mirror of
https://github.com/torvalds/linux.git
synced 2026-05-14 09:22:17 +02:00
a37fbe666c
The number of times yet another open coded `BITS_TO_LONGS(nbits) * sizeof(long)` can be spotted is huge. Some generic helper is long overdue. Add one, bitmap_size(), but with one detail. BITS_TO_LONGS() uses DIV_ROUND_UP(). The latter works well when both divident and divisor are compile-time constants or when the divisor is not a pow-of-2. When it is however, the compilers sometimes tend to generate suboptimal code (GCC 13): 48 83 c0 3f add $0x3f,%rax 48 c1 e8 06 shr $0x6,%rax 48 8d 14 c5 00 00 00 00 lea 0x0(,%rax,8),%rdx %BITS_PER_LONG is always a pow-2 (either 32 or 64), but GCC still does full division of `nbits + 63` by it and then multiplication by 8. Instead of BITS_TO_LONGS(), use ALIGN() and then divide by 8. GCC: 8d 50 3f lea 0x3f(%rax),%edx c1 ea 03 shr $0x3,%edx 81 e2 f8 ff ff 1f and $0x1ffffff8,%edx Now it shifts `nbits + 63` by 3 positions (IOW performs fast division by 8) and then masks bits[2:0]. bloat-o-meter: add/remove: 0/0 grow/shrink: 20/133 up/down: 156/-773 (-617) Clang does it better and generates the same code before/after starting from -O1, except that with the ALIGN() approach it uses %edx and thus still saves some bytes: add/remove: 0/0 grow/shrink: 9/133 up/down: 18/-538 (-520) Note that we can't expand DIV_ROUND_UP() by adding a check and using this approach there, as it's used in array declarations where expressions are not allowed. Add this helper to tools/ as well. Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Acked-by: Yury Norov <yury.norov@gmail.com> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
||
|---|---|---|
| .. | ||
| sched | ||
| unaligned | ||
| align.h | ||
| arm-smccc.h | ||
| atomic.h | ||
| bitfield.h | ||
| bitmap.h | ||
| bitops.h | ||
| bits.h | ||
| btf_ids.h | ||
| bug.h | ||
| build_bug.h | ||
| cache.h | ||
| compiler_types.h | ||
| compiler-gcc.h | ||
| compiler.h | ||
| const.h | ||
| coresight-pmu.h | ||
| ctype.h | ||
| debugfs.h | ||
| delay.h | ||
| err.h | ||
| export.h | ||
| filter.h | ||
| find.h | ||
| ftrace.h | ||
| gfp_types.h | ||
| gfp.h | ||
| hash.h | ||
| hashtable.h | ||
| interrupt.h | ||
| interval_tree_generic.h | ||
| io.h | ||
| jhash.h | ||
| kallsyms.h | ||
| kconfig.h | ||
| kern_levels.h | ||
| kernel.h | ||
| linkage.h | ||
| list_sort.h | ||
| list.h | ||
| log2.h | ||
| math.h | ||
| math64.h | ||
| mm.h | ||
| module.h | ||
| mutex.h | ||
| nmi.h | ||
| numa.h | ||
| objtool_types.h | ||
| overflow.h | ||
| pfn.h | ||
| poison.h | ||
| rbtree_augmented.h | ||
| rbtree.h | ||
| rcu.h | ||
| refcount.h | ||
| ring_buffer.h | ||
| rwsem.h | ||
| seq_file.h | ||
| sizes.h | ||
| slab.h | ||
| spinlock.h | ||
| static_call_types.h | ||
| string.h | ||
| stringify.h | ||
| time64.h | ||
| types.h | ||
| zalloc.h | ||