f3b0633b69a1 100644
--- a/arch/um/sys-x86_64/asm/elf.h
+++ b/arch/x86/um/asm/elf.h
@@ -1,15 +1,103 @@
/*
- * Copyright 2003 PathScale, Inc.
- * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- *
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*/
-#ifndef __UM_ELF_X86_64_H
-#define __UM_ELF_X86_64_H
+#ifndef __UM_ELF_X86_H
+#define __UM_ELF_X86_H
#include <asm/user.h>
#include "skas.h"
+#ifdef CONFIG_X86_32
+
+#define R_386_NONE 0
+#define R_386_32 1
+#define R_386_PC32 2
+#define R_386_GOT32 3
+#define R_386_PLT32 4
+#define R_386_COPY 5
+#define R_386_GLOB_DAT 6
+#define R_386_JMP_SLOT 7
+#define R_386_RELATIVE 8
+#define R_386_GOTOFF 9
+#define R_386_GOTPC 10
+#define R_386_NUM 11
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) \
+ (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
+
+#define ELF_CLASS ELFCLASS32
+#define ELF_DATA ELFDATA2LSB
+#define ELF_ARCH EM_386
+
+#define ELF_PLAT_INIT(regs, load_addr) do { \
+ PT_REGS_EBX(regs) = 0; \
+ PT_REGS_ECX(regs) = 0; \
+ PT_REGS_EDX(regs) = 0; \
+ PT_REGS_ESI(regs) = 0; \
+ PT_REGS_EDI(regs) = 0; \
+ PT_REGS_EBP(regs) = 0; \
+ PT_REGS_EAX(regs) = 0; \
+} while (0)
+
+/* Shamelessly stolen from include/asm-i386/elf.h */
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs) do { \
+ pr_reg[0] = PT_REGS_EBX(regs); \
+ pr_reg[1] = PT_REGS_ECX(regs); \
+ pr_reg[2] = PT_REGS_EDX(regs); \
+ pr_reg[3] = PT_REGS_ESI(regs); \
+ pr_reg[4] = PT_REGS_EDI(regs); \
+ pr_reg[5] = PT_REGS_EBP(regs); \
+ pr_reg[6] = PT_REGS_EAX(regs); \
+ pr_reg[7] = PT_REGS_DS(regs); \
+ pr_reg[8] = PT_REGS_ES(regs); \
+ /* fake once used fs and gs selectors? */ \
+ pr_reg[9] = PT_REGS_DS(regs); \
+ pr_reg[10] = PT_REGS_DS(regs); \
+ pr_reg[11] = PT_REGS_SYSCALL_NR(regs); \
+ pr_reg[12] = PT_REGS_IP(regs); \
+ pr_reg[13] = PT_REGS_CS(regs); \
+ pr_reg[14] = PT_REGS_EFLAGS(regs); \
+ pr_reg[15] = PT_REGS_SP(regs); \
+ pr_reg[16] = PT_REGS_SS(regs); \
+} while (0);
+
+extern char * elf_aux_platform;
+#define ELF_PLATFORM (elf_aux_platform)
+
+extern unsigned long vsyscall_ehdr;
+extern unsigned long vsyscall_end;
+extern unsigned long __kernel_vsyscall;
+
+/*
+ * This is the range that is readable by user mode, and things
+ * acting like user mode such as get_user_pages.
+ */
+#define FIXADDR_USER_START vsyscall_ehdr
+#define FIXADDR_USER_END vsyscall_end
+
+
+/*
+ * Architecture-neutral AT_ values in 0-17, leave some room
+ * for more of them, start the x86-specific ones at 32.
+ */
+#define AT_SYSINFO 32
+#define AT_SYSINFO_EHDR 33
+
+#define ARCH_DLINFO \
+do { \
+ if ( vsyscall_ehdr ) { \
+ NEW_AUX_ENT(AT_SYSINFO, __kernel_vsyscall); \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, vsyscall_ehdr); \
+ } \
+} while (0)
+
+#else
+
/* x86-64 relocation types, taken from asm-x86_64/elf.h */
#define R_X86_64_NONE 0 /* No reloc */
#define R_X86_64_64 1 /* Direct 64 bit */
@@ -31,13 +119,6 @@
#define R_X86_64_NUM 16
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_i387_struct elf_fpregset_t;
-
/*
* This is used to ensure we don't load something for the wrong architecture.
*/
@@ -95,6 +176,30 @@ typedef struct user_i387_struct elf_fpregset_t;
(pr_reg)[25] = 0; \
(pr_reg)[26] = 0;
+#define ELF_PLATFORM "x86_64"
+
+/* No user-accessible fixmap addresses, i.e. vsyscall */
+#define FIXADDR_USER_START 0
+#define FIXADDR_USER_END 0
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp);
+
+extern unsigned long um_vdso_addr;
+#define AT_SYSINFO_EHDR 33
+#define ARCH_DLINFO NEW_AUX_ENT(AT_SYSINFO_EHDR, um_vdso_addr)
+
+#endif
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_i387_struct elf_fpregset_t;
+
#define task_pt_regs(t) (&(t)->thread.regs)
struct task_struct;
@@ -103,11 +208,6 @@ extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
-#ifdef TIF_IA32 /* XXX */
-#error XXX, indeed
- clear_thread_flag(TIF_IA32);
-#endif
-
#define ELF_EXEC_PAGESIZE 4096
#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
@@ -115,18 +215,7 @@ extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
extern long elf_aux_hwcap;
#define ELF_HWCAP (elf_aux_hwcap)
-#define ELF_PLATFORM "x86_64"
-
#define SET_PERSONALITY(ex) do ; while(0)
-
#define __HAVE_ARCH_GATE_AREA 1
-#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
-struct linux_binprm;
-extern int arch_setup_additional_pages(struct linux_binprm *bprm,
- int uses_interp);
-
-extern unsigned long um_vdso_addr;
-#define AT_SYSINFO_EHDR 33
-#define ARCH_DLINFO NEW_AUX_ENT(AT_SYSINFO_EHDR, um_vdso_addr)
#endif
diff --git a/arch/um/include/asm/irq_vectors.h b/arch/x86/um/asm/irq_vectors.h
index 272a81e0ce14..272a81e0ce14 100644
--- a/arch/um/include/asm/irq_vectors.h
+++ b/arch/x86/um/asm/irq_vectors.h
diff --git a/arch/x86/um/asm/mm_context.h b/arch/x86/um/asm/mm_context.h
new file mode 100644
index 000000000000..4a73d63e4760
--- /dev/null
+++ b/arch/x86/um/asm/mm_context.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2004 Fujitsu Siemens Computers GmbH
+ * Licensed under the GPL
+ *
+ * Author: Bodo Stroesser <bstroesser@fujitsu-siemens.com>
+ */
+
+#ifndef __ASM_LDT_H
+#define __ASM_LDT_H
+
+#include <linux/mutex.h>
+#include <asm/ldt.h>
+
+extern void ldt_host_info(void);
+
+#define LDT_PAGES_MAX \
+ ((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE)
+#define LDT_ENTRIES_PER_PAGE \
+ (PAGE_SIZE/LDT_ENTRY_SIZE)
+#define LDT_DIRECT_ENTRIES \
+ ((LDT_PAGES_MAX*sizeof(void *))/LDT_ENTRY_SIZE)
+
+struct ldt_entry {
+ __u32 a;
+ __u32 b;
+};
+
+typedef struct uml_ldt {
+ int entry_count;
+ struct mutex lock;
+ union {
+ struct ldt_entry * pages[LDT_PAGES_MAX];
+ struct ldt_entry entries[LDT_DIRECT_ENTRIES];
+ } u;
+} uml_ldt_t;
+
+#define LDT_entry_a(info) \
+ ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
+
+#define LDT_entry_b(info) \
+ (((info)->base_addr & 0xff000000) | \
+ (((info)->base_addr & 0x00ff0000) >> 16) | \
+ ((info)->limit & 0xf0000) | \
+ (((info)->read_exec_only ^ 1) << 9) | \
+ ((info)->contents << 10) | \
+ (((info)->seg_not_present ^ 1) << 15) | \
+ ((info)->seg_32bit << 22) | \
+ ((info)->limit_in_pages << 23) | \
+ ((info)->useable << 20) | \
+ 0x7000)
+
+#define _LDT_empty(info) (\
+ (info)->base_addr == 0 && \
+ (info)->limit == 0 && \
+ (info)->contents == 0 && \
+ (info)->read_exec_only == 1 && \
+ (info)->seg_32bit == 0 && \
+ (info)->limit_in_pages == 0 && \
+ (info)->seg_not_present == 1 && \
+ (info)->useable == 0 )
+
+#ifdef CONFIG_X86_64
+#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
+#else
+#define LDT_empty(info) (_LDT_empty(info))
+#endif
+
+struct uml_arch_mm_context {
+ uml_ldt_t ldt;
+};
+
+#endif
diff --git a/arch/x86/um/asm/module.h b/arch/x86/um/asm/module.h
new file mode 100644
index 000000000000..61af80e932eb
--- /dev/null
+++ b/arch/x86/um/asm/module.h
@@ -0,0 +1,23 @@
+#ifndef __UM_MODULE_H
+#define __UM_MODULE_H
+
+/* UML is simple */
+struct mod_arch_specific
+{
+};
+
+#ifdef CONFIG_X86_32
+
+#define Elf_Shdr Elf32_Shdr
+#define Elf_Sym Elf32_Sym
+#define Elf_Ehdr Elf32_Ehdr
+
+#else
+
+#define Elf_Shdr Elf64_Shdr
+#define Elf_Sym Elf64_Sym
+#define Elf_Ehdr Elf64_Ehdr
+
+#endif
+
+#endif
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
new file mode 100644
index 000000000000..118c143a9cb4
--- /dev/null
+++ b/arch/x86/um/asm/processor.h
@@ -0,0 +1,22 @@
+#ifndef __UM_PROCESSOR_H
+#define __UM_PROCESSOR_H
+
+/* include faultinfo structure */
+#include <sysdep/faultinfo.h>
+
+#ifdef CONFIG_X86_32
+# include "processor_32.h"
+#else
+# include "processor_64.h"
+#endif
+
+#define KSTK_EIP(tsk) KSTK_REG(tsk, HOST_IP)
+#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_IP)
+#define KSTK_EBP(tsk) KSTK_REG(tsk, HOST_BP)
+
+#define ARCH_IS_STACKGROW(address) \
+ (address + 65536 + 32 * sizeof(unsigned long) >= UPT_SP(&current->thread.regs.regs))
+
+#include <asm/processor-generic.h>
+
+#endif
diff --git a/arch/um/sys-i386/asm/processor.h b/arch/x86/um/asm/processor_32.h
index 82a9061ab5be..018f732704dd 100644
--- a/arch/um/sys-i386/asm/processor.h
+++ b/arch/x86/um/asm/processor_32.h
@@ -6,15 +6,12 @@
#ifndef __UM_PROCESSOR_I386_H
#define __UM_PROCESSOR_I386_H
-#include "linux/string.h"
-#include <sysdep/host_ldt.h>
-#include "asm/segment.h"
+#include <linux/string.h>
+#include <asm/segment.h>
+#include <asm/ldt.h>
extern int host_has_cmov;
-/* include faultinfo structure */
-#include "sysdep/faultinfo.h"
-
struct uml_tls_struct {
struct user_desc tls;
unsigned flushed:1;
@@ -66,13 +63,4 @@ static inline void rep_nop(void)
#define current_text_addr() \
({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; })
-#define ARCH_IS_STACKGROW(address) \
- (address + 32 >= UPT_SP(&current->thread.regs.regs))
-
-#define KSTK_EIP(tsk) KSTK_REG(tsk, EIP)
-#define KSTK_ESP(tsk) KSTK_REG(tsk, UESP)
-#define KSTK_EBP(tsk) KSTK_REG(tsk, EBP)
-
-#include "asm/processor-generic.h"
-
#endif
diff --git a/arch/um/sys-x86_64/asm/processor.h b/arch/x86/um/asm/processor_64.h
index 875a26a62614..61de92d916c3 100644
--- a/arch/um/sys-x86_64/asm/processor.h
+++ b/arch/x86/um/asm/processor_64.h
@@ -7,9 +7,6 @@
#ifndef __UM_PROCESSOR_X86_64_H
#define __UM_PROCESSOR_X86_64_H
-/* include faultinfo structure */
-#include "sysdep/faultinfo.h"
-
struct arch_thread {
unsigned long debugregs[8];
int debugregs_seq;
@@ -45,12 +42,4 @@ static inline void arch_copy_thread(struct arch_thread *from,
#define current_text_addr() \
({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; })
-#define ARCH_IS_STACKGROW(address) \
- (address + 128 >= UPT_SP(&current->thread.regs.regs))
-
-#define KSTK_EIP(tsk) KSTK_REG(tsk, RIP)
-#define KSTK_ESP(tsk) KSTK_REG(tsk, RSP)
-
-#include "asm/processor-generic.h"
-
#endif
diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h
new file mode 100644
index 000000000000..c8aca8c501b0
--- /dev/null
+++ b/arch/x86/um/asm/ptrace.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "ptrace_32.h"
+#else
+# include "ptrace_64.h"
+#endif
diff --git a/arch/um/sys-i386/asm/ptrace.h b/arch/x86/um/asm/ptrace_32.h
index 5d2a59112537..5d2a59112537 100644
--- a/arch/um/sys-i386/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace_32.h
diff --git a/arch/um/sys-x86_64/asm/ptrace.h b/arch/x86/um/asm/ptrace_64.h
index 83d8c473b905..706a0d80545c 100644
--- a/arch/um/sys-x86_64/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace_64.h
@@ -40,7 +40,7 @@
#define PT_REGS_ORIG_RAX(r) UPT_ORIG_RAX(&(r)->regs)
#define PT_REGS_RIP(r) UPT_IP(&(r)->regs)
-#define PT_REGS_RSP(r) UPT_SP(&(r)->regs)
+#define PT_REGS_SP(r) UPT_SP(&(r)->regs)
#define PT_REGS_EFLAGS(r) UPT_EFLAGS(&(r)->regs)
diff --git a/arch/um/include/asm/required-features.h b/arch/x86/um/asm/required-features.h
index dfb967b2d2f3..dfb967b2d2f3 100644
--- a/arch/um/include/asm/required-features.h
+++ b/arch/x86/um/asm/required-features.h
diff --git a/arch/um/include/asm/segment.h b/arch/x86/um/asm/segment.h
index 45183fcd10b6..45183fcd10b6 100644
--- a/arch/um/include/asm/segment.h
+++ b/arch/x86/um/asm/segment.h
diff --git a/arch/um/sys-i386/shared/sysdep/system.h b/arch/x86/um/asm/system.h
index d1b93c436200..a459fd9b7598 100644
--- a/arch/um/sys-i386/shared/sysdep/system.h
+++ b/arch/x86/um/asm/system.h
@@ -129,4 +129,7 @@ static inline void rdtsc_barrier(void)
alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
}
+extern void *_switch_to(void *prev, void *next, void *last);
+#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
+
#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/vm-flags.h b/arch/x86/um/asm/vm-flags.h
index 3978e55132d2..7c297e9e2413 100644
--- a/arch/um/sys-x86_64/shared/sysdep/vm-flags.h
+++ b/arch/x86/um/asm/vm-flags.h
@@ -4,8 +4,17 @@
* Licensed under the GPL
*/
-#ifndef __VM_FLAGS_X86_64_H
-#define __VM_FLAGS_X86_64_H
+#ifndef __VM_FLAGS_X86_H
+#define __VM_FLAGS_X86_H
+
+#ifdef CONFIG_X86_32
+
+#define VM_DATA_DEFAULT_FLAGS \
+ (VM_READ | VM_WRITE | \
+ ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#else
#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
@@ -13,3 +22,4 @@
VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
#endif
+#endif
diff --git a/arch/um/sys-x86_64/bug.c b/arch/x86/um/bug.c
index e8034e363d83..e8034e363d83 100644
--- a/arch/um/sys-x86_64/bug.c
+++ b/arch/x86/um/bug.c
diff --git a/arch/um/sys-i386/bugs.c b/arch/x86/um/bugs_32.c
index 2c6d0d731c12..a1fba5fb9dbe 100644
--- a/arch/um/sys-i386/bugs.c
+++ b/arch/x86/um/bugs_32.c
@@ -4,17 +4,17 @@
*/
#include <signal.h>
-#include "kern_constants.h"
#include "kern_util.h"
#include "longjmp.h"
-#include "task.h"
-#include "user.h"
#include "sysdep/ptrace.h"
+#include <generated/asm-offsets.h>
/* Set during early boot */
static int host_has_cmov = 1;
static jmp_buf cmov_test_return;
+#define TASK_PID(task) *((int *) &(((char *) (task))[HOST_TASK_PID]))
+
static void cmov_sigill_test_handler(int sig)
{
host_has_cmov = 0;
diff --git a/arch/um/sys-x86_64/bugs.c b/arch/x86/um/bugs_64.c
index 44e02ba2a265..44e02ba2a265 100644
--- a/arch/um/sys-x86_64/bugs.c
+++ b/arch/x86/um/bugs_64.c
diff --git a/arch/um/sys-i386/checksum.S b/arch/x86/um/checksum_32.S
index f058d2f82e18..f058d2f82e18 100644
--- a/arch/um/sys-i386/checksum.S
+++ b/arch/x86/um/checksum_32.S
diff --git a/arch/um/sys-i386/delay.c b/arch/x86/um/delay.c
index f3fe1a688f7e..f3fe1a688f7e 100644
--- a/arch/um/sys-i386/delay.c
+++ b/arch/x86/um/delay.c
diff --git a/arch/um/sys-i386/elfcore.c b/arch/x86/um/elfcore.c
index 6bb49b687c97..6bb49b687c97 100644
--- a/arch/um/sys-i386/elfcore.c
+++ b/arch/x86/um/elfcore.c
diff --git a/arch/um/sys-i386/fault.c b/arch/x86/um/fault.c
index d670f68532f4..d670f68532f4 100644
--- a/arch/um/sys-i386/fault.c
+++ b/arch/x86/um/fault.c
diff --git a/arch/um/sys-x86_64/ksyms.c b/arch/x86/um/ksyms.c
index 1db2fce00948..2e8f43ec6214 100644
--- a/arch/um/sys-x86_64/ksyms.c
+++ b/arch/x86/um/ksyms.c
@@ -2,10 +2,12 @@
#include <asm/string.h>
#include <asm/checksum.h>
+#ifndef CONFIG_X86_32
/*XXX: we need them because they would be exported by x86_64 */
#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
EXPORT_SYMBOL(memcpy);
#else
EXPORT_SYMBOL(__memcpy);
#endif
+#endif
EXPORT_SYMBOL(csum_partial);
diff --git a/arch/um/sys-i386/ldt.c b/arch/x86/um/ldt.c
index 3f2bf208d884..26b0e39d2ce9 100644
--- a/arch/um/sys-i386/ldt.c
+++ b/arch/x86/um/ldt.c
@@ -137,7 +137,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount)
{
int i, err = 0;
unsigned long size;
- uml_ldt_t * ldt = &current->mm->context.ldt;
+ uml_ldt_t *ldt = &current->mm->context.arch.ldt;
if (!ldt->entry_count)
goto out;
@@ -205,7 +205,7 @@ static int read_default_ldt(void __user * ptr, unsigned long bytecount)
static int write_ldt(void __user * ptr, unsigned long bytecount, int func)
{
- uml_ldt_t * ldt = &current->mm->context.ldt;
+ uml_ldt_t *ldt = &current->mm->context.arch.ldt;
struct mm_id * mm_idp = &current->mm->context.id;
int i, err;
struct user_desc ldt_info;
@@ -397,7 +397,7 @@ long init_new_ldt(struct mm_context *new_mm, struct mm_context *from_mm)
if (!ptrace_ldt)
- mutex_init(&new_mm->ldt.lock);
+ mutex_init(&new_mm->arch.ldt.lock);
if (!from_mm) {
memset(&desc, 0, sizeof(desc));
@@ -429,7 +429,7 @@ long init_new_ldt(struct mm_context *new_mm, struct mm_context *from_mm)
break;
}
}
- new_mm->ldt.entry_count = 0;
+ new_mm->arch.ldt.entry_count = 0;
goto out;
}
@@ -457,26 +457,26 @@ long init_new_ldt(struct mm_context *new_mm, struct mm_context *from_mm)
* i.e., we have to use the stub for modify_ldt, which
* can't handle the big read buffer of up to 64kB.
*/
- mutex_lock(&from_mm->ldt.lock);
- if (from_mm->ldt.entry_count <= LDT_DIRECT_ENTRIES)
- memcpy(new_mm->ldt.u.entries, from_mm->ldt.u.entries,
- sizeof(new_mm->ldt.u.entries));
+ mutex_lock(&from_mm->arch.ldt.lock);
+ if (from_mm->arch.ldt.entry_count <= LDT_DIRECT_ENTRIES)
+ memcpy(new_mm->arch.ldt.u.entries, from_mm->arch.ldt.u.entries,
+ sizeof(new_mm->arch.ldt.u.entries));
else {
- i = from_mm->ldt.entry_count / LDT_ENTRIES_PER_PAGE;
+ i = from_mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE;
while (i-->0) {
page = __get_free_page(GFP_KERNEL|__GFP_ZERO);
if (!page) {
err = -ENOMEM;
break;
}
- new_mm->ldt.u.pages[i] =
+ new_mm->arch.ldt.u.pages[i] =
(struct ldt_entry *) page;
- memcpy(new_mm->ldt.u.pages[i],
- from_mm->ldt.u.pages[i], PAGE_SIZE);
+ memcpy(new_mm->arch.ldt.u.pages[i],
+ from_mm->arch.ldt.u.pages[i], PAGE_SIZE);
}
}
- new_mm->ldt.entry_count = from_mm->ldt.entry_count;
- mutex_unlock(&from_mm->ldt.lock);
+ new_mm->arch.ldt.entry_count = from_mm->arch.ldt.entry_count;
+ mutex_unlock(&from_mm->arch.ldt.lock);
}
out:
@@ -488,12 +488,12 @@ void free_ldt(struct mm_context *mm)
{
int i;
- if (!ptrace_ldt && mm->ldt.entry_count > LDT_DIRECT_ENTRIES) {
- i = mm->ldt.entry_count / LDT_ENTRIES_PER_PAGE;
+ if (!ptrace_ldt && mm->arch.ldt.entry_count > LDT_DIRECT_ENTRIES) {
+ i = mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE;
while (i-- > 0)
- free_page((long) mm->ldt.u.pages[i]);
+ free_page((long) mm->arch.ldt.u.pages[i]);
}
- mm->ldt.entry_count = 0;
+ mm->arch.ldt.entry_count = 0;
}
int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount)
diff --git a/arch/um/sys-i386/mem.c b/arch/x86/um/mem_32.c
index 639900a6fde9..639900a6fde9 100644
--- a/arch/um/sys-i386/mem.c
+++ b/arch/x86/um/mem_32.c
diff --git a/arch/um/sys-x86_64/mem.c b/arch/x86/um/mem_64.c
index 546518727a73..546518727a73 100644
--- a/arch/um/sys-x86_64/mem.c
+++ b/arch/x86/um/mem_64.c
diff --git a/arch/um/os-Linux/sys-i386/Makefile b/arch/x86/um/os-Linux/Makefile
index b4bc6ac4f30b..253bfb8cb702 100644
--- a/arch/um/os-Linux/sys-i386/Makefile
+++ b/arch/x86/um/os-Linux/Makefile
@@ -3,7 +3,10 @@
# Licensed under the GPL
#
-obj-y = registers.o signal.o task_size.o tls.o
+obj-y = registers.o task_size.o mcontext.o
+
+obj-$(CONFIG_X86_32) += tls.o
+obj-$(CONFIG_64BIT) += prctl.o
USER_OBJS := $(obj-y)
diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c
new file mode 100644
index 000000000000..1d33d72c6284
--- /dev/null
+++ b/arch/x86/um/os-Linux/mcontext.c
@@ -0,0 +1,31 @@
+#include <sys/ucontext.h>
+#define __FRAME_OFFSETS
+#include <asm/ptrace.h>
+#include <sysdep/ptrace.h>
+
+void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
+{
+#ifdef __i386__
+#define COPY2(X,Y) regs->gp[X] = mc->gregs[REG_##Y]
+#define COPY(X) regs->gp[X] = mc->gregs[REG_##X]
+#define COPY_SEG(X) regs->gp[X] = mc->gregs[REG_##X] & 0xffff;
+#define COPY_SEG_CPL3(X) regs->gp[X] = (mc->gregs[REG_##X] & 0xffff) | 3;
+ COPY_SEG(GS); COPY_SEG(FS); COPY_SEG(ES); COPY_SEG(DS);
+ COPY(EDI); COPY(ESI); COPY(EBP);
+ COPY2(UESP, ESP); /* sic */
+ COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX);
+ COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS);
+#else
+#define COPY2(X,Y) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##Y]
+#define COPY(X) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##X]
+ COPY(R8); COPY(R9); COPY(R10); COPY(R11);
+ COPY(R12); COPY(R13); COPY(R14); COPY(R15);
+ COPY(RDI); COPY(RSI); COPY(RBP); COPY(RBX);
+ COPY(RDX); COPY(RAX); COPY(RCX); COPY(RSP);
+ COPY(RIP);
+ COPY2(EFLAGS, EFL);
+ COPY2(CS, CSGSFS);
+ regs->gp[CS / sizeof(unsigned long)] &= 0xffff;
+ regs->gp[CS / sizeof(unsigned long)] |= 3;
+#endif
+}
diff --git a/arch/um/os-Linux/sys-x86_64/prctl.c b/arch/x86/um/os-Linux/prctl.c
index 9d34eddb517f..9d34eddb517f 100644
--- a/arch/um/os-Linux/sys-x86_64/prctl.c
+++ b/arch/x86/um/os-Linux/prctl.c
diff --git a/arch/um/os-Linux/sys-i386/registers.c b/arch/x86/um/os-Linux/registers.c
index 229f7a53d8da..0cdbb86b012b 100644
--- a/arch/um/os-Linux/sys-i386/registers.c
+++ b/arch/x86/um/os-Linux/registers.c
@@ -6,10 +6,10 @@
#include <errno.h>
#include <sys/ptrace.h>
+#ifdef __i386__
#include <sys/user.h>
-#include "kern_constants.h"
+#endif
#include "longjmp.h"
-#include "user.h"
#include "sysdep/ptrace_user.h"
int save_fp_registers(int pid, unsigned long *fp_regs)
@@ -26,6 +26,8 @@ int restore_fp_registers(int pid, unsigned long *fp_regs)
return 0;
}
+#ifdef __i386__
+int have_fpx_regs = 1;
int save_fpx_registers(int pid, unsigned long *fp_regs)
{
if (ptrace(PTRACE_GETFPXREGS, pid, 0, fp_regs) < 0)
@@ -40,24 +42,6 @@ int restore_fpx_registers(int pid, unsigned long *fp_regs)
return 0;
}
-unsigned long get_thread_reg(int reg, jmp_buf *buf)
-{
- switch (reg) {
- case EIP:
- return buf[0]->__eip;
- case UESP:
- return buf[0]->__esp;
- case EBP:
- return buf[0]->__ebp;
- default:
- printk(UM_KERN_ERR "get_thread_regs - unknown register %d\n",
- reg);
- return 0;
- }
-}
-
-int have_fpx_regs = 1;
-
int get_fp_registers(int pid, unsigned long *regs)
{
if (have_fpx_regs)
@@ -89,3 +73,41 @@ void arch_init_registers(int pid)
have_fpx_regs = 0;
}
+#else
+
+int get_fp_registers(int pid, unsigned long *regs)
+{
+ return save_fp_registers(pid, regs);
+}
+
+int put_fp_registers(int pid, unsigned long *regs)
+{
+ return restore_fp_registers(pid, regs);
+}
+
+#endif
+
+unsigned long get_thread_reg(int reg, jmp_buf *buf)
+{
+ switch (reg) {
+#ifdef __i386__
+ case HOST_IP:
+ return buf[0]->__eip;
+ case HOST_SP:
+ return buf[0]->__esp;
+ case HOST_BP:
+ return buf[0]->__ebp;
+#else
+ case HOST_IP:
+ return buf[0]->__rip;
+ case HOST_SP:
+ return buf[0]->__rsp;
+ case HOST_BP:
+ return buf[0]->__rbp;
+#endif
+ default:
+ printk(UM_KERN_ERR "get_thread_regs - unknown register %d\n",
+ reg);
+ return 0;
+ }
+}
diff --git a/arch/um/os-Linux/sys-i386/task_size.c b/arch/x86/um/os-Linux/task_size.c
index be04c1e183bf..efb16c5c9bcf 100644
--- a/arch/um/os-Linux/sys-i386/task_size.c
+++ b/arch/x86/um/os-Linux/task_size.c
@@ -3,7 +3,8 @@
#include <signal.h>
#include <sys/mman.h>
#include "longjmp.h"
-#include "kern_constants.h"
+
+#ifdef __i386__
static jmp_buf buf;
@@ -137,3 +138,13 @@ out:
return top;
}
+
+#else
+
+unsigned long os_get_top_address(void)
+{
+ /* The old value of CONFIG_TOP_ADDR */
+ return 0x7fc0000000;
+}
+
+#endif
diff --git a/arch/um/os-Linux/sys-i386/tls.c b/arch/x86/um/os-Linux/tls.c
index 32ed41ec1a3d..82276b6071af 100644
--- a/arch/um/os-Linux/sys-i386/tls.c
+++ b/arch/x86/um/os-Linux/tls.c
@@ -1,16 +1,25 @@
#include <errno.h>
#include <linux/unistd.h>
+#include <sys/ptrace.h>
#include <sys/syscall.h>
#include <unistd.h>
#include "sysdep/tls.h"
-#include "user.h"
+
+#ifndef PTRACE_GET_THREAD_AREA
+#define PTRACE_GET_THREAD_AREA 25
+#endif
+
+#ifndef PTRACE_SET_THREAD_AREA
+#define PTRACE_SET_THREAD_AREA 26
+#endif
/* Checks whether host supports TLS, and sets *tls_min according to the value
* valid on the host.
