x86 tlb optimisation and clean up
Subsystems (10)
v9 cover x86 tlb optimisation and clean up
Update to V9 version. This version is mainly for commit change.
1, It split the 6th patch into 6th and 7th for one patch to one issue.
2, update commit log for the 7th patch to include Yongjie's testing results, I don't know why lkml can not show the e-mail, maybe some words make it looks as spam?, Anyway I believe guys in to/cc list have the data. So, attached the e-mail contents into log.
3, change commit log for 8th, 9th to include most clear explaination and detailed testing result.
This patch set has clear performance gain, and clean up IDT table.
It is also quite safe after many review comments from Peter Anvin, PeterZ, Nick Piggin, Steven Rostedt, Andi Kleen and Borislav etc. And it runs well with my long time performance testing...
Anyone like to give the reason if it is not readly for upstream?
Best Regards!
Alex
[PATCH v9 1/9] x86/tlb_info: get last level TLB entry number of CPU [PATCH v9 2/9] x86/flush_tlb: try flush_tlb_single one by one in [PATCH v9 3/9] x86/tlb: fall back to flush all when meet a THP large [PATCH v9 4/9] x86/tlb: add tlb_flushall_shift for specific CPU [PATCH v9 5/9] x86/tlb: add tlb_flushall_shift knob into debugfs [PATCH v9 6/9] mm/mmu_gather: enable tlb flush range in generic [PATCH v9 7/9] x86/tlb: enable tlb flush range support for x86 [PATCH v9 8/9] x86/tlb: replace INVALIDATE_TLB_VECTOR by [PATCH v9 9/9] x86/tlb: do flush_tlb_kernel_range by 'invlpg'
PATCH v9 1/9 x86/tlb_info: get last level TLB entry number of CPU
For 4KB pages, x86 CPU has 2 or 1 level TLB, first level is data TLB and instruction TLB, second level is shared TLB for both data and instructions.
For hupe page TLB, usually there is just one level and seperated by 2MB/4MB and 1GB.
Although each levels TLB size is important for performance tuning, but for genernal and rude optimizing, last level TLB entry number is suitable. And in fact, last level TLB always has the biggest entry number.
This patch will get the biggest TLB entry number and use it in furture TLB optimizing.
Accroding Borislav's suggestion, except tlb_ll[i/d]_* array, other function and data will be released after system boot up.
For all kinds of x86 vendor friendly, vendor specific code was moved to its specific files.
--- arch/x86/include/asm/processor.h | 11 +++ arch/x86/kernel/cpu/common.c | 21 ++++++ arch/x86/kernel/cpu/cpu.h | 9 +++ arch/x86/kernel/cpu/intel.c | 141 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 182 insertions(+), 0 deletions(-)
arch/x86/include/asm/processor.h +11 -0
@@ -61,6 +61,17 @@ static inline void *current_text_addr(void)# define ARCH_MIN_MMSTRUCT_ALIGN 0#endif +enum tlb_infos { +ENTRIES , +NR_INFO +}; + +extern u16 __read_mostly tlb_lli_4k[NR_INFO ]; +extern u16 __read_mostly tlb_lli_2m[NR_INFO ]; +extern u16 __read_mostly tlb_lli_4m[NR_INFO ]; +extern u16 __read_mostly tlb_lld_4k[NR_INFO ]; +extern u16 __read_mostly tlb_lld_2m[NR_INFO ]; +extern u16 __read_mostly tlb_lld_4m[NR_INFO ];/* * CPU type and hardware bug flags. Kept separately for each CPU. * Members of this structure are referenced in head.S, so think twice
