Date: Sat, 11 Apr 2009 14:01:01 +0000 (UTC) From: Ed Schouten <ed@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org Subject: svn commit: r190919 - in head/sys: amd64/amd64 amd64/include i386/i386 i386/include Message-ID: <200904111401.n3BE1108088009@svn.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: ed Date: Sat Apr 11 14:01:01 2009 New Revision: 190919 URL: http://svn.freebsd.org/changeset/base/190919 Log: Simplify in/out functions (for i386 and AMD64). Remove a hack to generate more efficient code for port numbers below 0x100, which has been obsolete for at least ten years, because GCC has an asm constraint to specify that. Submitted by: Christoph Mallon <christoph mallon gmx de> Modified: head/sys/amd64/amd64/machdep.c head/sys/amd64/include/cpufunc.h head/sys/i386/i386/machdep.c head/sys/i386/include/cpufunc.h Modified: head/sys/amd64/amd64/machdep.c ============================================================================== --- head/sys/amd64/amd64/machdep.c Sat Apr 11 13:15:38 2009 (r190918) +++ head/sys/amd64/amd64/machdep.c Sat Apr 11 14:01:01 2009 (r190919) @@ -2178,45 +2178,24 @@ user_dbreg_trap(void) #ifdef KDB /* - * Provide inb() and outb() as functions. They are normally only - * available as macros calling inlined functions, thus cannot be - * called from the debugger. - * - * The actual code is stolen from <machine/cpufunc.h>, and de-inlined. + * Provide inb() and outb() as functions. They are normally only available as + * inline functions, thus cannot be called from the debugger. */ -#undef inb -#undef outb - /* silence compiler warnings */ -u_char inb(u_int); -void outb(u_int, u_char); +u_char inb_(u_short); +void outb_(u_short, u_char); u_char -inb(u_int port) +inb_(u_short port) { - u_char data; - /* - * We use %%dx and not %1 here because i/o is done at %dx and not at - * %edx, while gcc generates inferior code (movw instead of movl) - * if we tell it to load (u_short) port. - */ - __asm __volatile("inb %%dx,%0" : "=a" (data) : "d" (port)); - return (data); + return inb(port); } void -outb(u_int port, u_char data) +outb_(u_short port, u_char data) { - u_char al; - /* - * Use an unnecessary assignment to help gcc's register allocator. - * This make a large difference for gcc-1.40 and a tiny difference - * for gcc-2.6.0. For gcc-1.40, al had to be ``asm("ax")'' for - * best results. gcc-2.6.0 can't handle this. - */ - al = data; - __asm __volatile("outb %0,%%dx" : : "a" (al), "d" (port)); + outb(port, data); } #endif /* KDB */ Modified: head/sys/amd64/include/cpufunc.h ============================================================================== --- head/sys/amd64/include/cpufunc.h Sat Apr 11 13:15:38 2009 (r190918) +++ head/sys/amd64/include/cpufunc.h Sat Apr 11 14:01:01 2009 (r190919) @@ -164,70 +164,12 @@ halt(void) __asm __volatile("hlt"); } -#if !defined(__GNUCLIKE_BUILTIN_CONSTANT_P) || __GNUCLIKE_ASM < 3 - -#define inb(port) inbv(port) -#define outb(port, data) outbv(port, data) - -#else /* __GNUCLIKE_BUILTIN_CONSTANT_P && __GNUCLIKE_ASM >= 3 */ - -/* - * The following complications are to get around gcc not having a - * constraint letter for the range 0..255. We still put "d" in the - * constraint because "i" isn't a valid constraint when the port - * isn't constant. This only matters for -O0 because otherwise - * the non-working version gets optimized away. - * - * Use an expression-statement instead of a conditional expression - * because gcc-2.6.0 would promote the operands of the conditional - * and produce poor code for "if ((inb(var) & const1) == const2)". - * - * The unnecessary test `(port) < 0x10000' is to generate a warning if - * the `port' has type u_short or smaller. Such types are pessimal. - * This actually only works for signed types. The range check is - * careful to avoid generating warnings. - */ -#define inb(port) __extension__ ({ \ - u_char _data; \ - if (__builtin_constant_p(port) && ((port) & 0xffff) < 0x100 \ - && (port) < 0x10000) \ - _data = inbc(port); \ - else \ - _data = inbv(port); \ - _data; }) - -#define