| Message ID | 747e611a-2225-0685-b1e6-8b45ef45042d@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | __asm_copy_to-from_user: Reduce more byte_copy | expand |
Hi Akira,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on linus/master]
[also build test ERROR on v5.15 next-20211111]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Akira-Tsukamoto/__asm_copy_to-from_user-Reduce-more-byte_copy/20211111-161445
base: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git debe436e77c72fcee804fb867f275e6d31aa999c
config: riscv-buildonly-randconfig-r002-20211111 (attached as .config)
compiler: clang version 14.0.0 (https://github.com/llvm/llvm-project 63ef0e17e28827eae53133b3467bdac7d9729318)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install riscv cross compiling tool for clang build
# apt-get install binutils-riscv64-linux-gnu
# https://github.com/0day-ci/linux/commit/cf2e8e9c4e9dc65552ca5ac0c85c198785f5d91c
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Akira-Tsukamoto/__asm_copy_to-from_user-Reduce-more-byte_copy/20211111-161445
git checkout cf2e8e9c4e9dc65552ca5ac0c85c198785f5d91c
# save the attached .config to linux build tree
mkdir build_dir
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=riscv SHELL=/bin/bash
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
>> <instantiation>:5:14: error: unknown token in expression
.word 100b,
^
arch/riscv/lib/uaccess.S:92:2: note: while in macro instantiation
fixup lw a5, 0(a1)
^
>> <instantiation>:5:14: error: unknown token in expression
.word 100b,
^
arch/riscv/lib/uaccess.S:94:2: note: while in macro instantiation
fixup sw a5, 0(a0)
^
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
Hi Akira,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on linus/master]
[also build test WARNING on v5.15 next-20211111]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Akira-Tsukamoto/__asm_copy_to-from_user-Reduce-more-byte_copy/20211111-161445
base: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git debe436e77c72fcee804fb867f275e6d31aa999c
config: riscv-allyesconfig (attached as .config)
compiler: riscv64-linux-gcc (GCC) 11.2.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/0day-ci/linux/commit/cf2e8e9c4e9dc65552ca5ac0c85c198785f5d91c
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Akira-Tsukamoto/__asm_copy_to-from_user-Reduce-more-byte_copy/20211111-161445
git checkout cf2e8e9c4e9dc65552ca5ac0c85c198785f5d91c
# save the attached .config to linux build tree
mkdir build_dir
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.2.0 make.cross O=build_dir ARCH=riscv SHELL=/bin/bash
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All warnings (new ones prefixed by >>):
arch/riscv/lib/uaccess.S: Assembler messages:
>> arch/riscv/lib/uaccess.S:92: Warning: zero assumed for missing expression
arch/riscv/lib/uaccess.S:94: Warning: zero assumed for missing expression
vim +92 arch/riscv/lib/uaccess.S
17
18 /* Enable access to user memory */
19 li t6, SR_SUM
20 csrs CSR_STATUS, t6
21
22 /* Save for return value */
23 mv t5, a2
24
25 /*
26 * Register allocation for code below:
27 * a0 - start of uncopied dst
28 * a1 - start of uncopied src
29 * a2 - size
30 * t0 - end of uncopied dst
31 */
32 add t0, a0, a2
33
34 /*
35 * Use byte copy only if too small.
36 * SZREG holds 4 for RV32 and 8 for RV64
37 * a3 - 2*SZREG is minimum size for word_copy
38 * 1*SZREG for aligning dst + 1*SZREG for word_copy
39 */
40 li a3, 2*SZREG
41 bltu a2, a3, .Lbyte_copy_tail
42
43 /*
44 * Copy first bytes until dst is aligned to word boundary.
45 * a0 - start of dst
46 * t1 - start of aligned dst
47 */
48 addi t1, a0, SZREG-1
49 andi t1, t1, ~(SZREG-1)
50 /* dst is already aligned, skip */
51 beq a0, t1, .Lskip_align_dst
52 1:
53 /* a5 - one byte for copying data */
54 fixup lb a5, 0(a1), 10f
55 addi a1, a1, 1 /* src */
56 fixup sb a5, 0(a0), 10f
57 addi a0, a0, 1 /* dst */
58 bltu a0, t1, 1b /* t1 - start of aligned dst */
59
60 .Lskip_align_dst:
61 /*
62 * Now dst is aligned.
