x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range
x86 has no flush_tlb_range support in instruction level. Currently the
flush_tlb_range just implemented by flushing all page table. That is not
the best solution for all scenarios. In fact, if we just use 'invlpg' to
flush few lines from TLB, we can get the performance gain from later
remain TLB lines accessing.
But the 'invlpg' instruction costs much of time. Its execution time can
compete with cr3 rewriting, and even a bit more on SNB CPU.
So, on a 512 4KB TLB entries CPU, the balance points is at:
(512 - X) * 100ns(assumed TLB refill cost) =
X(TLB flush entries) * 100ns(assumed invlpg cost)
Here, X is 256, that is 1/2 of 512 entries.
But with the mysterious CPU pre-fetcher and page miss handler Unit, the
assumed TLB refill cost is far lower then 100ns in sequential access. And
2 HT siblings in one core makes the memory access more faster if they are
accessing the same memory. So, in the patch, I just do the change when
the target entries is less than 1/16 of whole active tlb entries.
Actually, I have no data support for the percentage '1/16', so any
suggestions are welcomed.
As to hugetlb, guess due to smaller page table, and smaller active TLB
entries, I didn't see benefit via my benchmark, so no optimizing now.
My micro benchmark show in ideal scenarios, the performance improves 70
percent in reading. And in worst scenario, the reading/writing
performance is similar with unpatched 3.4-rc4 kernel.
Here is the reading data on my 2P * 4cores *HT NHM EP machine, with THP
'always':
multi thread testing, '-t' paramter is thread number:
with patch unpatched 3.4-rc4
./mprotect -t 1 14ns 24ns
./mprotect -t 2 13ns 22ns
./mprotect -t 4 12ns 19ns
./mprotect -t 8 14ns 16ns
./mprotect -t 16 28ns 26ns
./mprotect -t 32 54ns 51ns
./mprotect -t 128 200ns 199ns
Single process with sequencial flushing and memory accessing:
with patch unpatched 3.4-rc4
./mprotect 7ns 11ns
./mprotect -p 4096 -l 8 -n 10240
21ns 21ns
[ hpa: http://lkml.kernel.org/r/1B4B44D9196EFF41AE41FDA404FC0A100BFF94@SHSMSX101.ccr.corp.intel.com
has additional performance numbers. ]
Signed-off-by: Alex Shi <alex.shi@intel.com>
Link: http://lkml.kernel.org/r/1340845344-27557-3-git-send-email-alex.shi@intel.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5e57e11..3b91c98 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -41,7 +41,8 @@
union smp_flush_state {
struct {
struct mm_struct *flush_mm;
- unsigned long flush_va;
+ unsigned long flush_start;
+ unsigned long flush_end;
raw_spinlock_t tlbstate_lock;
DECLARE_BITMAP(flush_cpumask, NR_CPUS);
};
@@ -156,10 +157,19 @@
if (f->flush_mm == this_cpu_read(cpu_tlbstate.active_mm)) {
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
- if (f->flush_va == TLB_FLUSH_ALL)
+ if (f->flush_end == TLB_FLUSH_ALL
+ || !cpu_has_invlpg)
local_flush_tlb();
- else
- __flush_tlb_one(f->flush_va);
+ else if (!f->flush_end)
+ __flush_tlb_single(f->flush_start);
+ else {
+ unsigned long addr;
+ addr = f->flush_start;
+ while (addr < f->flush_end) {
+ __flush_tlb_single(addr);
+ addr += PAGE_SIZE;
+ }
+ }
} else
leave_mm(cpu);
}
@@ -172,7 +182,8 @@
}
static void flush_tlb_others_ipi(const struct cpumask *cpumask,
- struct mm_struct *mm, unsigned long va)
+ struct mm_struct *mm, unsigned long start,
+ unsigned long end)
{
unsigned int sender;
union smp_flush_state *f;
@@ -185,7 +196,8 @@
raw_spin_lock(&f->tlbstate_lock);
f->flush_mm = mm;
- f->flush_va = va;
+ f->flush_start = start;
+ f->flush_end = end;
if (cpumask_andnot(to_cpumask(f->flush_cpumask), cpumask, cpumask_of(smp_processor_id()))) {
/*
* We have to send the IPI only to
@@ -199,24 +211,26 @@
}
f->flush_mm = NULL;
- f->flush_va = 0;
+ f->flush_start = 0;
+ f->flush_end = 0;
if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
raw_spin_unlock(&f->tlbstate_lock);
}
void native_flush_tlb_others(const struct cpumask *cpumask,
- struct mm_struct *mm, unsigned long va)
+ struct mm_struct *mm, unsigned long start,
+ unsigned long end)
{
if (is_uv_system()) {
unsigned int cpu;
cpu = smp_processor_id();
- cpumask = uv_flush_tlb_others(cpumask, mm, va, cpu);
+ cpumask = uv_flush_tlb_others(cpumask, mm, start, end, cpu);
if (cpumask)
- flush_tlb_others_ipi(cpumask, mm, va);
+ flush_tlb_others_ipi(cpumask, mm, start, end);
return;
}
- flush_tlb_others_ipi(cpumask, mm, va);
+ flush_tlb_others_ipi(cpumask, mm, start, end);
}
static void __cpuinit calculate_tlb_offset(void)
@@ -282,7 +296,7 @@
local_flush_tlb();
if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
- flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL);
+ flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
preempt_enable();
}
@@ -297,12 +311,63 @@
leave_mm(smp_processor_id());
}
if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
- flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL);
+ flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
preempt_enable();
}
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
+#define FLUSHALL_BAR 16
+
+void flush_tlb_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ struct mm_struct *mm;
+
+ if (!cpu_has_invlpg || vma->vm_flags & VM_HUGETLB) {
+ flush_tlb_mm(vma->vm_mm);
+ return;
+ }
+
+ preempt_disable();
+ mm = vma->vm_mm;
+ if (current->active_mm == mm) {
+ if (current->mm) {
+ unsigned long addr, vmflag = vma->vm_flags;
+ unsigned act_entries, tlb_entries = 0;
+
+ if (vmflag & VM_EXEC)
+ tlb_entries = tlb_lli_4k[ENTRIES];
+ else
+ tlb_entries = tlb_lld_4k[ENTRIES];
+
+ act_entries = tlb_entries > mm->total_vm ?
+ mm->total_vm : tlb_entries;
+
+ if ((end - start)/PAGE_SIZE > act_entries/FLUSHALL_BAR)
+ local_flush_tlb();
+ else {
+ for (addr = start; addr < end;
+ addr += PAGE_SIZE)
+ __flush_tlb_single(addr);
+
+ if (cpumask_any_but(mm_cpumask(mm),
+ smp_processor_id()) < nr_cpu_ids)
+ flush_tlb_others(mm_cpumask(mm), mm,
+ start, end);
+ preempt_enable();
+ return;
+ }
+ } else {
+ leave_mm(smp_processor_id());
+ }
+ }
+ if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+ flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
+ preempt_enable();
+}
+
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
{
struct mm_struct *mm = vma->vm_mm;
@@ -310,13 +375,13 @@
if (current->active_mm == mm) {
if (current->mm)
- __flush_tlb_one(va);
+ __flush_tlb_one(start);
else
leave_mm(smp_processor_id());
}
if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
- flush_tlb_others(mm_cpumask(mm), mm, va);
+ flush_tlb_others(mm_cpumask(mm), mm, start, 0UL);
preempt_enable();
}