[PATCH] xen/ARM: Drop __div64_fls()

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

Following the improvements to Xen's bitops, fls() does constant propagation in
all cases.  Use it, and drop the local opencoded helper.

No functional change.

Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
---
CC: Stefano Stabellini <sstabellini@xxxxxxxxxx>
CC: Julien Grall <julien@xxxxxxx>
CC: Volodymyr Babchuk <Volodymyr_Babchuk@xxxxxxxx>
CC: Bertrand Marquis <bertrand.marquis@xxxxxxx>
CC: Michal Orzel <michal.orzel@xxxxxxx>

ARM32 gets a very minor code generation improvement:

  xen.git/xen$ ../scripts/bloat-o-meter xen-syms-arm32-{before,after}
  add/remove: 0/0 grow/shrink: 0/6 up/down: 0/-48 (-48)
  Function                                     old     new   delta
  wallclock_time                               288     280      -8
  printk_start_of_line                         560     552      -8
  domain_vtimer_init                           472     464      -8
  do_settime                                   376     368      -8
  burn_credits                                 760     752      -8
  __printk_ratelimit                           424     416      -8

But it's just a couple of operations improvement and no real change in code
structure.  I expect that the constant propagation being done through
__builtin_clz(), rather than pure C, is giving the optimiser a bit more
information to work with.

This file also has an __GNUC__ < 4 case which seems ripe for removing...
---
 xen/arch/arm/include/asm/div64.h | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/xen/arch/arm/include/asm/div64.h b/xen/arch/arm/include/asm/div64.h
index 0459d5cc0122..da1f1fcbd503 100644
--- a/xen/arch/arm/include/asm/div64.h
+++ b/xen/arch/arm/include/asm/div64.h
@@ -102,7 +102,7 @@
                /* preserve low part of n for reminder computation */   \
                __r = __n;                                              \
                /* determine number of bits to represent __b */         \
-               __p = 1 << __div64_fls(__b);                            \
+               __p = 1 << fls(__b);                                    \
                /* compute __m = ((__p << 64) + __b - 1) / __b */       \
                __m = (~0ULL / __b) * __p;                              \
                __m += (((~0ULL % __b + 1) * __p) + __b - 1) / __b;     \
@@ -150,8 +150,8 @@
                                __p /= (__m & -__m);                    \
                                __m /= (__m & -__m);                    \
                        } else {                                        \
-                               __p >>= __div64_fls(__bits);            \
-                               __m >>= __div64_fls(__bits);            \
+                               __p >>= fls(__bits);                    \
+                               __m >>= fls(__bits);                    \
                        }                                               \
                        /* No correction needed. */                     \
                        __c = 0;                                        \
@@ -217,18 +217,6 @@
        __r;                                                            \
 })
 
-/* our own fls implementation to make sure constant propagation is fine */
-#define __div64_fls(bits)                                              \
-({                                                                     \
-       unsigned int __left = (bits), __nr = 0;                         \
-       if (__left & 0xffff0000) __nr += 16, __left >>= 16;             \
-       if (__left & 0x0000ff00) __nr +=  8, __left >>=  8;             \
-       if (__left & 0x000000f0) __nr +=  4, __left >>=  4;             \
-       if (__left & 0x0000000c) __nr +=  2, __left >>=  2;             \
-       if (__left & 0x00000002) __nr +=  1;                            \
-       __nr;                                                           \
-})
-
 #endif /* GCC version */
 
 #endif /* BITS_PER_LONG */

base-commit: b8cdfac2be38c98dd3ad0e911a3f7f787f5bcf6b
prerequisite-patch-id: 57ffe02b03d27a12f20d9e08fa21eed01c8c6299
prerequisite-patch-id: 56393fef18638a92eae127f36ffddb655fc7b9f4
prerequisite-patch-id: 4f963f44331104dc00663f8ff22bd306ef04f301
prerequisite-patch-id: 81a434352bbb36e17d3b7a45f489974fc4603ecb
prerequisite-patch-id: f2f2a00eee52f668b3f557fb6d357ec3bf00ac92
prerequisite-patch-id: 67b871715259e60fbf7db917233dbdecce6891da
prerequisite-patch-id: f8562e07c91fa42b1501efa759734a7874b9d909
prerequisite-patch-id: a5f304a67525412f0669a298a5f66285b56c3a58
prerequisite-patch-id: 6b5b1dc3f6760888a15c11cc658c52ba6fd3f33d
prerequisite-patch-id: 29eb6b854e9df37f5e8ed212215baab0ac7fbe87
prerequisite-patch-id: d87fe52c264dc5a33883a04b615043fbefd94f92
prerequisite-patch-id: 26a2978b861386fda945f1e60e9153cf0bdd24f3
prerequisite-patch-id: ab50b5247a29b4fbbd7207a558647dd3c57d5175
prerequisite-patch-id: 0f2a6cfa7d77c6f05f23c3aada161d02a9fc7660
prerequisite-patch-id: 7153c7bb3a45877fd84286dd9915046fa0a76056
prerequisite-patch-id: 74830838bac94ed1e036a8173cf3210a314b35d8
prerequisite-patch-id: 74a6e5ffb9f477afb61e73ed80a40c9359bc77a2
prerequisite-patch-id: 795f6e9425cc6a953166b530ae68df466a7a3c2b
prerequisite-patch-id: e37b1bc5dd69e7e68abf0e6c004431537f70175f
prerequisite-patch-id: 2e510b0a05df30c68bec8baf8b411a71e5f14d74
prerequisite-patch-id: e0397c86b545a1d65f2e6b2049c282b926c40c64
prerequisite-patch-id: 44606527ccbdf980a4c2401394f728f9c2011b8a
prerequisite-patch-id: 65b83839f7a477b9fa8e8913380e8eac2ac1ca0e
-- 
2.39.2