63 * Use shift-copy if src is misaligned.
64 * Use word-copy if both src and dst are aligned because
65 * can not use shift-copy which do not require shifting
66 */
67 /* a1 - start of src */
68 andi a3, a1, SZREG-1
69 bnez a3, .Lshift_copy
70
71 .Lcheck_size_bulk:
72 /*
73 * Evaluate the size if possible to use unrolled.
74 * The word_copy_unlrolled requires larger than 8*SZREG
75 */
76 li a3, 8*SZREG
77 add a4, a0, a3
78 bltu a4, t0, .Lword_copy_unlrolled
79
80 .Lword_copy:
81 /*
82 * Both src and dst are aligned
83 * Not unrolled word copy with every 1*SZREG iteration
84 *
85 * a0 - start of aligned dst
86 * a1 - start of aligned src
87 * t0 - end of aligned dst
88 */
89 bgeu a0, t0, .Lbyte_copy_tail /* check if end of copy */
90 addi t0, t0, -(SZREG) /* not to over run */
91 1:
> 92 fixup REG_L a5, 0(a1)
93 addi a1, a1, SZREG
94 fixup REG_S a5, 0(a0)
95 addi a0, a0, SZREG
96 bltu a0, t0, 1b
97
98 addi t0, t0, SZREG /* revert to original value */
99 j .Lbyte_copy_tail
100
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index 63bc691cff91..50013479cb86 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -34,8 +34,10 @@ ENTRY(__asm_copy_from_user) /* * Use byte copy only if too small. * SZREG holds 4 for RV32 and 8 for RV64 + * a3 - 2*SZREG is minimum size for word_copy + * 1*SZREG for aligning dst + 1*SZREG for word_copy */ - li a3, 9*SZREG /* size must be larger than size in word_copy */ + li a3, 2*SZREG bltu a2, a3, .Lbyte_copy_tail /* @@ -66,9 +68,40 @@ ENTRY(__asm_copy_from_user) andi a3, a1, SZREG-1 bnez a3, .Lshift_copy +.Lcheck_size_bulk: + /* + * Evaluate the size if possible to use unrolled. + * The word_copy_unlrolled requires larger than 8*SZREG + */ + li a3, 8*SZREG + add a4, a0, a3 + bltu a4, t0, .Lword_copy_unlrolled + .Lword_copy: - /* - * Both src and dst are aligned, unrolled word copy + /* + * Both src and dst are aligned + * Not unrolled word copy with every 1*SZREG iteration + * + * a0 - start of aligned dst + * a1 - start of aligned src + * t0 - end of aligned dst + */ + bgeu a0, t0, .Lbyte_copy_tail /* check if end of copy */ + addi t0, t0, -(SZREG) /* not to over run */ +1: + fixup REG_L a5, 0(a1) + addi a1, a1, SZREG + fixup REG_S a5, 0(a0) + addi a0, a0, SZREG + bltu a0, t0, 1b + + addi t0, t0, SZREG /* revert to original value */ + j .Lbyte_copy_tail + +.Lword_copy_unlrolled: + /* + * Both src and dst are aligned + * Unrolled word copy with every 8*SZREG iteration * * a0 - start of aligned dst * a1 - start of aligned src @@ -97,7 +130,12 @@ ENTRY(__asm_copy_from_user) bltu a0, t0, 2b addi t0, t0, 8*SZREG /* revert to original value */ - j .Lbyte_copy_tail + + /* + * Remaining might large enough for word_copy to reduce slow byte + * copy + */ + j .Lcheck_size_bulk .Lshift_copy:
Reduce the number of slow byte_copy being used. Currently byte_copy is used for all the cases when the size is smaller than 9*SZREG. When the size is in between 2*SZREG to 9*SZREG, use faster unrolled word_copy. Signed-off-by: Akira Tsukamoto <akira.tsukamoto@gmail.com> --- arch/riscv/lib/uaccess.S | 46 ++++++++++++++++++++++++++++++++++++---- 1 file changed, 42 insertions(+), 4 deletions(-)