arch/x86/kernel/cpu/common.c +21 -0
@@ -452,6 +452,25 @@ void __cpuinit cpu_detect_cache_sizes(struct cpuinfo_x86 *c) c->x86_cache_size = l2size; } +u16 __read_mostly tlb_lli_4k[NR_INFO ]; +u16 __read_mostly tlb_lli_2m[NR_INFO ]; +u16 __read_mostly tlb_lli_4m[NR_INFO ]; +u16 __read_mostly tlb_lld_4k[NR_INFO ]; +u16 __read_mostly tlb_lld_2m[NR_INFO ]; +u16 __read_mostly tlb_lld_4m[NR_INFO ]; + +void __cpuinit cpu_detect_tlb (struct cpuinfo_x86 *c) +{ +if (c->x86_vendor ==X86_VENDOR_INTEL ) +intel_cpu_detect_tlb (c); + +printk (KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ +"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" , + tlb_lli_4k[ENTRIES ], tlb_lli_2m[ENTRIES ], + tlb_lli_4m[ENTRIES ], tlb_lld_4k[ENTRIES ], + tlb_lld_2m[ENTRIES ], tlb_lld_4m[ENTRIES ]); +} +void __cpuinit detect_ht (struct cpuinfo_x86 *c) {#ifdef CONFIG_X86_HT
@@ -911,6 +930,8 @@ void __init identify_boot_cpu(void)#else vgetcpu_set_mode ();#endif +if (boot_cpu_data.cpuid_level >=2 ) +cpu_detect_tlb (&boot_cpu_data); }void __cpuinit identify_secondary_cpu (struct cpuinfo_x86 *c)
arch/x86/kernel/cpu/cpu.h +9 -0
@@ -24,6 +24,14 @@ struct cpu_dev {int c_x86_vendor; }; +struct _tlb_table { +unsigned char descriptor; +char tlb_type; +unsigned int entries; +/* unsigned int ways; */ +char info[128 ]; +}; +#define cpu_dev_register (cpu_devX) \ static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \ __attribute__((__section__(".x86_cpu_dev.init"))) = \
@@ -34,4 +42,5 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],extern void get_cpu_cap (struct cpuinfo_x86 *c);extern void cpu_detect_cache_sizes (struct cpuinfo_x86 *c); +extern void intel_cpu_detect_tlb (struct cpuinfo_x86 *c)__cpuinit ;#endif /* ARCH_X86_CPU_H */
arch/x86/kernel/cpu/intel.c +141 -0
147 lines not on this page · raw message
Signature · 1 line
1.7.5.4
[tip:x86/mm] x86/tlb_info: get last level TLB entry number of CPU
Commit-ID: dc869f34dc890189aafcd1812d0823b8207e507c Gitweb: http://git.kernel.org/tip/dc869f34dc890189aafcd1812d0823b8207e507c Author: Alex Shi <[email protected]> AuthorDate: Mon, 25 Jun 2012 14:08:19 +0800 Committer: H. Peter Anvin <[email protected]> CommitDate: Mon, 25 Jun 2012 20:53:13 -0700
x86/tlb_info: get last level TLB entry number of CPU
For 4KB pages, x86 CPU has 2 or 1 level TLB, first level is data TLB and instruction TLB, second level is shared TLB for both data and instructions.
For hupe page TLB, usually there is just one level and seperated by 2MB/4MB and 1GB.
Although each levels TLB size is important for performance tuning, but for genernal and rude optimizing, last level TLB entry number is suitable. And in fact, last level TLB always has the biggest entry number.
This patch will get the biggest TLB entry number and use it in furture TLB optimizing.
Accroding Borislav's suggestion, except tlb_ll[i/d]_* array, other function and data will be released after system boot up.
For all kinds of x86 vendor friendly, vendor specific code was moved to its specific files.
