mirror of https://github.com/torvalds/linux.git
The this_cpu_* options can be used to optimize __percpu_counter_add a bit. Avoids some address arithmetic and saves 12 bytes. Before: 00000000000001d3 <__percpu_counter_add>: 1d3: 55 push %rbp 1d4: 48 89 e5 mov %rsp,%rbp 1d7: 41 55 push %r13 1d9: 41 54 push %r12 1db: 53 push %rbx 1dc: 48 89 fb mov %rdi,%rbx 1df: 48 83 ec 08 sub $0x8,%rsp 1e3: 4c 8b 67 30 mov 0x30(%rdi),%r12 1e7: 65 4c 03 24 25 00 00 add %gs:0x0,%r12 1ee: 00 00 1f0: 4d 63 2c 24 movslq (%r12),%r13 1f4: 48 63 c2 movslq %edx,%rax 1f7: 49 01 f5 add %rsi,%r13 1fa: 49 39 c5 cmp %rax,%r13 1fd: 7d 0a jge 209 <__percpu_counter_add+0x36> 1ff: f7 da neg %edx 201: 48 63 d2 movslq %edx,%rdx 204: 49 39 d5 cmp %rdx,%r13 207: 7f 1e jg 227 <__percpu_counter_add+0x54> 209: 48 89 df mov %rbx,%rdi 20c: e8 00 00 00 00 callq 211 <__percpu_counter_add+0x3e> 211: 4c 01 6b 18 add %r13,0x18(%rbx) 215: 48 89 df mov %rbx,%rdi 218: 41 c7 04 24 00 00 00 movl $0x0,(%r12) 21f: 00 220: e8 00 00 00 00 callq 225 <__percpu_counter_add+0x52> 225: eb 04 jmp 22b <__percpu_counter_add+0x58> 227: 45 89 2c 24 mov %r13d,(%r12) 22b: 5b pop %rbx 22c: 5b pop %rbx 22d: 41 5c pop %r12 22f: 41 5d pop %r13 231: c9 leaveq 232: c3 retq After: 00000000000001d3 <__percpu_counter_add>: 1d3: 55 push %rbp 1d4: 48 63 ca movslq %edx,%rcx 1d7: 48 89 e5 mov %rsp,%rbp 1da: 41 54 push %r12 1dc: 53 push %rbx 1dd: 48 89 fb mov %rdi,%rbx 1e0: 48 8b 47 30 mov 0x30(%rdi),%rax 1e4: 65 44 8b 20 mov %gs:(%rax),%r12d 1e8: 4d 63 e4 movslq %r12d,%r12 1eb: 49 01 f4 add %rsi,%r12 1ee: 49 39 cc cmp %rcx,%r12 1f1: 7d 0a jge 1fd <__percpu_counter_add+0x2a> 1f3: f7 da neg %edx 1f5: 48 63 d2 movslq %edx,%rdx 1f8: 49 39 d4 cmp %rdx,%r12 1fb: 7f 21 jg 21e <__percpu_counter_add+0x4b> 1fd: 48 89 df mov %rbx,%rdi 200: e8 00 00 00 00 callq 205 <__percpu_counter_add+0x32> 205: 4c 01 63 18 add %r12,0x18(%rbx) 209: 48 8b 43 30 mov 0x30(%rbx),%rax 20d: 48 89 df mov %rbx,%rdi 210: 65 c7 00 00 00 00 00 movl $0x0,%gs:(%rax) 217: e8 00 00 00 00 callq 21c <__percpu_counter_add+0x49> 21c: eb 04 jmp 222 <__percpu_counter_add+0x4f> 21e: 65 44 89 20 mov %r12d,%gs:(%rax) 222: 5b pop %rbx 223: 41 5c pop %r12 225: c9 leaveq 226: c3 retq Reviewed-by: Pekka Enberg <penberg@kernel.org> Reviewed-by: Tejun Heo <tj@kernel.org> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Tejun Heo <tj@kernel.org> |
||
|---|---|---|
| .. | ||
| lzo | ||
| raid6 | ||
| reed_solomon | ||
| zlib_deflate | ||
| zlib_inflate | ||
| .gitignore | ||
