* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2020-06-03 12:32 kernel test robot
0 siblings, 0 replies; 10+ messages in thread
From: kernel test robot @ 2020-06-03 12:32 UTC (permalink / raw)
To: Jason, A., Donenfeld,
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 6584 bytes --]
Hi Jason,
FYI, the error/warning still remains.
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: d6f9469a03d832dcd17041ed67774ffb5f3e73b3
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 4 months ago
config: x86_64-randconfig-r012-20200603 (attached as .config)
compiler: clang version 11.0.0 (https://github.com/llvm/llvm-project 16437992cac249f6fe1efd392d20e3469b47e39e)
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 x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
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 >>, old ones prefixed by <<):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
arch/x86/crypto/curve25519-x86_64.c:609:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
arch/x86/crypto/curve25519-x86_64.c:609:3: error: inline assembly requires more registers than available
11 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 28231 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2021-05-10 8:30 kernel test robot
0 siblings, 0 replies; 10+ messages in thread
From: kernel test robot @ 2021-05-10 8:30 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 7675 bytes --]
Hi Jason,
FYI, the error/warning still remains.
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: 6efb943b8616ec53a5e444193dccf1af9ad627b5
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 1 year, 3 months ago
config: x86_64-randconfig-a014-20210510 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project 492173d42b32cb91d5d0d72d5ed84fcab80d059a)
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 x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
# https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=07b586fe06625b0b610dc3d3a969c51913d143d4
git remote add linus https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
git fetch --no-tags linus master
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 ARCH=x86_64
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 >>):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
19 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 36779 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2021-04-22 2:20 kernel test robot
0 siblings, 0 replies; 10+ messages in thread
From: kernel test robot @ 2021-04-22 2:20 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 7746 bytes --]
Hi Jason,
FYI, the error/warning still remains.
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: 16fc44d6387e260f4932e9248b985837324705d8
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 1 year, 2 months ago
config: x86_64-randconfig-a006-20210422 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project d87b9b81ccb95217181ce75515c6c68bbb408ca4)
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 x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
# https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=07b586fe06625b0b610dc3d3a969c51913d143d4
git remote add linus https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
git fetch --no-tags linus master
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 ARCH=x86_64
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 >>):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
fatal error: too many errors emitted, stopping now [-ferror-limit=]
20 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 33316 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2021-04-05 22:49 kernel test robot
0 siblings, 0 replies; 10+ messages in thread
From: kernel test robot @ 2021-04-05 22:49 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 7671 bytes --]
Hi Jason,
FYI, the error/warning still remains.
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: 0a50438c84363bd37fe18fe432888ae9a074dcab
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 1 year, 2 months ago
config: x86_64-randconfig-a012-20210406 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project 2760a808b9916a2839513b7fd7314a464f52481e)
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 x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
# https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=07b586fe06625b0b610dc3d3a969c51913d143d4
git remote add linus https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
git fetch --no-tags linus master
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
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 >>):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
19 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 24079 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2021-03-19 21:03 kernel test robot
0 siblings, 0 replies; 10+ messages in thread
From: kernel test robot @ 2021-03-19 21:03 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 7670 bytes --]
Hi Jason,
FYI, the error/warning still remains.
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: 8b12a62a4e3ed4ae99c715034f557eb391d6b196
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 1 year, 1 month ago
config: x86_64-randconfig-a014-20210319 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project fcc1ce00931751ac02498986feb37744e9ace8de)
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 x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
# https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=07b586fe06625b0b610dc3d3a969c51913d143d4
git remote add linus https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
git fetch --no-tags linus master
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
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 >>):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
19 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 26701 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2020-07-12 3:36 kernel test robot
0 siblings, 0 replies; 10+ messages in thread
From: kernel test robot @ 2020-07-12 3:36 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 6315 bytes --]
Hi Jason,
FYI, the error/warning still remains.