* i386 host have it == 6; x86_64 host have it == 12, for i386 emulation. */
-void check_host_supports_tls(int *supports_tls, int *tls_min) {
+void check_host_supports_tls(int *supports_tls, int *tls_min)
+{
/* Values for x86 and x86_64.*/
int val[] = {GDT_ENTRY_TLS_MIN_I386, GDT_ENTRY_TLS_MIN_X86_64};
int i;
@@ -34,3 +43,25 @@ void check_host_supports_tls(int *supports_tls, int *tls_min) {
*supports_tls = 0;
}
+
+int os_set_thread_area(user_desc_t *info, int pid)
+{
+ int ret;
+
+ ret = ptrace(PTRACE_SET_THREAD_AREA, pid, info->entry_number,
+ (unsigned long) info);
+ if (ret < 0)
+ ret = -errno;
+ return ret;
+}
+
+int os_get_thread_area(user_desc_t *info, int pid)
+{
+ int ret;
+
+ ret = ptrace(PTRACE_GET_THREAD_AREA, pid, info->entry_number,
+ (unsigned long) info);
+ if (ret < 0)
+ ret = -errno;
+ return ret;
+}
diff --git a/arch/um/sys-i386/ptrace.c b/arch/x86/um/ptrace_32.c
index 3375c2717851..3b949daa095c 100644
--- a/arch/um/sys-i386/ptrace.c
+++ b/arch/x86/um/ptrace_32.c
@@ -50,20 +50,47 @@ int is_syscall(unsigned long addr)
/* 1 = access 0 = no access */
#define FLAG_MASK 0x00044dd5
+static const int reg_offsets[] = {
+ [EBX] = HOST_BX,
+ [ECX] = HOST_CX,
+ [EDX] = HOST_DX,
+ [ESI] = HOST_SI,
+ [EDI] = HOST_DI,
+ [EBP] = HOST_BP,
+ [EAX] = HOST_AX,
+ [DS] = HOST_DS,
+ [ES] = HOST_ES,
+ [FS] = HOST_FS,
+ [GS] = HOST_GS,
+ [EIP] = HOST_IP,
+ [CS] = HOST_CS,
+ [EFL] = HOST_EFLAGS,
+ [UESP] = HOST_SP,
+ [SS] = HOST_SS,
+};
+
int putreg(struct task_struct *child, int regno, unsigned long value)
{
regno >>= 2;
switch (regno) {
+ case EBX:
+ case ECX:
+ case EDX:
+ case ESI:
+ case EDI:
+ case EBP:
+ case EAX:
+ case EIP:
+ case UESP:
+ break;
case FS:
if (value && (value & 3) != 3)
return -EIO;
- PT_REGS_FS(&child->thread.regs) = value;
- return 0;
+ break;
case GS:
if (value && (value & 3) != 3)
return -EIO;
- PT_REGS_GS(&child->thread.regs) = value;
- return 0;
+ break;
case DS:
case ES:
if (value && (value & 3) != 3)
@@ -78,10 +105,15 @@ int putreg(struct task_struct *child, int regno, unsigned long value)
break;
case EFL:
value &= FLAG_MASK;
- value |= PT_REGS_EFLAGS(&child->thread.regs);
- break;
+ 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);
}
- PT_REGS_SET(&child->thread.regs, regno, value);
+ child->thread.regs.regs.gp[reg_offsets[regno]] = value;
return 0;
}
@@ -106,22 +138,35 @@ int poke_user(struct task_struct *child, long addr, long data)
unsigned long getreg(struct task_struct *child, int regno)
{
- unsigned long retval = ~0UL;
+ unsigned long mask = ~0UL;
regno >>= 2;
switch (regno) {
+ case ORIG_EAX:
+ return child->thread.regs.regs.syscall;
case FS:
case GS:
case DS:
case ES:
case SS:
case CS:
- retval = 0xffff;
- /* fall through */
+ mask = 0xffff;
+ break;
+ case EIP:
+ case UESP:
+ case EAX:
+ case EBX:
+ case ECX:
+ case EDX:
+ case ESI:
+ case EDI:
+ case EBP:
+ case EFL:
+ break;
default:
- retval &= PT_REG(&child->thread.regs, regno);
+ panic("Bad register in getreg() : %d\n", regno);
}
- return retval;
+ return mask & child->thread.regs.regs.gp[reg_offsets[regno]];
}
/* read the word at location addr in the USER area. */
diff --git a/arch/um/sys-x86_64/ptrace.c b/arch/x86/um/ptrace_64.c
index 4005506834fd..3b52bf0b418a 100644
--- a/arch/um/sys-x86_64/ptrace.c
+++ b/arch/x86/um/ptrace_64.c
@@ -18,10 +18,39 @@
*/
#define FLAG_MASK 0x44dd5UL
-int putreg(struct task_struct *child, int regno, unsigned long value)
+static const int reg_offsets[] =
{
- unsigned long tmp;
+ [R8 >> 3] = HOST_R8,
+ [R9 >> 3] = HOST_R9,
+ [R10 >> 3] = HOST_R10,
+ [R11 >> 3] = HOST_R11,
+ [R12 >> 3] = HOST_R12,
+ [R13 >> 3] = HOST_R13,
+ [R14 >> 3] = HOST_R14,
+ [R15 >> 3] = HOST_R15,
+ [RIP >> 3] = HOST_IP,
+ [RSP >> 3] = HOST_SP,
+ [RAX >> 3] = HOST_AX,
+ [RBX >> 3] = HOST_BX,
+ [RCX >> 3] = HOST_CX,
+ [RDX >> 3] = HOST_DX,
+ [RSI >> 3] = HOST_SI,
+ [RDI >> 3] = HOST_DI,
+ [RBP >> 3] = HOST_BP,
+ [CS >> 3] = HOST_CS,
+ [SS >> 3] = HOST_SS,
+ [FS_BASE >> 3] = HOST_FS_BASE,
+ [GS_BASE >> 3] = HOST_GS_BASE,
+ [DS >> 3] = HOST_DS,
+ [ES >> 3] = HOST_ES,
+ [FS >> 3] = HOST_FS,
+ [GS >> 3] = HOST_GS,
+ [EFLAGS >> 3] = HOST_EFLAGS,
+ [ORIG_RAX >> 3] = HOST_ORIG_AX,
+};
+int putreg(struct task_struct *child, int regno, unsigned long value)
+{
#ifdef TIF_IA32
/*
* Some code in the 64bit emulation may not be 64bit clean.
@@ -31,6 +60,26 @@ int putreg(struct task_struct *child, int regno, unsigned long value)
value &= 0xffffffff;
#endif
switch (regno) {
+ case R8:
+ case R9:
+ case R10:
+ case R11:
+ case R12:
+ case R13:
+ case R14:
+ case R15:
+ case RIP:
+ case RSP:
+ case RAX:
+ case RBX:
+ case RCX:
+ case RDX:
+ case RSI:
+ case RDI:
+ case RBP:
+ case ORIG_RAX:
+ break;
+
case FS:
case GS:
case DS:
@@ -50,12 +99,14 @@ int putreg(struct task_struct *child, int regno, unsigned long value)
case EFLAGS:
value &= FLAG_MASK;
- tmp = PT_REGS_EFLAGS(&child->thread.regs) & ~FLAG_MASK;
- value |= tmp;
- break;
+ child->thread.regs.regs.gp[HOST_EFLAGS] |= value;
+ return 0;
+
+ default:
+ panic("Bad register in putreg(): %d\n", regno);
}
- PT_REGS_SET(&child->thread.regs, regno, value);
+ child->thread.regs.regs.gp[reg_offsets[regno >> 3]] = value;
return 0;
}
@@ -80,24 +131,46 @@ int poke_user(struct task_struct *child, long addr, long data)
unsigned long getreg(struct task_struct *child, int regno)
{
- unsigned long retval = ~0UL;
+ unsigned long mask = ~0UL;
+#ifdef TIF_IA32
+ if (test_tsk_thread_flag(child, TIF_IA32))
+ mask = 0xffffffff;
+#endif
switch (regno) {
+ case R8:
+ case R9:
+ case R10:
+ case R11:
+ case R12:
+ case R13:
+ case R14:
+ case R15:
+ case RIP:
+ case RSP:
+ case RAX:
+ case RBX:
+ case RCX:
+ case RDX:
+ case RSI:
+ case RDI:
+ case RBP:
+ case ORIG_RAX:
+ case EFLAGS:
+ case FS_BASE:
+ case GS_BASE:
+ break;
case FS:
case GS:
case DS:
case ES:
case SS:
case CS:
- retval = 0xffff;
- /* fall through */
+ mask = 0xffff;
+ break;
default:
- retval &= PT_REG(&child->thread.regs, regno);
-#ifdef TIF_IA32
- if (test_tsk_thread_flag(child, TIF_IA32))
- retval &= 0xffffffff;
-#endif
+ panic("Bad register in getreg: %d\n", regno);
}
- return retval;
+ return mask & child->thread.regs.regs.gp[reg_offsets[regno >> 3]];
}
int peek_user(struct task_struct *child, long addr, long data)
diff --git a/arch/um/sys-i386/ptrace_user.c b/arch/x86/um/ptrace_user.c
index 0b10c3e74028..3960ca1dd35a 100644
--- a/arch/um/sys-i386/ptrace_user.c
+++ b/arch/x86/um/ptrace_user.c
@@ -4,7 +4,7 @@
*/
#include <errno.h>
-#include <sys/ptrace.h>
+#include "ptrace_user.h"
int ptrace_getregs(long pid, unsigned long *regs_out)
{
diff --git a/arch/um/sys-i386/setjmp.S b/arch/x86/um/setjmp_32.S
index b766792c9933..b766792c9933 100644
--- a/arch/um/sys-i386/setjmp.S
+++ b/arch/x86/um/setjmp_32.S
diff --git a/arch/um/sys-x86_64/setjmp.S b/arch/x86/um/setjmp_64.S
index 45f547b4043e..45f547b4043e 100644
--- a/arch/um/sys-x86_64/setjmp.S
+++ b/arch/x86/um/setjmp_64.S
diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h
new file mode 100644
index 000000000000..ff7766d28226
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/archsetjmp.h
@@ -0,0 +1,5 @@
+#ifdef __i386__
+#include "archsetjmp_32.h"
+#else
+#include "archsetjmp_64.h"
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp_32.h
index 0f312085ce1d..0f312085ce1d 100644
--- a/arch/um/sys-i386/shared/sysdep/archsetjmp.h
+++ b/arch/x86/um/shared/sysdep/archsetjmp_32.h
diff --git a/arch/um/sys-x86_64/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp_64.h
index 2af8f12ca161..2af8f12ca161 100644
--- a/arch/um/sys-x86_64/shared/sysdep/archsetjmp.h
+++ b/arch/x86/um/shared/sysdep/archsetjmp_64.h
diff --git a/arch/x86/um/shared/sysdep/faultinfo.h b/arch/x86/um/shared/sysdep/faultinfo.h
new file mode 100644
index 000000000000..862ecb1c7781
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/faultinfo.h
@@ -0,0 +1,5 @@
+#ifdef __i386__
+#include "faultinfo_32.h"
+#else
+#include "faultinfo_64.h"
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/faultinfo.h b/arch/x86/um/shared/sysdep/faultinfo_32.h
index db437cc373bc..a26086b8a800 100644
--- a/arch/um/sys-i386/shared/sysdep/faultinfo.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_32.h
@@ -24,6 +24,12 @@ struct faultinfo {
#define FAULT_WRITE(fi) ((fi).error_code & 2)
#define FAULT_ADDRESS(fi) ((fi).cr2)
+/* This is Page Fault */
+#define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14)
+
+/* SKAS3 has no trap_no on i386, but get_skas_faultinfo() sets it to 0. */
+#define SEGV_MAYBE_FIXABLE(fi) ((fi)->trap_no == 0 && ptrace_faultinfo)
+
#define PTRACE_FULL_FAULTINFO 0
#endif
diff --git a/arch/um/sys-x86_64/shared/sysdep/faultinfo.h b/arch/x86/um/shared/sysdep/faultinfo_64.h
index cb917b0d5660..f811cbe15d62 100644
--- a/arch/um/sys-x86_64/shared/sysdep/faultinfo.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_64.h
@@ -24,6 +24,12 @@ struct faultinfo {
#define FAULT_WRITE(fi) ((fi).error_code & 2)
#define FAULT_ADDRESS(fi) ((fi).cr2)
+/* This is Page Fault */
+#define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14)
+
+/* No broken SKAS API, which doesn't pass trap_no, here. */
+#define SEGV_MAYBE_FIXABLE(fi) 0
+
#define PTRACE_FULL_FAULTINFO 1
#endif
diff --git a/arch/um/sys-i386/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h
index 5868526b5eef..5868526b5eef 100644
--- a/arch/um/sys-i386/shared/sysdep/kernel-offsets.h
+++ b/arch/x86/um/shared/sysdep/kernel-offsets.h
diff --git a/arch/x86/um/shared/sysdep/mcontext.h b/arch/x86/um/shared/sysdep/mcontext.h
new file mode 100644
index 000000000000..b724c54da316
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/mcontext.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __SYS_SIGCONTEXT_X86_H
+#define __SYS_SIGCONTEXT_X86_H
+
+extern void get_regs_from_mc(struct uml_pt_regs *, mcontext_t *);
+
+#ifdef __i386__
+
+#define GET_FAULTINFO_FROM_MC(fi, mc) \
+ { \
+ (fi).cr2 = (mc)->cr2; \
+ (fi).error_code = (mc)->gregs[REG_ERR]; \
+ (fi).trap_no = (mc)->gregs[REG_TRAPNO]; \
+ }
+
+#else
+
+#define GET_FAULTINFO_FROM_MC(fi, mc) \
+ { \
+ (fi).cr2 = (mc)->gregs[REG_CR2]; \
+ (fi).error_code = (mc)->gregs[REG_ERR]; \
+ (fi).trap_no = (mc)->gregs[REG_TRAPNO]; \
+ }
+
+#endif
+
+#endif
diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h
new file mode 100644
index 000000000000..711b1621747f
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/ptrace.h
@@ -0,0 +1,5 @@
+#ifdef __i386__
+#include "ptrace_32.h"
+#else
+#include "ptrace_64.h"
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace_32.h
index c398a5076111..befd1df32ed0 100644
--- a/arch/um/sys-i386/shared/sysdep/ptrace.h
+++ b/arch/x86/um/shared/sysdep/ptrace_32.h
@@ -6,7 +6,7 @@
#ifndef __SYSDEP_I386_PTRACE_H
#define __SYSDEP_I386_PTRACE_H
-#include "user_constants.h"
+#include <generated/user_constants.h>
#include "sysdep/faultinfo.h"
#define MAX_REG_NR (UM_FRAME_SIZE / sizeof(unsigned long))
@@ -24,18 +24,16 @@ void set_using_sysemu(int value);
int get_using_sysemu(void);
extern int sysemu_supported;
-#include "skas_ptregs.h"
-
#define REGS_IP(r) ((r)[HOST_IP])
#define REGS_SP(r) ((r)[HOST_SP])
#define REGS_EFLAGS(r) ((r)[HOST_EFLAGS])
-#define REGS_EAX(r) ((r)[HOST_EAX])
-#define REGS_EBX(r) ((r)[HOST_EBX])
-#define REGS_ECX(r) ((r)[HOST_ECX])
-#define REGS_EDX(r) ((r)[HOST_EDX])
-#define REGS_ESI(r) ((r)[HOST_ESI])
-#define REGS_EDI(r) ((r)[HOST_EDI])
-#define REGS_EBP(r) ((r)[HOST_EBP])
+#define REGS_EAX(r) ((r)[HOST_AX])
+#define REGS_EBX(r) ((r)[HOST_BX])
+#define REGS_ECX(r) ((r)[HOST_CX])
+#define REGS_EDX(r) ((r)[HOST_DX])
+#define REGS_ESI(r) ((r)[HOST_SI])
+#define REGS_EDI(r) ((r)[HOST_DI])
+#define REGS_EBP(r) ((r)[HOST_BP])
#define REGS_CS(r) ((r)[HOST_CS])
#define REGS_SS(r) ((r)[HOST_SS])
#define REGS_DS(r) ((r)[HOST_DS])
@@ -45,6 +43,7 @@ extern int sysemu_supported;
#define REGS_SET_SYSCALL_RETURN(r, res) REGS_EAX(r) = (res)
+#define IP_RESTART_SYSCALL(ip) ((ip) -= 2)
#define REGS_RESTART_SYSCALL(r) IP_RESTART_SYSCALL(REGS_IP(r))
#ifndef PTRACE_SYSEMU_SINGLESTEP
@@ -102,62 +101,6 @@ struct syscall_args {
UPT_SYSCALL_ARG5(r), \
UPT_SYSCALL_ARG6(r) } } )
-#define UPT_REG(regs, reg) \
- ({ unsigned long val; \
- switch(reg){ \
- case EIP: val = UPT_IP(regs); break; \
- case UESP: val = UPT_SP(regs); break; \
- case EAX: val = UPT_EAX(regs); break; \
- case EBX: val = UPT_EBX(regs); break; \
- case ECX: val = UPT_ECX(regs); break; \
- case EDX: val = UPT_EDX(regs); break; \
- case ESI: val = UPT_ESI(regs); break; \
- case EDI: val = UPT_EDI(regs); break; \
- case EBP: val = UPT_EBP(regs); break; \
- case ORIG_EAX: val = UPT_ORIG_EAX(regs); break; \
- case CS: val = UPT_CS(regs); break; \
- case SS: val = UPT_SS(regs); break; \
- case DS: val = UPT_DS(regs); break; \
- case ES: val = UPT_ES(regs); break; \
- case FS: val = UPT_FS(regs); break; \
- case GS: val = UPT_GS(regs); break; \
- case EFL: val = UPT_EFLAGS(regs); break; \
- default : \
- panic("Bad register in UPT_REG : %d\n", reg); \
- val = -1; \
- } \
- val; \
- })
-
-#define UPT_SET(regs, reg, val) \
- do { \
- switch(reg){ \
- case EIP: UPT_IP(regs) = val; break; \
- case UESP: UPT_SP(regs) = val; break; \
- case EAX: UPT_EAX(regs) = val; break; \
- case EBX: UPT_EBX(regs) = val; break; \
- case ECX: UPT_ECX(regs) = val; break; \
- case EDX: UPT_EDX(regs) = val; break; \
- case ESI: UPT_ESI(regs) = val; break; \
- case EDI: UPT_EDI(regs) = val; break; \
- case EBP: UPT_EBP(regs) = val; break; \
- case ORIG_EAX: UPT_ORIG_EAX(regs) = val; break; \
- case CS: UPT_CS(regs) = val; break; \
- case SS: UPT_SS(regs) = val; break; \
- case DS: UPT_DS(regs) = val; break; \
- case ES: UPT_ES(regs) = val; break; \
- case FS: UPT_FS(regs) = val; break; \
- case GS: UPT_GS(regs) = val; break; \
- case EFL: UPT_EFLAGS(regs) = val; break; \
- default : \
- panic("Bad register in UPT_SET : %d\n", reg); \
- break; \
- } \
- } while (0)
-
-#define UPT_SET_SYSCALL_RETURN(r, res) \
- REGS_SET_SYSCALL_RETURN((r)->regs, (res))
-
#define UPT_RESTART_SYSCALL(r) REGS_RESTART_SYSCALL((r)->gp)
#define UPT_ORIG_SYSCALL(r) UPT_EAX(r)
diff --git a/arch/um/sys-x86_64/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace_64.h
index 8ee8f8e12af1..031edc53ac57 100644
--- a/arch/um/sys-x86_64/shared/sysdep/ptrace.h
+++ b/arch/x86/um/shared/sysdep/ptrace_64.h
@@ -8,24 +8,22 @@
#ifndef __SYSDEP_X86_64_PTRACE_H
#define __SYSDEP_X86_64_PTRACE_H
-#include "user_constants.h"
+#include <generated/user_constants.h>
#include "sysdep/faultinfo.h"
#define MAX_REG_OFFSET (UM_FRAME_SIZE)
#define MAX_REG_NR ((MAX_REG_OFFSET) / sizeof(unsigned long))
-#include "skas_ptregs.h"
-
#define REGS_IP(r) ((r)[HOST_IP])
#define REGS_SP(r) ((r)[HOST_SP])
-#define REGS_RBX(r) ((r)[HOST_RBX])
-#define REGS_RCX(r) ((r)[HOST_RCX])
-#define REGS_RDX(r) ((r)[HOST_RDX])
-#define REGS_RSI(r) ((r)[HOST_RSI])
-#define REGS_RDI(r) ((r)[HOST_RDI])
-#define REGS_RBP(r) ((r)[HOST_RBP])
-#define REGS_RAX(r) ((r)[HOST_RAX])
+#define REGS_RBX(r) ((r)[HOST_BX])
+#define REGS_RCX(r) ((r)[HOST_CX])
+#define REGS_RDX(r) ((r)[HOST_DX])
+#define REGS_RSI(r) ((r)[HOST_SI])
+#define REGS_RDI(r) ((r)[HOST_DI])
+#define REGS_RBP(r) ((r)[HOST_BP])
+#define REGS_RAX(r) ((r)[HOST_AX])
#define REGS_R8(r) ((r)[HOST_R8])
#define REGS_R9(r) ((r)[HOST_R9])
#define REGS_R10(r) ((r)[HOST_R10])
@@ -67,14 +65,13 @@
#define REGS_FS(r) ((r)[HOST_FS])
#define REGS_GS(r) ((r)[HOST_GS])
-#define REGS_ORIG_RAX(r) ((r)[HOST_ORIG_RAX])
+#define REGS_ORIG_RAX(r) ((r)[HOST_ORIG_AX])
#define REGS_SET_SYSCALL_RETURN(r, res) REGS_RAX(r) = (res)
+#define IP_RESTART_SYSCALL(ip) ((ip) -= 2)
#define REGS_RESTART_SYSCALL(r) IP_RESTART_SYSCALL(REGS_IP(r))
-#define REGS_SEGV_IS_FIXABLE(r) SEGV_IS_FIXABLE((r)->trap_type)
-
#define REGS_FAULT_ADDR(r) ((r)->fault_addr)
#define REGS_FAULT_WRITE(r) FAULT_WRITE((r)->fault_type)
@@ -149,88 +146,8 @@ struct syscall_args {
UPT_SYSCALL_ARG5(r), \
UPT_SYSCALL_ARG6(r) } } )
-#define UPT_REG(regs, reg) \
- ({ unsigned long val; \
- switch(reg){ \
- case R8: val = UPT_R8(regs); break; \
- case R9: val = UPT_R9(regs); break; \
- case R10: val = UPT_R10(regs); break; \
- case R11: val = UPT_R11(regs); break; \
- case R12: val = UPT_R12(regs); break; \
- case R13: val = UPT_R13(regs); break; \
- case R14: val = UPT_R14(regs); break; \
- case R15: val = UPT_R15(regs); break; \
- case RIP: val = UPT_IP(regs); break; \
- case RSP: val = UPT_SP(regs); break; \
- case RAX: val = UPT_RAX(regs); break; \
- case RBX: val = UPT_RBX(regs); break; \
- case RCX: val = UPT_RCX(regs); break; \
- case RDX: val = UPT_RDX(regs); break; \
- case RSI: val = UPT_RSI(regs); break; \
- case RDI: val = UPT_RDI(regs); break; \
- case RBP: val = UPT_RBP(regs); break; \
- case ORIG_RAX: val = UPT_ORIG_RAX(regs); break; \
- case CS: val = UPT_CS(regs); break; \
- case SS: val = UPT_SS(regs); break; \
- case FS_BASE: val = UPT_FS_BASE(regs); break; \
- case GS_BASE: val = UPT_GS_BASE(regs); break; \
- case DS: val = UPT_DS(regs); break; \
- case ES: val = UPT_ES(regs); break; \
- case FS : val = UPT_FS (regs); break; \
- case GS: val = UPT_GS(regs); break; \
- case EFLAGS: val = UPT_EFLAGS(regs); break; \
- default : \
- panic("Bad register in UPT_REG : %d\n", reg); \
- val = -1; \
- } \
- val; \
- })
-
-
-#define UPT_SET(regs, reg, val) \
- ({ unsigned long __upt_val = val; \
- switch(reg){ \
- case R8: UPT_R8(regs) = __upt_val; break; \
- case R9: UPT_R9(regs) = __upt_val; break; \
- case R10: UPT_R10(regs) = __upt_val; break; \
- case R11: UPT_R11(regs) = __upt_val; break; \
- case R12: UPT_R12(regs) = __upt_val; break; \
- case R13: UPT_R13(regs) = __upt_val; break; \
- case R14: UPT_R14(regs) = __upt_val; break; \
- case R15: UPT_R15(regs) = __upt_val; break; \
- case RIP: UPT_IP(regs) = __upt_val; break; \
- case RSP: UPT_SP(regs) = __upt_val; break; \
- case RAX: UPT_RAX(regs) = __upt_val; break; \
- case RBX: UPT_RBX(regs) = __upt_val; break; \
- case RCX: UPT_RCX(regs) = __upt_val; break; \
- case RDX: UPT_RDX(regs) = __upt_val; break; \
- case RSI: UPT_RSI(regs) = __upt_val; break; \
- case RDI: UPT_RDI(regs) = __upt_val; break; \
- case RBP: UPT_RBP(regs) = __upt_val; break; \
- case ORIG_RAX: UPT_ORIG_RAX(regs) = __upt_val; break; \
- case CS: UPT_CS(regs) = __upt_val; break; \
- case SS: UPT_SS(regs) = __upt_val; break; \
- case FS_BASE: UPT_FS_BASE(regs) = __upt_val; break; \
- case GS_BASE: UPT_GS_BASE(regs) = __upt_val; break; \
- case DS: UPT_DS(regs) = __upt_val; break; \
- case ES: UPT_ES(regs) = __upt_val; break; \
- case FS: UPT_FS(regs) = __upt_val; break; \
- case GS: UPT_GS(regs) = __upt_val; break; \
- case EFLAGS: UPT_EFLAGS(regs) = __upt_val; break; \
- default : \
- panic("Bad register in UPT_SET : %d\n", reg); \
- break; \
- } \
- __upt_val; \
- })
-
-#define UPT_SET_SYSCALL_RETURN(r, res) \
- REGS_SET_SYSCALL_RETURN((r)->regs, (res))
-
#define UPT_RESTART_SYSCALL(r) REGS_RESTART_SYSCALL((r)->gp)
-#define UPT_SEGV_IS_FIXABLE(r) REGS_SEGV_IS_FIXABLE(&r->skas)
-
#define UPT_FAULTINFO(r) (&(r)->faultinfo)
static inline void arch_init_registers(int pid)
diff --git a/arch/x86/um/shared/sysdep/ptrace_user.h b/arch/x86/um/shared/sysdep/ptrace_user.h
new file mode 100644
index 000000000000..16cd6b5e71f7
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/ptrace_user.h
@@ -0,0 +1,27 @@
+#include <generated/user_constants.h>
+
+#define PT_OFFSET(r) ((r) * sizeof(long))
+
+#define PT_SYSCALL_NR(regs) ((regs)[HOST_ORIG_AX])
+#define PT_SYSCALL_NR_OFFSET PT_OFFSET(HOST_ORIG_AX)
+
+#define PT_SYSCALL_RET_OFFSET PT_OFFSET(HOST_AX)
+
+#define REGS_IP_INDEX HOST_IP
+#define REGS_SP_INDEX HOST_SP
+
+#ifdef __i386__
+#define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE)
+#else
+#define FP_SIZE HOST_FP_SIZE
+
+/*
+ * x86_64 FC3 doesn't define this in /usr/include/linux/ptrace.h even though
+ * it's defined in the kernel's include/linux/ptrace.h. Additionally, use the
+ * 2.4 name and value for 2.4 host compatibility.
+ */
+#ifndef PTRACE_OLDSETOPTIONS
+#define PTRACE_OLDSETOPTIONS 21
+#endif
+
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/skas_ptrace.h b/arch/x86/um/shared/sysdep/skas_ptrace.h
index e27b8a791773..453febe98993 100644
--- a/arch/um/sys-i386/shared/sysdep/skas_ptrace.h
+++ b/arch/x86/um/shared/sysdep/skas_ptrace.h
@@ -3,8 +3,8 @@
* Licensed under the GPL
*/
-#ifndef __SYSDEP_I386_SKAS_PTRACE_H
-#define __SYSDEP_I386_SKAS_PTRACE_H
+#ifndef __SYSDEP_X86_SKAS_PTRACE_H
+#define __SYSDEP_X86_SKAS_PTRACE_H
struct ptrace_faultinfo {
int is_write;
diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h
new file mode 100644
index 000000000000..bd161e300102
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/stub.h
@@ -0,0 +1,14 @@
+#include <asm/unistd.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include "as-layout.h"
+#include "stub-data.h"
+
+#ifdef __i386__
+#include "stub_32.h"
+#else
+#include "stub_64.h"
+#endif
+
+extern void stub_segv_handler(int, siginfo_t *, void *);
+extern void stub_clone_handler(void);
diff --git a/arch/um/sys-i386/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub_32.h
index 977dedd9221b..51fd256c75f0 100644
--- a/arch/um/sys-i386/shared/sysdep/stub.h
+++ b/arch/x86/um/shared/sysdep/stub_32.h
@@ -6,15 +6,7 @@
#ifndef __SYSDEP_STUB_H
#define __SYSDEP_STUB_H
-#include <sys/mman.h>
#include <asm/ptrace.h>
-#include <asm/unistd.h>
-#include "as-layout.h"
-#include "stub-data.h"
-#include "kern_constants.h"
-
-extern void stub_segv_handler(int sig);
-extern void stub_clone_handler(void);
#define STUB_SYSCALL_RET EAX
#define STUB_MMAP_NR __NR_mmap2
diff --git a/arch/um/sys-x86_64/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub_64.h
index 3432aa249970..994df93c5ed3 100644
--- a/arch/um/sys-x86_64/shared/sysdep/stub.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -6,15 +6,7 @@
#ifndef __SYSDEP_STUB_H
#define __SYSDEP_STUB_H
-#include <sys/mman.h>
-#include <asm/unistd.h>
#include <sysdep/ptrace_user.h>
-#include "as-layout.h"
-#include "stub-data.h"
-#include "kern_constants.h"
-
-extern void stub_segv_handler(int sig);
-extern void stub_clone_handler(void);
#define STUB_SYSCALL_RET PT_INDEX(RAX)
#define STUB_MMAP_NR __NR_mmap
diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h
new file mode 100644
index 000000000000..bd9a89b67e41
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/syscalls.h
@@ -0,0 +1,5 @@
+#ifdef __i386__
+#include "syscalls_32.h"
+#else
+#include "syscalls_64.h"
+#endif
diff --git a/arch/um/sys-i386/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls_32.h
index 05cb796aecb5..05cb796aecb5 100644
--- a/arch/um/sys-i386/shared/sysdep/syscalls.h
+++ b/arch/x86/um/shared/sysdep/syscalls_32.h
diff --git a/arch/um/sys-x86_64/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls_64.h
index 7cfb0b085655..8a7d5e1da98e 100644
--- a/arch/um/sys-x86_64/shared/sysdep/syscalls.h
+++ b/arch/x86/um/shared/sysdep/syscalls_64.h
@@ -9,7 +9,6 @@
#include <linux/msg.h>
#include <linux/shm.h>
-#include <kern_constants.h>
typedef long syscall_handler_t(void);
diff --git a/arch/um/sys-i386/shared/sysdep/tls.h b/arch/x86/um/shared/sysdep/tls.h
index 34550755b2a1..27cce00c6b30 100644
--- a/arch/um/sys-i386/shared/sysdep/tls.h
+++ b/arch/x86/um/shared/sysdep/tls.h
@@ -17,16 +17,23 @@ typedef struct um_dup_user_desc {
unsigned int limit_in_pages:1;
unsigned int seg_not_present:1;
unsigned int useable:1;
+#ifdef __x86_64__
+ unsigned int lm:1;
+#endif
} user_desc_t;
# else /* __KERNEL__ */
-# include <ldt.h>
typedef struct user_desc user_desc_t;
# endif /* __KERNEL__ */
+extern int os_set_thread_area(user_desc_t *info, int pid);
+extern int os_get_thread_area(user_desc_t *info, int pid);
+
+#ifdef __i386__
#define GDT_ENTRY_TLS_MIN_I386 6
#define GDT_ENTRY_TLS_MIN_X86_64 12
+#endif
#endif /* _SYSDEP_TLS_H */
diff --git a/arch/um/sys-i386/signal.c b/arch/x86/um/signal.c
index 89a46626bfd8..4883b9546016 100644
--- a/arch/um/sys-i386/signal.c
+++ b/arch/x86/um/signal.c
@@ -1,36 +1,20 @@
/*
- * Copyright (C) 2004 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright (C) 2003 PathScale, Inc.
+ * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*/
+
+#include <linux/personality.h>
#include <linux/ptrace.h>
+#include <linux/kernel.h>
#include <asm/unistd.h>
#include <asm/uaccess.h>
#include <asm/ucontext.h>
#include "frame_kern.h"
#include "skas.h"
-void copy_sc(struct uml_pt_regs *regs, void *from)
-{
- struct sigcontext *sc = from;
-
- REGS_GS(regs->gp) = sc->gs;
- REGS_FS(regs->gp) = sc->fs;
- REGS_ES(regs->gp) = sc->es;
- REGS_DS(regs->gp) = sc->ds;
- REGS_EDI(regs->gp) = sc->di;
- REGS_ESI(regs->gp) = sc->si;
- REGS_EBP(regs->gp) = sc->bp;
- REGS_SP(regs->gp) = sc->sp;
- REGS_EBX(regs->gp) = sc->bx;
- REGS_EDX(regs->gp) = sc->dx;
- REGS_ECX(regs->gp) = sc->cx;
- REGS_EAX(regs->gp) = sc->ax;
- REGS_IP(regs->gp) = sc->ip;
- REGS_CS(regs->gp) = sc->cs;
- REGS_EFLAGS(regs->gp) = sc->flags;
- REGS_SS(regs->gp) = sc->ss;
-}
+#ifdef CONFIG_X86_32
/*
* FPU tag word conversions.
@@ -164,6 +148,8 @@ static int convert_fxsr_from_user(struct user_fxsr_struct *fxsave,
extern int have_fpx_regs;
+#endif
+
static int copy_sc_from_user(struct pt_regs *regs,
struct sigcontext __user *from)
{
@@ -174,8 +160,45 @@ static int copy_sc_from_user(struct pt_regs *regs,
if (err)
return err;
+#define GETREG(regno, regname) regs->regs.gp[HOST_##regno] = sc.regname
+
+#ifdef CONFIG_X86_32
+ GETREG(GS, gs);
+ GETREG(FS, fs);
+ GETREG(ES, es);
+ GETREG(DS, ds);
+#endif
+ GETREG(DI, di);
+ GETREG(SI, si);
+ GETREG(BP, bp);
+ GETREG(SP, sp);
+ GETREG(BX, bx);
+ GETREG(DX, dx);
+ GETREG(CX, cx);
+ GETREG(AX, ax);
+ GETREG(IP, ip);
+
+#ifdef CONFIG_X86_64
+ GETREG(R8, r8);
+ GETREG(R9, r9);
+ GETREG(R10, r10);
+ GETREG(R11, r11);
+ GETREG(R12, r12);
+ GETREG(R13, r13);
+ GETREG(R14, r14);
+ GETREG(R15, r15);
+#endif
+
+ GETREG(CS, cs);
+ GETREG(EFLAGS, flags);
+#ifdef CONFIG_X86_32
+ GETREG(SS, ss);
+#endif
+
+#undef GETREG
+
pid = userspace_pid[current_thread_info()->cpu];
- copy_sc(&regs->regs, &sc);
+#ifdef CONFIG_X86_32
if (have_fpx_regs) {
struct user_fxsr_struct fpx;
@@ -196,8 +219,9 @@ static int copy_sc_from_user(struct pt_regs *regs,
-err);
return 1;
}
- }
- else {
+ } else
+#endif
+ {
struct user_i387_struct fp;
err = copy_from_user(&fp, sc.fpstate,
@@ -213,43 +237,66 @@ static int copy_sc_from_user(struct pt_regs *regs,
return 1;
}
}
-
return 0;
}
static int copy_sc_to_user(struct sigcontext __user *to,
struct _fpstate __user *to_fp, struct pt_regs *regs,
- unsigned long sp)
+ unsigned long mask)
{
struct sigcontext sc;
struct faultinfo * fi = &current->thread.arch.faultinfo;
int err, pid;
+ memset(&sc, 0, sizeof(struct sigcontext));
+
+#define PUTREG(regno, regname) sc.regname = regs->regs.gp[HOST_##regno]
+
+#ifdef CONFIG_X86_32
+ PUTREG(GS, gs);
+ PUTREG(FS, fs);
+ PUTREG(ES, es);
+ PUTREG(DS, ds);
+#endif
+ PUTREG(DI, di);
+ PUTREG(SI, si);
+ PUTREG(BP, bp);
+ PUTREG(SP, sp);
+ PUTREG(BX, bx);
+ PUTREG(DX, dx);
+ PUTREG(CX, cx);
+ PUTREG(AX, ax);
+#ifdef CONFIG_X86_64
+ PUTREG(R8, r8);
+ PUTREG(R9, r9);
+ PUTREG(R10, r10);
+ PUTREG(R11, r11);
+ PUTREG(R12, r12);
+ PUTREG(R13, r13);
+ PUTREG(R14, r14);
+ PUTREG(R15, r15);
+#endif
- sc.gs = REGS_GS(regs->regs.gp);
- sc.fs = REGS_FS(regs->regs.gp);
- sc.es = REGS_ES(regs->regs.gp);
- sc.ds = REGS_DS(regs->regs.gp);
- sc.di = REGS_EDI(regs->regs.gp);
- sc.si = REGS_ESI(regs->regs.gp);
- sc.bp = REGS_EBP(regs->regs.gp);
- sc.sp = sp;
- sc.bx = REGS_EBX(regs->regs.gp);
- sc.dx = REGS_EDX(regs->regs.gp);
- sc.cx = REGS_ECX(regs->regs.gp);
- sc.ax = REGS_EAX(regs->regs.gp);
- sc.ip = REGS_IP(regs->regs.gp);
- sc.cs = REGS_CS(regs->regs.gp);
- sc.flags = REGS_EFLAGS(regs->regs.gp);
- sc.sp_at_signal = regs->regs.gp[UESP];
- sc.ss = regs->regs.gp[SS];
sc.cr2 = fi->cr2;
sc.err = fi->error_code;
sc.trapno = fi->trap_no;
-
- to_fp = (to_fp ? to_fp : (struct _fpstate __user *) (to + 1));
+ PUTREG(IP, ip);
+ PUTREG(CS, cs);
+ PUTREG(EFLAGS, flags);
+#ifdef CONFIG_X86_32
+ PUTREG(SP, sp_at_signal);
+ PUTREG(SS, ss);
+#endif
+#undef PUTREG
+ sc.oldmask = mask;
sc.fpstate = to_fp;
+ err = copy_to_user(to, &sc, sizeof(struct sigcontext));
+ if (err)
+ return 1;
+
pid = userspace_pid[current_thread_info()->cpu];
+
+#ifdef CONFIG_X86_32
if (have_fpx_regs) {
struct user_fxsr_struct fpx;
@@ -272,8 +319,9 @@ static int copy_sc_to_user(struct sigcontext __user *to,
if (copy_to_user(&to_fp->_fxsr_env[0], &fpx,
sizeof(struct user_fxsr_struct)))
return 1;
- }
- else {
+ } else
+#endif
+ {
struct user_i387_struct fp;
err = save_fp_registers(pid, (unsigned long *) &fp);
@@ -281,9 +329,10 @@ static int copy_sc_to_user(struct sigcontext __user *to,
return 1;
}
- return copy_to_user(to, &sc, sizeof(sc));
+ return 0;
}
+#ifdef CONFIG_X86_32
static int copy_ucontext_to_user(struct ucontext __user *uc,
struct _fpstate __user *fp, sigset_t *set,
unsigned long sp)
@@ -293,7 +342,7 @@ static int copy_ucontext_to_user(struct ucontext __user *uc,
err |= put_user(current->sas_ss_sp, &uc->uc_stack.ss_sp);
err |= put_user(sas_ss_flags(sp), &uc->uc_stack.ss_flags);
err |= put_user(current->sas_ss_size, &uc->uc_stack.ss_size);
- err |= copy_sc_to_user(&uc->uc_mcontext, fp, &current->thread.regs, sp);
+ err |= copy_sc_to_user(&uc->uc_mcontext, fp, &current->thread.regs, 0);
err |= copy_to_user(&uc->uc_sigmask, set, sizeof(*set));
return err;
}
@@ -326,7 +375,6 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig,
{
struct sigframe __user *frame;
void __user *restorer;
- unsigned long save_sp = PT_REGS_SP(regs);
int err = 0;
/* This is the same calculation as i386 - ((sp + 4) & 15) == 0 */
@@ -339,20 +387,9 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig,
if (ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
- /* Update SP now because the page fault handler refuses to extend
- * the stack if the faulting address is too far below the current
- * SP, which frame now certainly is. If there's an error, the original
- * value is restored on the way out.
- * When writing the sigcontext to the stack, we have to write the
- * original value, so that's passed to copy_sc_to_user, which does
- * the right thing with it.
- */
- PT_REGS_SP(regs) = (unsigned long) frame;
-
err |= __put_user(restorer, &frame->pretcode);
err |= __put_user(sig, &frame->sig);
- err |= copy_sc_to_user(&frame->sc, NULL, regs, save_sp);
- err |= __put_user(mask->sig[0], &frame->sc.oldmask);
+ err |= copy_sc_to_user(&frame->sc, &frame->fpstate, regs, mask->sig[0]);
if (_NSIG_WORDS > 1)
err |= __copy_to_user(&frame->extramask, &mask->sig[1],
sizeof(frame->extramask));
@@ -369,7 +406,7 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig,
err |= __put_user(0x80cd, (short __user *)(frame->retcode+6));
if (err)
- goto err;
+ return err;
PT_REGS_SP(regs) = (unsigned long) frame;
PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler;
@@ -380,10 +417,6 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig,
if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
ptrace_notify(SIGTRAP);
return 0;
-
-err:
- PT_REGS_SP(regs) = save_sp;
- return err;
}
int setup_signal_stack_si(unsigned long stack_top, int sig,
@@ -392,7 +425,6 @@ int setup_signal_stack_si(unsigned long stack_top, int sig,
{
struct rt_sigframe __user *frame;
void __user *restorer;
- unsigned long save_sp = PT_REGS_SP(regs);
int err = 0;
stack_top &= -8UL;
@@ -404,16 +436,13 @@ int setup_signal_stack_si(unsigned long stack_top, int sig,
if (ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
- /* See comment above about why this is here */
- PT_REGS_SP(regs) = (unsigned long) frame;
-
err |= __put_user(restorer, &frame->pretcode);
err |= __put_user(sig, &frame->sig);
err |= __put_user(&frame->info, &frame->pinfo);
err |= __put_user(&frame->uc, &frame->puc);
err |= copy_siginfo_to_user(&frame->info, info);
err |= copy_ucontext_to_user(&frame->uc, &frame->fpstate, mask,
- save_sp);
+ PT_REGS_SP(regs));
/*
* This is movl $,%eax ; int $0x80
@@ -427,8 +456,9 @@ int setup_signal_stack_si(unsigned long stack_top, int sig,
err |= __put_user(0x80cd, (short __user *)(frame->retcode+5));
if (err)
- goto err;
+ return err;
+ PT_REGS_SP(regs) = (unsigned long) frame;
PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler;
PT_REGS_EAX(regs) = (unsigned long) sig;
PT_REGS_EDX(regs) = (unsigned long) &frame->info;
@@ -437,13 +467,9 @@ int setup_signal_stack_si(unsigned long stack_top, int sig,
if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
ptrace_notify(SIGTRAP);
return 0;
-
-err:
- PT_REGS_SP(regs) = save_sp;
- return err;
}
-long sys_sigreturn(struct pt_regs regs)
+long sys_sigreturn(struct pt_regs *regs)
{
unsigned long sp = PT_REGS_SP(&current->thread.regs);
struct sigframe __user *frame = (struct sigframe __user *)(sp - 8);
@@ -458,11 +484,7 @@ long sys_sigreturn(struct pt_regs regs)
goto segfault;
sigdelsetmask(&set, ~_BLOCKABLE);
-
- spin_lock_irq(&current->sighand->siglock);
- current->blocked = set;
- recalc_sigpending();
- spin_unlock_irq(&current->sighand->siglock);
+ set_current_blocked(&set);
if (copy_sc_from_user(&current->thread.regs, sc))
goto segfault;
@@ -476,24 +498,107 @@ long sys_sigreturn(struct pt_regs regs)
return 0;
}
-long sys_rt_sigreturn(struct pt_regs regs)
+#else
+
+struct rt_sigframe
+{
+ char __user *pretcode;
+ struct ucontext uc;
+ struct siginfo info;
+ struct _fpstate fpstate;
+};
+
+int setup_signal_stack_si(unsigned long stack_top, int sig,
+ struct k_sigaction *ka, struct pt_regs * regs,
+ siginfo_t *info, sigset_t *set)
+{
+ struct rt_sigframe __user *frame;
+ int err = 0;
+ struct task_struct *me = current;
+
+ frame = (struct rt_sigframe __user *)
+ round_down(stack_top - sizeof(struct rt_sigframe), 16);
+ /* Subtract 128 for a red zone and 8 for proper alignment */
+ frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8);
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ goto out;
+
+ if (ka->sa.sa_flags & SA_SIGINFO) {
+ err |= copy_siginfo_to_user(&frame->info, info);
+ if (err)
+ goto out;
+ }
+
+ /* Create the ucontext. */
+ err |= __put_user(0, &frame->uc.uc_flags);
+ err |= __put_user(0, &frame->uc.uc_link);
+ err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ err |= __put_user(sas_ss_flags(PT_REGS_SP(regs)),
+ &frame->uc.uc_stack.ss_flags);
+ err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs,
+ set->sig[0]);
+ err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate);
+ if (sizeof(*set) == 16) {
+ __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
+ __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
+ }
+ else
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set,
+ sizeof(*set));
+
+ /*
+ * Set up to return from userspace. If provided, use a stub
+ * already in userspace.
+ */
+ /* x86-64 should always use SA_RESTORER. */
+ if (ka->sa.sa_flags & SA_RESTORER)
+ err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+ else
+ /* could use a vstub here */
+ return err;
+
+ if (err)
+ return err;
+
+ /* Set up registers for signal handler */
+ {
+ struct exec_domain *ed = current_thread_info()->exec_domain;
+ if (unlikely(ed && ed->signal_invmap && sig < 32))
+ sig = ed->signal_invmap[sig];
+ }
+
+ PT_REGS_SP(regs) = (unsigned long) frame;
+ PT_REGS_RDI(regs) = sig;
+ /* In case the signal handler was declared without prototypes */
+ PT_REGS_RAX(regs) = 0;
+
+ /*
+ * This also works for non SA_SIGINFO handlers because they expect the
+ * next argument after the signal number on the stack.
+ */
+ PT_REGS_RSI(regs) = (unsigned long) &frame->info;
+ PT_REGS_RDX(regs) = (unsigned long) &frame->uc;
+ PT_REGS_RIP(regs) = (unsigned long) ka->sa.sa_handler;
+ out:
+ return err;
+}
+#endif
+
+long sys_rt_sigreturn(struct pt_regs *regs)
{
unsigned long sp = PT_REGS_SP(&current->thread.regs);
struct rt_sigframe __user *frame =
- (struct rt_sigframe __user *) (sp - 4);
- sigset_t set;
+ (struct rt_sigframe __user *)(sp - sizeof(long));
struct ucontext __user *uc = &frame->uc;
- int sig_size = _NSIG_WORDS * sizeof(unsigned long);
+ sigset_t set;
- if (copy_from_user(&set, &uc->uc_sigmask, sig_size))
+ if (copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
goto segfault;
sigdelsetmask(&set, ~_BLOCKABLE);
-
- spin_lock_irq(&current->sighand->siglock);
- current->blocked = set;
- recalc_sigpending();
- spin_unlock_irq(&current->sighand->siglock);
+ set_current_blocked(&set);
if (copy_sc_from_user(&current->thread.regs, &uc->uc_mcontext))
goto segfault;
@@ -506,3 +611,14 @@ long sys_rt_sigreturn(struct pt_regs regs)
force_sig(SIGSEGV, current);
return 0;
}
+
+#ifdef CONFIG_X86_32
+long ptregs_sigreturn(void)
+{
+ return sys_sigreturn(NULL);
+}
+long ptregs_rt_sigreturn(void)
+{
+ return sys_rt_sigreturn(NULL);
+}
+#endif
diff --git a/arch/um/sys-i386/stub.S b/arch/x86/um/stub_32.S
index 54a36ec20cb7..54a36ec20cb7 100644
--- a/arch/um/sys-i386/stub.S
+++ b/arch/x86/um/stub_32.S
diff --git a/arch/um/sys-x86_64/stub.S b/arch/x86/um/stub_64.S
index 20e4a96a6dcb..20e4a96a6dcb 100644
--- a/arch/um/sys-x86_64/stub.S
+++ b/arch/x86/um/stub_64.S
diff --git a/arch/um/sys-x86_64/stub_segv.c b/arch/x86/um/stub_segv.c
index ced051afc705..b7450bd22e7d 100644
--- a/arch/um/sys-x86_64/stub_segv.c
+++ b/arch/x86/um/stub_segv.c
@@ -3,19 +3,16 @@
* Licensed under the GPL
*/
-#include <signal.h>
-#include "as-layout.h"
#include "sysdep/stub.h"
#include "sysdep/faultinfo.h"
-#include "sysdep/sigcontext.h"
+#include "sysdep/mcontext.h"
void __attribute__ ((__section__ (".__syscall_stub")))
-stub_segv_handler(int sig)
+stub_segv_handler(int sig, siginfo_t *info, void *p)
{
- struct ucontext *uc;
+ struct ucontext *uc = p;
- __asm__ __volatile__("movq %%rdx, %0" : "=g" (uc) :);
- GET_FAULTINFO_FROM_SC(*((struct faultinfo *) STUB_DATA),
+ GET_FAULTINFO_FROM_MC(*((struct faultinfo *) STUB_DATA),
&uc->uc_mcontext);
trap_myself();
}
diff --git a/arch/um/sys-i386/sys_call_table.S b/arch/x86/um/sys_call_table_32.S
index de274071455d..a7ca80d2dceb 100644
--- a/arch/um/sys-i386/sys_call_table.S
+++ b/arch/x86/um/sys_call_table_32.S
@@ -13,16 +13,14 @@
#define ptregs_execve sys_execve
#define ptregs_iopl sys_iopl
#define ptregs_vm86old sys_vm86old
-#define ptregs_sigreturn sys_sigreturn
#define ptregs_clone sys_clone
#define ptregs_vm86 sys_vm86
-#define ptregs_rt_sigreturn sys_rt_sigreturn
#define ptregs_sigaltstack sys_sigaltstack
#define ptregs_vfork sys_vfork
.section .rodata,"a"
-#include "../../x86/kernel/syscall_table_32.S"
+#include "../kernel/syscall_table_32.S"
ENTRY(syscall_table_size)
.long .-sys_call_table
diff --git a/arch/um/sys-x86_64/syscall_table.c b/arch/x86/um/sys_call_table_64.c
index 47d469e7e7ce..99522f78b162 100644
--- a/arch/um/sys-x86_64/syscall_table.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -6,7 +6,6 @@
#include <linux/linkage.h>
#include <linux/sys.h>
#include <linux/cache.h>
-#include <kern_constants.h>
#define __NO_STUBS
@@ -59,7 +58,7 @@ extern void sys_ni_syscall(void);
*/
sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
-#include "../../x86/include/asm/unistd_64.h"
+#include <asm/unistd_64.h>
};
int syscall_table_size = sizeof(sys_call_table);
diff --git a/arch/um/sys-i386/syscalls.c b/arch/x86/um/syscalls_32.c
index 70ca357393b8..70ca357393b8 100644
--- a/arch/um/sys-i386/syscalls.c
+++ b/arch/x86/um/syscalls_32.c
diff --git a/arch/um/sys-x86_64/syscalls.c b/arch/x86/um/syscalls_64.c
index f3d82bb6e15a..f3d82bb6e15a 100644
--- a/arch/um/sys-x86_64/syscalls.c
+++ b/arch/x86/um/syscalls_64.c
diff --git a/arch/um/sys-i386/sysrq.c b/arch/x86/um/sysrq_32.c
index 171b3e9dc867..171b3e9dc867 100644
--- a/arch/um/sys-i386/sysrq.c
+++ b/arch/x86/um/sysrq_32.c
diff --git a/arch/um/sys-x86_64/sysrq.c b/arch/x86/um/sysrq_64.c
index f4f82beb3508..e8913436d7dc 100644
--- a/arch/um/sys-x86_64/sysrq.c
+++ b/arch/x86/um/sysrq_64.c
@@ -20,7 +20,7 @@ void __show_regs(struct pt_regs *regs)
current->comm, print_tainted(), init_utsname()->release);
printk(KERN_INFO "RIP: %04lx:[<%016lx>]\n", PT_REGS_CS(regs) & 0xffff,
PT_REGS_RIP(regs));
- printk(KERN_INFO "RSP: %016lx EFLAGS: %08lx\n", PT_REGS_RSP(regs),
+ printk(KERN_INFO "RSP: %016lx EFLAGS: %08lx\n", PT_REGS_SP(regs),
PT_REGS_EFLAGS(regs));
printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
PT_REGS_RAX(regs), PT_REGS_RBX(regs), PT_REGS_RCX(regs));
diff --git a/arch/um/sys-i386/tls.c b/arch/x86/um/tls_32.c
index c6c7131e563b..c6c7131e563b 100644
--- a/arch/um/sys-i386/tls.c
+++ b/arch/x86/um/tls_32.c
diff --git a/arch/um/sys-x86_64/tls.c b/arch/x86/um/tls_64.c
index f7ba46200ecd..f7ba46200ecd 100644
--- a/arch/um/sys-x86_64/tls.c
+++ b/arch/x86/um/tls_64.c
diff --git a/arch/um/sys-x86_64/user-offsets.c b/arch/x86/um/user-offsets.c
index 973585414a66..ca49be8ddd0c 100644
--- a/arch/um/sys-x86_64/user-offsets.c
+++ b/arch/x86/um/user-offsets.c
@@ -9,28 +9,43 @@
#include <asm/types.h>
#define DEFINE(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+ asm volatile("\n->" #sym " %0 " #val : : "i" (val))
#define DEFINE_LONGS(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long)))
-
-#define OFFSET(sym, str, mem) \
- DEFINE(sym, offsetof(struct str, mem));
+ asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long)))
void foo(void)
{
- OFFSET(HOST_SC_CR2, sigcontext, cr2);
- OFFSET(HOST_SC_ERR, sigcontext, err);
- OFFSET(HOST_SC_TRAPNO, sigcontext, trapno);
+#ifdef __i386__
+ DEFINE_LONGS(HOST_FP_SIZE, sizeof(struct user_fpregs_struct));
+ DEFINE_LONGS(HOST_FPX_SIZE, sizeof(struct user_fpxregs_struct));
+ DEFINE(HOST_IP, EIP);
+ DEFINE(HOST_SP, UESP);
+ DEFINE(HOST_EFLAGS, EFL);
+ DEFINE(HOST_AX, EAX);
+ DEFINE(HOST_BX, EBX);
+ DEFINE(HOST_CX, ECX);
+ DEFINE(HOST_DX, EDX);
+ DEFINE(HOST_SI, ESI);
+ DEFINE(HOST_DI, EDI);
+ DEFINE(HOST_BP, EBP);
+ DEFINE(HOST_CS, CS);
+ DEFINE(HOST_SS, SS);
+ DEFINE(HOST_DS, DS);
+ DEFINE(HOST_FS, FS);
+ DEFINE(HOST_ES, ES);
+ DEFINE(HOST_GS, GS);
+ DEFINE(HOST_ORIG_AX, ORIG_EAX);
+#else
DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long));
- DEFINE_LONGS(HOST_RBX, RBX);
- DEFINE_LONGS(HOST_RCX, RCX);
- DEFINE_LONGS(HOST_RDI, RDI);
- DEFINE_LONGS(HOST_RSI, RSI);
- DEFINE_LONGS(HOST_RDX, RDX);
- DEFINE_LONGS(HOST_RBP, RBP);
- DEFINE_LONGS(HOST_RAX, RAX);
+ DEFINE_LONGS(HOST_BX, RBX);
+ DEFINE_LONGS(HOST_CX, RCX);
+ DEFINE_LONGS(HOST_DI, RDI);
+ DEFINE_LONGS(HOST_SI, RSI);
+ DEFINE_LONGS(HOST_DX, RDX);
+ DEFINE_LONGS(HOST_BP, RBP);
+ DEFINE_LONGS(HOST_AX, RAX);
DEFINE_LONGS(HOST_R8, R8);
DEFINE_LONGS(HOST_R9, R9);
DEFINE_LONGS(HOST_R10, R10);
@@ -39,7 +54,7 @@ void foo(void)
DEFINE_LONGS(HOST_R13, R13);
DEFINE_LONGS(HOST_R14, R14);
DEFINE_LONGS(HOST_R15, R15);
- DEFINE_LONGS(HOST_ORIG_RAX, ORIG_RAX);
+ DEFINE_LONGS(HOST_ORIG_AX, ORIG_RAX);
DEFINE_LONGS(HOST_CS, CS);
DEFINE_LONGS(HOST_SS, SS);
DEFINE_LONGS(HOST_EFLAGS, EFLAGS);
@@ -52,9 +67,9 @@ void foo(void)
DEFINE_LONGS(HOST_IP, RIP);
DEFINE_LONGS(HOST_SP, RSP);
- DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct));
+#endif
- /* XXX Duplicated between i386 and x86_64 */
+ DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct));
DEFINE(UM_POLLIN, POLLIN);
DEFINE(UM_POLLPRI, POLLPRI);
DEFINE(UM_POLLOUT, POLLOUT);
diff --git a/arch/um/sys-x86_64/vdso/Makefile b/arch/x86/um/vdso/Makefile
index 5dffe6d46686..6c803ca49b5d 100644
--- a/arch/um/sys-x86_64/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -46,8 +46,8 @@ $(vobjs): KBUILD_CFLAGS += $(CFL)
#
# vDSO code runs in userspace and -pg doesn't help with profiling anyway.
#
-CFLAGS_REMOVE_vdso-note.o = -pg
-CFLAGS_REMOVE_um_vdso.o = -pg
+CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage
+CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage
targets += vdso-syms.lds
obj-$(VDSO64-y) += vdso-syms.lds
diff --git a/arch/um/sys-x86_64/vdso/checkundef.sh b/arch/x86/um/vdso/checkundef.sh
index 7ee90a9b549d..7ee90a9b549d 100644
--- a/arch/um/sys-x86_64/vdso/checkundef.sh
+++ b/arch/x86/um/vdso/checkundef.sh
diff --git a/arch/um/sys-x86_64/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c
index 7c441b59d375..7c441b59d375 100644
--- a/arch/um/sys-x86_64/vdso/um_vdso.c
+++ b/arch/x86/um/vdso/um_vdso.c
diff --git a/arch/um/sys-x86_64/vdso/vdso-layout.lds.S b/arch/x86/um/vdso/vdso-layout.lds.S
index 634a2cf62046..634a2cf62046 100644
--- a/arch/um/sys-x86_64/vdso/vdso-layout.lds.S
+++ b/arch/x86/um/vdso/vdso-layout.lds.S
diff --git a/arch/um/sys-x86_64/vdso/vdso-note.S b/arch/x86/um/vdso/vdso-note.S
index 79a071e4357e..79a071e4357e 100644
--- a/arch/um/sys-x86_64/vdso/vdso-note.S
+++ b/arch/x86/um/vdso/vdso-note.S
diff --git a/arch/um/sys-x86_64/vdso/vdso.S b/arch/x86/um/vdso/vdso.S
index ec82c1686bd6..1cb468adacbb 100644
--- a/arch/um/sys-x86_64/vdso/vdso.S
+++ b/arch/x86/um/vdso/vdso.S
@@ -4,7 +4,7 @@ __INITDATA
.globl vdso_start, vdso_end
vdso_start:
- .incbin "arch/um/sys-x86_64/vdso/vdso.so"
+ .incbin "arch/x86/um/vdso/vdso.so"
vdso_end:
__FINIT
diff --git a/arch/um/sys-x86_64/vdso/vdso.lds.S b/arch/x86/um/vdso/vdso.lds.S
index b96b2677cad8..b96b2677cad8 100644
--- a/arch/um/sys-x86_64/vdso/vdso.lds.S
+++ b/arch/x86/um/vdso/vdso.lds.S
diff --git a/arch/um/sys-x86_64/vdso/vma.c b/arch/x86/um/vdso/vma.c
index 9495c8d0ce37..91f4ec9a0a56 100644
--- a/arch/um/sys-x86_64/vdso/vma.c
+++ b/arch/x86/um/vdso/vma.c
@@ -28,7 +28,7 @@ static int __init init_vdso(void)
um_vdso_addr = task_size - PAGE_SIZE;
- vdsop = kmalloc(GFP_KERNEL, sizeof(struct page *));
+ vdsop = kmalloc(sizeof(struct page *), GFP_KERNEL);
if (!vdsop)
goto oom;
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 079c08808d8a..e7a5750a93d9 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -8,10 +8,13 @@
#include <linux/scatterlist.h>
#include <linux/string_helpers.h>
#include <scsi/scsi_cmnd.h>
+#include <linux/idr.h>
#define PART_BITS 4
-static int major, index;
+static int major;
+static DEFINE_IDA(vd_index_ida);
+
struct workqueue_struct *virtblk_wq;
struct virtio_blk
@@ -35,6 +38,9 @@ struct virtio_blk
/* What host tells us, plus 2 for header & tailer. */
unsigned int sg_elems;
+ /* Ida index - used to track minor number allocations. */
+ int index;
+
/* Scatterlist: can be too big for stack. */
struct scatterlist sg[/*sg_elems*/];
};
@@ -276,6 +282,11 @@ static int index_to_minor(int index)
return index << PART_BITS;
}
+static int minor_to_index(int minor)
+{
+ return minor >> PART_BITS;
+}
+
static ssize_t virtblk_serial_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -341,14 +352,17 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
{
struct virtio_blk *vblk;
struct request_queue *q;
- int err;
+ int err, index;
u64 cap;
u32 v, blk_size, sg_elems, opt_io_size;
u16 min_io_size;
u8 physical_block_exp, alignment_offset;
- if (index_to_minor(index) >= 1 << MINORBITS)
- return -ENOSPC;
+ err = ida_simple_get(&vd_index_ida, 0, minor_to_index(1 << MINORBITS),
+ GFP_KERNEL);
+ if (err < 0)
+ goto out;
+ index = err;
/* We need to know how many segments before we allocate. */
err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX,
@@ -365,7 +379,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
sizeof(vblk->sg[0]) * sg_elems, GFP_KERNEL);
if (!vblk) {
err = -ENOMEM;
- goto out;
+ goto out_free_index;
}
INIT_LIST_HEAD(&vblk->reqs);
@@ -421,7 +435,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
vblk->disk->private_data = vblk;
vblk->disk->fops = &virtblk_fops;
vblk->disk->driverfs_dev = &vdev->dev;
- index++;
+ vblk->index = index;
/* configure queue flush support */
if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
@@ -516,6 +530,8 @@ out_free_vq:
vdev->config->del_vqs(vdev);
out_free_vblk:
kfree(vblk);
+out_free_index:
+ ida_simple_remove(&vd_index_ida, index);
out:
return err;
}
@@ -523,6 +539,7 @@ out:
static void __devexit virtblk_remove(struct virtio_device *vdev)
{
struct virtio_blk *vblk = vdev->priv;
+ int index = vblk->index;
flush_work(&vblk->config_work);
@@ -538,6 +555,7 @@ static void __devexit virtblk_remove(struct virtio_device *vdev)
mempool_destroy(vblk->pool);
vdev->config->del_vqs(vdev);
kfree(vblk);
+ ida_simple_remove(&vd_index_ida, index);
}
static const struct virtio_device_id id_table[] = {
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 423fd56bf612..43643033a3ae 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -298,7 +298,7 @@ if RTC_LIB=n
config RTC
tristate "Enhanced Real Time Clock Support (legacy PC RTC driver)"
depends on !PPC && !PARISC && !IA64 && !M68K && !SPARC && !FRV \
- && !ARM && !SUPERH && !S390 && !AVR32 && !BLACKFIN
+ && !ARM && !SUPERH && !S390 && !AVR32 && !BLACKFIN && !UML
---help---
If you say Y here and create a character special file /dev/rtc with
major number 10 and minor number 135 using mknod ("man mknod"), you
@@ -346,7 +346,7 @@ config JS_RTC
config GEN_RTC
tristate "Generic /dev/rtc emulation"
- depends on RTC!=y && !IA64 && !ARM && !M32R && !MIPS && !SPARC && !FRV && !S390 && !SUPERH && !AVR32 && !BLACKFIN
+ depends on RTC!=y && !IA64 && !ARM && !M32R && !MIPS && !SPARC && !FRV && !S390 && !SUPERH && !AVR32 && !BLACKFIN && !UML
---help---
If you say Y here and create a character special file /dev/rtc with
major number 10 and minor number 135 using mknod ("man mknod"), you
@@ -490,7 +490,7 @@ config SCx200_GPIO
config PC8736x_GPIO
tristate "NatSemi PC8736x GPIO Support"
- depends on X86_32
+ depends on X86_32 && !UML
default SCx200_GPIO # mostly N
select NSC_GPIO # needed for support routines
help
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index e0135873ba9d..0689bf6b0183 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -235,3 +235,18 @@ config HW_RANDOM_PPC4XX
module will be called ppc4xx-rng.
