OpenCloudOS-Kernel/arch/x86/include/asm/tlbflush.h

334 lines
8.0 KiB
C
Raw Normal View History

#ifndef _ASM_X86_TLBFLUSH_H
#define _ASM_X86_TLBFLUSH_H
#include <linux/mm.h>
#include <linux/sched.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
#include <asm/special_insns.h>
static inline void __invpcid(unsigned long pcid, unsigned long addr,
unsigned long type)
{
struct { u64 d[2]; } desc = { { pcid, addr } };
/*
* The memory clobber is because the whole point is to invalidate
* stale TLB entries and, especially if we're flushing global
* mappings, we don't want the compiler to reorder any subsequent
* memory accesses before the TLB flush.
*
* The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
* invpcid (%rcx), %rax in long mode.
*/
asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
: : "m" (desc), "a" (type), "c" (&desc) : "memory");
}
#define INVPCID_TYPE_INDIV_ADDR 0
#define INVPCID_TYPE_SINGLE_CTXT 1
#define INVPCID_TYPE_ALL_INCL_GLOBAL 2
#define INVPCID_TYPE_ALL_NON_GLOBAL 3
/* Flush all mappings for a given pcid and addr, not including globals. */
static inline void invpcid_flush_one(unsigned long pcid,
unsigned long addr)
{
__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
}
/* Flush all mappings for a given PCID, not including globals. */
static inline void invpcid_flush_single_context(unsigned long pcid)
{
__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
}
/* Flush all mappings, including globals, for all PCIDs. */
static inline void invpcid_flush_all(void)
{
__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
}
/* Flush all mappings for all PCIDs except globals. */
static inline void invpcid_flush_all_nonglobals(void)
{
__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
}
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define __flush_tlb() __native_flush_tlb()
#define __flush_tlb_global() __native_flush_tlb_global()
#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
#endif
struct tlb_state {
#ifdef CONFIG_SMP
struct mm_struct *active_mm;
int state;
#endif
/*
* Access to this CR4 shadow and to H/W CR4 is protected by
* disabling interrupts when modifying either one.
*/
unsigned long cr4;
};
DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
/* Initialize cr4 shadow for this CPU. */
static inline void cr4_init_shadow(void)
{
this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
}
/* Set in this cpu's CR4. */
static inline void cr4_set_bits(unsigned long mask)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
if ((cr4 | mask) != cr4) {
cr4 |= mask;
this_cpu_write(cpu_tlbstate.cr4, cr4);
__write_cr4(cr4);
}
}
/* Clear in this cpu's CR4. */
static inline void cr4_clear_bits(unsigned long mask)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
if ((cr4 & ~mask) != cr4) {
cr4 &= ~mask;
this_cpu_write(cpu_tlbstate.cr4, cr4);
__write_cr4(cr4);
}
}
/* Read the CR4 shadow. */
static inline unsigned long cr4_read_shadow(void)
{
return this_cpu_read(cpu_tlbstate.cr4);
}
/*
* Save some of cr4 feature set we're using (e.g. Pentium 4MB
* enable and PPro Global page enable), so that any CPU's that boot
* up after us can get the correct flags. This should only be used
* during boot on the boot cpu.
*/
extern unsigned long mmu_cr4_features;
extern u32 *trampoline_cr4_features;
static inline void cr4_set_bits_and_update_boot(unsigned long mask)
{
mmu_cr4_features |= mask;
if (trampoline_cr4_features)
*trampoline_cr4_features = mmu_cr4_features;
cr4_set_bits(mask);
}
static inline void __native_flush_tlb(void)
{
native_write_cr3(native_read_cr3());
}
static inline void __native_flush_tlb_global_irq_disabled(void)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
/* clear PGE */
native_write_cr4(cr4 & ~X86_CR4_PGE);
/* write old PGE again and flush TLBs */
native_write_cr4(cr4);
}
static inline void __native_flush_tlb_global(void)
{
unsigned long flags;
if (static_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
*/
invpcid_flush_all();
return;
}
/*
* Read-modify-write to CR4 - protect it from preemption and
* from interrupts. (Use the raw variant because this code can
* be called from deep inside debugging code.)
*/
raw_local_irq_save(flags);
__native_flush_tlb_global_irq_disabled();
raw_local_irq_restore(flags);
}
static inline void __native_flush_tlb_single(unsigned long addr)
{
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
}
static inline void __flush_tlb_all(void)
{
if (static_cpu_has(X86_FEATURE_PGE))
__flush_tlb_global();
else
__flush_tlb();
}
static inline void __flush_tlb_one(unsigned long addr)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
}
#define TLB_FLUSH_ALL -1UL
/*
* TLB flushing:
*
* - flush_tlb() flushes the current mm struct TLBs
* - flush_tlb_all() flushes all processes TLBs
* - flush_tlb_mm(mm) flushes the specified mm context TLB's
* - flush_tlb_page(vma, vmaddr) flushes one page
* - flush_tlb_range(vma, start, end) flushes a range of pages
* - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
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>
2012-06-28 09:02:17 +08:00
* - flush_tlb_others(cpumask, mm, start, end) flushes TLBs on other cpus
*
* ..but the i386 has somewhat limited tlb flushing capabilities,
* and page-granular flushes are available only on i486 and up.
*/
#ifndef CONFIG_SMP
/* "_up" is for UniProcessor.
*
* This is a helper for other header functions. *Not* intended to be called
* directly. All global TLB flushes need to either call this, or to bump the
* vm statistics themselves.
