Re: [PATCH v2 4/4] __arch_xprod64(): make __always_inline when optimizing for performance

[kernel test robot <lkp@intel.com>]

Hi Nicolas,

kernel test robot noticed the following build errors:

[auto build test ERROR on arnd-asm-generic/master]
[also build test ERROR on arm/for-next arm/fixes soc/for-next linus/master v6.10-rc6 next-20240703]
[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#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Nicolas-Pitre/lib-math-test_div64-add-some-edge-cases-relevant-to-__div64_const32/20240708-013344
base:   https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master
patch link:    https://lore.kernel.org/r/20240707171919.1951895-5-nico%40fluxnic.net
patch subject: [PATCH v2 4/4] __arch_xprod64(): make __always_inline when optimizing for performance
config: arm-randconfig-002-20240708 (https://download.01.org/0day-ci/archive/20240708/202407080355.VUEmeBsv-lkp@intel.com/config)
compiler: arm-linux-gnueabi-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240708/202407080355.VUEmeBsv-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202407080355.VUEmeBsv-lkp@intel.com/

All errors (new ones prefixed by >>):

   scripts/genksyms/parse.y: warning: 9 shift/reduce conflicts [-Wconflicts-sr]
   scripts/genksyms/parse.y: warning: 5 reduce/reduce conflicts [-Wconflicts-rr]
   scripts/genksyms/parse.y: note: rerun with option '-Wcounterexamples' to generate conflict counterexamples
   In file included from include/linux/math.h:6,
                    from include/linux/kernel.h:27,
                    from include/linux/cpumask.h:11,
                    from include/linux/sched.h:16,
                    from arch/arm/kernel/asm-offsets.c:11:
>> arch/arm/include/asm/div64.h:60:1: error: return type defaults to 'int' [-Werror=implicit-int]
      60 | __arch_xprod_64(uint64_t m, uint64_t n, bool bias)
         | ^~~~~~~~~~~~~~~
   cc1: some warnings being treated as errors
   make[3]: *** [scripts/Makefile.build:117: arch/arm/kernel/asm-offsets.s] Error 1 shuffle=2335528022
   make[3]: Target 'prepare' not remade because of errors.
   make[2]: *** [Makefile:1208: prepare0] Error 2 shuffle=2335528022
   make[2]: Target 'prepare' not remade because of errors.
   make[1]: *** [Makefile:240: __sub-make] Error 2 shuffle=2335528022
   make[1]: Target 'prepare' not remade because of errors.
   make: *** [Makefile:240: __sub-make] Error 2 shuffle=2335528022
   make: Target 'prepare' not remade because of errors.


vim +/int +60 arch/arm/include/asm/div64.h

    54	
    55	#ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
    56	static __always_inline
    57	#else
    58	static inline
    59	#endif
  > 60	__arch_xprod_64(uint64_t m, uint64_t n, bool bias)
    61	{
    62		unsigned long long res;
    63		register unsigned int tmp asm("ip") = 0;
    64		bool no_ovf = __builtin_constant_p(m) &&
    65			      ((m >> 32) + (m & 0xffffffff) < 0x100000000);
    66	
    67		if (!bias) {
    68			asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"
    69				"mov	%Q0, #0"
    70				: "=&r" (res)
    71				: "r" (m), "r" (n)
    72				: "cc");
    73		} else if (no_ovf) {
    74			res = m;
    75			asm (	"umlal	%Q0, %R0, %Q1, %Q2\n\t"
    76				"mov	%Q0, #0"
    77				: "+&r" (res)
    78				: "r" (m), "r" (n)
    79				: "cc");
    80		} else {
    81			asm (	"umull	%Q0, %R0, %Q2, %Q3\n\t"
    82				"cmn	%Q0, %Q2\n\t"
    83				"adcs	%R0, %R0, %R2\n\t"
    84				"adc	%Q0, %1, #0"
    85				: "=&r" (res), "+&r" (tmp)
    86				: "r" (m), "r" (n)
    87				: "cc");
    88		}
    89	
    90		if (no_ovf) {
    91			asm (	"umlal	%R0, %Q0, %R1, %Q2\n\t"
    92				"umlal	%R0, %Q0, %Q1, %R2\n\t"
    93				"mov	%R0, #0\n\t"
    94				"umlal	%Q0, %R0, %R1, %R2"
    95				: "+&r" (res)
    96				: "r" (m), "r" (n)
    97				: "cc");
    98		} else {
    99			asm (	"umlal	%R0, %Q0, %R2, %Q3\n\t"
   100				"umlal	%R0, %1, %Q2, %R3\n\t"
   101				"mov	%R0, #0\n\t"
   102				"adds	%Q0, %1, %Q0\n\t"
   103				"adc	%R0, %R0, #0\n\t"
   104				"umlal	%Q0, %R0, %R2, %R3"
   105				: "+&r" (res), "+&r" (tmp)
   106				: "r" (m), "r" (n)
   107				: "cc");
   108		}
   109	
   110		return res;
   111	}
   112	#define __arch_xprod_64 __arch_xprod_64
   113	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki