sparc: Use popc if possible for hweight routines.

Just like powerpc, we code patch at boot time.

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 102 insertions, 40 deletions

diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h
index 325e295d60de..3588807baa6e 100644
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -42,45 +42,11 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr);
  * of bits set) of a N-bit word
  */
 
-#ifdef ULTRA_HAS_POPULATION_COUNT
+extern unsigned long __arch_hweight64(__u64 w);
+extern unsigned int __arch_hweight32(unsigned int w);
+extern unsigned int __arch_hweight16(unsigned int w);
+extern unsigned int __arch_hweight8(unsigned int w);
 
-static inline unsigned int __arch_hweight64(unsigned long w)
-{
-        unsigned int res;
-
-        __asm__ ("popc %1,%0" : "=r" (res) : "r" (w));
-        return res;
-}
-
-static inline unsigned int __arch_hweight32(unsigned int w)
-{
-        unsigned int res;
-
-        __asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffffffff));
-        return res;
-}
-
-static inline unsigned int __arch_hweight16(unsigned int w)
-{
-        unsigned int res;
-
-        __asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffff));
-        return res;
-}
-
-static inline unsigned int __arch_hweight8(unsigned int w)
-{
-        unsigned int res;
-
-        __asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xff));
-        return res;
-}
-
-#else
-
-#include <asm-generic/bitops/arch_hweight.h>
-
-#endif
 #include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index d1f1361c4167..16d1545d84fc 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -42,6 +42,13 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 extern void fpload(unsigned long *fpregs, unsigned long *fsr);
 
 #else /* CONFIG_SPARC32 */
+struct popc_3insn_patch_entry {
+        unsigned int    addr;
+        unsigned int    insns[3];
+};
+extern struct popc_3insn_patch_entry __popc_3insn_patch,
+        __popc_3insn_patch_end;
+
 extern void __init per_cpu_patch(void);
 extern void __init sun4v_patch(void);
 extern void __init boot_cpu_id_too_large(int cpu);
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 242dbb3f31d2..26d114187e10 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -272,6 +272,30 @@ void __init sun4v_patch(void)
         sun4v_hvapi_init();
 }
 
+static void __init popc_patch(void)
+{
+        struct popc_3insn_patch_entry *p3;
+
+        p3 = &__popc_3insn_patch;
+        while (p3 < &__popc_3insn_patch_end) {
+                unsigned long addr = p3->addr;
+
+                *(unsigned int *) (addr +  0) = p3->insns[0];
+                wmb();
+                __asm__ __volatile__("flush     %0" : : "r" (addr +  0));
+
+                *(unsigned int *) (addr +  4) = p3->insns[1];
+                wmb();
+                __asm__ __volatile__("flush     %0" : : "r" (addr +  4));
+
+                *(unsigned int *) (addr +  8) = p3->insns[2];
+                wmb();
+                __asm__ __volatile__("flush     %0" : : "r" (addr +  4));
+
+                p3++;
+        }
+}
+
 #ifdef CONFIG_SMP
 void __init boot_cpu_id_too_large(int cpu)
 {
@@ -424,6 +448,9 @@ static void __init init_sparc64_elf_hwcap(void)
         sparc64_elf_hwcap = cap | mdesc_caps;
 
         report_hwcaps(sparc64_elf_hwcap);
+
+        if (sparc64_elf_hwcap & AV_SPARC_POPC)
+                popc_patch();
 }
 
 void __init setup_arch(char **cmdline_p)
diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c
index 372ad59c4cba..d0ee65aced0d 100644
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/bitops.h>
 
 #include <asm/system.h>
 #include <asm/cpudata.h>
@@ -38,5 +39,11 @@ EXPORT_SYMBOL(sun4v_niagara_setperf);
 EXPORT_SYMBOL(sun4v_niagara2_getperf);
 EXPORT_SYMBOL(sun4v_niagara2_setperf);
 
+/* from hweight.S */
+EXPORT_SYMBOL(__arch_hweight8);
+EXPORT_SYMBOL(__arch_hweight16);
+EXPORT_SYMBOL(__arch_hweight32);
+EXPORT_SYMBOL(__arch_hweight64);
+
 /* Exporting a symbol from /init/main.c */
 EXPORT_SYMBOL(saved_command_line);
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index c0220759003e..de20c14625eb 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -107,7 +107,11 @@ SECTIONS
                 *(.sun4v_2insn_patch)
                 __sun4v_2insn_patch_end = .;
         }
-
+        .popc_3insn_patch : {
+                __popc_3insn_patch = .;
+                *(.popc_3insn_patch)
+                __popc_3insn_patch_end = .;
+        }
         PERCPU_SECTION(SMP_CACHE_BYTES)
 
         . = ALIGN(PAGE_SIZE);
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index c25f94d28df8..11c850a9b66f 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -37,7 +37,7 @@ lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
 lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
 
 lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
-lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o
+lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o
 
 obj-y                 += iomap.o
 obj-$(CONFIG_SPARC32) += atomic32.o
diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S
new file mode 100644
index 000000000000..95414e0a6808
--- /dev/null
+++ b/arch/sparc/lib/hweight.S
@@ -0,0 +1,51 @@
+#include <linux/linkage.h>
+
+        .text
+        .align  32
+ENTRY(__arch_hweight8)
+        ba,pt   %xcc, __sw_hweight8
+         nop
+        nop
+ENDPROC(__arch_hweight8)
+        .section        .popc_3insn_patch, "ax"
+        .word           __arch_hweight8
+        sllx            %o0, 64-8, %g1
+        retl
+         popc           %g1, %o0
+        .previous
+
+ENTRY(__arch_hweight16)
+        ba,pt   %xcc, __sw_hweight16
+         nop
+        nop
+ENDPROC(__arch_hweight16)
+        .section        .popc_3insn_patch, "ax"
+        .word           __arch_hweight16
+        sllx            %o0, 64-16, %g1
+        retl
+         popc           %g1, %o0
+        .previous
+
+ENTRY(__arch_hweight32)
+        ba,pt   %xcc, __sw_hweight32
+         nop
+        nop
+ENDPROC(__arch_hweight32)
+        .section        .popc_3insn_patch, "ax"
+        .word           __arch_hweight32
+        sllx            %o0, 64-32, %g1
+        retl
+         popc           %g1, %o0
+        .previous
+
+ENTRY(__arch_hweight64)
+        ba,pt   %xcc, __sw_hweight64
+         nop
+        nop
+ENDPROC(__arch_hweight64)
+        .section        .popc_3insn_patch, "ax"
+        .word           __arch_hweight64
+        retl
+         popc           %o0, %o0
+        nop
+        .previous