liblzma: Fix x86-64 movzw compatibility in range_decoder.h

Support for instruction "movzw" without suffix in "GNU as" was
added in commit [1] and stabilized in binutils 2.27, released
in August 2016. Earlier systems don't accept this instruction
without a suffix, making range_decoder.h's inline assembly
unable to build on old systems such as Ubuntu 16.04, creating
error messages like:

    lzma_decoder.c: Assembler messages:
    lzma_decoder.c:371: Error: no such instruction: `movzw 2(%r11),%esi'
    lzma_decoder.c:373: Error: no such instruction: `movzw 4(%r11),%edi'
    lzma_decoder.c:388: Error: no such instruction: `movzw 6(%r11),%edx'
    lzma_decoder.c:398: Error: no such instruction: `movzw (%r11,%r14,4),%esi'

Change "movzw" to "movzwl" for compatibility.

[1] https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=c07315e0c610e0e3317b4c02266f81793df253d2

Suggested-by: Lasse Collin <lasse.collin@tukaani.org>
Tested-by: Yifeng Li <tomli@tomli.me>
Signed-off-by: Yifeng Li <tomli@tomli.me>
Fixes: 3182a330c1512cc1f5c87b5c5a272578e60a5158
Fixes: https://github.com/tukaani-project/xz/issues/121
Closes: https://github.com/tukaani-project/xz/pull/136
(cherry picked from commit 6cd7c8607843c337edfe2c472aa316602a393754)

diff --git a/src/liblzma/rangecoder/range_decoder.h b/src/liblzma/rangecoder/range_decoder.h
index 31a58d1ffbeda277496db79ee5c9581fec84bb76..a8aca9077c13a8d5313428e6b750a30cde5c9579 100644 (file)
--- a/src/liblzma/rangecoder/range_decoder.h
+++ b/src/liblzma/rangecoder/range_decoder.h
@@ -592,13 +592,13 @@ do { \
 // *_only = rc_asm_y or _n to include or exclude code marked with them
 #define rc_asm_bittree(a, b, first_only, middle_only, last_only) \
        first_only( \
-               "movzw  2(%[probs_base]), %[prob" #a "]\n\t" \
+               "movzwl 2(%[probs_base]), %[prob" #a "]\n\t" \
                "mov    $2, %[symbol]\n\t" \
-               "movzw  4(%[probs_base]), %[prob" #b "]\n\t" \
+               "movzwl 4(%[probs_base]), %[prob" #b "]\n\t" \
        ) \
        middle_only( \
                /* Note the scaling of 4 instead of 2: */ \
-               "movzw  (%[probs_base], %q[symbol], 4), %[prob" #b "]\n\t" \
+               "movzwl (%[probs_base], %q[symbol], 4), %[prob" #b "]\n\t" \
        ) \
        last_only( \
                "add    %[symbol], %[symbol]\n\t" \
@@ -610,11 +610,11 @@ do { \
                "cmovae %[t0], %[range]\n\t" \
                \
        first_only( \
-               "movzw  6(%[probs_base]), %[t0]\n\t" \
+               "movzwl 6(%[probs_base]), %[t0]\n\t" \
                "cmovae %[t0], %[prob" #b "]\n\t" \
        ) \
        middle_only( \
-               "movzw  2(%[probs_base], %q[symbol], 4), %[t0]\n\t" \
+               "movzwl 2(%[probs_base], %q[symbol], 4), %[t0]\n\t" \
                "lea    (%q[symbol], %q[symbol]), %[symbol]\n\t" \
                "cmovae %[t0], %[prob" #b "]\n\t" \
        ) \
@@ -716,12 +716,12 @@ do { \
 #define rc_asm_bittree_rev(a, b, add, dcur, dnext0, dnext1, \
                first_only, middle_only, last_only) \
        first_only( \
-               "movzw  2(%[probs_base]), %[prob" #a "]\n\t" \
+               "movzwl 2(%[probs_base]), %[prob" #a "]\n\t" \
                "xor    %[symbol], %[symbol]\n\t" \
-               "movzw  4(%[probs_base]), %[prob" #b "]\n\t" \
+               "movzwl 4(%[probs_base]), %[prob" #b "]\n\t" \
        ) \
        middle_only( \
-               "movzw  " #dnext0 "(%[probs_base], %q[symbol], 2), " \
+               "movzwl " #dnext0 "(%[probs_base], %q[symbol], 2), " \
                        "%[prob" #b "]\n\t" \
        ) \
                \
@@ -731,11 +731,11 @@ do { \
                "cmovae %[t0], %[range]\n\t" \
                \
        first_only( \
-               "movzw  6(%[probs_base]), %[t0]\n\t" \
+               "movzwl 6(%[probs_base]), %[t0]\n\t" \
                "cmovae %[t0], %[prob" #b "]\n\t" \
        ) \
        middle_only( \
-               "movzw  " #dnext1 "(%[probs_base], %q[symbol], 2), %[t0]\n\t" \
+               "movzwl " #dnext1 "(%[probs_base], %q[symbol], 2), %[t0]\n\t" \
                "cmovae %[t0], %[prob" #b "]\n\t" \
        ) \
                \
@@ -788,7 +788,7 @@ do { \
        uint32_t t_index; \
        \
        __asm__( \
-               "movzw  (%[probs_base], %q[symbol], 2), %[prob]\n\t" \
+               "movzwl (%[probs_base], %q[symbol], 2), %[prob]\n\t" \
                "mov    %[symbol], %[index]\n\t" \
                \
                "add    %[dest], %[t2]\n\t" \
@@ -844,7 +844,7 @@ do { \
                "and    %[offset], %[match_bit]\n\t" \
                "add    %[match_bit], %[symbol]\n\t" \
                \
-               "movzw  (%[probs_base], %q[symbol], 2), %[prob]\n\t" \
+               "movzwl (%[probs_base], %q[symbol], 2), %[prob]\n\t" \
                \
                "add    %[symbol], %[symbol]\n\t" \
                \