[ hpa: http://lkml.kernel.org/r/1B4B44D9196EFF41AE41FDA404FC0A100BFF94@SHSMSX101.ccr.corp.intel.com
has some performance numbers. ]
--- arch/x86/include/asm/processor.h | 11 +++ arch/x86/kernel/cpu/common.c | 21 ++++++ arch/x86/kernel/cpu/cpu.h | 9 +++ arch/x86/kernel/cpu/intel.c | 141 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 182 insertions(+), 0 deletions(-)
arch/x86/include/asm/processor.h +11 -0
@@ -61,6 +61,17 @@ static inline void *current_text_addr(void)# define ARCH_MIN_MMSTRUCT_ALIGN 0#endif +enum tlb_infos { +ENTRIES , +NR_INFO +}; + +extern u16 __read_mostly tlb_lli_4k[NR_INFO ]; +extern u16 __read_mostly tlb_lli_2m[NR_INFO ]; +extern u16 __read_mostly tlb_lli_4m[NR_INFO ]; +extern u16 __read_mostly tlb_lld_4k[NR_INFO ]; +extern u16 __read_mostly tlb_lld_2m[NR_INFO ]; +extern u16 __read_mostly tlb_lld_4m[NR_INFO ];/* * CPU type and hardware bug flags. Kept separately for each CPU. * Members of this structure are referenced in head.S, so think twice
arch/x86/kernel/cpu/common.c +21 -0
@@ -452,6 +452,25 @@ void __cpuinit cpu_detect_cache_sizes(struct cpuinfo_x86 *c) c->x86_cache_size = l2size; } +u16 __read_mostly tlb_lli_4k[NR_INFO ]; +u16 __read_mostly tlb_lli_2m[NR_INFO ]; +u16 __read_mostly tlb_lli_4m[NR_INFO ]; +u16 __read_mostly tlb_lld_4k[NR_INFO ]; +u16 __read_mostly tlb_lld_2m[NR_INFO ]; +u16 __read_mostly tlb_lld_4m[NR_INFO ]; + +void __cpuinit cpu_detect_tlb (struct cpuinfo_x86 *c) +{ +if (c->x86_vendor ==X86_VENDOR_INTEL ) +intel_cpu_detect_tlb (c); + +printk (KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ +"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" , + tlb_lli_4k[ENTRIES ], tlb_lli_2m[ENTRIES ], + tlb_lli_4m[ENTRIES ], tlb_lld_4k[ENTRIES ], + tlb_lld_2m[ENTRIES ], tlb_lld_4m[ENTRIES ]); +} +void __cpuinit detect_ht (struct cpuinfo_x86 *c) {#ifdef CONFIG_X86_HT
@@ -911,6 +930,8 @@ void __init identify_boot_cpu(void)#else vgetcpu_set_mode ();#endif +if (boot_cpu_data.cpuid_level >=2 ) +cpu_detect_tlb (&boot_cpu_data); }void __cpuinit identify_secondary_cpu (struct cpuinfo_x86 *c)
arch/x86/kernel/cpu/cpu.h +9 -0
@@ -24,6 +24,14 @@ struct cpu_dev {int c_x86_vendor; }; +struct _tlb_table { +unsigned char descriptor; +char tlb_type; +unsigned int entries; +/* unsigned int ways; */ +char info[128 ]; +}; +#define cpu_dev_register (cpu_devX) \ static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \ __attribute__((__section__(".x86_cpu_dev.init"))) = \
@@ -34,4 +42,5 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],extern void get_cpu_cap (struct cpuinfo_x86 *c);extern void cpu_detect_cache_sizes (struct cpuinfo_x86 *c); +extern void intel_cpu_detect_tlb (struct cpuinfo_x86 *c)__cpuinit ;#endif /* ARCH_X86_CPU_H */
arch/x86/kernel/cpu/intel.c +141 -0
147 lines not on this page · raw message
PATCH v9 2/9 x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range
In reply to Alex Shix86 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 macro 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
--- arch/x86/include/asm/paravirt.h | 5 +- arch/x86/include/asm/paravirt_types.h | 3 +- arch/x86/include/asm/tlbflush.h | 23 +++----- arch/x86/include/asm/uv/uv.h | 5 +- arch/x86/mm/tlb.c | 97 +++++++++++++++++++++++++++------ arch/x86/platform/uv/tlb_uv.c | 6 +- arch/x86/xen/mmu.c | 12 ++-- include/trace/events/xen.h | 12 +++-- 8 files changed, 114 insertions(+), 49 deletions(-)
arch/x86/include/asm/paravirt.h +3 -2
@@ -397,9 +397,10 @@ static inline void __flush_tlb_single(unsigned long addr)static inline void flush_tlb_others (const struct cpumask *cpumask,struct mm_struct *mm, -unsigned long va) +unsigned long start, +unsigned long end) { -PVOP_VCALL3 (pv_mmu_ops.flush_tlb_others, cpumask, mm, va); +PVOP_VCALL4 (pv_mmu_ops.flush_tlb_others, cpumask, mm, start, end); }static inline int paravirt_pgd_alloc (struct mm_struct *mm)
arch/x86/include/asm/paravirt_types.h +2 -1
