Nicolas Pitre 00a31dd3ac asm-generic/div64: optimize/simplify __div64_const32() ... Several years later I just realized that this code could be greatly simplified. First, let's formalize the need for overflow handling in __arch_xprod64(). Assuming n = UINT64_MAX, there are 2 cases where an overflow may occur: 1) If a bias must be added, we have m_lo * n_lo + m or m_lo * 0xffffffff + ((m_hi << 32) + m_lo) or ((m_lo << 32) - m_lo) + ((m_hi << 32) + m_lo) or (m_lo + m_hi) << 32 which must be < (1 << 64). So the criteria for no overflow is m_lo + m_hi < (1 << 32). 2) The cross product m_lo * n_hi + m_hi * n_lo or m_lo * 0xffffffff + m_hi * 0xffffffff or ((m_lo << 32) - m_lo) + ((m_hi << 32) - m_hi). Assuming the top result from the previous step (m_lo + m_hi) that must be added to this, we get (m_lo + m_hi) << 32 again. So let's have a straight and simpler version when this is true. Otherwise some reordering allows for taking care of possible overflows without any actual conditionals. And prevent from generating both code variants by making sure this is considered only if m is perceived as constant by the compiler. This, in turn, allows for greatly simplifying __div64_const32(). The "special case" may go as well as the regular case works just fine without needing a bias. Then reduction should be applied all the time as minimizing m is the key. Signed-off-by: Nicolas Pitre <npitre@baylibre.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de>		2024-10-28 21:44:28 +00:00
..
bitops	bitops: Change function return types from long to int	2024-05-03 17:04:50 +02:00
vdso
access_ok.h	uaccess: remove CONFIG_SET_FS	2022-02-25 09:36:06 +01:00
agp.h	char/agp: introduce asm-generic/agp.h	2023-02-13 22:13:29 +01:00
archrandom.h	random: handle archrandom with multiple longs	2022-07-25 13:26:14 +02:00
asm-offsets.h
asm-prototypes.h
atomic64.h	locking/atomic: delete !ARCH_ATOMIC remnants	2021-05-26 13:20:52 +02:00
atomic.h	locking/atomic: make atomic*_{cmp,}xchg optional	2023-06-05 09:57:14 +02:00
audit_change_attr.h
audit_dir_write.h
audit_read.h
audit_signal.h
audit_write.h
barrier.h	sched: Add missing memory barrier in switch_mm_cid	2024-04-16 13:59:45 +02:00
bitops.h	include: move find.h from asm_generic to linux	2022-01-15 08:47:31 -08:00
bitsperlong.h	lib: extend the scope of small_const_nbits() macro	2021-05-06 19:24:11 -07:00
bug.h	bug: Improve comment	2024-05-07 14:20:48 +02:00
cache.h
cacheflush.h	mm: Introduce flush_cache_vmap_early()	2023-12-14 00:23:17 -08:00
cfi.h	cfi: Flip headers	2023-12-15 16:25:55 -08:00
checksum.h	asm-generic: Improve csum_fold	2024-01-17 17:52:29 -08:00
cmpxchg-local.h	asm-generic: Fix 32 bit __generic_cmpxchg_local	2024-01-05 23:19:14 +01:00
cmpxchg.h	asm-generic: avoid __generic_cmpxchg_local warnings	2023-04-04 17:58:11 +02:00
codetag.lds.h	lib: add allocation tagging support for memory allocation profiling	2024-04-25 20:55:52 -07:00
compat.h	asm-generic: compat: fix compat_arg_u64() and compat_arg_u64_dual()	2022-11-01 10:20:11 +11:00
current.h	asm-generic: current: Don't include thread-info.h if building asm	2023-08-26 22:38:49 +02:00
delay.h
device.h
div64.h	asm-generic/div64: optimize/simplify __div64_const32()	2024-10-28 21:44:28 +00:00
dma-mapping.h	dma-mapping: no need to pass a bus_type into get_arch_dma_ops()	2023-02-15 12:35:20 +01:00
dma.h
early_ioremap.h	mm/early_ioremap.c: remove redundant early_ioremap_shutdown()	2021-09-08 11:50:24 -07:00
emergency-restart.h
error-injection.h	docs: fault-injection: add requirements of error injectable functions	2023-02-02 22:50:00 -08:00
exec.h
extable.h
fixmap.h	fixmap: Remove unused set_fixmap_offset_io()	2024-07-11 17:41:23 +02:00
flat.h
ftrace.h
futex.h	futex: Fix additional regressions	2021-12-11 23:31:51 +01:00
getorder.h
hardirq.h
hugetlb.h	mm: provide mm_struct and address to huge_ptep_get()	2024-07-12 15:52:15 -07:00
hw_irq.h