| Kconfig | ||
| Kconfig.debug | ||
| Kconfig.kgdb | ||
| Kconfig.kmemcheck | ||
| Makefile | ||
| argv_split.c | ||
| atomic64.c | ||
| atomic64_test.c | ||
| audit.c | ||
| bcd.c | ||
| bitmap.c | ||
| bitrev.c | ||
| btree.c | ||
| bug.c | ||
| bust_spinlocks.c | ||
| check_signature.c | ||
| checksum.c | ||
| cmdline.c | ||
| cpu-notifier-error-inject.c | ||
| cpumask.c | ||
| crc-ccitt.c | ||
| crc-itu-t.c | ||
| crc-t10dif.c | ||
| crc7.c | ||
| crc16.c | ||
| crc32.c | ||
| crc32defs.h | ||
| ctype.c | ||
| debug_locks.c | ||
| debugobjects.c | ||
| dec_and_lock.c | ||
| decompress.c | ||
| decompress_bunzip2.c | ||
| decompress_inflate.c | ||
| decompress_unlzma.c | ||
| decompress_unlzo.c | ||
| devres.c | ||
| div64.c | ||
| dma-debug.c | ||
| dump_stack.c | ||
| dynamic_debug.c | ||
| extable.c | ||
| fault-inject.c | ||
| find_last_bit.c | ||
| find_next_bit.c | ||
| flex_array.c | ||
| gcd.c | ||
| gen_crc32table.c | ||
| genalloc.c | ||
| halfmd4.c | ||
| hexdump.c | ||
| hweight.c | ||
| idr.c | ||
| inflate.c | ||
| int_sqrt.c | ||
| iomap.c | ||
| iomap_copy.c | ||
| iommu-helper.c | ||
| ioremap.c | ||
| irq_regs.c | ||
| is_single_threaded.c | ||
| kasprintf.c | ||
| kernel_lock.c | ||
| klist.c | ||
| kobject.c | ||
| kobject_uevent.c | ||
| kref.c | ||
| lcm.c | ||
| libcrc32c.c | ||
| list_debug.c | ||
| list_sort.c | ||
| locking-selftest-hardirq.h | ||
| locking-selftest-mutex.h | ||
| locking-selftest-rlock-hardirq.h | ||
| locking-selftest-rlock-softirq.h | ||
| locking-selftest-rlock.h | ||
| locking-selftest-rsem.h | ||
| locking-selftest-softirq.h | ||
| locking-selftest-spin-hardirq.h | ||
| locking-selftest-spin-softirq.h | ||
| locking-selftest-spin.h | ||
| locking-selftest-wlock-hardirq.h | ||
| locking-selftest-wlock-softirq.h | ||
| locking-selftest-wlock.h | ||
| locking-selftest-wsem.h | ||
| locking-selftest.c | ||
| lru_cache.c | ||
| nlattr.c | ||
| parser.c | ||
| percpu_counter.c | ||
| plist.c | ||
| prio_heap.c | ||
| prio_tree.c | ||
| proportions.c | ||
| radix-tree.c | ||
| random32.c | ||
| ratelimit.c | ||
| rational.c | ||
| rbtree.c | ||
| reciprocal_div.c | ||
| rwsem-spinlock.c | ||
| rwsem.c | ||
| scatterlist.c | ||
| sha1.c | ||
| show_mem.c | ||
| smp_processor_id.c | ||
| sort.c | ||
| spinlock_debug.c | ||
| string.c | ||
| string_helpers.c | ||
| swiotlb.c | ||
| syscall.c | ||
| textsearch.c | ||
| ts_bm.c | ||
| ts_fsm.c | ||
| ts_kmp.c | ||
| uuid.c | ||
| vsprintf.c | ||