@@ -250,7 +250,8 @@ struct pv_mmu_ops {void (*flush_tlb_single)(unsigned long addr);void (*flush_tlb_others)(const struct cpumask *cpus,struct mm_struct *mm, -unsigned long va); +unsigned long start, +unsigned long end);/* Hooks for allocating and freeing a pagetable top-level */ int (*pgd_alloc)(struct mm_struct *mm);
arch/x86/include/asm/tlbflush.h +9 -14
@@ -73,14 +73,10 @@ static inline void __flush_tlb_one(unsigned long addr)* - 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 -* - flush_tlb_others(cpumask, mm, va) flushes TLBs on other cpus +* - 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. -* -* x86-64 can only flush individual pages or full VMs. For a range flush -* we always do the full VM. Might be worth trying if for a small -* range a few INVLPGs in a row are a win. */ #ifndef CONFIG_SMP
@@ -111,7 +107,8 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,static inline void native_flush_tlb_others (const struct cpumask *cpumask,struct mm_struct *mm, -unsigned long va) +unsigned long start, +unsigned long end) { }
@@ -129,17 +126,14 @@ extern void flush_tlb_all(void);extern void flush_tlb_current_task (void );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);#define flush_tlb () flush_tlb_current_task() -static inline void flush_tlb_range (struct vm_area_struct *vma, -unsigned long start,unsigned long end) -{ -flush_tlb_mm (vma->vm_mm); -} -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);#define TLBSTATE_OK 1#define TLBSTATE_LAZY 2
@@ -159,7 +153,8 @@ static inline void reset_lazy_tlbstate(void)#endif /* SMP */ #ifndef CONFIG_PARAVIRT -#define flush_tlb_others (mask, mm, va) native_flush_tlb_others(mask, mm, va) +#define flush_tlb_others (mask, mm, start, end) \ + native_flush_tlb_others(mask, mm, start, end)#endif static inline void flush_tlb_kernel_range(unsigned long start,
arch/x86/include/asm/uv/uv.h +3 -2
@@ -15,7 +15,8 @@ extern void uv_nmi_init(void);extern void uv_system_init (void );extern const struct cpumask *uv_flush_tlb_others (const struct cpumask *cpumask,struct mm_struct *mm, -unsigned long va, +unsigned long start, +unsigned end,unsigned int cpu);#else /* X86_UV */
@@ -26,7 +27,7 @@ static inline void uv_cpu_init(void) { }static inline void uv_system_init (void ) { }static inline const struct cpumask *uv_flush_tlb_others (const struct cpumask *cpumask,struct mm_struct *mm, -unsigned long va,unsigned int cpu) +unsigned long start,unsigned long end,unsigned int cpu) {return cpumask; }#endif /* X86_UV */
arch/x86/mm/tlb.c +81 -16
168 lines not on this page · raw message
arch/x86/platform/uv/tlb_uv.c +3 -3
@@ -1068,8 +1068,8 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,* done. The returned pointer is valid till preemption is re-enabled. */ const struct cpumask *uv_flush_tlb_others (const struct cpumask *cpumask, -struct mm_struct *mm,unsigned long va, -unsigned int cpu) +struct mm_struct *mm,unsigned long start, +unsigned end,unsigned int cpu) {int locals =0 ;int remotes =0 ;
@@ -1112,7 +1112,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,record_send_statistics (stat, locals, hubs, remotes, bau_desc); - bau_desc->payload.address = va; + bau_desc->payload.address = start; bau_desc->payload.sending_cpu = cpu;/* * uv_flush_send_and_wait returns 0 if all cpu's were messaged,
arch/x86/xen/mmu.c +6 -6
@@ -1244,7 +1244,8 @@ static void xen_flush_tlb_single(unsigned long addr) }static void xen_flush_tlb_others (const struct cpumask *cpus, -struct mm_struct *mm,unsigned long va) +struct mm_struct *mm,unsigned long start, +unsigned long end) {struct {struct mmuext_op op;
@@ -1256,7 +1257,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, } *args;struct multicall_space mcs; -trace_xen_mmu_flush_tlb_others (cpus, mm, va); +trace_xen_mmu_flush_tlb_others (cpus, mm, start, end);if (cpumask_empty (cpus))return ;/* nothing to do */
@@ -1269,11 +1270,10 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,cpumask_and (to_cpumask (args->mask), cpus, cpu_online_mask);cpumask_clear_cpu (smp_processor_id (),to_cpumask (args->mask)); -if (va ==TLB_FLUSH_ALL ) { - args->op.cmd =MMUEXT_TLB_FLUSH_MULTI ; - }else { + args->op.cmd =MMUEXT_TLB_FLUSH_MULTI ; +if (start !=TLB_FLUSH_ALL && (end - start) <=PAGE_SIZE ) { args->op.cmd =MMUEXT_INVLPG_MULTI ; - args->op.arg1.linear_addr = va; + args->op.arg1.linear_addr = start; }MULTI_mmuext_op (mcs.mc, &args->op,1 ,NULL ,DOMID_SELF );