*/
static inline void __flush_tlb_up(void)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb();
}
static inline void flush_tlb_all(void)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb_all();
}
static inline void flush_tlb(void)
{
__flush_tlb_up();
}
static inline void local_flush_tlb(void)
{
__flush_tlb_up();
}
static inline void flush_tlb_mm(struct mm_struct *mm)
{
if (mm == current->active_mm)
__flush_tlb_up();
}
static inline void flush_tlb_page(struct vm_area_struct *vma,
unsigned long addr)
{
if (vma->vm_mm == current->active_mm)
__flush_tlb_one(addr);
}
static inline void flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
if (vma->vm_mm == current->active_mm)
__flush_tlb_up();
}
static inline void flush_tlb_mm_range(struct mm_struct *mm,
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 09:02:22 +08:00
unsigned long start, unsigned long end, unsigned long vmflag)
{
if (mm == current->active_mm)
__flush_tlb_up();
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 09:02:22 +08:00
}
static inline void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
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>
2012-06-28 09:02:17 +08:00
unsigned long start,
unsigned long end)
{
}
static inline void reset_lazy_tlbstate(void)
{
}
static inline void flush_tlb_kernel_range(unsigned long start,
unsigned long end)
{
flush_tlb_all();
}
#else /* SMP */
#include <asm/smp.h>
#define local_flush_tlb() __flush_tlb()
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 09:02:22 +08:00
#define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
#define flush_tlb_range(vma, start, end) \
flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
extern void flush_tlb_all(void);
extern void flush_tlb_current_task(void);
extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
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 09:02:22 +08:00
extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end, unsigned long vmflag);
extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
#define flush_tlb() flush_tlb_current_task()
void native_flush_tlb_others(const struct cpumask *cpumask,
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>
2012-06-28 09:02:17 +08:00
struct mm_struct *mm,
unsigned long start, unsigned long end);
#define TLBSTATE_OK 1
#define TLBSTATE_LAZY 2
static inline void reset_lazy_tlbstate(void)
{
this_cpu_write(cpu_tlbstate.state, 0);
this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
}
#endif /* SMP */
mm: send one IPI per CPU to TLB flush all entries after unmapping pages An IPI is sent to flush remote TLBs when a page is unmapped that was potentially accesssed by other CPUs. There are many circumstances where this happens but the obvious one is kswapd reclaiming pages belonging to a running process as kswapd and the task are likely running on separate CPUs. On small machines, this is not a significant problem but as machine gets larger with more cores and more memory, the cost of these IPIs can be high. This patch uses a simple structure that tracks CPUs that potentially have TLB entries for pages being unmapped. When the unmapping is complete, the full TLB is flushed on the assumption that a refill cost is lower than flushing individual entries. Architectures wishing to do this must give the following guarantee. If a clean page is unmapped and not immediately flushed, the architecture must guarantee that a write to that linear address from a CPU with a cached TLB entry will trap a page fault. This is essentially what the kernel already depends on but the window is much larger with this patch applied and is worth highlighting. The architecture should consider whether the cost of the full TLB flush is higher than sending an IPI to flush each individual entry. An additional architecture helper called flush_tlb_local is required. It's a trivial wrapper with some accounting in the x86 case. The impact of this patch depends on the workload as measuring any benefit requires both mapped pages co-located on the LRU and memory pressure. The case with the biggest impact is multiple processes reading mapped pages taken from the vm-scalability test suite. The test case uses NR_CPU readers of mapped files that consume 10*RAM. Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 159.62 ( 0.00%) 120.68 ( 24.40%) Ops lru-file-mmap-read-time_range 30.59 ( 0.00%) 2.80 ( 90.85%) Ops lru-file-mmap-read-time_stddv 6.70 ( 0.00%) 0.64 ( 90.38%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 581.00 611.43 System 5804.93 4111.76 Elapsed 161.03 122.12 This is showing that the readers completed 24.40% faster with 29% less system CPU time. From vmstats, it is known that the vanilla kernel was interrupted roughly 900K times per second during the steady phase of the test and the patched kernel was interrupts 180K times per second. The impact is lower on a single socket machine. 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 25.33 ( 0.00%) 20.38 ( 19.54%) Ops lru-file-mmap-read-time_range 0.91 ( 0.00%) 1.44 (-58.24%) Ops lru-file-mmap-read-time_stddv 0.28 ( 0.00%) 0.47 (-65.34%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 58.09 57.64 System 111.82 76.56 Elapsed 27.29 22.55 It's still a noticeable improvement with vmstat showing interrupts went from roughly 500K per second to 45K per second. The patch will have no impact on workloads with no memory pressure or have relatively few mapped pages. It will have an unpredictable impact on the workload running on the CPU being flushed as it'll depend on how many TLB entries need to be refilled and how long that takes. Worst case, the TLB will be completely cleared of active entries when the target PFNs were not resident at all. [sasha.levin@oracle.com: trace tlb flush after disabling preemption in try_to_unmap_flush] Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:47:32 +08:00
/* Not inlined due to inc_irq_stat not being defined yet */
#define flush_tlb_local() { \
inc_irq_stat(irq_tlb_count); \
local_flush_tlb(); \
}
#ifndef CONFIG_PARAVIRT
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>
2012-06-28 09:02:17 +08:00
#define flush_tlb_others(mask, mm, start, end) \
native_flush_tlb_others(mask, mm, start, end)
#endif
#endif /* _ASM_X86_TLBFLUSH_H */