If unsure, say N.
+
+config UML_RANDOM
+ depends on UML
+ tristate "Hardware random number generator"
+ help
+ This option enables UML's "hardware" random number generator. It
+ attaches itself to the host's /dev/random, supplying as much entropy
+ as the host has, rather than the small amount the UML gets from its
+ own drivers. It registers itself as a standard hardware random number
+ generator, major 10, minor 183, and the canonical device name is
+ /dev/hwrng.
+ The way to make use of this is to install the rng-tools package
+ (check your distro, or download from
+ http://sourceforge.net/projects/gkernel/). rngd periodically reads
+ /dev/hwrng and injects the entropy into /dev/random.
diff --git a/drivers/char/ttyprintk.c b/drivers/char/ttyprintk.c
index a1f68af4ccf4..f22861511909 100644
--- a/drivers/char/ttyprintk.c
+++ b/drivers/char/ttyprintk.c
@@ -170,7 +170,7 @@ static const struct tty_operations ttyprintk_ops = {
.ioctl = tpk_ioctl,
};
-struct tty_port_operations null_ops = { };
+static struct tty_port_operations null_ops = { };
static struct tty_driver *ttyprintk_driver;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index fb68b1295373..4ca181f1378b 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -19,8 +19,10 @@
*/
#include <linux/cdev.h>
#include <linux/debugfs.h>
+#include <linux/completion.h>
#include <linux/device.h>
#include <linux/err.h>
+#include <linux/freezer.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/list.h>
@@ -73,6 +75,7 @@ struct ports_driver_data {
static struct ports_driver_data pdrvdata;
DEFINE_SPINLOCK(pdrvdata_lock);
+DECLARE_COMPLETION(early_console_added);
/* This struct holds information that's relevant only for console ports */
struct console {
@@ -151,6 +154,10 @@ struct ports_device {
int chr_major;
};
+struct port_stats {
+ unsigned long bytes_sent, bytes_received, bytes_discarded;
+};
+
/* This struct holds the per-port data */
struct port {
/* Next port in the list, head is in the ports_device */
@@ -179,6 +186,13 @@ struct port {
struct dentry *debugfs_file;
/*
+ * Keep count of the bytes sent, received and discarded for
+ * this port for accounting and debugging purposes. These
+ * counts are not reset across port open / close events.
+ */
+ struct port_stats stats;
+
+ /*
* The entries in this struct will be valid if this port is
* hooked up to an hvc console
*/
@@ -347,17 +361,19 @@ fail:
}
/* Callers should take appropriate locks */
-static void *get_inbuf(struct port *port)
+static struct port_buffer *get_inbuf(struct port *port)
{
struct port_buffer *buf;
- struct virtqueue *vq;
unsigned int len;
- vq = port->in_vq;
- buf = virtqueue_get_buf(vq, &len);
+ if (port->inbuf)
+ return port->inbuf;
+
+ buf = virtqueue_get_buf(port->in_vq, &len);
if (buf) {
buf->len = len;
buf->offset = 0;
+ port->stats.bytes_received += len;
}
return buf;
}
@@ -384,32 +400,27 @@ static int add_inbuf(struct virtqueue *vq, struct port_buffer *buf)
static void discard_port_data(struct port *port)
{
struct port_buffer *buf;
- struct virtqueue *vq;
- unsigned int len;
- int ret;
+ unsigned int err;
if (!port->portdev) {
/* Device has been unplugged. vqs are already gone. */
return;
}
- vq = port->in_vq;
- if (port->inbuf)
- buf = port->inbuf;
- else
- buf = virtqueue_get_buf(vq, &len);
+ buf = get_inbuf(port);
- ret = 0;
+ err = 0;
while (buf) {
- if (add_inbuf(vq, buf) < 0) {
- ret++;
+ port->stats.bytes_discarded += buf->len - buf->offset;
+ if (add_inbuf(port->in_vq, buf) < 0) {
+ err++;
free_buf(buf);
}
- buf = virtqueue_get_buf(vq, &len);
+ port->inbuf = NULL;
+ buf = get_inbuf(port);
}
- port->inbuf = NULL;
- if (ret)
+ if (err)
dev_warn(port->dev, "Errors adding %d buffers back to vq\n",
- ret);
+ err);
}
static bool port_has_data(struct port *port)
@@ -417,18 +428,12 @@ static bool port_has_data(struct port *port)
unsigned long flags;
bool ret;
+ ret = false;
spin_lock_irqsave(&port->inbuf_lock, flags);
- if (port->inbuf) {
- ret = true;
- goto out;
- }
port->inbuf = get_inbuf(port);
- if (port->inbuf) {
+ if (port->inbuf)
ret = true;
- goto out;
- }
- ret = false;
-out:
+
spin_unlock_irqrestore(&port->inbuf_lock, flags);
return ret;
}
@@ -529,6 +534,8 @@ static ssize_t send_buf(struct port *port, void *in_buf, size_t in_count,
cpu_relax();
done:
spin_unlock_irqrestore(&port->outvq_lock, flags);
+
+ port->stats.bytes_sent += in_count;
/*
* We're expected to return the amount of data we wrote -- all
* of it
@@ -633,8 +640,8 @@ static ssize_t port_fops_read(struct file *filp, char __user *ubuf,
if (filp->f_flags & O_NONBLOCK)
return -EAGAIN;
- ret = wait_event_interruptible(port->waitqueue,
- !will_read_block(port));
+ ret = wait_event_freezable(port->waitqueue,
+ !will_read_block(port));
if (ret < 0)
return ret;
}
@@ -677,8 +684,8 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
if (nonblock)
return -EAGAIN;
- ret = wait_event_interruptible(port->waitqueue,
- !will_write_block(port));
+ ret = wait_event_freezable(port->waitqueue,
+ !will_write_block(port));
if (ret < 0)
return ret;
}
@@ -1059,6 +1066,14 @@ static ssize_t debugfs_read(struct file *filp, char __user *ubuf,
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"outvq_full: %d\n", port->outvq_full);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "bytes_sent: %lu\n", port->stats.bytes_sent);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "bytes_received: %lu\n",
+ port->stats.bytes_received);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "bytes_discarded: %lu\n",
+ port->stats.bytes_discarded);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
"is_console: %s\n",
is_console_port(port) ? "yes" : "no");
out_offset += snprintf(buf + out_offset, out_count - out_offset,
@@ -1143,6 +1158,7 @@ static int add_port(struct ports_device *portdev, u32 id)
port->cons.ws.ws_row = port->cons.ws.ws_col = 0;
port->host_connected = port->guest_connected = false;
+ port->stats = (struct port_stats) { 0 };
port->outvq_full = false;
@@ -1352,6 +1368,7 @@ static void handle_control_message(struct ports_device *portdev,
break;
init_port_console(port);
+ complete(&early_console_added);
/*
* Could remove the port here in case init fails - but
* have to notify the host first.
@@ -1394,6 +1411,13 @@ static void handle_control_message(struct ports_device *portdev,
break;
case VIRTIO_CONSOLE_PORT_NAME:
/*
+ * If we woke up after hibernation, we can get this
+ * again. Skip it in that case.
+ */
+ if (port->name)
+ break;
+
+ /*
* Skip the size of the header and the cpkt to get the size
* of the name that was sent
*/
@@ -1481,8 +1505,7 @@ static void in_intr(struct virtqueue *vq)
return;
spin_lock_irqsave(&port->inbuf_lock, flags);
- if (!port->inbuf)
- port->inbuf = get_inbuf(port);
+ port->inbuf = get_inbuf(port);
/*
* Don't queue up data when port is closed. This condition
@@ -1563,7 +1586,7 @@ static int init_vqs(struct ports_device *portdev)
portdev->out_vqs = kmalloc(nr_ports * sizeof(struct virtqueue *),
GFP_KERNEL);
if (!vqs || !io_callbacks || !io_names || !portdev->in_vqs ||
- !portdev->out_vqs) {
+ !portdev->out_vqs) {
err = -ENOMEM;
goto free;
}
@@ -1648,6 +1671,10 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
struct ports_device *portdev;
int err;
bool multiport;
+ bool early = early_put_chars != NULL;
+
+ /* Ensure to read early_put_chars now */
+ barrier();
portdev = kmalloc(sizeof(*portdev), GFP_KERNEL);
if (!portdev) {
@@ -1675,13 +1702,11 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
multiport = false;
portdev->config.max_nr_ports = 1;
- if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) {
+ if (virtio_config_val(vdev, VIRTIO_CONSOLE_F_MULTIPORT,
+ offsetof(struct virtio_console_config,
+ max_nr_ports),
+ &portdev->config.max_nr_ports) == 0)
multiport = true;
- vdev->config->get(vdev, offsetof(struct virtio_console_config,
- max_nr_ports),
- &portdev->config.max_nr_ports,
- sizeof(portdev->config.max_nr_ports));
- }
err = init_vqs(portdev);
if (err < 0) {
@@ -1719,6 +1744,19 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
VIRTIO_CONSOLE_DEVICE_READY, 1);
+
+ /*
+ * If there was an early virtio console, assume that there are no
+ * other consoles. We need to wait until the hvc_alloc matches the
+ * hvc_instantiate, otherwise tty_open will complain, resulting in
+ * a "Warning: unable to open an initial console" boot failure.
+ * Without multiport this is done in add_port above. With multiport
+ * this might take some host<->guest communication - thus we have to
+ * wait.
+ */
+ if (multiport && early)
+ wait_for_completion(&early_console_added);
+
return 0;
free_vqs:
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index 23e82e46656d..001b147c7f95 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -3,7 +3,7 @@
#
menu "Input device support"
- depends on !S390
+ depends on !S390 && !UML
config INPUT
tristate "Generic input layer (needed for keyboard, mouse, ...)" if EXPERT
diff --git a/drivers/isdn/Kconfig b/drivers/isdn/Kconfig
index 4fb601670de3..a233ed53913a 100644
--- a/drivers/isdn/Kconfig
+++ b/drivers/isdn/Kconfig
@@ -5,7 +5,7 @@
menuconfig ISDN
bool "ISDN support"
depends on NET
- depends on !S390
+ depends on !S390 && !UML
---help---
ISDN ("Integrated Services Digital Network", called RNIS in France)
is a fully digital telephone service that can be used for voice and
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index f1af2228a1b1..61086ea3cc6b 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -1144,7 +1144,7 @@ static void mtdchar_notify_remove(struct mtd_info *mtd)
if (mtd_ino) {
/* Destroy the inode if it exists */
- mtd_ino->i_nlink = 0;
+ clear_nlink(mtd_ino);
iput(mtd_ino);
}
}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 91039ab16728..6ee8410443c4 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -925,12 +925,10 @@ static void virtnet_update_status(struct virtnet_info *vi)
{
u16 v;
- if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS))
- return;
-
- vi->vdev->config->get(vi->vdev,
+ if (virtio_config_val(vi->vdev, VIRTIO_NET_F_STATUS,
offsetof(struct virtio_net_config, status),
- &v, sizeof(v));
+ &v) < 0)
+ return;
/* Ignore unknown (future) status bits */
v &= VIRTIO_NET_S_LINK_UP;
@@ -1006,11 +1004,9 @@ static int virtnet_probe(struct virtio_device *vdev)
}
/* Configuration may specify what MAC to use. Otherwise random. */
- if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) {
- vdev->config->get(vdev,
+ if (virtio_config_val_len(vdev, VIRTIO_NET_F_MAC,
offsetof(struct virtio_net_config, mac),
- dev->dev_addr, dev->addr_len);
- } else
+ dev->dev_addr, dev->addr_len) < 0)
random_ether_addr(dev->dev_addr);
/* Set up our device-specific information */
diff --git a/drivers/net/wireless/ath/Kconfig b/drivers/net/wireless/ath/Kconfig
index 073548836413..09602241901b 100644
--- a/drivers/net/wireless/ath/Kconfig
+++ b/drivers/net/wireless/ath/Kconfig
@@ -1,6 +1,6 @@
menuconfig ATH_COMMON
tristate "Atheros Wireless Cards"
- depends on CFG80211
+ depends on CFG80211 && (!UML || BROKEN)
---help---
This will enable the support for the Atheros wireless drivers.
ath5k, ath9k, ath9k_htc and ar9170 drivers share some common code, this option
diff --git a/drivers/net/wireless/rtlwifi/Kconfig b/drivers/net/wireless/rtlwifi/Kconfig
index 45e14760c16e..d6c42e69bdbd 100644
--- a/drivers/net/wireless/rtlwifi/Kconfig
+++ b/drivers/net/wireless/rtlwifi/Kconfig
@@ -12,7 +12,7 @@ config RTL8192CE
config RTL8192SE
tristate "Realtek RTL8192SE/RTL8191SE PCIe Wireless Network Adapter"
- depends on MAC80211 && EXPERIMENTAL
+ depends on MAC80211 && EXPERIMENTAL && PCI
select FW_LOADER
select RTLWIFI
---help---
@@ -23,7 +23,7 @@ config RTL8192SE
config RTL8192DE
tristate "Realtek RTL8192DE/RTL8188DE PCIe Wireless Network Adapter"
- depends on MAC80211 && EXPERIMENTAL
+ depends on MAC80211 && EXPERIMENTAL && PCI
select FW_LOADER
select RTLWIFI
---help---
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 57de051a74b3..9f88641e67f9 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -70,6 +70,7 @@ config BATTERY_DS2760
config BATTERY_DS2780
tristate "DS2780 battery driver"
+ depends on HAS_IOMEM
select W1
select W1_SLAVE_DS2780
help
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 5a538fc1cc85..53eb4e55b289 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -8,7 +8,7 @@ config RTC_LIB
menuconfig RTC_CLASS
bool "Real Time Clock"
default n
- depends on !S390
+ depends on !S390 && !UML
select RTC_LIB
help
Generic RTC class support. If you say yes here, you will
diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c
index f3c6060c96b8..7a1955583b7d 100644
--- a/drivers/staging/pohmelfs/inode.c
+++ b/drivers/staging/pohmelfs/inode.c
@@ -1197,7 +1197,7 @@ const struct inode_operations pohmelfs_file_inode_operations = {
void pohmelfs_fill_inode(struct inode *inode, struct netfs_inode_info *info)
{
inode->i_mode = info->mode;
- inode->i_nlink = info->nlink;
+ set_nlink(inode, info->nlink);
inode->i_uid = info->uid;
inode->i_gid = info->gid;
inode->i_blocks = info->blocks;
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 8816f53e004d..b3d17416d86a 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -1,6 +1,6 @@
config VT
bool "Virtual terminal" if EXPERT
- depends on !S390
+ depends on !S390 && !UML
select INPUT
default y
---help---
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 57e493b1bd20..816ed08e7cf3 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -35,4 +35,15 @@ config VIRTIO_BALLOON
If unsure, say M.
+ config VIRTIO_MMIO
+ tristate "Platform bus driver for memory mapped virtio devices (EXPERIMENTAL)"
+ depends on EXPERIMENTAL
+ select VIRTIO
+ select VIRTIO_RING
+ ---help---
+ This drivers provides support for memory mapped virtio
+ platform device driver.
+
+ If unsure, say N.
+
endmenu
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 6738c446c199..5a4c63cfd380 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,4 +1,5 @@
obj-$(CONFIG_VIRTIO) += virtio.o
obj-$(CONFIG_VIRTIO_RING) += virtio_ring.o
+obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
new file mode 100644
index 000000000000..acc5e43c373e
--- /dev/null
+++ b/drivers/virtio/virtio_mmio.c
@@ -0,0 +1,479 @@
+/*
+ * Virtio memory mapped device driver
+ *
+ * Copyright 2011, ARM Ltd.
+ *
+ * This module allows virtio devices to be used over a virtual, memory mapped
+ * platform device.
+ *
+ * Registers layout (all 32-bit wide):
+ *
+ * offset d. name description
+ * ------ -- ---------------- -----------------
+ *
+ * 0x000 R MagicValue Magic value "virt"
+ * 0x004 R Version Device version (current max. 1)
+ * 0x008 R DeviceID Virtio device ID
+ * 0x00c R VendorID Virtio vendor ID
+ *
+ * 0x010 R HostFeatures Features supported by the host
+ * 0x014 W HostFeaturesSel Set of host features to access via HostFeatures
+ *
+ * 0x020 W GuestFeatures Features activated by the guest
+ * 0x024 W GuestFeaturesSel Set of activated features to set via GuestFeatures
+ * 0x028 W GuestPageSize Size of guest's memory page in bytes
+ *
+ * 0x030 W QueueSel Queue selector
+ * 0x034 R QueueNumMax Maximum size of the currently selected queue
+ * 0x038 W QueueNum Queue size for the currently selected queue
+ * 0x03c W QueueAlign Used Ring alignment for the current queue
+ * 0x040 RW QueuePFN PFN for the currently selected queue
+ *
+ * 0x050 W QueueNotify Queue notifier
+ * 0x060 R InterruptStatus Interrupt status register
+ * 0x060 W InterruptACK Interrupt acknowledge register
+ * 0x070 RW Status Device status register
+ *
+ * 0x100+ RW Device-specific configuration space
+ *
+ * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include <linux/highmem.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_mmio.h>
+#include <linux/virtio_ring.h>
+
+
+
+/* The alignment to use between consumer and producer parts of vring.
+ * Currently hardcoded to the page size. */
+#define VIRTIO_MMIO_VRING_ALIGN PAGE_SIZE
+
+
+
+#define to_virtio_mmio_device(_plat_dev) \
+ container_of(_plat_dev, struct virtio_mmio_device, vdev)
+
+struct virtio_mmio_device {
+ struct virtio_device vdev;
+ struct platform_device *pdev;
+
+ void __iomem *base;
+ unsigned long version;
+
+ /* a list of queues so we can dispatch IRQs */
+ spinlock_t lock;
+ struct list_head virtqueues;
+};
+
+struct virtio_mmio_vq_info {
+ /* the actual virtqueue */
+ struct virtqueue *vq;
+
+ /* the number of entries in the queue */
+ unsigned int num;
+
+ /* the index of the queue */
+ int queue_index;
+
+ /* the virtual address of the ring queue */
+ void *queue;
+
+ /* the list node for the virtqueues list */
+ struct list_head node;
+};
+
+
+
+/* Configuration interface */
+
+static u32 vm_get_features(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+ /* TODO: Features > 32 bits */
+ writel(0, vm_dev->base + VIRTIO_MMIO_HOST_FEATURES_SEL);
+
+ return readl(vm_dev->base + VIRTIO_MMIO_HOST_FEATURES);
+}
+
+static void vm_finalize_features(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ int i;
+
+ /* Give virtio_ring a chance to accept features. */
+ vring_transport_features(vdev);
+
+ for (i = 0; i < ARRAY_SIZE(vdev->features); i++) {
+ writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SET);
+ writel(vdev->features[i],
+ vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
+ }
+}
+
+static void vm_get(struct virtio_device *vdev, unsigned offset,
+ void *buf, unsigned len)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ ptr[i] = readb(vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static void vm_set(struct virtio_device *vdev, unsigned offset,
+ const void *buf, unsigned len)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ const u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ writeb(ptr[i], vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static u8 vm_get_status(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+ return readl(vm_dev->base + VIRTIO_MMIO_STATUS) & 0xff;
+}
+
+static void vm_set_status(struct virtio_device *vdev, u8 status)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+ /* We should never be setting status to 0. */
+ BUG_ON(status == 0);
+
+ writel(status, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+static void vm_reset(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+ /* 0 status means a reset. */
+ writel(0, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+
+
+/* Transport interface */
+
+/* the notify function used when creating a virt queue */
+static void vm_notify(struct virtqueue *vq)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+ struct virtio_mmio_vq_info *info = vq->priv;
+
+ /* We write the queue's selector into the notification register to
+ * signal the other end */
+ writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+}
+
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vm_interrupt(int irq, void *opaque)
+{
+ struct virtio_mmio_device *vm_dev = opaque;
+ struct virtio_mmio_vq_info *info;
+ struct virtio_driver *vdrv = container_of(vm_dev->vdev.dev.driver,
+ struct virtio_driver, driver);
+ unsigned long status;
+ unsigned long flags;
+ irqreturn_t ret = IRQ_NONE;
+
+ /* Read and acknowledge interrupts */
+ status = readl(vm_dev->base + VIRTIO_MMIO_INTERRUPT_STATUS);
+ writel(status, vm_dev->base + VIRTIO_MMIO_INTERRUPT_ACK);
+
+ if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)
+ && vdrv && vdrv->config_changed) {
+ vdrv->config_changed(&vm_dev->vdev);
+ ret = IRQ_HANDLED;
+ }
+
+ if (likely(status & VIRTIO_MMIO_INT_VRING)) {
+ spin_lock_irqsave(&vm_dev->lock, flags);
+ list_for_each_entry(info, &vm_dev->virtqueues, node)
+ ret |= vring_interrupt(irq, info->vq);
+ spin_unlock_irqrestore(&vm_dev->lock, flags);
+ }
+
+ return ret;
+}
+
+
+
+static void vm_del_vq(struct virtqueue *vq)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+ struct virtio_mmio_vq_info *info = vq->priv;
+ unsigned long flags, size;
+
+ spin_lock_irqsave(&vm_dev->lock, flags);
+ list_del(&info->node);
+ spin_unlock_irqrestore(&vm_dev->lock, flags);
+
+ vring_del_virtqueue(vq);
+
+ /* Select and deactivate the queue */
+ writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+ writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+
+ size = PAGE_ALIGN(vring_size(info->num, VIRTIO_MMIO_VRING_ALIGN));
+ free_pages_exact(info->queue, size);
+ kfree(info);
+}
+
+static void vm_del_vqs(struct virtio_device *vdev)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ struct virtqueue *vq, *n;
+
+ list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+ vm_del_vq(vq);
+
+ free_irq(platform_get_irq(vm_dev->pdev, 0), vm_dev);
+}
+
+
+
+static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
+ void (*callback)(struct virtqueue *vq),
+ const char *name)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ struct virtio_mmio_vq_info *info;
+ struct virtqueue *vq;
+ unsigned long flags, size;
+ int err;
+
+ /* Select the queue we're interested in */
+ writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+
+ /* Queue shouldn't already be set up. */
+ if (readl(vm_dev->base + VIRTIO_MMIO_QUEUE_PFN)) {
+ err = -ENOENT;
+ goto error_available;
+ }
+
+ /* Allocate and fill out our active queue description */
+ info = kmalloc(sizeof(*info), GFP_KERNEL);
+ if (!info) {
+ err = -ENOMEM;
+ goto error_kmalloc;
+ }
+ info->queue_index = index;
+
+ /* Allocate pages for the queue - start with a queue as big as
+ * possible (limited by maximum size allowed by device), drop down
+ * to a minimal size, just big enough to fit descriptor table
+ * and two rings (which makes it "alignment_size * 2")
+ */
+ info->num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX);
+ while (1) {
+ size = PAGE_ALIGN(vring_size(info->num,
+ VIRTIO_MMIO_VRING_ALIGN));
+ /* Already smallest possible allocation? */
+ if (size <= VIRTIO_MMIO_VRING_ALIGN * 2) {
+ err = -ENOMEM;
+ goto error_alloc_pages;
+ }
+
+ info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+ if (info->queue)
+ break;
+
+ info->num /= 2;
+ }
+
+ /* Activate the queue */
+ writel(info->num, vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
+ writel(VIRTIO_MMIO_VRING_ALIGN,
+ vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
+ writel(virt_to_phys(info->queue) >> PAGE_SHIFT,
+ vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+
+ /* Create the vring */
+ vq = vring_new_virtqueue(info->num, VIRTIO_MMIO_VRING_ALIGN,
+ vdev, info->queue, vm_notify, callback, name);
+ if (!vq) {
+ err = -ENOMEM;
+ goto error_new_virtqueue;
+ }
+
+ vq->priv = info;
+ info->vq = vq;
+
+ spin_lock_irqsave(&vm_dev->lock, flags);
+ list_add(&info->node, &vm_dev->virtqueues);
+ spin_unlock_irqrestore(&vm_dev->lock, flags);
+
+ return vq;
+
+error_new_virtqueue:
+ writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+ free_pages_exact(info->queue, size);
+error_alloc_pages:
+ kfree(info);
+error_kmalloc:
+error_available:
+ return ERR_PTR(err);
+}
+
+static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char *names[])
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
+ int i, err;
+
+ err = request_irq(irq, vm_interrupt, IRQF_SHARED,
+ dev_name(&vdev->dev), vm_dev);
+ if (err)
+ return err;
+
+ for (i = 0; i < nvqs; ++i) {
+ vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i]);
+ if (IS_ERR(vqs[i])) {
+ vm_del_vqs(vdev);
+ return PTR_ERR(vqs[i]);
+ }
+ }
+
+ return 0;
+}
+
+
+
+static struct virtio_config_ops virtio_mmio_config_ops = {
+ .get = vm_get,
+ .set = vm_set,
+ .get_status = vm_get_status,
+ .set_status = vm_set_status,
+ .reset = vm_reset,
+ .find_vqs = vm_find_vqs,
+ .del_vqs = vm_del_vqs,
+ .get_features = vm_get_features,
+ .finalize_features = vm_finalize_features,
+};
+
+
+
+/* Platform device */
+
+static int __devinit virtio_mmio_probe(struct platform_device *pdev)
+{
+ struct virtio_mmio_device *vm_dev;
+ struct resource *mem;
+ unsigned long magic;
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!mem)
+ return -EINVAL;
+
+ if (!devm_request_mem_region(&pdev->dev, mem->start,
+ resource_size(mem), pdev->name))
+ return -EBUSY;
+
+ vm_dev = devm_kzalloc(&pdev->dev, sizeof(*vm_dev), GFP_KERNEL);
+ if (!vm_dev)
+ return -ENOMEM;
+
+ vm_dev->vdev.dev.parent = &pdev->dev;
+ vm_dev->vdev.config = &virtio_mmio_config_ops;
+ vm_dev->pdev = pdev;
+ INIT_LIST_HEAD(&vm_dev->virtqueues);
+ spin_lock_init(&vm_dev->lock);
+
+ vm_dev->base = devm_ioremap(&pdev->dev, mem->start, resource_size(mem));
+ if (vm_dev->base == NULL)
+ return -EFAULT;
+
+ /* Check magic value */
+ magic = readl(vm_dev->base + VIRTIO_MMIO_MAGIC_VALUE);
+ if (memcmp(&magic, "virt", 4) != 0) {
+ dev_warn(&pdev->dev, "Wrong magic value 0x%08lx!\n", magic);
+ return -ENODEV;
+ }
+
+ /* Check device version */
+ vm_dev->version = readl(vm_dev->base + VIRTIO_MMIO_VERSION);
+ if (vm_dev->version != 1) {
+ dev_err(&pdev->dev, "Version %ld not supported!\n",
+ vm_dev->version);
+ return -ENXIO;
+ }
+
+ vm_dev->vdev.id.device = readl(vm_dev->base + VIRTIO_MMIO_DEVICE_ID);
+ vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID);
+
+ writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+
+ platform_set_drvdata(pdev, vm_dev);
+
+ return register_virtio_device(&vm_dev->vdev);
+}
+
+static int __devexit virtio_mmio_remove(struct platform_device *pdev)
+{
+ struct virtio_mmio_device *vm_dev = platform_get_drvdata(pdev);
+
+ unregister_virtio_device(&vm_dev->vdev);
+
+ return 0;
+}
+
+
+
+/* Platform driver */
+
+static struct of_device_id virtio_mmio_match[] = {
+ { .compatible = "virtio,mmio", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, virtio_mmio_match);
+
+static struct platform_driver virtio_mmio_driver = {
+ .probe = virtio_mmio_probe,
+ .remove = __devexit_p(virtio_mmio_remove),
+ .driver = {
+ .name = "virtio-mmio",
+ .owner = THIS_MODULE,
+ .of_match_table = virtio_mmio_match,
+ },
+};
+
+static int __init virtio_mmio_init(void)
+{
+ return platform_driver_register(&virtio_mmio_driver);
+}
+
+static void __exit virtio_mmio_exit(void)
+{
+ platform_driver_unregister(&virtio_mmio_driver);
+}
+
+module_init(virtio_mmio_init);
+module_exit(virtio_mmio_exit);
+
+MODULE_AUTHOR("Pawel Moll <pawel.moll@arm.com>");
+MODULE_DESCRIPTION("Platform bus driver for memory mapped virtio devices");
+MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 4bcc8b82640b..79a31e5b4b68 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -415,9 +415,13 @@ static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
}
}
- spin_lock_irqsave(&vp_dev->lock, flags);
- list_add(&info->node, &vp_dev->virtqueues);
- spin_unlock_irqrestore(&vp_dev->lock, flags);
+ if (callback) {
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_add(&info->node, &vp_dev->virtqueues);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+ } else {
+ INIT_LIST_HEAD(&info->node);
+ }
return vq;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 86b0735e6aa0..64c6752ea2c6 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -726,7 +726,7 @@ config SBC8360_WDT
config SBC7240_WDT
tristate "SBC Nano 7240 Watchdog Timer"
- depends on X86_32
+ depends on X86_32 && !UML
---help---
This is the driver for the hardware watchdog found on the IEI
single board computers EPIC Nano 7240 (and likely others). This
@@ -1174,6 +1174,10 @@ config XEN_WDT
by Xen 4.0 and newer. The watchdog timeout period is normally one
minute but can be changed with a boot-time parameter.