include/trace/events/xen.h +7 -5
@@ -397,18 +397,20 @@ TRACE_EVENT(xen_mmu_flush_tlb_single,TRACE_EVENT (xen_mmu_flush_tlb_others, TP_PROTO(const struct cpumask *cpus, struct mm_struct *mm, - unsigned long addr), -TP_ARGS (cpus, mm, addr), + unsigned long addr, unsigned long end), +TP_ARGS (cpus, mm, addr, end),TP_STRUCT__entry ( __field(unsigned, ncpus) __field(struct mm_struct *, mm) __field(unsigned long, addr) + __field(unsigned long, end) ), TP_fast_assign(__entry->ncpus = cpumask_weight(cpus); __entry->mm = mm; - __entry->addr = addr), -TP_printk ("ncpus %d mm %p addr %lx" , - __entry->ncpus, __entry->mm, __entry->addr) + __entry->addr = addr, + __entry->end = end), +TP_printk ("ncpus %d mm %p addr %lx, end %lx" , + __entry->ncpus, __entry->mm, __entry->addr, __entry->end) ); TRACE_EVENT(xen_mmu_write_cr3,
Signature · 1 line
1.7.5.4
[tip:x86/mm] x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range
Commit-ID: be7949049cc76384d98857a7762de0c778df43e0 Gitweb: http://git.kernel.org/tip/be7949049cc76384d98857a7762de0c778df43e0 Author: Alex Shi <[email protected]> AuthorDate: Mon, 25 Jun 2012 14:08:20 +0800 Committer: H. Peter Anvin <[email protected]> CommitDate: Mon, 25 Jun 2012 20:53:16 -0700
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 macro 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
--- arch/x86/include/asm/paravirt.h | 5 +- arch/x86/include/asm/paravirt_types.h | 3 +- arch/x86/include/asm/tlbflush.h | 23 +++----- arch/x86/include/asm/uv/uv.h | 5 +- arch/x86/mm/tlb.c | 97 +++++++++++++++++++++++++++------ arch/x86/platform/uv/tlb_uv.c | 6 +- arch/x86/xen/mmu.c | 12 ++-- include/trace/events/xen.h | 12 +++-- 8 files changed, 114 insertions(+), 49 deletions(-)
arch/x86/include/asm/paravirt.h +3 -2
@@ -397,9 +397,10 @@ static inline void __flush_tlb_single(unsigned long addr)static inline void flush_tlb_others (const struct cpumask *cpumask,struct mm_struct *mm, -unsigned long va) +unsigned long start, +unsigned long end) { -PVOP_VCALL3 (pv_mmu_ops.flush_tlb_others, cpumask, mm, va); +PVOP_VCALL4 (pv_mmu_ops.flush_tlb_others, cpumask, mm, start, end); }static inline int paravirt_pgd_alloc (struct mm_struct *mm)
arch/x86/include/asm/paravirt_types.h +2 -1
@@ -250,7 +250,8 @@ struct pv_mmu_ops {void (*flush_tlb_single)(unsigned long addr);void (*flush_tlb_others)(const struct cpumask *cpus,struct mm_struct *mm, -unsigned long va); +unsigned long start, +unsigned long end);/* Hooks for allocating and freeing a pagetable top-level */ int (*pgd_alloc)(struct mm_struct *mm);
arch/x86/include/asm/tlbflush.h +9 -14
@@ -73,14 +73,10 @@ static inline void __flush_tlb_one(unsigned long addr)* - 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 -* - flush_tlb_others(cpumask, mm, va) flushes TLBs on other cpus +* - 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. -* -* x86-64 can only flush individual pages or full VMs. For a range flush -* we always do the full VM. Might be worth trying if for a small -* range a few INVLPGs in a row are a win. */ #ifndef CONFIG_SMP
@@ -111,7 +107,8 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,static inline void native_flush_tlb_others (const struct cpumask *cpumask,struct mm_struct *mm, -unsigned long va) +unsigned long start, +unsigned long end) { }
@@ -129,17 +126,14 @@ extern void flush_tlb_all(void);extern void flush_tlb_current_task (void );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);#define flush_tlb () flush_tlb_current_task() -static inline void flush_tlb_range (struct vm_area_struct *vma, -unsigned long start,unsigned long end) -{ -flush_tlb_mm (vma->vm_mm); -} -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);#define TLBSTATE_OK 1#define TLBSTATE_LAZY 2
