| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <4FB3ACD2.5010900@intel.com>
Date: Wed, 16 May 2012 21:34:10 +0800
From: Alex Shi <alex.shi@...el.com>
To: Peter Zijlstra <peterz@...radead.org>
CC: Nick Piggin <npiggin@...il.com>, tglx@...utronix.de,
mingo@...hat.com, hpa@...or.com, arnd@...db.de,
rostedt@...dmis.org, fweisbec@...il.com, jeremy@...p.org,
riel@...hat.com, luto@....edu, avi@...hat.com, len.brown@...el.com,
dhowells@...hat.com, fenghua.yu@...el.com, borislav.petkov@....com,
yinghai@...nel.org, ak@...ux.intel.com, cpw@....com,
steiner@....com, akpm@...ux-foundation.org, penberg@...nel.org,
hughd@...gle.com, rientjes@...gle.com,
kosaki.motohiro@...fujitsu.com, n-horiguchi@...jp.nec.com,
tj@...nel.org, oleg@...hat.com, axboe@...nel.dk, jmorris@...ei.org,
kamezawa.hiroyu@...fujitsu.com, viro@...iv.linux.org.uk,
linux-kernel@...r.kernel.org, yongjie.ren@...el.com,
linux-arch@...r.kernel.org
Subject: Re: [PATCH v5 6/7] x86/tlb: optimizing flush_tlb_mm
On 05/16/2012 04:00 PM, Peter Zijlstra wrote:
> On Wed, 2012-05-16 at 14:46 +0800, Alex Shi wrote:
>> diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
>> index 75e888b..ed6642a 100644
>> --- a/include/asm-generic/tlb.h
>> +++ b/include/asm-generic/tlb.h
>> @@ -86,6 +86,8 @@ struct mmu_gather {
>> #ifdef CONFIG_HAVE_RCU_TABLE_FREE
>> struct mmu_table_batch *batch;
>> #endif
>> + unsigned long start;
>> + unsigned long end;
>> unsigned int need_flush : 1, /* Did free PTEs */
>> fast_mode : 1; /* No batching */
>>
>> diff --git a/mm/memory.c b/mm/memory.c
>> index 6105f47..b176172 100644
>> --- a/mm/memory.c
>> +++ b/mm/memory.c
>> @@ -206,6 +206,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
>> tlb->mm = mm;
>>
>> tlb->fullmm = fullmm;
>> + tlb->start = -1UL;
>> + tlb->end = 0;
>> tlb->need_flush = 0;
>> tlb->fast_mode = (num_possible_cpus() == 1);
>> tlb->local.next = NULL;
>> @@ -248,6 +250,8 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
>> {
>> struct mmu_gather_batch *batch, *next;
>>
>> + tlb->start = start;
>> + tlb->end = end;
>> tlb_flush_mmu(tlb);
>>
>> /* keep the page table cache within bounds */
>> @@ -1204,6 +1208,8 @@ again:
>> */
>> if (force_flush) {
>> force_flush = 0;
>> + tlb->start = addr;
>> + tlb->end = end;
>> tlb_flush_mmu(tlb);
>> if (addr != end)
>> goto again;
>
>
> ARGH.. no. What bit about you don't need to modify the generic code
> don't you get?
>
> Both ARM and IA64 (and possible others) already do range tracking, you
> don't need to modify mm/memory.c _AT_ALL_.
Thanks for time and time remdiner. (shame for me)
In my code checking, the other archs can use self mmu_gather struct
since they code are excluded by HAVE_GENERIC_MMU_GATHER. In another word
if the code protected by HAVE_GENERIC_MMU_GATHER, it is safe for others
That is why tlb_flush_mmu/tlb_finish_mmu enabled both in mm/memory.c and
other archs.
So, if the minimum change of tlb->start/end can be protected by
HAVE_GENERIC_MMU_GATHER, it is safe and harmless, am I right?
If so, the following patch should work on any condition.
---
>From ca29d791c3524887c1776136e9274d10d2114624 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@...el.com>
Date: Mon, 14 May 2012 09:17:03 +0800
Subject: [PATCH 6/7] x86/tlb: optimizing tlb_finish_mmu on x86
Not every tlb_flush execution moment is really need to evacuate all
TLB entries, like in munmap, just few 'invlpg' is better for whole
process performance, since it leaves most of TLB entries for later
accessing.
Since all of tlb interfaces in mm/memory.c is reused by all
architecture CPU, except few of them which protected under
HAVE_GENERIC_MMU_GATHER, I keeps global interfaces, just
re-implement x86 specific 'tlb_flush' only. and put the minimum
change under HAVE_GENERIC_MMU_GATHER too.
This patch also rewrite flush_tlb_range for 2 purposes:
1, split it out to get flush_blt_mm_range function.
2, clean up to reduce line breaking, thanks for Borislav's input.
Thanks for Peter Zijlstra time and time reminder for multiple
architecture code safe!
