2008-10-23 05:26:29 +00:00
|
|
|
#ifndef _ASM_X86_TLB_H
|
|
|
|
|
#define _ASM_X86_TLB_H
|
2007-10-15 21:28:21 +00:00
|
|
|
|
|
|
|
|
#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)
|
x86/tlb: enable tlb flush range support for 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.
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.
My micro benchmark 'mummap' http://lkml.org/lkml/2012/5/17/59
show that the random memory access on other CPU has 0~50% speed up
on a 2P * 4cores * HT NHM EP while do 'munmap'.
Thanks Yongjie's testing on this patch:
-------------
I used Linux 3.4-RC6 w/ and w/o his patches as Xen dom0 and guest
kernel.
After running two benchmarks in Xen HVM guest, I found his patches
brought about 1%~3% performance gain in 'kernel build' and 'netperf'
testing, though the performance gain was not very stable in 'kernel
build' testing.
Some detailed testing results are below.
Testing Environment:
Hardware: Romley-EP platform
Xen version: latest upstream
Linux kernel: 3.4-RC6
Guest vCPU number: 8
NIC: Intel 82599 (10GB bandwidth)
In 'kernel build' testing in guest:
Command line | performance gain
make -j 4 | 3.81%
make -j 8 | 0.37%
make -j 16 | -0.52%
In 'netperf' testing, we tested TCP_STREAM with default socket size
16384 byte as large packet and 64 byte as small packet.
I used several clients to add networking pressure, then 'netperf' server
automatically generated several threads to response them.
I also used large-size packet and small-size packet in the testing.
Packet size | Thread number | performance gain
16384 bytes | 4 | 0.02%
16384 bytes | 8 | 2.21%
16384 bytes | 16 | 2.04%
64 bytes | 4 | 1.07%
64 bytes | 8 | 3.31%
64 bytes | 16 | 0.71%
Signed-off-by: Alex Shi <alex.shi@intel.com>
Link: http://lkml.kernel.org/r/1340845344-27557-8-git-send-email-alex.shi@intel.com
Tested-by: Ren, Yongjie <yongjie.ren@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2012-06-28 01:02:22 +00:00
|
|
|
|
|
|
|
|
#define tlb_flush(tlb) \
|
|
|
|
|
{ \
|
2013-04-12 23:23:54 +00:00
|
|
|
if (!tlb->fullmm && !tlb->need_flush_all) \
|
x86/tlb: enable tlb flush range support for 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.
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.
My micro benchmark 'mummap' http://lkml.org/lkml/2012/5/17/59
show that the random memory access on other CPU has 0~50% speed up
on a 2P * 4cores * HT NHM EP while do 'munmap'.
Thanks Yongjie's testing on this patch:
-------------
I used Linux 3.4-RC6 w/ and w/o his patches as Xen dom0 and guest
kernel.
After running two benchmarks in Xen HVM guest, I found his patches
brought about 1%~3% performance gain in 'kernel build' and 'netperf'
testing, though the performance gain was not very stable in 'kernel
build' testing.
Some detailed testing results are below.
Testing Environment:
Hardware: Romley-EP platform
Xen version: latest upstream
Linux kernel: 3.4-RC6
Guest vCPU number: 8
NIC: Intel 82599 (10GB bandwidth)
In 'kernel build' testing in guest:
Command line | performance gain
make -j 4 | 3.81%
make -j 8 | 0.37%
make -j 16 | -0.52%
In 'netperf' testing, we tested TCP_STREAM with default socket size
16384 byte as large packet and 64 byte as small packet.
I used several clients to add networking pressure, then 'netperf' server
automatically generated several threads to response them.
I also used large-size packet and small-size packet in the testing.
Packet size | Thread number | performance gain
16384 bytes | 4 | 0.02%
16384 bytes | 8 | 2.21%
16384 bytes | 16 | 2.04%
64 bytes | 4 | 1.07%
64 bytes | 8 | 3.31%
64 bytes | 16 | 0.71%
Signed-off-by: Alex Shi <alex.shi@intel.com>
Link: http://lkml.kernel.org/r/1340845344-27557-8-git-send-email-alex.shi@intel.com
Tested-by: Ren, Yongjie <yongjie.ren@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2012-06-28 01:02:22 +00:00
|
|
|
flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL); \
|
|
|
|
|
else \
|
|
|
|
|
flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL); \
|
|
|
|
|
}
|
2007-10-15 21:28:21 +00:00
|
|
|
|
|
|
|
|
#include <asm-generic/tlb.h>
|
|
|
|
|
|
2017-08-28 08:22:51 +00:00
|
|
|
/*
|
|
|
|
|
* While x86 architecture in general requires an IPI to perform TLB
|
|
|
|
|
* shootdown, enablement code for several hypervisors overrides
|
|
|
|
|
* .flush_tlb_others hook in pv_mmu_ops and implements it by issuing
|
|
|
|
|
* a hypercall. To keep software pagetable walkers safe in this case we
|
|
|
|
|
* switch to RCU based table free (HAVE_RCU_TABLE_FREE). See the comment
|
|
|
|
|
* below 'ifdef CONFIG_HAVE_RCU_TABLE_FREE' in include/asm-generic/tlb.h
|
|
|
|
|
* for more details.
|
|
|
|
|
*/
|
|
|
|
|
static inline void __tlb_remove_table(void *table)
|
|
|
|
|
{
|
|
|
|
|
free_page_and_swap_cache(table);
|
|
|
|
|
}
|
|
|
|
|
|
2008-10-23 05:26:29 +00:00
|
|
|
#endif /* _ASM_X86_TLB_H */
|