@@ -159,7 +153,8 @@ static inline void reset_lazy_tlbstate(void)#endif /* SMP */ #ifndef CONFIG_PARAVIRT -#define flush_tlb_others (mask, mm, va) native_flush_tlb_others(mask, mm, va) +#define flush_tlb_others (mask, mm, start, end) \ + native_flush_tlb_others(mask, mm, start, end)#endif static inline void flush_tlb_kernel_range(unsigned long start,
arch/x86/include/asm/uv/uv.h +3 -2
@@ -15,7 +15,8 @@ extern void uv_nmi_init(void);extern void uv_system_init (void );extern const struct cpumask *uv_flush_tlb_others (const struct cpumask *cpumask,struct mm_struct *mm, -unsigned long va, +unsigned long start, +unsigned end,unsigned int cpu);#else /* X86_UV */
@@ -26,7 +27,7 @@ static inline void uv_cpu_init(void) { }static inline void uv_system_init (void ) { }static inline const struct cpumask *uv_flush_tlb_others (const struct cpumask *cpumask,struct mm_struct *mm, -unsigned long va,unsigned int cpu) +unsigned long start,unsigned long end,unsigned int cpu) {return cpumask; }#endif /* X86_UV */
arch/x86/mm/tlb.c +81 -16
168 lines not on this page · raw message
arch/x86/platform/uv/tlb_uv.c +3 -3
@@ -1068,8 +1068,8 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,* done. The returned pointer is valid till preemption is re-enabled. */ const struct cpumask *uv_flush_tlb_others (const struct cpumask *cpumask, -struct mm_struct *mm,unsigned long va, -unsigned int cpu) +struct mm_struct *mm,unsigned long start, +unsigned end,unsigned int cpu) {int locals =0 ;int remotes =0 ;
@@ -1112,7 +1112,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,record_send_statistics (stat, locals, hubs, remotes, bau_desc); - bau_desc->payload.address = va; + bau_desc->payload.address = start; bau_desc->payload.sending_cpu = cpu;/* * uv_flush_send_and_wait returns 0 if all cpu's were messaged,
arch/x86/xen/mmu.c +6 -6
@@ -1244,7 +1244,8 @@ static void xen_flush_tlb_single(unsigned long addr) }static void xen_flush_tlb_others (const struct cpumask *cpus, -struct mm_struct *mm,unsigned long va) +struct mm_struct *mm,unsigned long start, +unsigned long end) {struct {struct mmuext_op op;
@@ -1256,7 +1257,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, } *args;struct multicall_space mcs; -trace_xen_mmu_flush_tlb_others (cpus, mm, va); +trace_xen_mmu_flush_tlb_others (cpus, mm, start, end);if (cpumask_empty (cpus))return ;/* nothing to do */
@@ -1269,11 +1270,10 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,cpumask_and (to_cpumask (args->mask), cpus, cpu_online_mask);cpumask_clear_cpu (smp_processor_id (),to_cpumask (args->mask)); -if (va ==TLB_FLUSH_ALL ) { - args->op.cmd =MMUEXT_TLB_FLUSH_MULTI ; - }else { + args->op.cmd =MMUEXT_TLB_FLUSH_MULTI ; +if (start !=TLB_FLUSH_ALL && (end - start) <=PAGE_SIZE ) { args->op.cmd =MMUEXT_INVLPG_MULTI ; - args->op.arg1.linear_addr = va; + args->op.arg1.linear_addr = start; }MULTI_mmuext_op (mcs.mc, &args->op,1 ,NULL ,DOMID_SELF );
include/trace/events/xen.h +7 -5
@@ -397,18 +397,20 @@ TRACE_EVENT(xen_mmu_flush_tlb_single,TRACE_EVENT (xen_mmu_flush_tlb_others, TP_PROTO(const struct cpumask *cpus, struct mm_struct *mm, - unsigned long addr), -TP_ARGS (cpus, mm, addr), + unsigned long addr, unsigned long end), +TP_ARGS (cpus, mm, addr, end),TP_STRUCT__entry ( __field(unsigned, ncpus) __field(struct mm_struct *, mm) __field(unsigned long, addr) + __field(unsigned long, end) ), TP_fast_assign(__entry->ncpus = cpumask_weight(cpus); __entry->mm = mm; - __entry->addr = addr), -TP_printk ("ncpus %d mm %p addr %lx" , - __entry->ncpus, __entry->mm, __entry->addr) + __entry->addr = addr, + __entry->end = end), +TP_printk ("ncpus %d mm %p addr %lx, end %lx" , + __entry->ncpus, __entry->mm, __entry->addr, __entry->end) ); TRACE_EVENT(xen_mmu_write_cr3,
PATCH v9 3/9 x86/tlb: fall back to flush all when meet a THP large page
In reply to Alex ShiWe don't need to flush large pages by PAGE_SIZE step, that just waste time. and actually, large page don't need 'invlpg' optimizing according to our macro benchmark. So, just flush whole TLB is enough for them.
