um: mdd support for 64 bit atomic operations

This adds support for 64 bit atomic operations on 32 bit UML systems.  XFS
needs them since 2.6.38.

  $ make ARCH=um SUBARCH=i386
  ...
    LD      .tmp_vmlinux1
  fs/built-in.o: In function `xlog_regrant_reserve_log_space':
  xfs_log.c:(.text+0xd8584): undefined reference to `atomic64_read_386'
  xfs_log.c:(.text+0xd85ac): undefined reference to `cmpxchg8b_emu'
  ...

Addresses https://bugzilla.kernel.org/show_bug.cgi?id=32812

Reported-by: Martin Walch <walch.martin@web.de>
Tested-by: Martin Walch <walch.martin@web.de>
Cc: Martin Walch <walch.martin@web.de>
Cc: <stable@kernel.org> [2.6.38.x 084189a: um: disable CONFIG_CMPXCHG_LOCAL]
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 226 insertions, 1 deletions

diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile
index 804b28dd0328..b1da91c1b200 100644
--- a/arch/um/sys-i386/Makefile
+++ b/arch/um/sys-i386/Makefile
@@ -4,7 +4,7 @@
 
 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
+        sys_call_table.o tls.o atomic64_cx8_32.o
 
 obj-$(CONFIG_BINFMT_ELF) += elfcore.o
 
diff --git a/arch/um/sys-i386/atomic64_cx8_32.S b/arch/um/sys-i386/atomic64_cx8_32.S
new file mode 100644
index 000000000000..1e901d3d4a95
--- /dev/null
+++ b/arch/um/sys-i386/atomic64_cx8_32.S
@@ -0,0 +1,225 @@
+/*
+ * 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)