6a2d7a955d
When some objects are allocated by one CPU but freed by another CPU we can consume lot of cycles doing divides in obj_to_index(). (Typical load on a dual processor machine where network interrupts are handled by one particular CPU (allocating skbufs), and the other CPU is running the application (consuming and freeing skbufs)) Here on one production server (dual-core AMD Opteron 285), I noticed this divide took 1.20 % of CPU_CLK_UNHALTED events in kernel. But Opteron are quite modern cpus and the divide is much more expensive on oldest architectures : On a 200 MHz sparcv9 machine, the division takes 64 cycles instead of 1 cycle for a multiply. Doing some math, we can use a reciprocal multiplication instead of a divide. If we want to compute V = (A / B) (A and B being u32 quantities) we can instead use : V = ((u64)A * RECIPROCAL(B)) >> 32 ; where RECIPROCAL(B) is precalculated to ((1LL << 32) + (B - 1)) / B Note : I wrote pure C code for clarity. gcc output for i386 is not optimal but acceptable : mull 0x14(%ebx) mov %edx,%eax // part of the >> 32 xor %edx,%edx // useless mov %eax,(%esp) // could be avoided mov %edx,0x4(%esp) // useless mov (%esp),%ebx [akpm@osdl.org: small cleanups] Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Christoph Lameter <clameter@sgi.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
72 lines
2.1 KiB
Makefile
72 lines
2.1 KiB
Makefile
#
|
|
# Makefile for some libs needed in the kernel.
|
|
#
|
|
|
|
lib-y := ctype.o string.o vsprintf.o cmdline.o \
|
|
bust_spinlocks.o rbtree.o radix-tree.o dump_stack.o \
|
|
idr.o div64.o int_sqrt.o bitmap.o extable.o prio_tree.o \
|
|
sha1.o irq_regs.o reciprocal_div.o
|
|
|
|
lib-$(CONFIG_MMU) += ioremap.o
|
|
lib-$(CONFIG_SMP) += cpumask.o
|
|
|
|
lib-y += kobject.o kref.o kobject_uevent.o klist.o
|
|
|
|
obj-y += sort.o parser.o halfmd4.o iomap_copy.o debug_locks.o random32.o
|
|
|
|
ifeq ($(CONFIG_DEBUG_KOBJECT),y)
|
|
CFLAGS_kobject.o += -DDEBUG
|
|
CFLAGS_kobject_uevent.o += -DDEBUG
|
|
endif
|
|
|
|
obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
|
|
obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
|
|
lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
|
|
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
|
|
lib-$(CONFIG_SEMAPHORE_SLEEPERS) += semaphore-sleepers.o
|
|
lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o
|
|
obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
|
|
obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
|
|
obj-$(CONFIG_PLIST) += plist.o
|
|
obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
|
|
obj-$(CONFIG_DEBUG_LIST) += list_debug.o
|
|
|
|
ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
|
|
lib-y += dec_and_lock.o
|
|
endif
|
|
|
|
obj-$(CONFIG_BITREVERSE) += bitrev.o
|
|
obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o
|
|
obj-$(CONFIG_CRC16) += crc16.o
|
|
obj-$(CONFIG_CRC32) += crc32.o
|
|
obj-$(CONFIG_LIBCRC32C) += libcrc32c.o
|
|
obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
|
|
obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
|
|
|
|
obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
|
|
obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
|
|
obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
|
|
|
|
obj-$(CONFIG_TEXTSEARCH) += textsearch.o
|
|
obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
|
|
obj-$(CONFIG_TEXTSEARCH_BM) += ts_bm.o
|
|
obj-$(CONFIG_TEXTSEARCH_FSM) += ts_fsm.o
|
|
obj-$(CONFIG_SMP) += percpu_counter.o
|
|
obj-$(CONFIG_AUDIT_GENERIC) += audit.o
|
|
|
|
obj-$(CONFIG_SWIOTLB) += swiotlb.o
|
|
obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
|
|
|
|
lib-$(CONFIG_GENERIC_BUG) += bug.o
|
|
|
|
hostprogs-y := gen_crc32table
|
|
clean-files := crc32table.h
|
|
|
|
$(obj)/crc32.o: $(obj)/crc32table.h
|
|
|
|
quiet_cmd_crc32 = GEN $@
|
|
cmd_crc32 = $< > $@
|
|
|
|
$(obj)/crc32table.h: $(obj)/gen_crc32table
|
|
$(call cmd,crc32)
|