The following result is tested on a 2CPU * 4cores * 2HT NHM EP machine, with THP 'always' setting.
Multi-thread testing, '-t' paramter is thread number:
without this patch with this patch
./mprotect -t 1 14ns 13ns ./mprotect -t 2 13ns 13ns ./mprotect -t 4 12ns 11ns ./mprotect -t 8 14ns 10ns ./mprotect -t 16 28ns 28ns ./mprotect -t 32 54ns 52ns ./mprotect -t 128 200ns 200ns
--- arch/x86/mm/tlb.c | 34 ++++++++++++++++++++++++++++++++++ 1 files changed, 34 insertions(+), 0 deletions(-)
arch/x86/mm/tlb.c +34 -0
@@ -318,12 +318,42 @@ void flush_tlb_mm(struct mm_struct *mm)#define FLUSHALL_BAR 16 +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline unsigned long has_large_page (struct mm_struct *mm, +unsigned long start,unsigned long end) +{ +pgd_t *pgd; +pud_t *pud; +pmd_t *pmd; +unsigned long addr =ALIGN (start,HPAGE_SIZE ); +for (; addr < end; addr +=HPAGE_SIZE ) { + pgd =pgd_offset (mm, addr); +if (likely (!pgd_none (*pgd))) { + pud =pud_offset (pgd, addr); +if (likely (!pud_none (*pud))) { + pmd =pmd_offset (pud, addr); +if (likely (!pmd_none (*pmd))) +if (pmd_large (*pmd)) +return addr; + } + } + } +return 0 ; +} +#else +static inline unsigned long has_large_page (struct mm_struct *mm, +unsigned long start,unsigned long end) +{ +return 0 ; +} +#endif 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_all:flush_tlb_mm (vma->vm_mm);return ; }
@@ -346,6 +376,10 @@ void flush_tlb_range(struct vm_area_struct *vma,if ((end - start)/PAGE_SIZE > act_entries/FLUSHALL_BAR )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);
Signature · 1 line
1.7.5.4
[tip:x86/mm] x86/tlb: fall back to flush all when meet a THP large page
Commit-ID: fd460eec063227223e9b1151e36c846e2a87b619 Gitweb: http://git.kernel.org/tip/fd460eec063227223e9b1151e36c846e2a87b619 Author: Alex Shi <[email protected]> AuthorDate: Mon, 25 Jun 2012 14:08:21 +0800 Committer: H. Peter Anvin <[email protected]> CommitDate: Mon, 25 Jun 2012 20:53:16 -0700
x86/tlb: fall back to flush all when meet a THP large page
We don't need to flush large pages by PAGE_SIZE step, that just waste time. and actually, large page don't need 'invlpg' optimizing according to our macro benchmark. So, just flush whole TLB is enough for them.
The following result is tested on a 2CPU * 4cores * 2HT NHM EP machine, with THP 'always' setting.