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: 0aea6d5c5be33ce94c16f9ab2f64de1f481f424b
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 5 months ago
config: x86_64-randconfig-a003-20200712 (attached as .config)
compiler: clang version 11.0.0 (https://github.com/llvm/llvm-project 02946de3802d3bc65bc9f2eb9b8d4969b5a7add8)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
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 >>):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
9 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 34048 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2020-07-04 20:40 kernel test robot
0 siblings, 0 replies; 10+ messages in thread
From: kernel test robot @ 2020-07-04 20:40 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 6644 bytes --]
Hi Jason,
FYI, the error/warning still remains.
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: 35e884f89df4c48566d745dc5a97a0d058d04263
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 5 months ago
config: x86_64-randconfig-a002-20200705 (attached as .config)
compiler: clang version 11.0.0 (https://github.com/llvm/llvm-project e359ab1eca5727ce4c688bb49323b8a09478d61c)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
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 >>):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
arch/x86/crypto/curve25519-x86_64.c:609:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
arch/x86/crypto/curve25519-x86_64.c:609:3: error: inline assembly requires more registers than available
11 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 30973 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2020-06-18 14:53 kernel test robot
0 siblings, 0 replies; 10+ messages in thread
From: kernel test robot @ 2020-06-18 14:53 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 6315 bytes --]
Hi Jason,
FYI, the error/warning still remains.
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: 1b5044021070efa3259f3e9548dc35d1eb6aa844
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 4 months ago
config: x86_64-randconfig-r011-20200618 (attached as .config)
compiler: clang version 11.0.0 (https://github.com/llvm/llvm-project 487ca07fcc75d52755c9fe2ee05bcb3b6eeeec44)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
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 >>):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
9 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 36257 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2020-05-18 17:42 kbuild test robot
0 siblings, 0 replies; 10+ messages in thread
From: kbuild test robot @ 2020-05-18 17:42 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 6277 bytes --]
Hi Jason,
FYI, the error/warning still remains.
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: b9bbe6ed63b2b9f2c9ee5cbd0f2c946a2723f4ce
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 3 months ago
config: x86_64-randconfig-r001-20200518 (attached as .config)
compiler: clang version 11.0.0 (https://github.com/llvm/llvm-project 135b877874fae96b4372c8a3fbfaa8ff44ff86e3)
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
If you fix the issue, kindly add following tag as appropriate
Reported-by: kbuild test robot <lkp@intel.com>
All errors (new ones prefixed by >>, old ones prefixed by <<):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
9 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 35620 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread* arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
@ 2020-05-01 0:51 kbuild test robot
0 siblings, 0 replies; 10+ messages in thread
From: kbuild test robot @ 2020-05-01 0:51 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: kbuild-all, clang-built-linux, linux-kernel, Herbert Xu
[-- Attachment #1: Type: text/plain, Size: 6243 bytes --]
tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
head: c45e8bccecaf633480d378daff11e122dfd5e96d
commit: 07b586fe06625b0b610dc3d3a969c51913d143d4 crypto: x86/curve25519 - replace with formally verified implementation
date: 3 months ago
config: x86_64-randconfig-a002-20200501 (attached as .config)
compiler: clang version 11.0.0 (https://github.com/llvm/llvm-project 1ccde533425a4ba9d379510206ad680ff9702129)
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
git checkout 07b586fe06625b0b610dc3d3a969c51913d143d4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
If you fix the issue, kindly add following tag as appropriate
Reported-by: kbuild test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
" movq 0(%1), %%rdx;" /* f[0] */
^
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
>> arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available
9 errors generated.
vim +518 arch/x86/crypto/curve25519-x86_64.c
509
510 /* Computes the square of a field element: out <- f * f
511 * Uses the 8-element buffer tmp for intermediate results */
512 static inline void fsqr(u64 *out, const u64 *f, u64 *tmp)
513 {
514 asm volatile(
515 /* Compute the raw multiplication: tmp <- f * f */
516
517 /* Step 1: Compute all partial products */
> 518 " movq 0(%1), %%rdx;" /* f[0] */
519 " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */
520 " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */
521 " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */
522 " movq 24(%1), %%rdx;" /* f[3] */
523 " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */
524 " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */
525 " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */
526 " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */
527
528 /* Step 2: Compute two parallel carry chains */
529 " xor %%r15, %%r15;"
530 " adox %%rax, %%r10;"
531 " adcx %%r8, %%r8;"
532 " adox %%rcx, %%r11;"
533 " adcx %%r9, %%r9;"
534 " adox %%r15, %%r12;"
535 " adcx %%r10, %%r10;"
536 " adox %%r15, %%r13;"
537 " adcx %%r11, %%r11;"
538 " adox %%r15, %%r14;"
539 " adcx %%r12, %%r12;"
540 " adcx %%r13, %%r13;"
541 " adcx %%r14, %%r14;"
542
543 /* Step 3: Compute intermediate squares */
544 " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */
545 " movq %%rax, 0(%0);"
546 " add %%rcx, %%r8;" " movq %%r8, 8(%0);"
547 " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */
548 " adcx %%rax, %%r9;" " movq %%r9, 16(%0);"
549 " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);"
550 " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */
551 " adcx %%rax, %%r11;" " movq %%r11, 32(%0);"
552 " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);"
553 " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */
554 " adcx %%rax, %%r13;" " movq %%r13, 48(%0);"
555 " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);"
556
557 /* Line up pointers */
558 " mov %0, %1;"
559 " mov %2, %0;"
560
561 /* Wrap the result back into the field */
562
563 /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */
564 " mov $38, %%rdx;"
565 " mulxq 32(%1), %%r8, %%r13;"
566 " xor %%rcx, %%rcx;"
567 " adoxq 0(%1), %%r8;"
568 " mulxq 40(%1), %%r9, %%r12;"
569 " adcx %%r13, %%r9;"
570 " adoxq 8(%1), %%r9;"
571 " mulxq 48(%1), %%r10, %%r13;"
572 " adcx %%r12, %%r10;"
573 " adoxq 16(%1), %%r10;"
574 " mulxq 56(%1), %%r11, %%rax;"
575 " adcx %%r13, %%r11;"
576 " adoxq 24(%1), %%r11;"
577 " adcx %%rcx, %%rax;"
578 " adox %%rcx, %%rax;"
579 " imul %%rdx, %%rax;"
580
581 /* Step 2: Fold the carry back into dst */
582 " add %%rax, %%r8;"
583 " adcx %%rcx, %%r9;"
584 " movq %%r9, 8(%0);"
585 " adcx %%rcx, %%r10;"
586 " movq %%r10, 16(%0);"
587 " adcx %%rcx, %%r11;"
588 " movq %%r11, 24(%0);"
589
590 /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */
591 " mov $0, %%rax;"
592 " cmovc %%rdx, %%rax;"
593 " add %%rax, %%r8;"
594 " movq %%r8, 0(%0);"
595 : "+&r" (tmp), "+&r" (f), "+&r" (out)
596 :
597 : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc"
598 );
599 }
600
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 35460 bytes --]
^ permalink raw reply [flat|nested] 10+ messages in thread
end of thread, other threads:[~2021-05-10 8:31 UTC | newest]
Thread overview: 10+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-06-03 12:32 arch/x86/crypto/curve25519-x86_64.c:518:3: error: inline assembly requires more registers than available kernel test robot
-- strict thread matches above, loose matches on Subject: below --
2021-05-10 8:30 kernel test robot
2021-04-22 2:20 kernel test robot
2021-04-05 22:49 kernel test robot
2021-03-19 21:03 kernel test robot
2020-07-12 3:36 kernel test robot
2020-07-04 20:40 kernel test robot
2020-06-18 14:53 kernel test robot
2020-05-18 17:42 kbuild test robot
2020-05-01 0:51 kbuild test robot
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).