+config UML_WATCHDOG
+ tristate "UML watchdog"
+ depends on UML
+
#
# ISA-based Watchdog Cards
#
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index b5a1076aaa6c..879ed8851737 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1138,7 +1138,7 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
struct v9fs_session_info *v9ses = sb->s_fs_info;
struct v9fs_inode *v9inode = V9FS_I(inode);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_atime.tv_sec = stat->atime;
inode->i_mtime.tv_sec = stat->mtime;
@@ -1164,7 +1164,7 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
/* HARDLINKCOUNT %u */
sscanf(ext, "%13s %u", tag_name, &i_nlink);
if (!strncmp(tag_name, "HARDLINKCOUNT", 13))
- inode->i_nlink = i_nlink;
+ set_nlink(inode, i_nlink);
}
}
mode = stat->mode & S_IALLUGO;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index aded79fcd5cf..0b5745e21946 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -606,7 +606,7 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode)
inode->i_ctime.tv_nsec = stat->st_ctime_nsec;
inode->i_uid = stat->st_uid;
inode->i_gid = stat->st_gid;
- inode->i_nlink = stat->st_nlink;
+ set_nlink(inode, stat->st_nlink);
mode = stat->st_mode & S_IALLUGO;
mode |= inode->i_mode & ~S_IALLUGO;
@@ -632,7 +632,7 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode)
if (stat->st_result_mask & P9_STATS_GID)
inode->i_gid = stat->st_gid;
if (stat->st_result_mask & P9_STATS_NLINK)
- inode->i_nlink = stat->st_nlink;
+ set_nlink(inode, stat->st_nlink);
if (stat->st_result_mask & P9_STATS_MODE) {
inode->i_mode = stat->st_mode;
if ((S_ISBLK(inode->i_mode)) ||
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index d5250c5aae21..1dab6a174d6a 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -247,7 +247,7 @@ adfs_iget(struct super_block *sb, struct object_info *obj)
inode->i_gid = ADFS_SB(sb)->s_gid;
inode->i_ino = obj->file_id;
inode->i_size = obj->size;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_blocks = (inode->i_size + sb->s_blocksize - 1) >>
sb->s_blocksize_bits;
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 3a4557e8325c..de37ec842340 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -215,7 +215,7 @@ affs_remove_link(struct dentry *dentry)
break;
default:
if (!AFFS_TAIL(sb, bh)->link_chain)
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
affs_free_block(sb, link_ino);
goto done;
@@ -316,7 +316,7 @@ affs_remove_header(struct dentry *dentry)
if (inode->i_nlink > 1)
retval = affs_remove_link(dentry);
else
- inode->i_nlink = 0;
+ clear_nlink(inode);
affs_unlock_link(inode);
inode->i_ctime = CURRENT_TIME_SEC;
mark_inode_dirty(inode);
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 5d828903ac69..88a4b0b50058 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -54,7 +54,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
prot = be32_to_cpu(tail->protect);
inode->i_size = 0;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_mode = 0;
AFFS_I(inode)->i_extcnt = 1;
AFFS_I(inode)->i_ext_last = ~1;
@@ -137,7 +137,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
sbi->s_hashsize + 1;
}
if (tail->link_chain)
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_mapping->a_ops = (sbi->s_flags & SF_OFS) ? &affs_aops_ofs : &affs_aops;
inode->i_op = &affs_file_inode_operations;
inode->i_fop = &affs_file_operations;
@@ -304,7 +304,7 @@ affs_new_inode(struct inode *dir)
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
inode->i_ino = block;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
atomic_set(&AFFS_I(inode)->i_opencnt, 0);
AFFS_I(inode)->i_blkcnt = 0;
@@ -387,7 +387,7 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3
AFFS_TAIL(sb, inode_bh)->link_chain = cpu_to_be32(block);
affs_adjust_checksum(inode_bh, block - be32_to_cpu(chain));
mark_buffer_dirty_inode(inode_bh, inode);
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
ihold(inode);
}
affs_fix_checksum(sb, bh);
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index e3e9efc1fdd8..780a11dc6318 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -277,7 +277,7 @@ affs_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata
inode->i_mapping->a_ops = (AFFS_SB(sb)->s_flags & SF_OFS) ? &affs_aops_ofs : &affs_aops;
error = affs_add_entry(dir, inode, dentry, ST_FILE);
if (error) {
- inode->i_nlink = 0;
+ clear_nlink(inode);
iput(inode);
return error;
}
@@ -305,7 +305,7 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
error = affs_add_entry(dir, inode, dentry, ST_USERDIR);
if (error) {
- inode->i_nlink = 0;
+ clear_nlink(inode);
mark_inode_dirty(inode);
iput(inode);
return error;
@@ -392,7 +392,7 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
return 0;
err:
- inode->i_nlink = 0;
+ clear_nlink(inode);
mark_inode_dirty(inode);
iput(inode);
return error;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 346e3289abd7..2f213d109c21 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -90,7 +90,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
vnode->vfs_inode.i_uid = status->owner;
vnode->vfs_inode.i_gid = status->group;
vnode->vfs_inode.i_generation = vnode->fid.unique;
- vnode->vfs_inode.i_nlink = status->nlink;
+ set_nlink(&vnode->vfs_inode, status->nlink);
mode = vnode->vfs_inode.i_mode;
mode &= ~S_IALLUGO;
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 0fdab6e03d87..d890ae3b2ce6 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -67,7 +67,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
fscache_attr_changed(vnode->cache);
#endif
- inode->i_nlink = vnode->status.nlink;
+ set_nlink(inode, vnode->status.nlink);
inode->i_uid = vnode->status.owner;
inode->i_gid = 0;
inode->i_size = vnode->status.size;
@@ -174,7 +174,7 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
inode->i_size = 0;
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
inode->i_op = &afs_autocell_inode_operations;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_uid = 0;
inode->i_gid = 0;
inode->i_ctime.tv_sec = get_seconds();
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 180fa2425e49..8179f1ab8175 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -342,7 +342,7 @@ struct inode *autofs4_get_inode(struct super_block *sb, mode_t mode)
inode->i_ino = get_next_ino();
if (S_ISDIR(mode)) {
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_op = &autofs4_dir_inode_operations;
inode->i_fop = &autofs4_dir_operations;
} else if (S_ISLNK(mode)) {
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 720d885e8dca..8342ca67abcd 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -357,7 +357,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
inode->i_gid = befs_sb->mount_opts.use_gid ?
befs_sb->mount_opts.gid : (gid_t) fs32_to_cpu(sb, raw_inode->gid);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
/*
* BEFS's time is 64 bits, but current VFS is 32 bits...
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index b14cebfd9047..9cc074019479 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -199,7 +199,7 @@ static int bfs_unlink(struct inode *dir, struct dentry *dentry)
printf("unlinking non-existent file %s:%lu (nlink=%d)\n",
inode->i_sb->s_id, inode->i_ino,
inode->i_nlink);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
de->ino = 0;
mark_buffer_dirty_inode(bh, dir);
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index a8e37f81d097..697af5bf70b3 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -78,7 +78,7 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino)
BFS_I(inode)->i_dsk_ino = le16_to_cpu(di->i_ino);
inode->i_uid = le32_to_cpu(di->i_uid);
inode->i_gid = le32_to_cpu(di->i_gid);
- inode->i_nlink = le32_to_cpu(di->i_nlink);
+ set_nlink(inode, le32_to_cpu(di->i_nlink));
inode->i_size = BFS_FILESIZE(di);
inode->i_blocks = BFS_FILEBLOCKS(di);
inode->i_atime.tv_sec = le32_to_cpu(di->i_atime);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index ba1a1ae4a18a..1e9edbdeda7e 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -521,7 +521,7 @@ static void kill_node(Node *e)
write_unlock(&entries_lock);
if (dentry) {
- dentry->d_inode->i_nlink--;
+ drop_nlink(dentry->d_inode);
d_drop(dentry);
dput(dentry);
simple_release_fs(&bm_mnt, &entry_count);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index b52c672f4c18..ae4d9cd10961 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1641,7 +1641,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
inode->i_gid = btrfs_stack_inode_gid(inode_item);
btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item));
inode->i_mode = btrfs_stack_inode_mode(inode_item);
- inode->i_nlink = btrfs_stack_inode_nlink(inode_item);
+ set_nlink(inode, btrfs_stack_inode_nlink(inode_item));
inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item));
BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item);
BTRFS_I(inode)->sequence = btrfs_stack_inode_sequence(inode_item);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 07b3ac662e19..07ea91879a91 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1705,7 +1705,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
sb->s_bdi = &fs_info->bdi;
fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
- fs_info->btree_inode->i_nlink = 1;
+ set_nlink(fs_info->btree_inode, 1);
/*
* we set the i_size on the btree inode to the max possible int.
* the real end of the address space is determined by all of
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b2d004ad66a0..75686a61bd45 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2534,7 +2534,7 @@ static void btrfs_read_locked_inode(struct inode *inode)
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
inode->i_mode = btrfs_inode_mode(leaf, inode_item);
- inode->i_nlink = btrfs_inode_nlink(leaf, inode_item);
+ set_nlink(inode, btrfs_inode_nlink(leaf, inode_item));
inode->i_uid = btrfs_inode_uid(leaf, inode_item);
inode->i_gid = btrfs_inode_gid(leaf, inode_item);
btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
@@ -6728,7 +6728,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
inode->i_op = &btrfs_dir_inode_operations;
inode->i_fop = &btrfs_dir_file_operations;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
btrfs_i_size_write(inode, 0);
err = btrfs_update_inode(trans, new_root, inode);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 786639fca067..0618aa39740b 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1030,7 +1030,7 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
}
btrfs_release_path(path);
if (nlink != inode->i_nlink) {
- inode->i_nlink = nlink;
+ set_nlink(inode, nlink);
btrfs_update_inode(trans, root, inode);
}
BTRFS_I(inode)->index_cnt = (u64)-1;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b8731bf3ef1f..15b21e35078a 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2363,7 +2363,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
}
if ((issued & CEPH_CAP_LINK_EXCL) == 0)
- inode->i_nlink = le32_to_cpu(grant->nlink);
+ set_nlink(inode, le32_to_cpu(grant->nlink));
if ((issued & CEPH_CAP_XATTR_EXCL) == 0 && grant->xattr_len) {
int len = le32_to_cpu(grant->xattr_len);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 5dde7d51dc11..1616a0d37cbd 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -618,7 +618,7 @@ static int fill_inode(struct inode *inode,
}
if ((issued & CEPH_CAP_LINK_EXCL) == 0)
- inode->i_nlink = le32_to_cpu(info->nlink);
+ set_nlink(inode, le32_to_cpu(info->nlink));
/* be careful with mtime, atime, size */
ceph_decode_timespec(&atime, &info->atime);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 2c50bd2f65d1..e851d5b8931e 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -132,7 +132,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
inode->i_mtime = fattr->cf_mtime;
inode->i_ctime = fattr->cf_ctime;
inode->i_rdev = fattr->cf_rdev;
- inode->i_nlink = fattr->cf_nlink;
+ set_nlink(inode, fattr->cf_nlink);
inode->i_uid = fattr->cf_uid;
inode->i_gid = fattr->cf_gid;
@@ -905,7 +905,7 @@ struct inode *cifs_root_iget(struct super_block *sb)
if (rc && tcon->ipc) {
cFYI(1, "ipc connection - fake read inode");
inode->i_mode |= S_IFDIR;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
inode->i_op = &cifs_ipc_inode_ops;
inode->i_fop = &simple_dir_operations;
inode->i_uid = cifs_sb->mnt_uid;
@@ -1367,7 +1367,7 @@ mkdir_get_info:
/* setting nlink not necessary except in cases where we
* failed to get it from the server or was set bogus */
if ((direntry->d_inode) && (direntry->d_inode->i_nlink < 2))
- direntry->d_inode->i_nlink = 2;
+ set_nlink(direntry->d_inode, 2);
mode &= ~current_umask();
/* must turn on setgid bit if parent dir has it */
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 8693b5d0e180..6b0e06434391 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -433,7 +433,7 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
if (old_file->d_inode) {
cifsInode = CIFS_I(old_file->d_inode);
if (rc == 0) {
- old_file->d_inode->i_nlink++;
+ inc_nlink(old_file->d_inode);
/* BB should we make this contingent on superblock flag NOATIME? */
/* old_file->d_inode->i_ctime = CURRENT_TIME;*/
/* parent dir timestamps will update from srv
diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c
index 2bdbcc11b373..854ace712685 100644
--- a/fs/coda/coda_linux.c
+++ b/fs/coda/coda_linux.c
@@ -104,7 +104,7 @@ void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr)
if (attr->va_gid != -1)
inode->i_gid = (gid_t) attr->va_gid;
if (attr->va_nlink != -1)
- inode->i_nlink = attr->va_nlink;
+ set_nlink(inode, attr->va_nlink);
if (attr->va_size != -1)
inode->i_size = attr->va_size;
if (attr->va_size != -1)
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 0239433f50cb..28e7e135cfab 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -340,7 +340,7 @@ static int coda_rmdir(struct inode *dir, struct dentry *de)
if (!error) {
/* VFS may delete the child */
if (de->d_inode)
- de->d_inode->i_nlink = 0;
+ clear_nlink(de->d_inode);
/* fix the link count of the parent */
coda_dir_drop_nlink(dir);
diff --git a/fs/dcache.c b/fs/dcache.c
index a88948b8bd17..274f13e2f094 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -225,7 +225,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
}
/*
- * dentry_lru_(add|del|move_tail) must be called with d_lock held.
+ * dentry_lru_(add|del|prune|move_tail) must be called with d_lock held.
*/
static void dentry_lru_add(struct dentry *dentry)
{
@@ -245,6 +245,9 @@ static void __dentry_lru_del(struct dentry *dentry)
dentry_stat.nr_unused--;
}
+/*
+ * Remove a dentry with references from the LRU.
+ */
static void dentry_lru_del(struct dentry *dentry)
{
if (!list_empty(&dentry->d_lru)) {
@@ -254,6 +257,23 @@ static void dentry_lru_del(struct dentry *dentry)
}
}
+/*
+ * Remove a dentry that is unreferenced and about to be pruned
+ * (unhashed and destroyed) from the LRU, and inform the file system.
+ * This wrapper should be called _prior_ to unhashing a victim dentry.
+ */
+static void dentry_lru_prune(struct dentry *dentry)
+{
+ if (!list_empty(&dentry->d_lru)) {
+ if (dentry->d_flags & DCACHE_OP_PRUNE)
+ dentry->d_op->d_prune(dentry);
+
+ spin_lock(&dcache_lru_lock);
+ __dentry_lru_del(dentry);
+ spin_unlock(&dcache_lru_lock);
+ }
+}
+
static void dentry_lru_move_tail(struct dentry *dentry)
{
spin_lock(&dcache_lru_lock);
@@ -403,8 +423,12 @@ relock:
if (ref)
dentry->d_count--;
- /* if dentry was on the d_lru list delete it from there */
- dentry_lru_del(dentry);
+ /*
+ * if dentry was on the d_lru list delete it from there.
+ * inform the fs via d_prune that this dentry is about to be
+ * unhashed and destroyed.
+ */
+ dentry_lru_prune(dentry);
/* if it was on the hash then remove it */
__d_drop(dentry);
return d_kill(dentry, parent);
@@ -854,8 +878,12 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
do {
struct inode *inode;
- /* detach from the system */
- dentry_lru_del(dentry);
+ /*
+ * remove the dentry from the lru, and inform
+ * the fs that this dentry is about to be
+ * unhashed and destroyed.
+ */
+ dentry_lru_prune(dentry);
__d_shrink(dentry);
if (dentry->d_count != 0) {
@@ -1283,6 +1311,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
dentry->d_flags |= DCACHE_OP_REVALIDATE;
if (op->d_delete)
dentry->d_flags |= DCACHE_OP_DELETE;
+ if (op->d_prune)
+ dentry->d_flags |= DCACHE_OP_PRUNE;
}
EXPORT_SYMBOL(d_set_d_op);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 2f27e578d466..d5d5297efe97 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -307,7 +307,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR;
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
s->s_root = d_alloc_root(inode);
if (s->s_root)
@@ -549,7 +549,7 @@ void devpts_pty_kill(struct tty_struct *tty)
dentry = d_find_alias(inode);
- inode->i_nlink--;
+ drop_nlink(inode);
d_delete(dentry);
dput(dentry); /* d_alloc_name() in devpts_pty_new() */
dput(dentry); /* d_find_alias above */
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 11f8582d7218..a36d327f1521 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -474,8 +474,8 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
goto out_lock;
fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
- old_dentry->d_inode->i_nlink =
- ecryptfs_inode_to_lower(old_dentry->d_inode)->i_nlink;
+ set_nlink(old_dentry->d_inode,
+ ecryptfs_inode_to_lower(old_dentry->d_inode)->i_nlink);
i_size_write(new_dentry->d_inode, file_size_save);
out_lock:
unlock_dir(lower_dir_dentry);
@@ -499,8 +499,8 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry)
goto out_unlock;
}
fsstack_copy_attr_times(dir, lower_dir_inode);
- dentry->d_inode->i_nlink =
- ecryptfs_inode_to_lower(dentry->d_inode)->i_nlink;
+ set_nlink(dentry->d_inode,
+ ecryptfs_inode_to_lower(dentry->d_inode)->i_nlink);
dentry->d_inode->i_ctime = dir->i_ctime;
d_drop(dentry);
out_unlock:
@@ -565,7 +565,7 @@ static int ecryptfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
goto out;
fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
- dir->i_nlink = lower_dir_dentry->d_inode->i_nlink;
+ set_nlink(dir, lower_dir_dentry->d_inode->i_nlink);
out:
unlock_dir(lower_dir_dentry);
if (!dentry->d_inode)
@@ -588,7 +588,7 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry)
if (!rc && dentry->d_inode)
clear_nlink(dentry->d_inode);
fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
- dir->i_nlink = lower_dir_dentry->d_inode->i_nlink;
+ set_nlink(dir, lower_dir_dentry->d_inode->i_nlink);
unlock_dir(lower_dir_dentry);
if (!rc)
d_drop(dentry);
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
index 9c13412e6c99..bc84f365d75c 100644
--- a/fs/efs/inode.c
+++ b/fs/efs/inode.c
@@ -96,7 +96,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino)
efs_inode = (struct efs_dinode *) (bh->b_data + offset);
inode->i_mode = be16_to_cpu(efs_inode->di_mode);
- inode->i_nlink = be16_to_cpu(efs_inode->di_nlink);
+ set_nlink(inode, be16_to_cpu(efs_inode->di_nlink));
inode->i_uid = (uid_t)be16_to_cpu(efs_inode->di_uid);
inode->i_gid = (gid_t)be16_to_cpu(efs_inode->di_gid);
inode->i_size = be32_to_cpu(efs_inode->di_size);
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 3e5f3a6be90a..f6dbf7768ce6 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1165,7 +1165,7 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
inode->i_mode = le16_to_cpu(fcb.i_mode);
inode->i_uid = le32_to_cpu(fcb.i_uid);
inode->i_gid = le32_to_cpu(fcb.i_gid);
- inode->i_nlink = le16_to_cpu(fcb.i_links_count);
+ set_nlink(inode, le16_to_cpu(fcb.i_links_count));
inode->i_ctime.tv_sec = (signed)le32_to_cpu(fcb.i_ctime);
inode->i_atime.tv_sec = (signed)le32_to_cpu(fcb.i_atime);
inode->i_mtime.tv_sec = (signed)le32_to_cpu(fcb.i_mtime);
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 8f44cef1b3ef..a8cbe1bc6ad4 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -421,7 +421,7 @@ static inline int rsv_is_empty(struct ext2_reserve_window *rsv)
void ext2_init_block_alloc_info(struct inode *inode)
{
struct ext2_inode_info *ei = EXT2_I(inode);
- struct ext2_block_alloc_info *block_i = ei->i_block_alloc_info;
+ struct ext2_block_alloc_info *block_i;
struct super_block *sb = inode->i_sb;
block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index ee9ed31948e1..c4e81dfb74ba 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -601,7 +601,7 @@ fail_free_drop:
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
return ERR_PTR(err);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index a8a58f63f07c..91a6945af6d8 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1321,7 +1321,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
- inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+ set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
inode->i_size = le32_to_cpu(raw_inode->i_size);
inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 1dd62ed35b85..bd8ac164a3bf 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -327,10 +327,10 @@ static struct inode *ext2_nfs_get_inode(struct super_block *sb,
if (ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count))
return ERR_PTR(-ESTALE);
- /* iget isn't really right if the inode is currently unallocated!!
- * ext2_read_inode currently does appropriate checks, but
- * it might be "neater" to call ext2_get_inode first and check
- * if the inode is valid.....
+ /*
+ * ext2_iget isn't quite right if the inode is currently unallocated!
+ * However ext2_iget currently does appropriate checks to handle stale
+ * inodes so everything is OK.
*/
inode = ext2_iget(sb, ino);
if (IS_ERR(inode))
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 6386d76f44a7..a2038928f9a3 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -427,7 +427,7 @@ static inline int rsv_is_empty(struct ext3_reserve_window *rsv)
void ext3_init_block_alloc_info(struct inode *inode)
{
struct ext3_inode_info *ei = EXT3_I(inode);
- struct ext3_block_alloc_info *block_i = ei->i_block_alloc_info;
+ struct ext3_block_alloc_info *block_i;
struct super_block *sb = inode->i_sb;
block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
@@ -1440,14 +1440,14 @@ out:
*
* Check if filesystem has at least 1 free block available for allocation.
*/
-static int ext3_has_free_blocks(struct ext3_sb_info *sbi)
+static int ext3_has_free_blocks(struct ext3_sb_info *sbi, int use_reservation)
{
ext3_fsblk_t free_blocks, root_blocks;
free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
- sbi->s_resuid != current_fsuid() &&
+ !use_reservation && sbi->s_resuid != current_fsuid() &&
(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
return 0;
}
@@ -1468,7 +1468,7 @@ static int ext3_has_free_blocks(struct ext3_sb_info *sbi)
*/
int ext3_should_retry_alloc(struct super_block *sb, int *retries)
{
- if (!ext3_has_free_blocks(EXT3_SB(sb)) || (*retries)++ > 3)
+ if (!ext3_has_free_blocks(EXT3_SB(sb), 0) || (*retries)++ > 3)
return 0;
jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
@@ -1546,7 +1546,7 @@ ext3_fsblk_t ext3_new_blocks(handle_t *handle, struct inode *inode,
if (block_i && ((windowsz = block_i->rsv_window_node.rsv_goal_size) > 0))
my_rsv = &block_i->rsv_window_node;
- if (!ext3_has_free_blocks(sbi)) {
+ if (!ext3_has_free_blocks(sbi, IS_NOQUOTA(inode))) {
*errp = -ENOSPC;
goto out;
}
@@ -1924,9 +1924,10 @@ unsigned long ext3_bg_num_gdb(struct super_block *sb, int group)
* reaches any used block. Then issue a TRIM command on this extent and free
* the extent in the block bitmap. This is done until whole group is scanned.
*/
-ext3_grpblk_t ext3_trim_all_free(struct super_block *sb, unsigned int group,
- ext3_grpblk_t start, ext3_grpblk_t max,
- ext3_grpblk_t minblocks)
+static ext3_grpblk_t ext3_trim_all_free(struct super_block *sb,
+ unsigned int group,
+ ext3_grpblk_t start, ext3_grpblk_t max,
+ ext3_grpblk_t minblocks)
{
handle_t *handle;
ext3_grpblk_t next, free_blocks, bit, freed, count = 0;
diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c
index d494c554c6e6..1860ed356323 100644
--- a/fs/ext3/fsync.c
+++ b/fs/ext3/fsync.c
@@ -61,13 +61,6 @@ int ext3_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (ret)
goto out;
- /*
- * Taking the mutex here just to keep consistent with how fsync was
- * called previously, however it looks like we don't need to take
- * i_mutex at all.
- */
- mutex_lock(&inode->i_mutex);
-
J_ASSERT(ext3_journal_current_handle() == NULL);
/*
@@ -85,7 +78,6 @@ int ext3_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* safe in-journal, which is all fsync() needs to ensure.
*/
if (ext3_should_journal_data(inode)) {
- mutex_unlock(&inode->i_mutex);
ret = ext3_force_commit(inode->i_sb);
goto out;
}
@@ -108,8 +100,6 @@ int ext3_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
*/
if (needs_barrier)
blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
-
- mutex_unlock(&inode->i_mutex);
out:
trace_ext3_sync_file_exit(inode, ret);
return ret;
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index bf09cbf938cc..5c866e06e7ab 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -178,42 +178,6 @@ error_return:
}
/*
- * There are two policies for allocating an inode. If the new inode is
- * a directory, then a forward search is made for a block group with both
- * free space and a low directory-to-inode ratio; if that fails, then of
- * the groups with above-average free space, that group with the fewest
- * directories already is chosen.
- *
- * For other inodes, search forward from the parent directory\'s block
- * group to find a free inode.
- */
-static int find_group_dir(struct super_block *sb, struct inode *parent)
-{
- int ngroups = EXT3_SB(sb)->s_groups_count;
- unsigned int freei, avefreei;
- struct ext3_group_desc *desc, *best_desc = NULL;
- int group, best_group = -1;
-
- freei = percpu_counter_read_positive(&EXT3_SB(sb)->s_freeinodes_counter);
- avefreei = freei / ngroups;
-
- for (group = 0; group < ngroups; group++) {
- desc = ext3_get_group_desc (sb, group, NULL);
- if (!desc || !desc->bg_free_inodes_count)
- continue;
- if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
- continue;
- if (!best_desc ||
- (le16_to_cpu(desc->bg_free_blocks_count) >
- le16_to_cpu(best_desc->bg_free_blocks_count))) {
- best_group = group;
- best_desc = desc;
- }
- }
- return best_group;
-}
-
-/*
* Orlov's allocator for directories.
*
* We always try to spread first-level directories.
@@ -436,12 +400,9 @@ struct inode *ext3_new_inode(handle_t *handle, struct inode * dir,
sbi = EXT3_SB(sb);
es = sbi->s_es;
- if (S_ISDIR(mode)) {
- if (test_opt (sb, OLDALLOC))
- group = find_group_dir(sb, dir);
- else
- group = find_group_orlov(sb, dir);
- } else
+ if (S_ISDIR(mode))
+ group = find_group_orlov(sb, dir);
+ else
group = find_group_other(sb, dir);
err = -ENOSPC;
@@ -621,7 +582,7 @@ fail_free_drop:
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
brelse(bitmap_bh);
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 12661e1deedd..85fe655fe3e0 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -2899,7 +2899,7 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino)
inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
- inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+ set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
inode->i_size = le32_to_cpu(raw_inode->i_size);
inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index c7f43944f160..ba1b54e23cae 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -150,30 +150,6 @@ setversion_out:
mnt_drop_write(filp->f_path.mnt);
return err;
}
-#ifdef CONFIG_JBD_DEBUG
- case EXT3_IOC_WAIT_FOR_READONLY:
- /*
- * This is racy - by the time we're woken up and running,
- * the superblock could be released. And the module could
- * have been unloaded. So sue me.
- *
- * Returns 1 if it slept, else zero.
- */
- {
- struct super_block *sb = inode->i_sb;
- DECLARE_WAITQUEUE(wait, current);
- int ret = 0;
-
- set_current_state(TASK_INTERRUPTIBLE);
- add_wait_queue(&EXT3_SB(sb)->ro_wait_queue, &wait);
- if (timer_pending(&EXT3_SB(sb)->turn_ro_timer)) {
- schedule();
- ret = 1;
- }
- remove_wait_queue(&EXT3_SB(sb)->ro_wait_queue, &wait);
- return ret;
- }
-#endif
case EXT3_IOC_GETRSVSZ:
if (test_opt(inode->i_sb, RESERVATION)
&& S_ISREG(inode->i_mode)
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 0629e09f6511..642dc6d66dfd 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1821,7 +1821,7 @@ retry:
de->name_len = 2;
strcpy (de->name, "..");
ext3_set_de_type(dir->i_sb, de, S_IFDIR);
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
BUFFER_TRACE(dir_block, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, dir_block);
if (err)
@@ -1833,7 +1833,7 @@ retry:
if (err) {
out_clear_inode:
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
ext3_mark_inode_dirty(handle, inode);
iput (inode);
@@ -2170,7 +2170,7 @@ static int ext3_unlink(struct inode * dir, struct dentry *dentry)
ext3_warning (inode->i_sb, "ext3_unlink",
"Deleting nonexistent file (%lu), %d",
inode->i_ino, inode->i_nlink);
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
}
retval = ext3_delete_entry(handle, dir, de, bh);
if (retval)
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 7beb69ae0015..922d289aeeb3 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -652,8 +652,6 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, ",nouid32");
if (test_opt(sb, DEBUG))
seq_puts(seq, ",debug");
- if (test_opt(sb, OLDALLOC))
- seq_puts(seq, ",oldalloc");
#ifdef CONFIG_EXT3_FS_XATTR
if (test_opt(sb, XATTR_USER))
seq_puts(seq, ",user_xattr");
@@ -1049,10 +1047,12 @@ static int parse_options (char *options, struct super_block *sb,
set_opt (sbi->s_mount_opt, DEBUG);
break;
case Opt_oldalloc:
- set_opt (sbi->s_mount_opt, OLDALLOC);
+ ext3_msg(sb, KERN_WARNING,
+ "Ignoring deprecated oldalloc option");
break;
case Opt_orlov:
- clear_opt (sbi->s_mount_opt, OLDALLOC);
+ ext3_msg(sb, KERN_WARNING,
+ "Ignoring deprecated orlov option");
break;
#ifdef CONFIG_EXT3_FS_XATTR
case Opt_user_xattr:
@@ -2669,13 +2669,13 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
/*
* If we have an unprocessed orphan list hanging
* around from a previously readonly bdev mount,
- * require a full umount/remount for now.
+ * require a full umount & mount for now.
*/
if (es->s_last_orphan) {
ext3_msg(sb, KERN_WARNING, "warning: couldn't "
"remount RDWR because of unprocessed "
"orphan inode list. Please "
- "umount/remount instead.");
+ "umount & mount instead.");
err = -EINVAL;
goto restore_opts;
}
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f8224adf496e..f6dba4505f1c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -28,7 +28,8 @@
*/
/*
- * Calculate the block group number and offset, given a block number
+ * Calculate the block group number and offset into the block/cluster
+ * allocation bitmap, given a block number
*/
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
@@ -37,7 +38,8 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
ext4_grpblk_t offset;
blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
- offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb));
+ offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)) >>
+ EXT4_SB(sb)->s_cluster_bits;
if (offsetp)
*offsetp = offset;
if (blockgrpp)
@@ -55,130 +57,169 @@ static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block,
return 0;
}
-static int ext4_group_used_meta_blocks(struct super_block *sb,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp)
+/* Return the number of clusters used for file system metadata; this
+ * represents the overhead needed by the file system.
+ */
+unsigned ext4_num_overhead_clusters(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
{
- ext4_fsblk_t tmp;
+ unsigned num_clusters;
+ int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
+ ext4_fsblk_t start = ext4_group_first_block_no(sb, block_group);
+ ext4_fsblk_t itbl_blk;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- /* block bitmap, inode bitmap, and inode table blocks */
- int used_blocks = sbi->s_itb_per_group + 2;
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
- if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp),
- block_group))
- used_blocks--;
-
- if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp),
- block_group))
- used_blocks--;
-
- tmp = ext4_inode_table(sb, gdp);
- for (; tmp < ext4_inode_table(sb, gdp) +
- sbi->s_itb_per_group; tmp++) {
- if (!ext4_block_in_group(sb, tmp, block_group))
- used_blocks -= 1;
+ /* This is the number of clusters used by the superblock,
+ * block group descriptors, and reserved block group
+ * descriptor blocks */
+ num_clusters = ext4_num_base_meta_clusters(sb, block_group);
+
+ /*
+ * For the allocation bitmaps and inode table, we first need
+ * to check to see if the block is in the block group. If it
+ * is, then check to see if the cluster is already accounted
+ * for in the clusters used for the base metadata cluster, or
+ * if we can increment the base metadata cluster to include
+ * that block. Otherwise, we will have to track the cluster
+ * used for the allocation bitmap or inode table explicitly.
+ * Normally all of these blocks are contiguous, so the special
+ * case handling shouldn't be necessary except for *very*
+ * unusual file system layouts.