Signed-off-by: Alex Shi <alex.shi@...el.com>
---
arch/x86/include/asm/tlb.h | 9 +++-
arch/x86/include/asm/tlbflush.h | 2 +
arch/x86/mm/tlb.c | 120 +++++++++++++++++++++------------------
include/asm-generic/tlb.h | 2 +
mm/memory.c | 9 +++
5 files changed, 85 insertions(+), 57 deletions(-)
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 829215f..4fef207 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -4,7 +4,14 @@
#define tlb_start_vma(tlb, vma) do { } while (0)
#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+
+#define tlb_flush(tlb) \
+{ \
+ if (tlb->fullmm == 0) \
+ flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL); \
+ else \
+ flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL); \
+}
#include <asm-generic/tlb.h>
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index c39c94e..0107f3c 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -128,6 +128,8 @@ extern void flush_tlb_mm(struct mm_struct *);
extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
extern void flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
+extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+ unsigned long end, unsigned long vmflag);
#define flush_tlb() flush_tlb_current_task()
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5bf4e85..52f6a5a 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -298,22 +298,6 @@ void flush_tlb_current_task(void)
preempt_enable();
}
-void flush_tlb_mm(struct mm_struct *mm)
-{
- preempt_disable();
-
- if (current->active_mm == mm) {
- if (current->mm)
- local_flush_tlb();
- 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();
-}
-
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline int has_large_page(struct mm_struct *mm,
unsigned long start, unsigned long end)
@@ -343,61 +327,85 @@ static inline int has_large_page(struct mm_struct *mm,
return 0;
}
#endif
-void flush_tlb_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
+
+void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+ unsigned long end, unsigned long vmflag)
{
- struct mm_struct *mm;
+ unsigned long addr;
+ unsigned act_entries, tlb_entries = 0;
- if (!cpu_has_invlpg || vma->vm_flags & VM_HUGETLB
- || tlb_flushall_shift == (u16)TLB_FLUSH_ALL) {
-flush_all:
- flush_tlb_mm(vma->vm_mm);
- return;
+ preempt_disable();
+ if (current->active_mm != mm)
+ goto flush_all;
+
+ if (!current->mm) {
+ leave_mm(smp_processor_id());
+ goto flush_all;
}
- 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 (end == TLB_FLUSH_ALL ||
+ tlb_flushall_shift == (u16)TLB_FLUSH_ALL) {
+ local_flush_tlb();
+ goto flush_all;
+ }
- if (vmflag & VM_EXEC)
- tlb_entries = tlb_lli_4k[ENTRIES];
- else
- tlb_entries = tlb_lld_4k[ENTRIES];
+ if (vmflag & VM_EXEC)
+ tlb_entries = tlb_lli_4k[ENTRIES];
+ else
+ tlb_entries = tlb_lld_4k[ENTRIES];
+ act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
- act_entries = tlb_entries > mm->total_vm ?
- mm->total_vm : tlb_entries;
+ if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+ local_flush_tlb();
+ else {
+ if (has_large_page(mm, start, end)) {
+ local_flush_tlb();
+ goto flush_all;
+ }
+ for (addr = start; addr <= end; addr += PAGE_SIZE)
+ __flush_tlb_single(addr);
- if ((end - start) >> PAGE_SHIFT >
- act_entries >> tlb_flushall_shift)
- local_flush_tlb();
- else {
- if (has_large_page(mm, start, end)) {
- preempt_enable();
- goto flush_all;
- }
- 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;
+ }
- 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 {
+flush_all:
+ 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_mm(struct mm_struct *mm)
+{
+ preempt_disable();
+
+ if (current->active_mm == mm) {
+ if (current->mm)
+ local_flush_tlb();
+ 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_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long vmflag = vma->vm_flags;
+
+ if (!cpu_has_invlpg || vma->vm_flags & VM_HUGETLB)
+ flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL);
+ else
+ flush_tlb_mm_range(mm, start, end, vmflag);
+}
+
void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
{
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 75e888b..ed6642a 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -86,6 +86,8 @@ struct mmu_gather {
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
struct mmu_table_batch *batch;
#endif
+ unsigned long start;
+ unsigned long end;
unsigned int need_flush : 1, /* Did free PTEs */
fast_mode : 1; /* No batching */
diff --git a/mm/memory.c b/mm/memory.c
index 6105f47..a1078af 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -206,6 +206,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
tlb->mm = mm;
tlb->fullmm = fullmm;
+ tlb->start = -1UL;
+ tlb->end = 0;
tlb->need_flush = 0;
tlb->fast_mode = (num_possible_cpus() == 1);
tlb->local.next = NULL;
@@ -248,6 +250,8 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
{
struct mmu_gather_batch *batch, *next;
+ tlb->start = start;
+ tlb->end = end;
tlb_flush_mmu(tlb);
/* keep the page table cache within bounds */
@@ -1204,6 +1208,11 @@ again:
*/
if (force_flush) {
force_flush = 0;
+
+#ifdef HAVE_GENERIC_MMU_GATHER
+ tlb->start = addr;
+ tlb->end = end;
+#endif
tlb_flush_mmu(tlb);
if (addr != end)
goto again;
--
1.7.5.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists