xen/bitops: Implement fls()/flsl() in common logic

This is most easily done together because of how arm32 is currently
structured, but it does just mirror the existing ffs()/ffsl() work.

Introduce compile and boot time testing.

Signed-off-by: Oleksii Kurochko <oleksii.kurochko@gmail.com>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Release-acked-by: Oleksii Kurochko <oleksii.kurochko@gmail.com>

diff --git a/xen/arch/arm/include/asm/arm32/bitops.h b/xen/arch/arm/include/asm/arm32/bitops.h
index d0309d47c1883d66c430adaaedee506517ce08a9..0d7bb12d5c198e5ca917c753519bbc9f1d88b2f2 100644 (file)
--- a/xen/arch/arm/include/asm/arm32/bitops.h
+++ b/xen/arch/arm/include/asm/arm32/bitops.h
@@ -1,8 +1,6 @@
 #ifndef _ARM_ARM32_BITOPS_H
 #define _ARM_ARM32_BITOPS_H
 
-#define flsl fls
-
 /*
  * Little endian assembly bitops.  nr = 0 -> byte 0 bit 0.
  */

diff --git a/xen/arch/arm/include/asm/arm64/bitops.h b/xen/arch/arm/include/asm/arm64/bitops.h
index 906d84e5f295cefd68a700fb688785d2aac34b59..a6135838dcfa16be1d1a53f3a20e098780a797df 100644 (file)
--- a/xen/arch/arm/include/asm/arm64/bitops.h
+++ b/xen/arch/arm/include/asm/arm64/bitops.h
@@ -1,18 +1,6 @@
 #ifndef _ARM_ARM64_BITOPS_H
 #define _ARM_ARM64_BITOPS_H
 
-static inline int flsl(unsigned long x)
-{
-        uint64_t ret;
-
-        if (__builtin_constant_p(x))
-               return generic_flsl(x);
-
-        asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
-
-        return BITS_PER_LONG - ret;
-}
-
 /* Based on linux/include/asm-generic/bitops/find.h */
 
 #ifndef CONFIG_GENERIC_FIND_FIRST_BIT

diff --git a/xen/arch/arm/include/asm/bitops.h b/xen/arch/arm/include/asm/bitops.h
index d30ba44598e3a6ae86f3f354d7d2522d1cb536cb..8f4bdc09d128642443422bc46c09691b99aac4bf 100644 (file)
--- a/xen/arch/arm/include/asm/bitops.h
+++ b/xen/arch/arm/include/asm/bitops.h
@@ -140,25 +140,10 @@ static inline int test_bit(int nr, const volatile void *addr)
         return 1UL & (p[BITOP_WORD(nr)] >> (nr & (BITOP_BITS_PER_WORD-1)));
 }
 
-/*
- * On ARMv5 and above those functions can be implemented around
- * the clz instruction for much better code efficiency.
- */
-
-static inline int fls(unsigned int x)
-{
-        int ret;
-
-        if (__builtin_constant_p(x))
-               return generic_flsl(x);
-
-        asm("clz\t%"__OP32"0, %"__OP32"1" : "=r" (ret) : "r" (x));
-        return 32 - ret;
-}
-
-
 #define arch_ffs(x)  ((x) ? 1 + __builtin_ctz(x) : 0)
 #define arch_ffsl(x) ((x) ? 1 + __builtin_ctzl(x) : 0)
+#define arch_fls(x)  ((x) ? 32 - __builtin_clz(x) : 0)
+#define arch_flsl(x) ((x) ? BITS_PER_LONG - __builtin_clzl(x) : 0)
 
 /**
  * hweightN - returns the hamming weight of a N-bit word

diff --git a/xen/arch/ppc/include/asm/bitops.h b/xen/arch/ppc/include/asm/bitops.h
index 761361291e6fcf10573bc38048fac3d4e4e30955..8119b5ace877b3c399647228d5474e45eb2bb818 100644 (file)
--- a/xen/arch/ppc/include/asm/bitops.h
+++ b/xen/arch/ppc/include/asm/bitops.h
@@ -171,10 +171,10 @@ static inline int __test_and_clear_bit(int nr, volatile void *addr)
     return (old & mask) != 0;
 }
 
-#define flsl(x) generic_flsl(x)
-#define fls(x) generic_flsl(x)
 #define arch_ffs(x)  ((x) ? 1 + __builtin_ctz(x) : 0)
 #define arch_ffsl(x) ((x) ? 1 + __builtin_ctzl(x) : 0)
+#define arch_fls(x)  ((x) ? 32 - __builtin_clz(x) : 0)
+#define arch_flsl(x) ((x) ? BITS_PER_LONG - __builtin_clzl(x) : 0)
 