+ */
+ if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) {
+ block_cluster = EXT4_B2C(sbi, (start -
+ ext4_block_bitmap(sb, gdp)));
+ if (block_cluster < num_clusters)
+ block_cluster = -1;
+ else if (block_cluster == num_clusters) {
+ num_clusters++;
+ block_cluster = -1;
}
}
- return used_blocks;
-}
-/* Initializes an uninitialized block bitmap if given, and returns the
- * number of blocks free in the group. */
-unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
- ext4_group_t block_group, struct ext4_group_desc *gdp)
-{
- int bit, bit_max;
- ext4_group_t ngroups = ext4_get_groups_count(sb);
- unsigned free_blocks, group_blocks;
- struct ext4_sb_info *sbi = EXT4_SB(sb);
-
- if (bh) {
- J_ASSERT_BH(bh, buffer_locked(bh));
-
- /* If checksum is bad mark all blocks used to prevent allocation
- * essentially implementing a per-group read-only flag. */
- if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
- ext4_error(sb, "Checksum bad for group %u",
- block_group);
- ext4_free_blks_set(sb, gdp, 0);
- ext4_free_inodes_set(sb, gdp, 0);
- ext4_itable_unused_set(sb, gdp, 0);
- memset(bh->b_data, 0xff, sb->s_blocksize);
- return 0;
+ if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) {
+ inode_cluster = EXT4_B2C(sbi,
+ start - ext4_inode_bitmap(sb, gdp));
+ if (inode_cluster < num_clusters)
+ inode_cluster = -1;
+ else if (inode_cluster == num_clusters) {
+ num_clusters++;
+ inode_cluster = -1;
}
- memset(bh->b_data, 0, sb->s_blocksize);
}
- /* Check for superblock and gdt backups in this group */
- bit_max = ext4_bg_has_super(sb, block_group);
-
- if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
- block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
- sbi->s_desc_per_block) {
- if (bit_max) {
- bit_max += ext4_bg_num_gdb(sb, block_group);
- bit_max +=
- le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+ itbl_blk = ext4_inode_table(sb, gdp);
+ for (i = 0; i < sbi->s_itb_per_group; i++) {
+ if (ext4_block_in_group(sb, itbl_blk + i, block_group)) {
+ c = EXT4_B2C(sbi, start - itbl_blk + i);
+ if ((c < num_clusters) || (c == inode_cluster) ||
+ (c == block_cluster) || (c == itbl_cluster))
+ continue;
+ if (c == num_clusters) {
+ num_clusters++;
+ continue;
+ }
+ num_clusters++;
+ itbl_cluster = c;
}
- } else { /* For META_BG_BLOCK_GROUPS */
- bit_max += ext4_bg_num_gdb(sb, block_group);
}
- if (block_group == ngroups - 1) {
+ if (block_cluster != -1)
+ num_clusters++;
+ if (inode_cluster != -1)
+ num_clusters++;
+
+ return num_clusters;
+}
+
+static unsigned int num_clusters_in_group(struct super_block *sb,
+ ext4_group_t block_group)
+{
+ unsigned int blocks;
+
+ if (block_group == ext4_get_groups_count(sb) - 1) {
/*
- * Even though mke2fs always initialize first and last group
- * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
- * to make sure we calculate the right free blocks
+ * Even though mke2fs always initializes the first and
+ * last group, just in case some other tool was used,
+ * we need to make sure we calculate the right free
+ * blocks.
*/
- group_blocks = ext4_blocks_count(sbi->s_es) -
- ext4_group_first_block_no(sb, ngroups - 1);
- } else {
- group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
- }
+ blocks = ext4_blocks_count(EXT4_SB(sb)->s_es) -
+ ext4_group_first_block_no(sb, block_group);
+ } else
+ blocks = EXT4_BLOCKS_PER_GROUP(sb);
+ return EXT4_NUM_B2C(EXT4_SB(sb), blocks);
+}
- free_blocks = group_blocks - bit_max;
+/* Initializes an uninitialized block bitmap */
+void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
+{
+ unsigned int bit, bit_max;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_fsblk_t start, tmp;
+ int flex_bg = 0;
+
+ J_ASSERT_BH(bh, buffer_locked(bh));
+
+ /* If checksum is bad mark all blocks used to prevent allocation
+ * essentially implementing a per-group read-only flag. */
+ if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
+ ext4_error(sb, "Checksum bad for group %u", block_group);
+ ext4_free_group_clusters_set(sb, gdp, 0);
+ ext4_free_inodes_set(sb, gdp, 0);
+ ext4_itable_unused_set(sb, gdp, 0);
+ memset(bh->b_data, 0xff, sb->s_blocksize);
+ return;
+ }
+ memset(bh->b_data, 0, sb->s_blocksize);
- if (bh) {
- ext4_fsblk_t start, tmp;
- int flex_bg = 0;
+ bit_max = ext4_num_base_meta_clusters(sb, block_group);
+ for (bit = 0; bit < bit_max; bit++)
+ ext4_set_bit(bit, bh->b_data);
- for (bit = 0; bit < bit_max; bit++)
- ext4_set_bit(bit, bh->b_data);
+ start = ext4_group_first_block_no(sb, block_group);
- start = ext4_group_first_block_no(sb, block_group);
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+ flex_bg = 1;
- if (EXT4_HAS_INCOMPAT_FEATURE(sb,
- EXT4_FEATURE_INCOMPAT_FLEX_BG))
- flex_bg = 1;
+ /* Set bits for block and inode bitmaps, and inode table */
+ tmp = ext4_block_bitmap(sb, gdp);
+ if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
- /* Set bits for block and inode bitmaps, and inode table */
- tmp = ext4_block_bitmap(sb, gdp);
- if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
- ext4_set_bit(tmp - start, bh->b_data);
+ tmp = ext4_inode_bitmap(sb, gdp);
+ if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
- tmp = ext4_inode_bitmap(sb, gdp);
+ tmp = ext4_inode_table(sb, gdp);
+ for (; tmp < ext4_inode_table(sb, gdp) +
+ sbi->s_itb_per_group; tmp++) {
if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
- ext4_set_bit(tmp - start, bh->b_data);
-
- tmp = ext4_inode_table(sb, gdp);
- for (; tmp < ext4_inode_table(sb, gdp) +
- sbi->s_itb_per_group; tmp++) {
- if (!flex_bg ||
- ext4_block_in_group(sb, tmp, block_group))
- ext4_set_bit(tmp - start, bh->b_data);
- }
- /*
- * Also if the number of blocks within the group is
- * less than the blocksize * 8 ( which is the size
- * of bitmap ), set rest of the block bitmap to 1
- */
- ext4_mark_bitmap_end(group_blocks, sb->s_blocksize * 8,
- bh->b_data);
+ ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
}
- return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
+
+ /*
+ * Also if the number of blocks within the group is less than
+ * the blocksize * 8 ( which is the size of bitmap ), set rest
+ * of the block bitmap to 1
+ */
+ ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group),
+ sb->s_blocksize * 8, bh->b_data);
}
+/* Return the number of free blocks in a block group. It is used when
+ * the block bitmap is uninitialized, so we can't just count the bits
+ * in the bitmap. */
+unsigned ext4_free_clusters_after_init(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
+{
+ return num_clusters_in_group(sb, block_group) -
+ ext4_num_overhead_clusters(sb, block_group, gdp);
+}
/*
* The free blocks are managed by bitmaps. A file system contains several
@@ -362,53 +403,54 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
}
/**
- * ext4_has_free_blocks()
+ * ext4_has_free_clusters()
* @sbi: in-core super block structure.
- * @nblocks: number of needed blocks
+ * @nclusters: number of needed blocks
+ * @flags: flags from ext4_mb_new_blocks()
*
- * Check if filesystem has nblocks free & available for allocation.
+ * Check if filesystem has nclusters free & available for allocation.
* On success return 1, return 0 on failure.
*/
-static int ext4_has_free_blocks(struct ext4_sb_info *sbi,
- s64 nblocks, unsigned int flags)
+static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
+ s64 nclusters, unsigned int flags)
{
- s64 free_blocks, dirty_blocks, root_blocks;
- struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
- struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
-
- free_blocks = percpu_counter_read_positive(fbc);
- dirty_blocks = percpu_counter_read_positive(dbc);
- root_blocks = ext4_r_blocks_count(sbi->s_es);
-
- if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
- EXT4_FREEBLOCKS_WATERMARK) {
- free_blocks = percpu_counter_sum_positive(fbc);
- dirty_blocks = percpu_counter_sum_positive(dbc);
+ s64 free_clusters, dirty_clusters, root_clusters;
+ struct percpu_counter *fcc = &sbi->s_freeclusters_counter;
+ struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter;
+
+ free_clusters = percpu_counter_read_positive(fcc);
+ dirty_clusters = percpu_counter_read_positive(dcc);
+ root_clusters = EXT4_B2C(sbi, ext4_r_blocks_count(sbi->s_es));
+
+ if (free_clusters - (nclusters + root_clusters + dirty_clusters) <
+ EXT4_FREECLUSTERS_WATERMARK) {
+ free_clusters = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc));
+ dirty_clusters = percpu_counter_sum_positive(dcc);
}
- /* Check whether we have space after
- * accounting for current dirty blocks & root reserved blocks.
+ /* Check whether we have space after accounting for current
+ * dirty clusters & root reserved clusters.
*/
- if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks))
+ if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters))
return 1;
- /* Hm, nope. Are (enough) root reserved blocks available? */
+ /* Hm, nope. Are (enough) root reserved clusters available? */
if (sbi->s_resuid == current_fsuid() ||
((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
capable(CAP_SYS_RESOURCE) ||
(flags & EXT4_MB_USE_ROOT_BLOCKS)) {
- if (free_blocks >= (nblocks + dirty_blocks))
+ if (free_clusters >= (nclusters + dirty_clusters))
return 1;
}
return 0;
}
-int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
- s64 nblocks, unsigned int flags)
+int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
+ s64 nclusters, unsigned int flags)
{
- if (ext4_has_free_blocks(sbi, nblocks, flags)) {
- percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks);
+ if (ext4_has_free_clusters(sbi, nclusters, flags)) {
+ percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters);
return 0;
} else
return -ENOSPC;
@@ -428,7 +470,7 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
*/
int ext4_should_retry_alloc(struct super_block *sb, int *retries)
{
- if (!ext4_has_free_blocks(EXT4_SB(sb), 1, 0) ||
+ if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
(*retries)++ > 3 ||
!EXT4_SB(sb)->s_journal)
return 0;
@@ -444,7 +486,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
* @handle: handle to this transaction
* @inode: file inode
* @goal: given target block(filesystem wide)
- * @count: pointer to total number of blocks needed
+ * @count: pointer to total number of clusters needed
* @errp: error code
*
* Return 1st allocated block number on success, *count stores total account
@@ -476,18 +518,19 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- dquot_alloc_block_nofail(inode, ar.len);
+ dquot_alloc_block_nofail(inode,
+ EXT4_C2B(EXT4_SB(inode->i_sb), ar.len));
}
return ret;
}
/**
- * ext4_count_free_blocks() -- count filesystem free blocks
+ * ext4_count_free_clusters() -- count filesystem free clusters
* @sb: superblock
*
- * Adds up the number of free blocks from each block group.
+ * Adds up the number of free clusters from each block group.
*/
-ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
+ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
{
ext4_fsblk_t desc_count;
struct ext4_group_desc *gdp;
@@ -508,7 +551,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += ext4_free_blks_count(sb, gdp);
+ desc_count += ext4_free_group_clusters(sb, gdp);
brelse(bitmap_bh);
bitmap_bh = ext4_read_block_bitmap(sb, i);
if (bitmap_bh == NULL)
@@ -516,12 +559,13 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
x = ext4_count_free(bitmap_bh, sb->s_blocksize);
printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
- i, ext4_free_blks_count(sb, gdp), x);
+ i, ext4_free_group_clusters(sb, gdp), x);
bitmap_count += x;
}
brelse(bitmap_bh);
- printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu"
- ", computed = %llu, %llu\n", ext4_free_blocks_count(es),
+ printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
+ ", computed = %llu, %llu\n",
+ EXT4_B2C(sbi, ext4_free_blocks_count(es)),
desc_count, bitmap_count);
return bitmap_count;
#else
@@ -530,7 +574,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
gdp = ext4_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
- desc_count += ext4_free_blks_count(sb, gdp);
+ desc_count += ext4_free_group_clusters(sb, gdp);
}
return desc_count;
@@ -620,6 +664,31 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
}
+/*
+ * This function returns the number of file system metadata clusters at
+ * the beginning of a block group, including the reserved gdt blocks.
+ */
+unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+ ext4_group_t block_group)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ unsigned num;
+
+ /* Check for superblock and gdt backups in this group */
+ num = ext4_bg_has_super(sb, block_group);
+
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
+ block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
+ sbi->s_desc_per_block) {
+ if (num) {
+ num += ext4_bg_num_gdb(sb, block_group);
+ num += le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+ }
+ } else { /* For META_BG_BLOCK_GROUPS */
+ num += ext4_bg_num_gdb(sb, block_group);
+ }
+ return EXT4_NUM_B2C(sbi, num);
+}
/**
* ext4_inode_to_goal_block - return a hint for block allocation
* @inode: inode for block allocation
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index cec3145e532c..5b0e26a1272d 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -144,9 +144,17 @@ struct ext4_allocation_request {
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
#define EXT4_MAP_UNINIT (1 << BH_Uninit)
+/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
+ * ext4_map_blocks wants to know whether or not the underlying cluster has
+ * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
+ * the requested mapping was from previously mapped (or delayed allocated)
+ * cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster
+ * should never appear on buffer_head's state flags.
+ */
+#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
- EXT4_MAP_UNINIT)
+ EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
@@ -239,8 +247,11 @@ struct ext4_io_submit {
# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
#endif
#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof(__u32))
+#define EXT4_CLUSTER_SIZE(s) (EXT4_BLOCK_SIZE(s) << \
+ EXT4_SB(s)->s_cluster_bits)
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits)
+# define EXT4_CLUSTER_BITS(s) (EXT4_SB(s)->s_cluster_bits)
#else
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10)
#endif
@@ -258,6 +269,14 @@ struct ext4_io_submit {
#endif
#define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits)))
+/* Translate a block number to a cluster number */
+#define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits)
+/* Translate a cluster number to a block number */
+#define EXT4_C2B(sbi, cluster) ((cluster) << (sbi)->s_cluster_bits)
+/* Translate # of blks to # of clusters */
+#define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \
+ (sbi)->s_cluster_bits)
+
/*
* Structure of a blocks group descriptor
*/
@@ -289,7 +308,7 @@ struct ext4_group_desc
struct flex_groups {
atomic_t free_inodes;
- atomic_t free_blocks;
+ atomic_t free_clusters;
atomic_t used_dirs;
};
@@ -306,6 +325,7 @@ struct flex_groups {
#define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size)
#ifdef __KERNEL__
# define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group)
+# define EXT4_CLUSTERS_PER_GROUP(s) (EXT4_SB(s)->s_clusters_per_group)
# define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block)
# define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group)
# define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits)
@@ -358,8 +378,7 @@ struct flex_groups {
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
- EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\
- EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
+ EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
@@ -520,6 +539,8 @@ struct ext4_new_group_data {
#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 0x0020
/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040
+ /* Request will not result in inode size update (user for fallocate) */
+#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080
/*
* Flags used by ext4_free_blocks
@@ -528,6 +549,13 @@ struct ext4_new_group_data {
#define EXT4_FREE_BLOCKS_FORGET 0x0002
#define EXT4_FREE_BLOCKS_VALIDATED 0x0004
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008
+#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010
+#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020
+
+/*
+ * Flags used by ext4_discard_partial_page_buffers
+ */
+#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED 0x0001
/*
* ioctl commands
@@ -538,9 +566,6 @@ struct ext4_new_group_data {
#define EXT4_IOC_SETVERSION _IOW('f', 4, long)
#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION
#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION
-#ifdef CONFIG_JBD2_DEBUG
-#define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long)
-#endif
#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long)
#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long)
#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long)
@@ -563,9 +588,6 @@ struct ext4_new_group_data {
#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int)
#define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input)
-#ifdef CONFIG_JBD2_DEBUG
-#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int)
-#endif
#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
#endif
@@ -837,6 +859,7 @@ struct ext4_inode_info {
ext4_group_t i_last_alloc_group;
/* allocation reservation info for delalloc */
+ /* In case of bigalloc, these refer to clusters rather than blocks */
unsigned int i_reserved_data_blocks;
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
@@ -886,7 +909,6 @@ struct ext4_inode_info {
/*
* Mount flags
*/
-#define EXT4_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */
#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */
#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */
#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
@@ -918,6 +940,9 @@ struct ext4_inode_info {
#define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */
#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */
+#define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly
+ specified delalloc */
+
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
#define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \
@@ -968,9 +993,9 @@ struct ext4_super_block {
/*10*/ __le32 s_free_inodes_count; /* Free inodes count */
__le32 s_first_data_block; /* First Data Block */
__le32 s_log_block_size; /* Block size */
- __le32 s_obso_log_frag_size; /* Obsoleted fragment size */
+ __le32 s_log_cluster_size; /* Allocation cluster size */
/*20*/ __le32 s_blocks_per_group; /* # Blocks per group */
- __le32 s_obso_frags_per_group; /* Obsoleted fragments per group */
+ __le32 s_clusters_per_group; /* # Clusters per group */
__le32 s_inodes_per_group; /* # Inodes per group */
__le32 s_mtime; /* Mount time */
/*30*/ __le32 s_wtime; /* Write time */
@@ -1066,7 +1091,10 @@ struct ext4_super_block {
__u8 s_last_error_func[32]; /* function where the error happened */
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
__u8 s_mount_opts[64];
- __le32 s_reserved[112]; /* Padding to the end of the block */
+ __le32 s_usr_quota_inum; /* inode for tracking user quota */
+ __le32 s_grp_quota_inum; /* inode for tracking group quota */
+ __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
+ __le32 s_reserved[109]; /* Padding to the end of the block */
};
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
@@ -1086,6 +1114,7 @@ struct ext4_sb_info {
unsigned long s_desc_size; /* Size of a group descriptor in bytes */
unsigned long s_inodes_per_block;/* Number of inodes per block */
unsigned long s_blocks_per_group;/* Number of blocks in a group */
+ unsigned long s_clusters_per_group; /* Number of clusters in a group */
unsigned long s_inodes_per_group;/* Number of inodes in a group */
unsigned long s_itb_per_group; /* Number of inode table blocks per group */
unsigned long s_gdb_count; /* Number of group descriptor blocks */
@@ -1094,6 +1123,8 @@ struct ext4_sb_info {
ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
unsigned long s_overhead_last; /* Last calculated overhead */
unsigned long s_blocks_last; /* Last seen block count */
+ unsigned int s_cluster_ratio; /* Number of blocks per cluster */
+ unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
@@ -1117,10 +1148,10 @@ struct ext4_sb_info {
u32 s_hash_seed[4];
int s_def_hash_version;
int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
- struct percpu_counter s_freeblocks_counter;
+ struct percpu_counter s_freeclusters_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
- struct percpu_counter s_dirtyblocks_counter;
+ struct percpu_counter s_dirtyclusters_counter;
struct blockgroup_lock *s_blockgroup_lock;
struct proc_dir_entry *s_proc;
struct kobject s_kobj;
@@ -1136,10 +1167,6 @@ struct ext4_sb_info {
u32 s_max_batch_time;
u32 s_min_batch_time;
struct block_device *journal_bdev;
-#ifdef CONFIG_JBD2_DEBUG
- struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */
- wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */
-#endif
#ifdef CONFIG_QUOTA
char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
int s_jquota_fmt; /* Format of quota to use */
@@ -1248,6 +1275,15 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
+static inline void ext4_set_io_unwritten_flag(struct inode *inode,
+ struct ext4_io_end *io_end)
+{
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ }
+}
+
/*
* Inode dynamic state flags
*/
@@ -1360,6 +1396,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
#define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100
+#define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200
#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001
#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002
@@ -1402,7 +1439,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
- EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
+ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC)
/*
* Default values for user and/or group using reserved blocks
@@ -1735,9 +1773,9 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
unsigned int flags,
unsigned long *count,
int *errp);
-extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
- s64 nblocks, unsigned int flags);
-extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
+extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
+ s64 nclusters, unsigned int flags);
+extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
extern void ext4_check_blocks_bitmap(struct super_block *);
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
ext4_group_t block_group,
@@ -1745,12 +1783,18 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
ext4_group_t block_group);
-extern unsigned ext4_init_block_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
-#define ext4_free_blocks_after_init(sb, group, desc) \
- ext4_init_block_bitmap(sb, NULL, group, desc)
+extern void ext4_init_block_bitmap(struct super_block *sb,
+ struct buffer_head *bh,
+ ext4_group_t group,
+ struct ext4_group_desc *desc);
+extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp);
+extern unsigned ext4_num_base_meta_clusters(struct super_block *sb,
+ ext4_group_t block_group);
+extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
/* dir.c */
@@ -1776,7 +1820,8 @@ extern int ext4fs_dirhash(const char *name, int len, struct
/* ialloc.c */
extern struct inode *ext4_new_inode(handle_t *, struct inode *, int,
- const struct qstr *qstr, __u32 goal);
+ const struct qstr *qstr, __u32 goal,
+ uid_t *owner);
extern void ext4_free_inode(handle_t *, struct inode *);
extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
extern unsigned long ext4_count_free_inodes(struct super_block *);
@@ -1839,6 +1884,12 @@ extern int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from);
extern int ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length);
+extern int ext4_discard_partial_page_buffers(handle_t *handle,
+ struct address_space *mapping, loff_t from,
+ loff_t length, int flags);
+extern int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+ struct inode *inode, struct page *page, loff_t from,
+ loff_t length, int flags);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
@@ -1927,8 +1978,8 @@ extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg);
-extern __u32 ext4_free_blks_count(struct super_block *sb,
- struct ext4_group_desc *bg);
+extern __u32 ext4_free_group_clusters(struct super_block *sb,
+ struct ext4_group_desc *bg);
extern __u32 ext4_free_inodes_count(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_used_dirs_count(struct super_block *sb,
@@ -1941,8 +1992,9 @@ extern void ext4_inode_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
-extern void ext4_free_blks_set(struct super_block *sb,
- struct ext4_group_desc *bg, __u32 count);
+extern void ext4_free_group_clusters_set(struct super_block *sb,
+ struct ext4_group_desc *bg,
+ __u32 count);
extern void ext4_free_inodes_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count);
extern void ext4_used_dirs_set(struct super_block *sb,
@@ -2051,13 +2103,13 @@ do { \
} while (0)
#ifdef CONFIG_SMP
-/* Each CPU can accumulate percpu_counter_batch blocks in their local
- * counters. So we need to make sure we have free blocks more
+/* Each CPU can accumulate percpu_counter_batch clusters in their local
+ * counters. So we need to make sure we have free clusters more
* than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times.
*/
-#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
+#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
#else
-#define EXT4_FREEBLOCKS_WATERMARK 0
+#define EXT4_FREECLUSTERS_WATERMARK 0
#endif
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
@@ -2243,10 +2295,19 @@ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
enum ext4_state_bits {
BH_Uninit /* blocks are allocated but uninitialized on disk */
= BH_JBDPrivateStart,
+ BH_AllocFromCluster, /* allocated blocks were part of already
+ * allocated cluster. Note that this flag will
+ * never, ever appear in a buffer_head's state
+ * flag. See EXT4_MAP_FROM_CLUSTER to see where
+ * this is used. */
+ BH_Da_Mapped, /* Delayed allocated block that now has a mapping. This
+ * flag is set when ext4_map_blocks is called on a
+ * delayed allocated block to get its real mapping. */
};
BUFFER_FNS(Uninit, uninit)
TAS_BUFFER_FNS(Uninit, uninit)
+BUFFER_FNS(Da_Mapped, da_mapped)
/*
* Add new method to test wether block and inode bitmaps are properly
@@ -2282,4 +2343,6 @@ extern void ext4_resize_end(struct super_block *sb);
#endif /* __KERNEL__ */
+#include "ext4_extents.h"
+
#endif /* _EXT4_H */
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 095c36f3b612..a52db3a69a30 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -290,5 +290,7 @@ extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
struct ext4_ext_path *);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
+extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
+ int search_hint_reverse);
#endif /* _EXT4_EXTENTS */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index f5240aa15601..aca179017582 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -109,9 +109,11 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, line, __func__,
- bh, handle, err);
+ if (err) {
+ /* Errors can only happen if there is a bug */
+ handle->h_err = err;
+ __ext4_journal_stop(where, line, handle);
+ }
} else {
if (inode)
mark_buffer_dirty_inode(bh, inode);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 57cf568a98ab..61fa9e1614af 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -42,7 +42,6 @@
#include <asm/uaccess.h>
#include <linux/fiemap.h>
#include "ext4_jbd2.h"
-#include "ext4_extents.h"
#include <trace/events/ext4.h>
@@ -96,13 +95,17 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
* - ENOMEM
* - EIO
*/
-static int ext4_ext_dirty(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path)
+#define ext4_ext_dirty(handle, inode, path) \
+ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
+static int __ext4_ext_dirty(const char *where, unsigned int line,
+ handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
{
int err;
if (path->p_bh) {
/* path points to block */
- err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
+ err = __ext4_handle_dirty_metadata(where, line, handle,
+ inode, path->p_bh);
} else {
/* path points to leaf/index in inode body */
err = ext4_mark_inode_dirty(handle, inode);
@@ -114,11 +117,9 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t block)
{
- int depth;
-
if (path) {
+ int depth = path->p_depth;
struct ext4_extent *ex;
- depth = path->p_depth;
/*
* Try to predict block placement assuming that we are
@@ -180,12 +181,10 @@ static inline int ext4_ext_space_block(struct inode *inode, int check)
size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 6)
- size = 6;
+ if (!check && size > 6)
+ size = 6;
#endif
- }
return size;
}
@@ -195,12 +194,10 @@ static inline int ext4_ext_space_block_idx(struct inode *inode, int check)
size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent_idx);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 5)
- size = 5;
+ if (!check && size > 5)
+ size = 5;
#endif
- }
return size;
}
@@ -211,12 +208,10 @@ static inline int ext4_ext_space_root(struct inode *inode, int check)
size = sizeof(EXT4_I(inode)->i_data);
size -= sizeof(struct ext4_extent_header);
size /= sizeof(struct ext4_extent);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 3)
- size = 3;
+ if (!check && size > 3)
+ size = 3;
#endif
- }
return size;
}
@@ -227,12 +222,10 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
size = sizeof(EXT4_I(inode)->i_data);
size -= sizeof(struct ext4_extent_header);
size /= sizeof(struct ext4_extent_idx);
- if (!check) {
#ifdef AGGRESSIVE_TEST
- if (size > 4)
- size = 4;
+ if (!check && size > 4)
+ size = 4;
#endif
- }
return size;
}
@@ -244,7 +237,7 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
{
struct ext4_inode_info *ei = EXT4_I(inode);
- int idxs, num = 0;
+ int idxs;
idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent_idx));
@@ -259,6 +252,8 @@ int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
*/
if (ei->i_da_metadata_calc_len &&
ei->i_da_metadata_calc_last_lblock+1 == lblock) {
+ int num = 0;
+
if ((ei->i_da_metadata_calc_len % idxs) == 0)
num++;
if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
@@ -321,8 +316,6 @@ static int ext4_valid_extent_entries(struct inode *inode,
struct ext4_extent_header *eh,
int depth)
{
- struct ext4_extent *ext;
- struct ext4_extent_idx *ext_idx;
unsigned short entries;
if (eh->eh_entries == 0)
return 1;
@@ -331,7 +324,7 @@ static int ext4_valid_extent_entries(struct inode *inode,
if (depth == 0) {
/* leaf entries */
- ext = EXT_FIRST_EXTENT(eh);
+ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
while (entries) {
if (!ext4_valid_extent(inode, ext))
return 0;
@@ -339,7 +332,7 @@ static int ext4_valid_extent_entries(struct inode *inode,
entries--;
}
} else {
- ext_idx = EXT_FIRST_INDEX(eh);
+ struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
while (entries) {
if (!ext4_valid_extent_idx(inode, ext_idx))
return 0;
@@ -751,31 +744,30 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
return -EIO;
}
- len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
/* insert after */
- if (curp->p_idx != EXT_LAST_INDEX(curp->p_hdr)) {
- len = (len - 1) * sizeof(struct ext4_extent_idx);
- len = len < 0 ? 0 : len;
- ext_debug("insert new index %d after: %llu. "
- "move %d from 0x%p to 0x%p\n",
- logical, ptr, len,
- (curp->p_idx + 1), (curp->p_idx + 2));
- memmove(curp->p_idx + 2, curp->p_idx + 1, len);
- }
+ ext_debug("insert new index %d after: %llu\n", logical, ptr);
ix = curp->p_idx + 1;
} else {
/* insert before */
- len = len * sizeof(struct ext4_extent_idx);
- len = len < 0 ? 0 : len;
- ext_debug("insert new index %d before: %llu. "
- "move %d from 0x%p to 0x%p\n",
- logical, ptr, len,
- curp->p_idx, (curp->p_idx + 1));
- memmove(curp->p_idx + 1, curp->p_idx, len);
+ ext_debug("insert new index %d before: %llu\n", logical, ptr);
ix = curp->p_idx;
}
+ len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1;
+ BUG_ON(len < 0);
+ if (len > 0) {
+ ext_debug("insert new index %d: "
+ "move %d indices from 0x%p to 0x%p\n",
+ logical, len, ix, ix + 1);
+ memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx));
+ }
+
+ if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) {
+ EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!");
+ return -EIO;
+ }
+
ix->ei_block = cpu_to_le32(logical);
ext4_idx_store_pblock(ix, ptr);
le16_add_cpu(&curp->p_hdr->eh_entries, 1);
@@ -1042,16 +1034,14 @@ cleanup:
*/
static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
unsigned int flags,
- struct ext4_ext_path *path,
struct ext4_extent *newext)
{
- struct ext4_ext_path *curp = path;
struct ext4_extent_header *neh;
struct buffer_head *bh;
ext4_fsblk_t newblock;
int err = 0;
- newblock = ext4_ext_new_meta_block(handle, inode, path,
+ newblock = ext4_ext_new_meta_block(handle, inode, NULL,
newext, &err, flags);
if (newblock == 0)
return err;
@@ -1071,7 +1061,8 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
}
/* move top-level index/leaf into new block */
- memmove(bh->b_data, curp->p_hdr, sizeof(EXT4_I(inode)->i_data));
+ memmove(bh->b_data, EXT4_I(inode)->i_data,
+ sizeof(EXT4_I(inode)->i_data));
/* set size of new block */
neh = ext_block_hdr(bh);
@@ -1089,32 +1080,23 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
if (err)
goto out;
- /* create index in new top-level index: num,max,pointer */
- err = ext4_ext_get_access(handle, inode, curp);
- if (err)
- goto out;
-
- curp->p_hdr->eh_magic = EXT4_EXT_MAGIC;
- curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
- curp->p_hdr->eh_entries = cpu_to_le16(1);
- curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr);
-
- if (path[0].p_hdr->eh_depth)
- curp->p_idx->ei_block =
- EXT_FIRST_INDEX(path[0].p_hdr)->ei_block;
- else
- curp->p_idx->ei_block =
- EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block;
- ext4_idx_store_pblock(curp->p_idx, newblock);
-
+ /* Update top-level index: num,max,pointer */
neh = ext_inode_hdr(inode);
+ neh->eh_entries = cpu_to_le16(1);
+ ext4_idx_store_pblock(EXT_FIRST_INDEX(neh), newblock);
+ if (neh->eh_depth == 0) {
+ /* Root extent block becomes index block */
+ neh->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
+ EXT_FIRST_INDEX(neh)->ei_block =
+ EXT_FIRST_EXTENT(neh)->ee_block;
+ }
ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n",
le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max),
le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
- neh->eh_depth = cpu_to_le16(path->p_depth + 1);
- err = ext4_ext_dirty(handle, inode, curp);
+ neh->eh_depth = cpu_to_le16(neh->eh_depth + 1);
+ ext4_mark_inode_dirty(handle, inode);
out:
brelse(bh);
@@ -1162,8 +1144,7 @@ repeat:
err = PTR_ERR(path);
} else {
/* tree is full, time to grow in depth */
- err = ext4_ext_grow_indepth(handle, inode, flags,
- path, newext);
+ err = ext4_ext_grow_indepth(handle, inode, flags, newext);
if (err)
goto out;
@@ -1235,9 +1216,9 @@ static int ext4_ext_search_left(struct inode *inode,
if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
EXT4_ERROR_INODE(inode,
"ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!",
- ix != NULL ? ix->ei_block : 0,
+ ix != NULL ? le32_to_cpu(ix->ei_block) : 0,
EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ?
- EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block : 0,
+ le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0,
depth);
return -EIO;
}
@@ -1260,13 +1241,14 @@ static int ext4_ext_search_left(struct inode *inode,
/*
* search the closest allocated block to the right for *logical
* and returns it at @logical + it's physical address at @phys
- * if *logical is the smallest allocated block, the function
+ * if *logical is the largest allocated block, the function
* returns 0 at @phys
* return value contains 0 (success) or error code
*/
static int ext4_ext_search_right(struct inode *inode,
struct ext4_ext_path *path,
- ext4_lblk_t *logical, ext4_fsblk_t *phys)
+ ext4_lblk_t *logical, ext4_fsblk_t *phys,
+ struct ext4_extent **ret_ex)
{
struct buffer_head *bh = NULL;
struct ext4_extent_header *eh;
@@ -1308,9 +1290,7 @@ static int ext4_ext_search_right(struct inode *inode,
return -EIO;
}
}
- *logical = le32_to_cpu(ex->ee_block);
- *phys = ext4_ext_pblock(ex);
- return 0;
+ goto found_extent;
}
if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
@@ -1323,9 +1303,7 @@ static int ext4_ext_search_right(struct inode *inode,
if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
/* next allocated block in this leaf */
ex++;
- *logical = le32_to_cpu(ex->ee_block);
- *phys = ext4_ext_pblock(ex);
- return 0;
+ goto found_extent;
}
/* go up and search for index to the right */
@@ -1368,9 +1346,12 @@ got_index:
return -EIO;
}
ex = EXT_FIRST_EXTENT(eh);
+found_extent:
*logical = le32_to_cpu(ex->ee_block);
*phys = ext4_ext_pblock(ex);
- put_bh(bh);
+ *ret_ex = ex;
+ if (bh)
+ put_bh(bh);
return 0;
}
@@ -1395,7 +1376,8 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
while (depth >= 0) {
if (depth == path->p_depth) {
/* leaf */
- if (path[depth].p_ext !=
+ if (path[depth].p_ext &&
+ path[depth].p_ext !=
EXT_LAST_EXTENT(path[depth].p_hdr))
return le32_to_cpu(path[depth].p_ext[1].ee_block);
} else {
@@ -1623,7 +1605,8 @@ static int ext4_ext_try_to_merge(struct inode *inode,
* such that there will be no overlap, and then returns 1.
* If there is no overlap found, it returns 0.
*/
-static unsigned int ext4_ext_check_overlap(struct inode *inode,
+static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
+ struct inode *inode,
struct ext4_extent *newext,
struct ext4_ext_path *path)
{
@@ -1637,6 +1620,7 @@ static unsigned int ext4_ext_check_overlap(struct inode *inode,
if (!path[depth].p_ext)
goto out;
b2 = le32_to_cpu(path[depth].p_ext->ee_block);
+ b2 &= ~(sbi->s_cluster_ratio - 1);
/*
* get the next allocated block if the extent in the path
@@ -1646,6 +1630,7 @@ static unsigned int ext4_ext_check_overlap(struct inode *inode,
b2 = ext4_ext_next_allocated_block(path);
if (b2 == EXT_MAX_BLOCKS)
goto out;
+ b2 &= ~(sbi->s_cluster_ratio - 1);
}
/* check for wrap through zero on extent logical start block*/
@@ -1697,7 +1682,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
/* try to insert block into found extent and return */
if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
&& ext4_can_extents_be_merged(inode, ex, newext)) {
- ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
+ ext_debug("append [%d]%d block to %u:[%d]%d (from %llu)\n",
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
@@ -1735,7 +1720,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block))
next = ext4_ext_next_leaf_block(path);
if (next != EXT_MAX_BLOCKS) {
- ext_debug("next leaf block - %d\n", next);
+ ext_debug("next leaf block - %u\n", next);
BUG_ON(npath != NULL);
npath = ext4_ext_find_extent(inode, next, NULL);
if (IS_ERR(npath))
@@ -1773,46 +1758,51 @@ has_space:
if (!nearex) {
/* there is no extent in this leaf, create first one */
- ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n",
+ ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext));
- path[depth].p_ext = EXT_FIRST_EXTENT(eh);
- } else if (le32_to_cpu(newext->ee_block)
+ nearex = EXT_FIRST_EXTENT(eh);
+ } else {
+ if (le32_to_cpu(newext->ee_block)
> le32_to_cpu(nearex->ee_block)) {
-/* BUG_ON(newext->ee_block == nearex->ee_block); */
- if (nearex != EXT_LAST_EXTENT(eh)) {
- len = EXT_MAX_EXTENT(eh) - nearex;
- len = (len - 1) * sizeof(struct ext4_extent);
- len = len < 0 ? 0 : len;
- ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, "
- "move %d from 0x%p to 0x%p\n",
+ /* Insert after */
+ ext_debug("insert %u:%llu:[%d]%d before: "
+ "nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext),
- nearex, len, nearex + 1, nearex + 2);
- memmove(nearex + 2, nearex + 1, len);
+ nearex);
+ nearex++;
+ } else {
+ /* Insert before */
+ BUG_ON(newext->ee_block == nearex->ee_block);
+ ext_debug("insert %u:%llu:[%d]%d after: "
+ "nearest %p\n",
+ le32_to_cpu(newext->ee_block),
+ ext4_ext_pblock(newext),
+ ext4_ext_is_uninitialized(newext),
+ ext4_ext_get_actual_len(newext),
+ nearex);
+ }
+ len = EXT_LAST_EXTENT(eh) - nearex + 1;
+ if (len > 0) {
+ ext_debug("insert %u:%llu:[%d]%d: "
+ "move %d extents from 0x%p to 0x%p\n",
+ le32_to_cpu(newext->ee_block),
+ ext4_ext_pblock(newext),
+ ext4_ext_is_uninitialized(newext),
+ ext4_ext_get_actual_len(newext),
+ len, nearex, nearex + 1);
+ memmove(nearex + 1, nearex,
+ len * sizeof(struct ext4_extent));
}
- path[depth].p_ext = nearex + 1;
- } else {
- BUG_ON(newext->ee_block == nearex->ee_block);
- len = (EXT_MAX_EXTENT(eh) - nearex) * sizeof(struct ext4_extent);
- len = len < 0 ? 0 : len;
- ext_debug("insert %d:%llu:[%d]%d before: nearest 0x%p, "
- "move %d from 0x%p to 0x%p\n",
- le32_to_cpu(newext->ee_block),
- ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
- ext4_ext_get_actual_len(newext),
- nearex, len, nearex, nearex + 1);
- memmove(nearex + 1, nearex, len);
- path[depth].p_ext = nearex;
}
le16_add_cpu(&eh->eh_entries, 1);
- nearex = path[depth].p_ext;
+ path[depth].p_ext = nearex;
nearex->ee_block = newext->ee_block;
ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext));
nearex->ee_len = newext->ee_len;
@@ -1962,6 +1952,7 @@ ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
struct ext4_ext_cache *cex;
BUG_ON(len == 0);
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+ trace_ext4_ext_put_in_cache(inode, block, len, start);
cex = &EXT4_I(inode)->i_cached_extent;
cex->ec_block = block;
cex->ec_len = len;
@@ -2063,6 +2054,7 @@ errout:
sbi->extent_cache_misses++;
else
sbi->extent_cache_hits++;
+ trace_ext4_ext_in_cache(inode, block, ret);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
return ret;
}
@@ -2130,6 +2122,8 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
if (err)
return err;
ext_debug("index is empty, remove it, free block %llu\n", leaf);
+ trace_ext4_ext_rm_idx(inode, leaf);
+
ext4_free_blocks(handle, inode, NULL, leaf, 1,
EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
return err;
@@ -2158,7 +2152,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks,
* need to account for leaf block credit
*
* bitmaps and block group descriptor blocks
- * and other metadat blocks still need to be
+ * and other metadata blocks still need to be
* accounted.
*/
/* 1 bitmap, 1 block group descriptor */
@@ -2195,14 +2189,40 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
}
static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
- struct ext4_extent *ex,
- ext4_lblk_t from, ext4_lblk_t to)
+ struct ext4_extent *ex,
+ ext4_fsblk_t *partial_cluster,
+ ext4_lblk_t from, ext4_lblk_t to)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned short ee_len = ext4_ext_get_actual_len(ex);
+ ext4_fsblk_t pblk;
int flags = EXT4_FREE_BLOCKS_FORGET;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
flags |= EXT4_FREE_BLOCKS_METADATA;
+ /*
+ * For bigalloc file systems, we never free a partial cluster
+ * at the beginning of the extent. Instead, we make a note
+ * that we tried freeing the cluster, and check to see if we
+ * need to free it on a subsequent call to ext4_remove_blocks,
+ * or at the end of the ext4_truncate() operation.
+ */
+ flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER;
+
+ trace_ext4_remove_blocks(inode, ex, from, to, *partial_cluster);
+ /*
+ * If we have a partial cluster, and it's different from the
+ * cluster of the last block, we need to explicitly free the
+ * partial cluster here.
+ */
+ pblk = ext4_ext_pblock(ex) + ee_len - 1;
+ if (*partial_cluster && (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(sbi, *partial_cluster),
+ sbi->s_cluster_ratio, flags);
+ *partial_cluster = 0;
+ }
+
#ifdef EXTENTS_STATS
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -2222,12 +2242,24 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
&& to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* tail removal */
ext4_lblk_t num;
- ext4_fsblk_t start;
num = le32_to_cpu(ex->ee_block) + ee_len - from;
- start = ext4_ext_pblock(ex) + ee_len - num;
- ext_debug("free last %u blocks starting %llu\n", num, start);
- ext4_free_blocks(handle, inode, NULL, start, num, flags);
+ pblk = ext4_ext_pblock(ex) + ee_len - num;
+ ext_debug("free last %u blocks starting %llu\n", num, pblk);
+ ext4_free_blocks(handle, inode, NULL, pblk, num, flags);
+ /*
+ * If the block range to be freed didn't start at the
+ * beginning of a cluster, and we removed the entire
+ * extent, save the partial cluster here, since we
+ * might need to delete if we determine that the
+ * truncate operation has removed all of the blocks in
+ * the cluster.
+ */
+ if (pblk & (sbi->s_cluster_ratio - 1) &&
+ (ee_len == num))
+ *partial_cluster = EXT4_B2C(sbi, pblk);
+ else
+ *partial_cluster = 0;
} else if (from == le32_to_cpu(ex->ee_block)
&& to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* head removal */
@@ -2238,7 +2270,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
start = ext4_ext_pblock(ex);
ext_debug("free first %u blocks starting %llu\n", num, start);
- ext4_free_blocks(handle, inode, 0, start, num, flags);
+ ext4_free_blocks(handle, inode, NULL, start, num, flags);
} else {
printk(KERN_INFO "strange request: removal(2) "
@@ -2262,19 +2294,19 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
*/
static int
ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path, ext4_lblk_t start,
- ext4_lblk_t end)
+ struct ext4_ext_path *path, ext4_fsblk_t *partial_cluster,
+ ext4_lblk_t start, ext4_lblk_t end)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int err = 0, correct_index = 0;
int depth = ext_depth(inode), credits;
struct ext4_extent_header *eh;
- ext4_lblk_t a, b, block;
+ ext4_lblk_t a, b;
unsigned num;
ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
unsigned uninitialized = 0;
struct ext4_extent *ex;
- struct ext4_map_blocks map;
/* the header must be checked already in ext4_ext_remove_space() */
ext_debug("truncate since %u in leaf\n", start);
@@ -2291,6 +2323,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
+ trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
+
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
@@ -2315,86 +2349,18 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
continue;
- } else if (a != ex_ee_block &&
- b != ex_ee_block + ex_ee_len - 1) {
- /*
- * If this is a truncate, then this condition should
- * never happen because at least one of the end points
- * needs to be on the edge of the extent.
- */
- if (end == EXT_MAX_BLOCKS - 1) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- block = 0;
- num = 0;
- err = -EIO;
- goto out;
- }
- /*
- * else this is a hole punch, so the extent needs to
- * be split since neither edge of the hole is on the
- * extent edge
- */
- else{
- map.m_pblk = ext4_ext_pblock(ex);
- map.m_lblk = ex_ee_block;
- map.m_len = b - ex_ee_block;
-
- err = ext4_split_extent(handle,
- inode, path, &map, 0,
- EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
- EXT4_GET_BLOCKS_PRE_IO);
-
- if (err < 0)
- goto out;
-
- ex_ee_len = ext4_ext_get_actual_len(ex);
-
- b = ex_ee_block+ex_ee_len - 1 < end ?
- ex_ee_block+ex_ee_len - 1 : end;
-
- /* Then remove tail of this extent */
- block = ex_ee_block;
- num = a - block;
- }
+ } else if (b != ex_ee_block + ex_ee_len - 1) {
+ EXT4_ERROR_INODE(inode," bad truncate %u:%u\n",
+ start, end);
+ err = -EIO;
+ goto out;
} else if (a != ex_ee_block) {
/* remove tail of the extent */
- block = ex_ee_block;
- num = a - block;
- } else if (b != ex_ee_block + ex_ee_len - 1) {
- /* remove head of the extent */
- block = b;
- num = ex_ee_block + ex_ee_len - b;
-
- /*
- * If this is a truncate, this condition
- * should never happen
- */
- if (end == EXT_MAX_BLOCKS - 1) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- err = -EIO;
- goto out;
- }
+ num = a - ex_ee_block;
} else {
/* remove whole extent: excellent! */
- block = ex_ee_block;
num = 0;
- if (a != ex_ee_block) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- err = -EIO;
- goto out;
- }
-
- if (b != ex_ee_block + ex_ee_len - 1) {
- ext_debug(" bad truncate %u:%u\n",
- start, end);
- err = -EIO;
- goto out;
- }
}
-
/*
* 3 for leaf, sb, and inode plus 2 (bmap and group
* descriptor) for each block group; assume two block
@@ -2416,23 +2382,15 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
if (err)
goto out;
- err = ext4_remove_blocks(handle, inode, ex, a, b);
+ err = ext4_remove_blocks(handle, inode, ex, partial_cluster,
+ a, b);
if (err)
goto out;
- if (num == 0) {
+ if (num == 0)
/* this extent is removed; mark slot entirely unused */
ext4_ext_store_pblock(ex, 0);
- } else if (block != ex_ee_block) {
- /*
- * If this was a head removal, then we need to update
- * the physical block since it is now at a different
- * location
- */
- ext4_ext_store_pblock(ex, ext4_ext_pblock(ex) + (b-a));
- }
- ex->ee_block = cpu_to_le32(block);
ex->ee_len = cpu_to_le16(num);
/*
* Do not mark uninitialized if all the blocks in the
@@ -2440,11 +2398,6 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
*/
if (uninitialized && num)
ext4_ext_mark_uninitialized(ex);
-
- err = ext4_ext_dirty(handle, inode, path + depth);
- if (err)
- goto out;
-
/*
* If the extent was completely released,
* we need to remove it from the leaf
@@ -2464,9 +2417,14 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
sizeof(struct ext4_extent));
}
le16_add_cpu(&eh->eh_entries, -1);
- }
+ } else
+ *partial_cluster = 0;
- ext_debug("new extent: %u:%u:%llu\n", block, num,
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ ext_debug("new extent: %u:%u:%llu\n", ex_ee_block, num,
ext4_ext_pblock(ex));
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
@@ -2476,6 +2434,25 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
if (correct_index && eh->eh_entries)
err = ext4_ext_correct_indexes(handle, inode, path);
+ /*
+ * If there is still a entry in the leaf node, check to see if
+ * it references the partial cluster. This is the only place
+ * where it could; if it doesn't, we can free the cluster.
+ */
+ if (*partial_cluster && ex >= EXT_FIRST_EXTENT(eh) &&
+ (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
+ *partial_cluster)) {
+ int flags = EXT4_FREE_BLOCKS_FORGET;
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
+
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(sbi, *partial_cluster),
+ sbi->s_cluster_ratio, flags);
+ *partial_cluster = 0;
+ }
+
/* if this leaf is free, then we should
* remove it from index block above */
if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
@@ -2511,6 +2488,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
struct ext4_ext_path *path;
+ ext4_fsblk_t partial_cluster = 0;
handle_t *handle;
int i, err;
@@ -2524,6 +2502,8 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
again:
ext4_ext_invalidate_cache(inode);
+ trace_ext4_ext_remove_space(inode, start, depth);
+
/*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
@@ -2546,7 +2526,8 @@ again:
if (i == depth) {
/* this is leaf block */
err = ext4_ext_rm_leaf(handle, inode, path,
- start, EXT_MAX_BLOCKS - 1);
+ &partial_cluster, start,
+ EXT_MAX_BLOCKS - 1);
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
path[i].p_bh = NULL;
@@ -2618,6 +2599,24 @@ again:
}
}
+ trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster,
+ path->p_hdr->eh_entries);
+
+ /* If we still have something in the partial cluster and we have removed
+ * even the first extent, then we should free the blocks in the partial
+ * cluster as well. */
+ if (partial_cluster && path->p_hdr->eh_entries == 0) {
+ int flags = EXT4_FREE_BLOCKS_FORGET;
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
+
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(EXT4_SB(sb), partial_cluster),
+ EXT4_SB(sb)->s_cluster_ratio, flags);
+ partial_cluster = 0;
+ }
+
/* TODO: flexible tree reduction should be here */
if (path->p_hdr->eh_entries == 0) {
/*
@@ -2909,17 +2908,29 @@ out:
* a> There is no split required: Entire extent should be initialized
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
+ *
+ * Pre-conditions:
+ * - The extent pointed to by 'path' is uninitialized.
+ * - The extent pointed to by 'path' contains a superset
+ * of the logical span [map->m_lblk, map->m_lblk + map->m_len).
+ *
+ * Post-conditions on success:
+ * - the returned value is the number of blocks beyond map->l_lblk
+ * that are allocated and initialized.
+ * It is guaranteed to be >= map->m_len.
*/
static int ext4_ext_convert_to_initialized(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path *path)
{
+ struct ext4_extent_header *eh;
struct ext4_map_blocks split_map;
struct ext4_extent zero_ex;
struct ext4_extent *ex;
ext4_lblk_t ee_block, eof_block;
- unsigned int allocated, ee_len, depth;
+ unsigned int ee_len, depth;
+ int allocated;
int err = 0;
int split_flag = 0;
@@ -2933,11 +2944,93 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
eof_block = map->m_lblk + map->m_len;
depth = ext_depth(inode);
+ eh = path[depth].p_hdr;
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (map->m_lblk - ee_block);
+ trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
+
+ /* Pre-conditions */
+ BUG_ON(!ext4_ext_is_uninitialized(ex));
+ BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
+ BUG_ON(map->m_lblk + map->m_len > ee_block + ee_len);
+
+ /*
+ * Attempt to transfer newly initialized blocks from the currently
+ * uninitialized extent to its left neighbor. This is much cheaper
+ * than an insertion followed by a merge as those involve costly
+ * memmove() calls. This is the common case in steady state for
+ * workloads doing fallocate(FALLOC_FL_KEEP_SIZE) followed by append
+ * writes.
+ *
+ * Limitations of the current logic:
+ * - L1: we only deal with writes at the start of the extent.
+ * The approach could be extended to writes at the end
+ * of the extent but this scenario was deemed less common.
+ * - L2: we do not deal with writes covering the whole extent.
+ * This would require removing the extent if the transfer
+ * is possible.
+ * - L3: we only attempt to merge with an extent stored in the
+ * same extent tree node.
+ */
+ if ((map->m_lblk == ee_block) && /*L1*/
+ (map->m_len < ee_len) && /*L2*/
+ (ex > EXT_FIRST_EXTENT(eh))) { /*L3*/
+ struct ext4_extent *prev_ex;
+ ext4_lblk_t prev_lblk;
+ ext4_fsblk_t prev_pblk, ee_pblk;
+ unsigned int prev_len, write_len;
+
+ prev_ex = ex - 1;
+ prev_lblk = le32_to_cpu(prev_ex->ee_block);
+ prev_len = ext4_ext_get_actual_len(prev_ex);
+ prev_pblk = ext4_ext_pblock(prev_ex);
+ ee_pblk = ext4_ext_pblock(ex);
+ write_len = map->m_len;
+
+ /*
+ * A transfer of blocks from 'ex' to 'prev_ex' is allowed
+ * upon those conditions:
+ * - C1: prev_ex is initialized,
+ * - C2: prev_ex is logically abutting ex,
+ * - C3: prev_ex is physically abutting ex,
+ * - C4: prev_ex can receive the additional blocks without
+ * overflowing the (initialized) length limit.
+ */
+ if ((!ext4_ext_is_uninitialized(prev_ex)) && /*C1*/
+ ((prev_lblk + prev_len) == ee_block) && /*C2*/
+ ((prev_pblk + prev_len) == ee_pblk) && /*C3*/
+ (prev_len < (EXT_INIT_MAX_LEN - write_len))) { /*C4*/
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ trace_ext4_ext_convert_to_initialized_fastpath(inode,
+ map, ex, prev_ex);
+
+ /* Shift the start of ex by 'write_len' blocks */
+ ex->ee_block = cpu_to_le32(ee_block + write_len);
+ ext4_ext_store_pblock(ex, ee_pblk + write_len);
+ ex->ee_len = cpu_to_le16(ee_len - write_len);
+ ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+
+ /* Extend prev_ex by 'write_len' blocks */
+ prev_ex->ee_len = cpu_to_le16(prev_len + write_len);
+
+ /* Mark the block containing both extents as dirty */
+ ext4_ext_dirty(handle, inode, path + depth);
+
+ /* Update path to point to the right extent */
+ path[depth].p_ext = prev_ex;
+
+ /* Result: number of initialized blocks past m_lblk */
+ allocated = write_len;
+ goto out;
+ }
+ }
+
WARN_ON(map->m_lblk < ee_block);
/*
* It is safe to convert extent to initialized via explicit
@@ -3165,6 +3258,192 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
return ext4_mark_inode_dirty(handle, inode);
}
+/**
+ * ext4_find_delalloc_range: find delayed allocated block in the given range.
+ *
+ * Goes through the buffer heads in the range [lblk_start, lblk_end] and returns
+ * whether there are any buffers marked for delayed allocation. It returns '1'
+ * on the first delalloc'ed buffer head found. If no buffer head in the given
+ * range is marked for delalloc, it returns 0.
+ * lblk_start should always be <= lblk_end.
+ * search_hint_reverse is to indicate that searching in reverse from lblk_end to
+ * lblk_start might be more efficient (i.e., we will likely hit the delalloc'ed
+ * block sooner). This is useful when blocks are truncated sequentially from
+ * lblk_start towards lblk_end.
+ */
+static int ext4_find_delalloc_range(struct inode *inode,
+ ext4_lblk_t lblk_start,
+ ext4_lblk_t lblk_end,
+ int search_hint_reverse)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct buffer_head *head, *bh = NULL;
+ struct page *page;
+ ext4_lblk_t i, pg_lblk;
+ pgoff_t index;
+
+ /* reverse search wont work if fs block size is less than page size */
+ if (inode->i_blkbits < PAGE_CACHE_SHIFT)
+ search_hint_reverse = 0;
+
+ if (search_hint_reverse)
+ i = lblk_end;
+ else
+ i = lblk_start;
+
+ index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ while ((i >= lblk_start) && (i <= lblk_end)) {
+ page = find_get_page(mapping, index);
+ if (!page)
+ goto nextpage;
+
+ if (!page_has_buffers(page))
+ goto nextpage;
+
+ head = page_buffers(page);
+ if (!head)
+ goto nextpage;
+
+ bh = head;
+ pg_lblk = index << (PAGE_CACHE_SHIFT -
+ inode->i_blkbits);
+ do {
+ if (unlikely(pg_lblk < lblk_start)) {
+ /*
+ * This is possible when fs block size is less
+ * than page size and our cluster starts/ends in
+ * middle of the page. So we need to skip the
+ * initial few blocks till we reach the 'lblk'
+ */
+ pg_lblk++;
+ continue;
+ }
+
+ /* Check if the buffer is delayed allocated and that it
+ * is not yet mapped. (when da-buffers are mapped during
+ * their writeout, their da_mapped bit is set.)
+ */
+ if (buffer_delay(bh) && !buffer_da_mapped(bh)) {
+ page_cache_release(page);
+ trace_ext4_find_delalloc_range(inode,
+ lblk_start, lblk_end,
+ search_hint_reverse,
+ 1, i);
+ return 1;
+ }
+ if (search_hint_reverse)
+ i--;
+ else
+ i++;
+ } while ((i >= lblk_start) && (i <= lblk_end) &&
+ ((bh = bh->b_this_page) != head));
+nextpage:
+ if (page)
+ page_cache_release(page);
+ /*
+ * Move to next page. 'i' will be the first lblk in the next
+ * page.
+ */
+ if (search_hint_reverse)
+ index--;
+ else
+ index++;
+ i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ }
+
+ trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end,
+ search_hint_reverse, 0, 0);
+ return 0;
+}
+
+int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
+ int search_hint_reverse)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ ext4_lblk_t lblk_start, lblk_end;
+ lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+ lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
+
+ return ext4_find_delalloc_range(inode, lblk_start, lblk_end,
+ search_hint_reverse);
+}
+
+/**
+ * Determines how many complete clusters (out of those specified by the 'map')
+ * are under delalloc and were reserved quota for.
+ * This function is called when we are writing out the blocks that were
+ * originally written with their allocation delayed, but then the space was
+ * allocated using fallocate() before the delayed allocation could be resolved.
+ * The cases to look for are:
+ * ('=' indicated delayed allocated blocks
+ * '-' indicates non-delayed allocated blocks)
+ * (a) partial clusters towards beginning and/or end outside of allocated range
+ * are not delalloc'ed.
+ * Ex:
+ * |----c---=|====c====|====c====|===-c----|
+ * |++++++ allocated ++++++|
+ * ==> 4 complete clusters in above example
+ *
+ * (b) partial cluster (outside of allocated range) towards either end is
+ * marked for delayed allocation. In this case, we will exclude that
+ * cluster.
+ * Ex:
+ * |----====c========|========c========|
+ * |++++++ allocated ++++++|
+ * ==> 1 complete clusters in above example
+ *
+ * Ex:
+ * |================c================|
+ * |++++++ allocated ++++++|
+ * ==> 0 complete clusters in above example
+ *
+ * The ext4_da_update_reserve_space will be called only if we
+ * determine here that there were some "entire" clusters that span
+ * this 'allocated' range.
+ * In the non-bigalloc case, this function will just end up returning num_blks
+ * without ever calling ext4_find_delalloc_range.
+ */
+static unsigned int
+get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
+ unsigned int num_blks)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ ext4_lblk_t alloc_cluster_start, alloc_cluster_end;
+ ext4_lblk_t lblk_from, lblk_to, c_offset;
+ unsigned int allocated_clusters = 0;
+
+ alloc_cluster_start = EXT4_B2C(sbi, lblk_start);
+ alloc_cluster_end = EXT4_B2C(sbi, lblk_start + num_blks - 1);
+
+ /* max possible clusters for this allocation */
+ allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1;
+
+ trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
+
+ /* Check towards left side */
+ c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+ if (c_offset) {
+ lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+ lblk_to = lblk_from + c_offset - 1;
+
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ allocated_clusters--;
+ }
+
+ /* Now check towards right. */
+ c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+ if (allocated_clusters && c_offset) {
+ lblk_from = lblk_start + num_blks;
+ lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
+
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ allocated_clusters--;
+ }
+
+ return allocated_clusters;
+}
+
static int
ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
@@ -3181,6 +3460,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
flags, allocated);
ext4_ext_show_leaf(inode, path);
+ trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated,
+ newblock);
+
/* get_block() before submit the IO, split the extent */
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
ret = ext4_split_unwritten_extents(handle, inode, map,
@@ -3190,10 +3472,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
* that this IO needs to conversion to written when IO is
* completed
*/
- if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
- io->flag = EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
- } else
+ if (io)
+ ext4_set_io_unwritten_flag(inode, io);
+ else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
if (ext4_should_dioread_nolock(inode))
map->m_flags |= EXT4_MAP_UNINIT;
@@ -3234,14 +3515,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
/* buffered write, writepage time, convert*/
ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
- if (ret >= 0) {
+ if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
- err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
- map->m_len);
- if (err < 0)
- goto out2;
- }
-
out:
if (ret <= 0) {
err = ret;
@@ -3270,11 +3545,24 @@ out:
* But fallocate would have already updated quota and block
* count for this offset. So cancel these reservation
*/
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- ext4_da_update_reserve_space(inode, allocated, 0);
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+ unsigned int reserved_clusters;
+ reserved_clusters = get_reserved_cluster_alloc(inode,
+ map->m_lblk, map->m_len);
+ if (reserved_clusters)
+ ext4_da_update_reserve_space(inode,
+ reserved_clusters,
+ 0);
+ }
map_out:
map->m_flags |= EXT4_MAP_MAPPED;
+ if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) {
+ err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
+ map->m_len);
+ if (err < 0)
+ goto out2;
+ }
out1:
if (allocated > map->m_len)
allocated = map->m_len;
@@ -3290,6 +3578,111 @@ out2:
}
/*
+ * get_implied_cluster_alloc - check to see if the requested
+ * allocation (in the map structure) overlaps with a cluster already
+ * allocated in an extent.
+ * @sb The filesystem superblock structure
+ * @map The requested lblk->pblk mapping
+ * @ex The extent structure which might contain an implied
+ * cluster allocation
+ *
+ * This function is called by ext4_ext_map_blocks() after we failed to
+ * find blocks that were already in the inode's extent tree. Hence,
+ * we know that the beginning of the requested region cannot overlap
+ * the extent from the inode's extent tree. There are three cases we
+ * want to catch. The first is this case:
+ *
+ * |--- cluster # N--|
+ * |--- extent ---| |---- requested region ---|
+ * |==========|
+ *
+ * The second case that we need to test for is this one:
+ *
+ * |--------- cluster # N ----------------|
+ * |--- requested region --| |------- extent ----|
+ * |=======================|
+ *
+ * The third case is when the requested region lies between two extents
+ * within the same cluster:
+ * |------------- cluster # N-------------|
+ * |----- ex -----| |---- ex_right ----|
+ * |------ requested region ------|
+ * |================|
+ *
+ * In each of the above cases, we need to set the map->m_pblk and
+ * map->m_len so it corresponds to the return the extent labelled as
+ * "|====|" from cluster #N, since it is already in use for data in
+ * cluster EXT4_B2C(sbi, map->m_lblk). We will then return 1 to
+ * signal to ext4_ext_map_blocks() that map->m_pblk should be treated
+ * as a new "allocated" block region. Otherwise, we will return 0 and
+ * ext4_ext_map_blocks() will then allocate one or more new clusters
+ * by calling ext4_mb_new_blocks().
+ */
+static int get_implied_cluster_alloc(struct super_block *sb,
+ struct ext4_map_blocks *map,
+ struct ext4_extent *ex,
+ struct ext4_ext_path *path)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+ ext4_lblk_t ex_cluster_start, ex_cluster_end;
+ ext4_lblk_t rr_cluster_start, rr_cluster_end;
+ ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
+ ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
+ unsigned short ee_len = ext4_ext_get_actual_len(ex);
+
+ /* The extent passed in that we are trying to match */
+ ex_cluster_start = EXT4_B2C(sbi, ee_block);
+ ex_cluster_end = EXT4_B2C(sbi, ee_block + ee_len - 1);
+
+ /* The requested region passed into ext4_map_blocks() */
+ rr_cluster_start = EXT4_B2C(sbi, map->m_lblk);
+ rr_cluster_end = EXT4_B2C(sbi, map->m_lblk + map->m_len - 1);
+
+ if ((rr_cluster_start == ex_cluster_end) ||
+ (rr_cluster_start == ex_cluster_start)) {
+ if (rr_cluster_start == ex_cluster_end)
+ ee_start += ee_len - 1;
+ map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
+ c_offset;
+ map->m_len = min(map->m_len,
+ (unsigned) sbi->s_cluster_ratio - c_offset);
+ /*
+ * Check for and handle this case:
+ *
+ * |--------- cluster # N-------------|
+ * |------- extent ----|
+ * |--- requested region ---|
+ * |===========|
+ */
+
+ if (map->m_lblk < ee_block)
+ map->m_len = min(map->m_len, ee_block - map->m_lblk);
+
+ /*
+ * Check for the case where there is already another allocated
+ * block to the right of 'ex' but before the end of the cluster.
+ *
+ * |------------- cluster # N-------------|
+ * |----- ex -----| |---- ex_right ----|
+ * |------ requested region ------|
+ * |================|
+ */
+ if (map->m_lblk > ee_block) {
+ ext4_lblk_t next = ext4_ext_next_allocated_block(path);
+ map->m_len = min(map->m_len, next - map->m_lblk);
+ }
+
+ trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1);
+ return 1;
+ }
+
+ trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0);
+ return 0;
+}
+
+
+/*
* Block allocation/map/preallocation routine for extents based files
*
*
@@ -3311,15 +3704,17 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
struct ext4_ext_path *path = NULL;
- struct ext4_extent newex, *ex;
+ struct ext4_extent newex, *ex, *ex2;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_fsblk_t newblock = 0;
- int err = 0, depth, ret;
- unsigned int allocated = 0;
+ int free_on_err = 0, err = 0, depth, ret;
+ unsigned int allocated = 0, offset = 0;
+ unsigned int allocated_clusters = 0;
unsigned int punched_out = 0;
unsigned int result = 0;
struct ext4_allocation_request ar;
ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
- struct ext4_map_blocks punch_map;
+ ext4_lblk_t cluster_offset;
ext_debug("blocks %u/%u requested for inode %lu\n",
map->m_lblk, map->m_len, inode->i_ino);
@@ -3329,6 +3724,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) &&
ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
if (!newex.ee_start_lo && !newex.ee_start_hi) {
+ if ((sbi->s_cluster_ratio > 1) &&
+ ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
/*
* block isn't allocated yet and
@@ -3339,6 +3738,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/* we should allocate requested block */
} else {
/* block is already allocated */
+ if (sbi->s_cluster_ratio > 1)
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
newblock = map->m_lblk
- le32_to_cpu(newex.ee_block)
+ ext4_ext_pblock(&newex);
@@ -3384,8 +3785,14 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* we split out initialized portions during a write.
*/
ee_len = ext4_ext_get_actual_len(ex);
+
+ trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len);
+
/* if found extent covers block, simply return it */
if (in_range(map->m_lblk, ee_block, ee_len)) {
+ struct ext4_map_blocks punch_map;
+ ext4_fsblk_t partial_cluster = 0;
+
newblock = map->m_lblk - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (map->m_lblk - ee_block);
@@ -3469,7 +3876,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ext4_ext_invalidate_cache(inode);
err = ext4_ext_rm_leaf(handle, inode, path,
- map->m_lblk, map->m_lblk + punched_out);
+ &partial_cluster, map->m_lblk,
+ map->m_lblk + punched_out);
if (!err && path->p_hdr->eh_entries == 0) {
/*
@@ -3492,6 +3900,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
}
}
+ if ((sbi->s_cluster_ratio > 1) &&
+ ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+
/*
* requested block isn't allocated yet;
* we couldn't try to create block if create flag is zero
@@ -3504,9 +3916,25 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
goto out2;
}
+
/*
* Okay, we need to do block allocation.
*/
+ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
+ newex.ee_block = cpu_to_le32(map->m_lblk);
+ cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+
+ /*
+ * If we are doing bigalloc, check to see if the extent returned
+ * by ext4_ext_find_extent() implies a cluster we can use.
+ */
+ if (cluster_offset && ex &&
+ get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
+ ar.len = allocated = map->m_len;
+ newblock = map->m_pblk;
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+ goto got_allocated_blocks;
+ }
/* find neighbour allocated blocks */
ar.lleft = map->m_lblk;
@@ -3514,10 +3942,21 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
if (err)
goto out2;
ar.lright = map->m_lblk;
- err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
+ ex2 = NULL;
+ err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2);
if (err)
goto out2;
+ /* Check if the extent after searching to the right implies a
+ * cluster we can use. */
+ if ((sbi->s_cluster_ratio > 1) && ex2 &&
+ get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
+ ar.len = allocated = map->m_len;
+ newblock = map->m_pblk;
+ map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+ goto got_allocated_blocks;
+ }
+
/*
* See if request is beyond maximum number of blocks we can have in
* a single extent. For an initialized extent this limit is
@@ -3532,9 +3971,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
map->m_len = EXT_UNINIT_MAX_LEN;
/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
- newex.ee_block = cpu_to_le32(map->m_lblk);
newex.ee_len = cpu_to_le16(map->m_len);
- err = ext4_ext_check_overlap(inode, &newex, path);
+ err = ext4_ext_check_overlap(sbi, inode, &newex, path);
if (err)
allocated = ext4_ext_get_actual_len(&newex);
else
@@ -3544,7 +3982,18 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ar.inode = inode;
ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk);
ar.logical = map->m_lblk;
- ar.len = allocated;
+ /*
+ * We calculate the offset from the beginning of the cluster
+ * for the logical block number, since when we allocate a
+ * physical cluster, the physical block should start at the
+ * same offset from the beginning of the cluster. This is
+ * needed so that future calls to get_implied_cluster_alloc()
+ * work correctly.
+ */
+ offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+ ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
+ ar.goal -= offset;
+ ar.logical -= offset;
if (S_ISREG(inode->i_mode))
ar.flags = EXT4_MB_HINT_DATA;
else
@@ -3557,9 +4006,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
goto out2;
ext_debug("allocate new block: goal %llu, found %llu/%u\n",
ar.goal, newblock, allocated);
+ free_on_err = 1;
+ allocated_clusters = ar.len;
+ ar.len = EXT4_C2B(sbi, ar.len) - offset;
+ if (ar.len > allocated)
+ ar.len = allocated;
+got_allocated_blocks:
/* try to insert new extent into found leaf and return */
- ext4_ext_store_pblock(&newex, newblock);
+ ext4_ext_store_pblock(&newex, newblock + offset);
newex.ee_len = cpu_to_le16(ar.len);
/* Mark uninitialized */
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
@@ -3572,10 +4027,9 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* that we need to perform conversion when IO is done.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
- if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
- io->flag = EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
- } else
+ if (io)
+ ext4_set_io_unwritten_flag(inode, io);
+ else
ext4_set_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN);
}
@@ -3583,11 +4037,14 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
map->m_flags |= EXT4_MAP_UNINIT;
}
- err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len);
+ err = 0;
+ if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0)
+ err = check_eofblocks_fl(handle, inode, map->m_lblk,
+ path, ar.len);
if (!err)
err = ext4_ext_insert_extent(handle, inode, path,
&newex, flags);
- if (err) {
+ if (err && free_on_err) {
int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
/* free data blocks we just allocated */
@@ -3610,8 +4067,82 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* Update reserved blocks/metadata blocks after successful
* block allocation which had been deferred till now.
*/
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- ext4_da_update_reserve_space(inode, allocated, 1);
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+ unsigned int reserved_clusters;
+ /*
+ * Check how many clusters we had reserved this allocated range
+ */
+ reserved_clusters = get_reserved_cluster_alloc(inode,
+ map->m_lblk, allocated);
+ if (map->m_flags & EXT4_MAP_FROM_CLUSTER) {
+ if (reserved_clusters) {
+ /*
+ * We have clusters reserved for this range.
+ * But since we are not doing actual allocation
+ * and are simply using blocks from previously
+ * allocated cluster, we should release the
+ * reservation and not claim quota.
+ */
+ ext4_da_update_reserve_space(inode,
+ reserved_clusters, 0);
+ }
+ } else {
+ BUG_ON(allocated_clusters < reserved_clusters);
+ /* We will claim quota for all newly allocated blocks.*/
+ ext4_da_update_reserve_space(inode, allocated_clusters,
+ 1);
+ if (reserved_clusters < allocated_clusters) {
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int reservation = allocated_clusters -
+ reserved_clusters;
+ /*
+ * It seems we claimed few clusters outside of
+ * the range of this allocation. We should give
+ * it back to the reservation pool. This can
+ * happen in the following case:
+ *
+ * * Suppose s_cluster_ratio is 4 (i.e., each
+ * cluster has 4 blocks. Thus, the clusters
+ * are [0-3],[4-7],[8-11]...
+ * * First comes delayed allocation write for
+ * logical blocks 10 & 11. Since there were no
+ * previous delayed allocated blocks in the
+ * range [8-11], we would reserve 1 cluster
+ * for this write.
+ * * Next comes write for logical blocks 3 to 8.
+ * In this case, we will reserve 2 clusters
+ * (for [0-3] and [4-7]; and not for [8-11] as
+ * that range has a delayed allocated blocks.
+ * Thus total reserved clusters now becomes 3.
+ * * Now, during the delayed allocation writeout
+ * time, we will first write blocks [3-8] and
+ * allocate 3 clusters for writing these
+ * blocks. Also, we would claim all these
+ * three clusters above.
+ * * Now when we come here to writeout the
+ * blocks [10-11], we would expect to claim
+ * the reservation of 1 cluster we had made
+ * (and we would claim it since there are no
+ * more delayed allocated blocks in the range
+ * [8-11]. But our reserved cluster count had
+ * already gone to 0.
+ *
+ * Thus, at the step 4 above when we determine
+ * that there are still some unwritten delayed
+ * allocated blocks outside of our current
+ * block range, we should increment the
+ * reserved clusters count so that when the
+ * remaining blocks finally gets written, we
+ * could claim them.
+ */
+ dquot_reserve_block(inode,
+ EXT4_C2B(sbi, reservation));
+ spin_lock(&ei->i_block_reservation_lock);
+ ei->i_reserved_data_blocks += reservation;
+ spin_unlock(&ei->i_block_reservation_lock);
+ }
+ }
+ }
/*
* Cache the extent and update transaction to commit on fdatasync only
@@ -3634,12 +4165,12 @@ out2:
ext4_ext_drop_refs(path);
kfree(path);
}
- trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
- newblock, map->m_len, err ? err : allocated);
-
result = (flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) ?
punched_out : allocated;
+ trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
+ newblock, map->m_len, err ? err : result);
+
return err ? err : result;
}
@@ -3649,6 +4180,7 @@ void ext4_ext_truncate(struct inode *inode)
struct super_block *sb = inode->i_sb;
ext4_lblk_t last_block;
handle_t *handle;
+ loff_t page_len;
int err = 0;
/*
@@ -3665,8 +4197,16 @@ void ext4_ext_truncate(struct inode *inode)
if (IS_ERR(handle))
return;
- if (inode->i_size & (sb->s_blocksize - 1))
- ext4_block_truncate_page(handle, mapping, inode->i_size);
+ if (inode->i_size % PAGE_CACHE_SIZE != 0) {
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0);
+
+ if (err)
+ goto out_stop;
+ }
if (ext4_orphan_add(handle, inode))
goto out_stop;
@@ -3760,6 +4300,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
int ret = 0;
int ret2 = 0;
int retries = 0;
+ int flags;
struct ext4_map_blocks map;
unsigned int credits, blkbits = inode->i_blkbits;
@@ -3796,6 +4337,16 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
return ret;
}
+ flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
+ if (mode & FALLOC_FL_KEEP_SIZE)
+ flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+ /*
+ * Don't normalize the request if it can fit in one extent so
+ * that it doesn't get unnecessarily split into multiple
+ * extents.
+ */
+ if (len <= EXT_UNINIT_MAX_LEN << blkbits)
+ flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
retry:
while (ret >= 0 && ret < max_blocks) {
map.m_lblk = map.m_lblk + ret;
@@ -3805,9 +4356,7 @@ retry:
ret = PTR_ERR(handle);
break;
}
- ret = ext4_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
- EXT4_GET_BLOCKS_NO_NORMALIZE);
+ ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret <= 0) {
#ifdef EXT4FS_DEBUG
WARN_ON(ret <= 0);
@@ -4102,7 +4651,6 @@ found_delayed_extent:
return EXT_BREAK;
return EXT_CONTINUE;
}
-
/* fiemap flags we can handle specified here */
#define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
@@ -4162,17 +4710,28 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
struct address_space *mapping = inode->i_mapping;
struct ext4_map_blocks map;
handle_t *handle;
- loff_t first_block_offset, last_block_offset, block_len;
- loff_t first_page, last_page, first_page_offset, last_page_offset;
+ loff_t first_page, last_page, page_len;
+ loff_t first_page_offset, last_page_offset;
int ret, credits, blocks_released, err = 0;
+ /* No need to punch hole beyond i_size */
+ if (offset >= inode->i_size)
+ return 0;
+
+ /*
+ * If the hole extends beyond i_size, set the hole
+ * to end after the page that contains i_size
+ */
+ if (offset + length > inode->i_size) {
+ length = inode->i_size +
+ PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
+ offset;
+ }
+
first_block = (offset + sb->s_blocksize - 1) >>
EXT4_BLOCK_SIZE_BITS(sb);
last_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
- first_block_offset = first_block << EXT4_BLOCK_SIZE_BITS(sb);
- last_block_offset = last_block << EXT4_BLOCK_SIZE_BITS(sb);
-
first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
last_page = (offset + length) >> PAGE_CACHE_SHIFT;
@@ -4185,11 +4744,10 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
*/
if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
err = filemap_write_and_wait_range(mapping,
- first_page_offset == 0 ? 0 : first_page_offset-1,
- last_page_offset);
+ offset, offset + length - 1);
- if (err)
- return err;
+ if (err)
+ return err;
}
/* Now release the pages */
@@ -4211,24 +4769,64 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
goto out;
/*
- * Now we need to zero out the un block aligned data.
- * If the file is smaller than a block, just
- * zero out the middle
+ * Now we need to zero out the non-page-aligned data in the
+ * pages at the start and tail of the hole, and unmap the buffer
+ * heads for the block aligned regions of the page that were
+ * completely zeroed.
*/
- if (first_block > last_block)
- ext4_block_zero_page_range(handle, mapping, offset, length);
- else {
- /* zero out the head of the hole before the first block */
- block_len = first_block_offset - offset;
- if (block_len > 0)
- ext4_block_zero_page_range(handle, mapping,
- offset, block_len);
-
- /* zero out the tail of the hole after the last block */
- block_len = offset + length - last_block_offset;
- if (block_len > 0) {
- ext4_block_zero_page_range(handle, mapping,
- last_block_offset, block_len);
+ if (first_page > last_page) {
+ /*
+ * If the file space being truncated is contained within a page
+ * just zero out and unmap the middle of that page
+ */
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, offset, length, 0);
+
+ if (err)
+ goto out;
+ } else {
+ /*
+ * zero out and unmap the partial page that contains
+ * the start of the hole
+ */
+ page_len = first_page_offset - offset;
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle, mapping,
+ offset, page_len, 0);
+ if (err)
+ goto out;
+ }
+
+ /*
+ * zero out and unmap the partial page that contains
+ * the end of the hole
+ */
+ page_len = offset + length - last_page_offset;
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle, mapping,
+ last_page_offset, page_len, 0);
+ if (err)
+ goto out;
+ }
+ }
+
+
+ /*
+ * If i_size is contained in the last page, we need to
+ * unmap and zero the partial page after i_size
+ */
+ if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
+ inode->i_size % PAGE_CACHE_SIZE != 0) {
+
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0);
+
+ if (err)
+ goto out;
}
}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index b9548f477bb8..cb70f1812a70 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -181,8 +181,8 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
- memcpy(sbi->s_es->s_last_mounted, cp,
- sizeof(sbi->s_es->s_last_mounted));
+ strlcpy(sbi->s_es->s_last_mounted, cp,
+ sizeof(sbi->s_es->s_last_mounted));
ext4_mark_super_dirty(sb);
}
}
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 036f78f7a1ef..00a2cb753efd 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -75,7 +75,7 @@ static void dump_completed_IO(struct inode * inode)
* to written.
* The function return the number of pending IOs on success.
*/
-extern int ext4_flush_completed_IO(struct inode *inode)
+int ext4_flush_completed_IO(struct inode *inode)
{
ext4_io_end_t *io;
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -83,14 +83,12 @@ extern int ext4_flush_completed_IO(struct inode *inode)
int ret = 0;
int ret2 = 0;
- if (list_empty(&ei->i_completed_io_list))
- return ret;
-
dump_completed_IO(inode);
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
while (!list_empty(&ei->i_completed_io_list)){
io = list_entry(ei->i_completed_io_list.next,
ext4_io_end_t, list);
+ list_del_init(&io->list);
/*
* Calling ext4_end_io_nolock() to convert completed
* IO to written.
@@ -107,11 +105,9 @@ extern int ext4_flush_completed_IO(struct inode *inode)
*/
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
ret = ext4_end_io_nolock(io);
- spin_lock_irqsave(&ei->i_completed_io_lock, flags);
if (ret < 0)
ret2 = ret;
- else
- list_del_init(&io->list);
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
}
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
return (ret2 < 0) ? ret2 : 0;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 9c63f273b550..00beb4f9cc4f 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -78,7 +78,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
* allocation, essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, "Checksum bad for group %u", block_group);
- ext4_free_blks_set(sb, gdp, 0);
+ ext4_free_group_clusters_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
memset(bh->b_data, 0xff, sb->s_blocksize);
@@ -293,121 +293,9 @@ error_return:
ext4_std_error(sb, fatal);
}
-/*
- * There are two policies for allocating an inode. If the new inode is
- * a directory, then a forward search is made for a block group with both
- * free space and a low directory-to-inode ratio; if that fails, then of
- * the groups with above-average free space, that group with the fewest
- * directories already is chosen.
- *
- * For other inodes, search forward from the parent directory\'s block
- * group to find a free inode.
- */
-static int find_group_dir(struct super_block *sb, struct inode *parent,
- ext4_group_t *best_group)
-{
- ext4_group_t ngroups = ext4_get_groups_count(sb);
- unsigned int freei, avefreei;
- struct ext4_group_desc *desc, *best_desc = NULL;
- ext4_group_t group;
- int ret = -1;
-
- freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
- avefreei = freei / ngroups;
-
- for (group = 0; group < ngroups; group++) {
- desc = ext4_get_group_desc(sb, group, NULL);
- if (!desc || !ext4_free_inodes_count(sb, desc))
- continue;
- if (ext4_free_inodes_count(sb, desc) < avefreei)
- continue;
- if (!best_desc ||
- (ext4_free_blks_count(sb, desc) >
- ext4_free_blks_count(sb, best_desc))) {
- *best_group = group;
- best_desc = desc;
- ret = 0;
- }
- }
- return ret;
-}
-
-#define free_block_ratio 10
-
-static int find_group_flex(struct super_block *sb, struct inode *parent,
- ext4_group_t *best_group)
-{
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_group_desc *desc;
- struct flex_groups *flex_group = sbi->s_flex_groups;
- ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
- ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
- ext4_group_t ngroups = ext4_get_groups_count(sb);
- int flex_size = ext4_flex_bg_size(sbi);
- ext4_group_t best_flex = parent_fbg_group;
- int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
- int flexbg_free_blocks;
- int flex_freeb_ratio;
- ext4_group_t n_fbg_groups;
- ext4_group_t i;
-
- n_fbg_groups = (ngroups + flex_size - 1) >>
- sbi->s_log_groups_per_flex;
-
-find_close_to_parent:
- flexbg_free_blocks = atomic_read(&flex_group[best_flex].free_blocks);
- flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
- if (atomic_read(&flex_group[best_flex].free_inodes) &&
- flex_freeb_ratio > free_block_ratio)
- goto found_flexbg;
-
- if (best_flex && best_flex == parent_fbg_group) {
- best_flex--;
- goto find_close_to_parent;
- }
-
- for (i = 0; i < n_fbg_groups; i++) {
- if (i == parent_fbg_group || i == parent_fbg_group - 1)
- continue;
-
- flexbg_free_blocks = atomic_read(&flex_group[i].free_blocks);
- flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
-
- if (flex_freeb_ratio > free_block_ratio &&
- (atomic_read(&flex_group[i].free_inodes))) {
- best_flex = i;
- goto found_flexbg;
- }
-
- if ((atomic_read(&flex_group[best_flex].free_inodes) == 0) ||
- ((atomic_read(&flex_group[i].free_blocks) >
- atomic_read(&flex_group[best_flex].free_blocks)) &&
- atomic_read(&flex_group[i].free_inodes)))
- best_flex = i;
- }
-
- if (!atomic_read(&flex_group[best_flex].free_inodes) ||
- !atomic_read(&flex_group[best_flex].free_blocks))
- return -1;
-
-found_flexbg:
- for (i = best_flex * flex_size; i < ngroups &&
- i < (best_flex + 1) * flex_size; i++) {
- desc = ext4_get_group_desc(sb, i, NULL);
- if (ext4_free_inodes_count(sb, desc)) {
- *best_group = i;
- goto out;
- }
- }
-
- return -1;
-out:
- return 0;
-}
-
struct orlov_stats {
__u32 free_inodes;
- __u32 free_blocks;
+ __u32 free_clusters;
__u32 used_dirs;
};
@@ -424,7 +312,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
if (flex_size > 1) {
stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
- stats->free_blocks = atomic_read(&flex_group[g].free_blocks);
+ stats->free_clusters = atomic_read(&flex_group[g].free_clusters);
stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
return;
}
@@ -432,11 +320,11 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
desc = ext4_get_group_desc(sb, g, NULL);
if (desc) {
stats->free_inodes = ext4_free_inodes_count(sb, desc);
- stats->free_blocks = ext4_free_blks_count(sb, desc);
+ stats->free_clusters = ext4_free_group_clusters(sb, desc);
stats->used_dirs = ext4_used_dirs_count(sb, desc);
} else {
stats->free_inodes = 0;
- stats->free_blocks = 0;
+ stats->free_clusters = 0;
stats->used_dirs = 0;
}
}
@@ -471,10 +359,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
ext4_group_t real_ngroups = ext4_get_groups_count(sb);
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
- ext4_fsblk_t freeb, avefreeb;
+ ext4_fsblk_t freeb, avefreec;
unsigned int ndirs;
int max_dirs, min_inodes;
- ext4_grpblk_t min_blocks;
+ ext4_grpblk_t min_clusters;
ext4_group_t i, grp, g, ngroups;
struct ext4_group_desc *desc;
struct orlov_stats stats;
@@ -490,9 +378,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
avefreei = freei / ngroups;
- freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
- avefreeb = freeb;
- do_div(avefreeb, ngroups);
+ freeb = EXT4_C2B(sbi,
+ percpu_counter_read_positive(&sbi->s_freeclusters_counter));
+ avefreec = freeb;
+ do_div(avefreec, ngroups);
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
if (S_ISDIR(mode) &&
@@ -518,7 +407,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
continue;
if (stats.free_inodes < avefreei)
continue;
- if (stats.free_blocks < avefreeb)
+ if (stats.free_clusters < avefreec)
continue;
grp = g;
ret = 0;
@@ -556,7 +445,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
min_inodes = avefreei - inodes_per_group*flex_size / 4;
if (min_inodes < 1)
min_inodes = 1;
- min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb)*flex_size / 4;
+ min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4;
/*
* Start looking in the flex group where we last allocated an
@@ -575,7 +464,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
continue;
if (stats.free_inodes < min_inodes)
continue;
- if (stats.free_blocks < min_blocks)
+ if (stats.free_clusters < min_clusters)
continue;
goto found_flex_bg;
}
@@ -659,7 +548,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
*group = parent_group;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && ext4_free_inodes_count(sb, desc) &&
- ext4_free_blks_count(sb, desc))
+ ext4_free_group_clusters(sb, desc))
return 0;
/*
@@ -683,7 +572,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
*group -= ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && ext4_free_inodes_count(sb, desc) &&
- ext4_free_blks_count(sb, desc))
+ ext4_free_group_clusters(sb, desc))
return 0;
}
@@ -802,7 +691,7 @@ err_ret:
* group to find a free inode.
*/
struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
- const struct qstr *qstr, __u32 goal)
+ const struct qstr *qstr, __u32 goal, uid_t *owner)
{
struct super_block *sb;
struct buffer_head *inode_bitmap_bh = NULL;
@@ -816,8 +705,6 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
int ret2, err = 0;
struct inode *ret;
ext4_group_t i;
- int free = 0;
- static int once = 1;
ext4_group_t flex_group;
/* Cannot create files in a deleted directory */
@@ -843,26 +730,9 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
goto got_group;
}
- if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
- ret2 = find_group_flex(sb, dir, &group);
- if (ret2 == -1) {
- ret2 = find_group_other(sb, dir, &group, mode);
- if (ret2 == 0 && once) {
- once = 0;
- printk(KERN_NOTICE "ext4: find_group_flex "
- "failed, fallback succeeded dir %lu\n",
- dir->i_ino);
- }
- }
- goto got_group;
- }
-
- if (S_ISDIR(mode)) {
- if (test_opt(sb, OLDALLOC))
- ret2 = find_group_dir(sb, dir, &group);
- else
- ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
- } else
+ if (S_ISDIR(mode))
+ ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
+ else
ret2 = find_group_other(sb, dir, &group, mode);
got_group:
@@ -950,26 +820,21 @@ got:
goto fail;
}
- free = 0;
- ext4_lock_group(sb, group);
+ BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
+ err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh);
+ brelse(block_bitmap_bh);
+
/* recheck and clear flag under lock if we still need to */
+ ext4_lock_group(sb, group);
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
- free = ext4_free_blocks_after_init(sb, group, gdp);
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
- ext4_free_blks_set(sb, gdp, free);
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_clusters_after_init(sb, group, gdp));
gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
gdp);
}
ext4_unlock_group(sb, group);
- /* Don't need to dirty bitmap block if we didn't change it */
- if (free) {
- BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
- err = ext4_handle_dirty_metadata(handle,
- NULL, block_bitmap_bh);
- }
-
- brelse(block_bitmap_bh);
if (err)
goto fail;
}
@@ -987,8 +852,11 @@ got:
flex_group = ext4_flex_group(sbi, group);
atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
}
-
- if (test_opt(sb, GRPID)) {
+ if (owner) {
+ inode->i_mode = mode;
+ inode->i_uid = owner[0];
+ inode->i_gid = owner[1];
+ } else if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = dir->i_gid;
@@ -1005,11 +873,7 @@ got:
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
- /*
- * Don't inherit extent flag from directory, amongst others. We set
- * extent flag on newly created directory and file only if -o extent
- * mount option is specified
- */
+ /* Don't inherit extent flag from directory, amongst others. */
ei->i_flags =
ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED);
ei->i_file_acl = 0;
@@ -1084,7 +948,7 @@ fail_free_drop:
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
- inode->i_nlink = 0;
+ clear_nlink(inode);
unlock_new_inode(inode);
iput(inode);
brelse(inode_bitmap_bh);
@@ -1235,7 +1099,7 @@ unsigned long ext4_count_dirs(struct super_block * sb)
* inode allocation from the current group, so we take alloc_sem lock, to
* block ext4_claim_inode until we are finished.
*/
-extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
+int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
int barrier)
{
struct ext4_group_info *grp = ext4_get_group_info(sb, group);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 0962642119c0..3cfc73fbca8e 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -699,6 +699,13 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
/*
* Okay, we need to do block allocation.
*/
+ if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
+ EXT4_ERROR_INODE(inode, "Can't allocate blocks for "
+ "non-extent mapped inodes with bigalloc");
+ return -ENOSPC;
+ }
+
goal = ext4_find_goal(inode, map->m_lblk, partial);
/* the number of blocks need to allocate for [d,t]indirect blocks */
@@ -1343,7 +1350,9 @@ void ext4_ind_truncate(struct inode *inode)
__le32 nr = 0;
int n = 0;
ext4_lblk_t last_block, max_block;
+ loff_t page_len;
unsigned blocksize = inode->i_sb->s_blocksize;
+ int err;
handle = start_transaction(inode);
if (IS_ERR(handle))
@@ -1354,9 +1363,16 @@ void ext4_ind_truncate(struct inode *inode)
max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
- if (inode->i_size & (blocksize - 1))
- if (ext4_block_truncate_page(handle, mapping, inode->i_size))
+ if (inode->i_size % PAGE_CACHE_SIZE != 0) {
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0);
+
+ if (err)
goto out_stop;
+ }
if (last_block != max_block) {
n = ext4_block_to_path(inode, last_block, offsets, NULL);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0defe0bfe019..cc5a6da030a1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -42,7 +42,6 @@
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
-#include "ext4_extents.h"
#include "truncate.h"
#include <trace/events/ext4.h>
@@ -268,7 +267,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
struct ext4_inode_info *ei = EXT4_I(inode);
spin_lock(&ei->i_block_reservation_lock);
- trace_ext4_da_update_reserve_space(inode, used);
+ trace_ext4_da_update_reserve_space(inode, used, quota_claim);
if (unlikely(used > ei->i_reserved_data_blocks)) {
ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
"with only %d reserved data blocks\n",
@@ -281,7 +280,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
used + ei->i_allocated_meta_blocks);
ei->i_allocated_meta_blocks = 0;
@@ -291,7 +290,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
* only when we have written all of the delayed
* allocation blocks.
*/
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
@@ -300,14 +299,14 @@ void ext4_da_update_reserve_space(struct inode *inode,
/* Update quota subsystem for data blocks */
if (quota_claim)
- dquot_claim_block(inode, used);
+ dquot_claim_block(inode, EXT4_C2B(sbi, used));
else {
/*
* We did fallocate with an offset that is already delayed
* allocated. So on delayed allocated writeback we should
* not re-claim the quota for fallocated blocks.
*/
- dquot_release_reservation_block(inode, used);
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
}
/*
@@ -399,6 +398,49 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
}
/*
+ * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map.
+ */
+static void set_buffers_da_mapped(struct inode *inode,
+ struct ext4_map_blocks *map)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct pagevec pvec;
+ int i, nr_pages;
+ pgoff_t index, end;
+
+ index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (map->m_lblk + map->m_len - 1) >>
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ pagevec_init(&pvec, 0);
+ while (index <= end) {
+ nr_pages = pagevec_lookup(&pvec, mapping, index,
+ min(end - index + 1,
+ (pgoff_t)PAGEVEC_SIZE));
+ if (nr_pages == 0)
+ break;
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ struct buffer_head *bh, *head;
+
+ if (unlikely(page->mapping != mapping) ||
+ !PageDirty(page))
+ break;
+
+ if (page_has_buffers(page)) {
+ bh = head = page_buffers(page);
+ do {
+ set_buffer_da_mapped(bh);
+ bh = bh->b_this_page;
+ } while (bh != head);
+ }
+ index++;
+ }
+ pagevec_release(&pvec);
+ }
+}
+
+/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
@@ -416,7 +458,7 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
* the buffer head is mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
- * that casem, buffer head is unmapped
+ * that case, buffer head is unmapped
*
* It returns the error in case of allocation failure.
*/
@@ -435,9 +477,11 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
*/
down_read((&EXT4_I(inode)->i_data_sem));
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
- retval = ext4_ext_map_blocks(handle, inode, map, 0);
+ retval = ext4_ext_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
} else {
- retval = ext4_ind_map_blocks(handle, inode, map, 0);
+ retval = ext4_ind_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
}
up_read((&EXT4_I(inode)->i_data_sem));
@@ -455,7 +499,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
* Returns if the blocks have already allocated
*
* Note that if blocks have been preallocated
- * ext4_ext_get_block() returns th create = 0
+ * ext4_ext_get_block() returns the create = 0
* with buffer head unmapped.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
@@ -517,9 +561,17 @@ int ext4_map_block