hyperv-tlfs.h	hyperv-fixes for v6.9-rc4	2024-04-11 16:23:56 -07:00
int-ll64.h
io.h	asm-generic/io.h: Remove I/O port accessors for HAS_IOPORT=n	2024-10-28 21:44:28 +00:00
ioctl.h
iomap.h	asm-generic/iomap.h: remove ARCH_HAS_IOREMAP_xx macros	2023-08-18 10:12:32 -07:00
irq_regs.h
irq_work.h
irq.h
irqflags.h
Kbuild	move asm/unaligned.h to linux/unaligned.h	2024-10-02 17:23:23 -04:00
kdebug.h
kmap_size.h
kprobes.h
kvm_para.h
kvm_types.h
linkage.h
local64.h	locking/generic: Wire up local{,64}_try_cmpxchg()	2023-04-29 09:09:09 +02:00
local.h	locking/generic: Wire up local{,64}_try_cmpxchg()	2023-04-29 09:09:09 +02:00
logic_io.h	logic_io instance of iounmap() needs volatile on argument	2021-12-21 21:31:08 +01:00
mcs_spinlock.h
memory_model.h	asm-generic: add an optional pfn_valid check to page_to_phys	2024-10-28 21:44:28 +00:00
mm_hooks.h	mm: remove arch_unmap()	2024-09-01 20:26:13 -07:00
mmiowb_types.h
mmiowb.h
mmu_context.h
mmu.h
mmzone.h	arch, mm: move definition of node_data to generic code	2024-09-03 21:15:28 -07:00
module.h
module.lds.h
mshyperv.h	hyperv-fixes for v6.9-rc4	2024-04-11 16:23:56 -07:00
msi.h	genirq: Get rid of GENERIC_MSI_IRQ_DOMAIN	2022-11-17 15:15:20 +01:00
nommu_context.h
numa.h	arch_numa: switch over to numa_memblks	2024-09-03 21:15:32 -07:00
param.h
parport.h
pci_iomap.h	PCI: Stub __pci_ioport_map() for arches that don't support it at all	2022-07-29 12:01:00 -05:00
pci.h	asm-generic: Add new pci.h and use it	2022-07-22 17:34:57 -05:00
percpu.h	percpu: Fix self-assignment of __old in raw_cpu_generic_try_cmpxchg()	2023-06-08 10:28:39 +02:00
pgalloc.h	mm: change inlined allocation helpers to account at the call site	2024-04-25 20:55:59 -07:00
pgtable_uffd.h
pgtable-nop4d.h	mm: rename p4d_page_vaddr to p4d_pgtable and make it return pud_t *	2021-07-08 11:48:22 -07:00
pgtable-nopmd.h	mm: recover pud_leaf() definitions in nopmd case	2024-03-13 12:12:21 -07:00
pgtable-nopud.h	mm: rename p4d_page_vaddr to p4d_pgtable and make it return pud_t *	2021-07-08 11:48:22 -07:00
preempt.h	riscv: support PREEMPT_DYNAMIC with static keys	2023-08-31 00:18:34 -07:00
qrwlock_types.h	locking/qrwlock: Change "queue rwlock" to "queued rwlock"	2022-05-11 16:27:04 +02:00
qrwlock.h	asm-generic changes for 5.19	2022-05-26 10:50:30 -07:00
qspinlock_types.h
qspinlock.h	asm-generic: qspinlock: fix queued_spin_value_unlocked() implementation	2023-11-22 09:32:49 -08:00
resource.h
runtime-const.h	runtime constants: add default dummy infrastructure	2024-06-19 12:34:34 -07:00
rwonce.h
seccomp.h
sections.h	jump_label,module: Don't alloc static_key_mod for __ro_after_init keys	2024-03-22 11:18:16 +01:00
serial.h
set_memory.h
shmparam.h
signal.h	asm-generic: Remove empty #ifdef SA_RESTORER	2022-09-10 09:56:53 +02:00
simd.h
softirq_stack.h	asm-generic: Conditionally enable do_softirq_own_stack() via Kconfig.	2022-09-05 17:20:55 +02:00
spinlock_types.h	asm-generic: ticket-lock: New generic ticket-based spinlock	2022-05-11 11:49:38 -07:00
spinlock.h	asm-generic: ticket-lock: Optimize arch_spin_value_unlocked()	2023-09-21 10:17:00 +02:00
statfs.h
string.h
switch_to.h
syscall.h	ptrace: Create ptrace_report_syscall_{entry,exit} in ptrace.h	2022-03-10 13:35:08 -06:00
syscalls.h	syscalls: mmap(): use unsigned offset type consistently	2024-06-25 15:57:38 +02:00
timex.h
tlb.h	mm/mmu_gather: add __tlb_remove_folio_pages()	2024-02-22 15:27:17 -08:00
tlbflush.h
topology.h	mm: replace CONFIG_NEED_MULTIPLE_NODES with CONFIG_NUMA	2021-06-29 10:53:55 -07:00
trace_clock.h
uaccess.h	move asm/unaligned.h to linux/unaligned.h	2024-10-02 17:23:23 -04:00
user.h
vermagic.h
vga.h
video.h	arch: Rename fbdev header and source files	2024-05-03 17:07:50 +02:00
vmlinux.lds.h	asm-generic updates for 6.12	2024-09-26 11:54:40 -07:00
word-at-a-time.h	kernel.h: removed REPEAT_BYTE from kernel.h	2024-02-01 09:47:59 -08:00
xor.h	lib/xor: make xor prototypes more friendly to compiler vectorization	2022-02-11 20:39:39 +11:00