 /**
  * hweightN - returns the hamming weight of a N-bit word

diff --git a/xen/arch/x86/include/asm/bitops.h b/xen/arch/x86/include/asm/bitops.h
index 90d892e1dd64e8c869dfb2951e307a00bad9f778..aa71542e7b951a1e2fac1f857693b0930699167b 100644 (file)
--- a/xen/arch/x86/include/asm/bitops.h
+++ b/xen/arch/x86/include/asm/bitops.h
@@ -458,33 +458,41 @@ static always_inline unsigned int arch_ffsl(unsigned long x)
 }
 #define arch_ffsl arch_ffsl
 
-/**
- * fls - find last bit set
- * @x: the word to search
- *
- * This is defined the same way as ffs.
- */
-static inline int flsl(unsigned long x)
+static always_inline unsigned int arch_fls(unsigned int x)
 {
-    long r;
+    unsigned int r;
+
+    /* See arch_ffs() for safety discussions. */
+    if ( __builtin_constant_p(x > 0) && x > 0 )
+        asm ( "bsr %[val], %[res]"
+              : [res] "=r" (r)
+              : [val] "rm" (x) );
+    else
+        asm ( "bsr %[val], %[res]"
+              : [res] "=r" (r)
+              : [val] "rm" (x), "[res]" (-1) );
 
-    asm ( "bsr %1,%0\n\t"
-          "jnz 1f\n\t"
-          "mov $-1,%0\n"
-          "1:" : "=r" (r) : "rm" (x));
-    return (int)r+1;
+    return r + 1;
 }
+#define arch_fls arch_fls
 
-static inline int fls(unsigned int x)
+static always_inline unsigned int arch_flsl(unsigned long x)
 {
-    int r;
+    unsigned int r;
+
+    /* See arch_ffs() for safety discussions. */
+    if ( __builtin_constant_p(x > 0) && x > 0 )
+        asm ( "bsr %[val], %q[res]"
+              : [res] "=r" (r)
+              : [val] "rm" (x) );
+    else
+        asm ( "bsr %[val], %q[res]"
+              : [res] "=r" (r)
+              : [val] "rm" (x), "[res]" (-1) );
 
-    asm ( "bsr %1,%0\n\t"
-          "jnz 1f\n\t"
-          "mov $-1,%0\n"
-          "1:" : "=r" (r) : "rm" (x));
     return r + 1;
 }
+#define arch_flsl arch_flsl
 
 /**
  * hweightN - returns the hamming weight of a N-bit word

diff --git a/xen/common/bitops.c b/xen/common/bitops.c
index df0e9bacbccdc86526eac5717ee2473842407328..0e1cc1f509dc19b2890211db94e6d3e227b17185 100644 (file)
--- a/xen/common/bitops.c
+++ b/xen/common/bitops.c
@@ -28,7 +28,32 @@ static void __init test_ffs(void)
 #endif
 }
 
+static void __init test_fls(void)
+{
+    /* unsigned int fls(unsigned int) */
+    CHECK(fls, 0, 0);
+    CHECK(fls, 1, 1);
+    CHECK(fls, 3, 2);
+    CHECK(fls, 7, 3);
+    CHECK(fls, 6, 3);
+    CHECK(fls, 0x80000000U, 32);
+
+    /* unsigned int flsl(unsigned long) */
+    CHECK(flsl, 0, 0);
+    CHECK(flsl, 1, 1);
+    CHECK(flsl, 3, 2);
+    CHECK(flsl, 7, 3);
+    CHECK(flsl, 6, 3);
+
+    CHECK(flsl, 1 | (1UL << (BITS_PER_LONG - 1)), BITS_PER_LONG);
+#if BITS_PER_LONG > 32
+    CHECK(flsl, 1 | (1UL << 32), 33);
+    CHECK(flsl, 1 | (1UL << 63), 64);
+#endif
+}
+
 static void __init __constructor test_bitops(void)
 {
     test_ffs();
+    test_fls();
 }

diff --git a/xen/include/xen/bitops.h b/xen/include/xen/bitops.h
index 5aa8d7aa5a059497935f74e85f9b06b49e5bfd96..9f8d9eff115f00c7b254cbbcf30e6c407b373bb4 100644 (file)
--- a/xen/include/xen/bitops.h
+++ b/xen/include/xen/bitops.h
@@ -60,6 +60,30 @@ static always_inline __pure unsigned int ffsl(unsigned long x)
 #endif
 }
 
+static always_inline __pure unsigned int fls(unsigned int x)
+{
+    if ( __builtin_constant_p(x) )
+        return x ? 32 - __builtin_clz(x) : 0;
+
+#ifdef arch_fls
+    return arch_fls(x);
+#else
+    return generic_flsl(x);
+#endif
+}
+
+static always_inline __pure unsigned int flsl(unsigned long x)
+{
+    if ( __builtin_constant_p(x) )
+        return x ? BITS_PER_LONG - __builtin_clzl(x) : 0;
+
+#ifdef arch_fls
+    return arch_flsl(x);
+#else
+    return generic_flsl(x);
+#endif
+}
+
 /* --------------------- Please tidy below here --------------------- */
 
 #ifndef find_next_bit