outb(port, data) ( \ - __builtin_constant_p(port) && ((port) & 0xffff) < 0x100 \ - && (port) < 0x10000 \ - ? outbc(port, data) : outbv(port, data)) - static __inline u_char -inbc(u_int port) +inb(u_int port) { u_char data; - __asm __volatile("inb %1,%0" : "=a" (data) : "id" ((u_short)(port))); - return (data); -} - -static __inline void -outbc(u_int port, u_char data) -{ - __asm __volatile("outb %0,%1" : : "a" (data), "id" ((u_short)(port))); -} - -#endif /* __GNUCLIKE_BUILTIN_CONSTANT_P && __GNUCLIKE_ASM >= 3*/ - -static __inline u_char -inbv(u_int port) -{ - u_char data; - /* - * We use %%dx and not %1 here because i/o is done at %dx and not at - * %edx, while gcc generates inferior code (movw instead of movl) - * if we tell it to load (u_short) port. - */ - __asm __volatile("inb %%dx,%0" : "=a" (data) : "d" (port)); + __asm volatile("inb %w1, %0" : "=a" (data) : "Nd" (port)); return (data); } @@ -236,7 +178,7 @@ inl(u_int port) { u_int data; - __asm __volatile("inl %%dx,%0" : "=a" (data) : "d" (port)); + __asm volatile("inl %w1, %0" : "=a" (data) : "Nd" (port)); return (data); } @@ -278,33 +220,20 @@ inw(u_int port) { u_short data; - __asm __volatile("inw %%dx,%0" : "=a" (data) : "d" (port)); + __asm volatile("inw %w1, %0" : "=a" (data) : "Nd" (port)); return (data); } static __inline void -outbv(u_int port, u_char data) +outb(u_int port, u_char data) { - u_char al; - /* - * Use an unnecessary assignment to help gcc's register allocator. - * This make a large difference for gcc-1.40 and a tiny difference - * for gcc-2.6.0. For gcc-1.40, al had to be ``asm("ax")'' for - * best results. gcc-2.6.0 can't handle this. - */ - al = data; - __asm __volatile("outb %0,%%dx" : : "a" (al), "d" (port)); + __asm volatile("outb %0, %w1" : : "a" (data), "Nd" (port)); } static __inline void outl(u_int port, u_int data) { - /* - * outl() and outw() aren't used much so we haven't looked at - * possible micro-optimizations such as the unnecessary - * assignment for them. - */ - __asm __volatile("outl %0,%%dx" : : "a" (data), "d" (port)); + __asm volatile("outl %0, %w1" : : "a" (data), "Nd" (port)); } static __inline void @@ -334,7 +263,7 @@ outsl(u_int port, const void *addr, size static __inline void outw(u_int port, u_short data) { - __asm __volatile("outw %0,%%dx" : : "a" (data), "d" (port)); + __asm volatile("outw %0, %w1" : : "a" (data), "Nd" (port)); } static __inline void Modified: head/sys/i386/i386/machdep.c ============================================================================== --- head/sys/i386/i386/machdep.c Sat Apr 11 13:15:38 2009 (r190918) +++ head/sys/i386/i386/machdep.c Sat Apr 11 14:01:01 2009 (r190919) @@ -3555,45 +3555,24 @@ lapic_set_lvt_triggermode(u_int apic_id, #ifdef KDB /* - * Provide inb() and outb() as functions. They are normally only - * available as macros calling inlined functions, thus cannot be - * called from the debugger. - * - * The actual code is stolen from <machine/cpufunc.h>, and de-inlined. + * Provide inb() and outb() as functions. They are normally only available as + * inline functions, thus cannot be called from the debugger. */ -#undef inb -#undef outb - /* silence compiler warnings */ -u_char inb(u_int); -void outb(u_int, u_char); +u_char inb_(u_short); +void outb_(u_short, u_char); u_char -inb(u_int port) +inb_(u_short port) { - u_char data; - /* - * We use %%dx and not %1 here because i/o is done at %dx and not at - * %edx, while gcc generates inferior code (movw instead of movl) - * if we tell it to load (u_short) port. - */ - __asm __volatile("inb %%dx,%0" : "=a" (data) : "d" (port)); - return (data); + return inb(port); } void -outb(u_int port, u_char data) +outb_(u_short port, u_char data) { - u_char al; - /* - * Use an unnecessary assignment to help gcc's register allocator. - * This make a large difference for gcc-1.40 and a tiny difference - * for gcc-2.6.0. For gcc-1.40, al had to be ``asm("ax")'' for - * best results. gcc-2.6.0 can't handle this. - */ - al = data; - __asm __volatile("outb %0,%%dx" : : "a" (al), "d" (port)); + outb(port, data); } #endif /* KDB */ Modified: head/sys/i386/include/cpufunc.h ============================================================================== --- head/sys/i386/include/cpufunc.h Sat Apr 11 13:15:38 2009 (r190918) +++ head/sys/i386/include/cpufunc.h Sat Apr 11 14:01:01 2009 (r190919) @@ -170,70 +170,12 @@ halt(void) __asm __volatile("hlt"); } -#if !defined(__GNUCLIKE_BUILTIN_CONSTANT_P) || __GNUCLIKE_ASM < 3 - -#define inb(port) inbv(port) -#define outb(port, data) outbv(port, data) - -#else /* __GNUCLIKE_BUILTIN_CONSTANT_P && __GNUCLIKE_ASM >= 3 */ - -/* - * The following complications are to get around gcc not having a - * constraint letter for the range 0..255. We still put "d" in the - * constraint because "i" isn't a valid constraint when the port - * isn't constant. This only matters for -O0 because otherwise - * the non-working version gets optimized away. - * - * Use an expression-statement instead of a conditional expression - * because gcc-2.6.0 would promote the operands of the conditional - * and produce poor code for "if ((inb(var) & const1) == const2)". - * - * The unnecessary test `(port) < 0x10000' is to generate a warning if - * the `port' has type u_short or smaller. Such types are pessimal. - * This actually only works for signed types. The range check is - * careful to avoid generating warnings. - */ -#define inb(port) __extension__ ({ \ - u_char _data; \ - if (__builtin_constant_p(port) && ((port) & 0xffff) < 0x100 \ - && (port) < 0x10000) \ - _data = inbc(port); \ - else \ - _data = inbv(port); \ - _data; }) - -#define outb(port, data) ( \ - __builtin_constant_p(port) && ((port) & 0xffff) < 0x100 \ - && (port) < 0x10000 \ - ? outbc(port, data) : outbv(port, data)) - static __inline u_char -inbc(u_int port) +inb(u_int port) { u_char data; - __asm __volatile("inb %1,%0" : "=a" (data) : "id" ((u_short)(port))); - return (data); -} - -static __inline void -outbc(u_int port, u_char data) -{ - __asm __volatile("outb %0,%1" : : "a" (data), "id" ((u_short)(port))); -} - -#endif /* __GNUCLIKE_BUILTIN_CONSTANT_P && __GNUCLIKE_ASM >= 3*/ - -static __inline u_char -inbv(u_int port) -{ - u_char data; - /* - * We use %%dx and not %1 here because i/o is done at %dx and not at - * %edx, while gcc generates inferior code (movw instead of movl) - * if we tell it to load (u_short) port. - */ - __asm __volatile("inb %%dx,%0" : "=a" (data) : "d" (port)); + __asm volatile("inb %w1, %0" : "=a" (data) : "Nd" (port)); return (data); } @@ -242,7 +184,7 @@ inl(u_int port) { u_int data; - __asm __volatile("inl %%dx,%0" : "=a" (data) : "d" (port)); + __asm volatile("inl %w1, %0" : "=a" (data) : "Nd" (port)); return (data); } @@ -284,33 +226,20 @@ inw(u_int port) { u_short data; - __asm __volatile("inw %%dx,%0" : "=a" (data) : "d" (port)); + __asm volatile("inw %w1, %0" : "=a" (data) : "Nd" (port)); return (data); } static __inline void -outbv(u_int port, u_char data) +outb(u_int port, u_char data) { - u_char al; - /* - * Use an unnecessary assignment to help gcc's register allocator. - * This make a large difference for gcc-1.40 and a tiny difference - * for gcc-2.6.0. For gcc-1.40, al had to be ``asm("ax")'' for - * best results. gcc-2.6.0 can't handle this. - */ - al = data; - __asm __volatile("outb %0,%%dx" : : "a" (al), "d" (port)); + __asm __volatile("outb %0, %w1" : : "a" (data), "Nd" (port)); } static __inline void outl(u_int port, u_int data) { - /* - * outl() and outw() aren't used much so we haven't looked at - * possible micro-optimizations such as the unnecessary - * assignment for them. - */ - __asm __volatile("outl %0,%%dx" : : "a" (data), "d" (port)); + __asm volatile("outl %0, %w1" : : "a" (data), "Nd" (port)); } static __inline void @@ -340,7 +269,7 @@ outsl(u_int port, const void *addr, size static __inline void outw(u_int port, u_short data) { - __asm __volatile("outw %0,%%dx" : : "a" (data), "d" (port)); + __asm volatile("outw %0, %w1" : : "a" (data), "Nd" (port)); } static __inline void
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200904111401.n3BE1108088009>