Multi-thread testing, '-t' paramter is thread number:
without this patch with this patch
./mprotect -t 1 14ns 13ns ./mprotect -t 2 13ns 13ns ./mprotect -t 4 12ns 11ns ./mprotect -t 8 14ns 10ns ./mprotect -t 16 28ns 28ns ./mprotect -t 32 54ns 52ns ./mprotect -t 128 200ns 200ns
--- arch/x86/mm/tlb.c | 34 ++++++++++++++++++++++++++++++++++ 1 files changed, 34 insertions(+), 0 deletions(-)
arch/x86/mm/tlb.c +34 -0
@@ -318,12 +318,42 @@ void flush_tlb_mm(struct mm_struct *mm)#define FLUSHALL_BAR 16 +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline unsigned long has_large_page (struct mm_struct *mm, +unsigned long start,unsigned long end) +{ +pgd_t *pgd; +pud_t *pud; +pmd_t *pmd; +unsigned long addr =ALIGN (start,HPAGE_SIZE ); +for (; addr < end; addr +=HPAGE_SIZE ) { + pgd =pgd_offset (mm, addr); +if (likely (!pgd_none (*pgd))) { + pud =pud_offset (pgd, addr); +if (likely (!pud_none (*pud))) { + pmd =pmd_offset (pud, addr); +if (likely (!pmd_none (*pmd))) +if (pmd_large (*pmd)) +return addr; + } + } + } +return 0 ; +} +#else +static inline unsigned long has_large_page (struct mm_struct *mm, +unsigned long start,unsigned long end) +{ +return 0 ; +} +#endif 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_all:flush_tlb_mm (vma->vm_mm);return ; }
@@ -346,6 +376,10 @@ void flush_tlb_range(struct vm_area_struct *vma,if ((end - start)/PAGE_SIZE > act_entries/FLUSHALL_BAR )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);
PATCH v9 4/9 x86/tlb: add tlb_flushall_shift for specific CPU
In reply to Alex ShiTesting show different CPU type(micro architectures and NUMA mode) has different balance points between the TLB flush all and multiple invlpg. And there also has cases the tlb flush change has no any help.
This patch give a interface to let x86 vendor developers have a chance to set different shift for different CPU type.
like some machine in my hands, balance points is 16 entries on Romely-EP; while it is at 8 entries on Bloomfield NHM-EP; and is 256 on IVB mobile CPU. but on model 15 core2 Xeon using invlpg has nothing help.
For untested machine, do a conservative optimization, same as NHM CPU.
--- arch/x86/include/asm/processor.h | 2 ++ arch/x86/kernel/cpu/common.c | 14 ++++++++++++-- arch/x86/kernel/cpu/intel.c | 34 ++++++++++++++++++++++++++++++++++ arch/x86/mm/tlb.c | 7 +++---- include/asm-generic/tlb.h | 3 ++- 5 files changed, 53 insertions(+), 7 deletions(-)
arch/x86/include/asm/processor.h +2 -0
@@ -72,6 +72,8 @@ extern u16 __read_mostly tlb_lli_4m[NR_INFO];extern u16 __read_mostly tlb_lld_4k[NR_INFO ];extern u16 __read_mostly tlb_lld_2m[NR_INFO ];extern u16 __read_mostly tlb_lld_4m[NR_INFO ]; +extern s8 __read_mostly tlb_flushall_shift; +/* * CPU type and hardware bug flags. Kept separately for each CPU. * Members of this structure are referenced in head.S, so think twice
arch/x86/kernel/cpu/common.c +12 -2
@@ -459,16 +459,26 @@ u16 __read_mostly tlb_lld_4k[NR_INFO];u16 __read_mostly tlb_lld_2m[NR_INFO ];u16 __read_mostly tlb_lld_4m[NR_INFO ]; +/* +* tlb_flushall_shift shows the balance point in replacing cr3 write +* with multiple 'invlpg'. It will do this replacement when +* flush_tlb_lines <= active_lines/2^tlb_flushall_shift. +* If tlb_flushall_shift is -1, means the replacement will be disabled. +*/ +s8 __read_mostly tlb_flushall_shift =-1 ; +void __cpuinit cpu_detect_tlb (struct cpuinfo_x86 *c) {if (c->x86_vendor ==X86_VENDOR_INTEL )intel_cpu_detect_tlb (c);printk (KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ -"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" , +"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ +"tlb_flushall_shift is 0x%x\n" , tlb_lli_4k[ENTRIES ], tlb_lli_2m[ENTRIES ], tlb_lli_4m[ENTRIES ], tlb_lld_4k[ENTRIES ], - tlb_lld_2m[ENTRIES ], tlb_lld_4m[ENTRIES ]); + tlb_lld_2m[ENTRIES ], tlb_lld_4m[ENTRIES ], + tlb_flushall_shift); }void __cpuinit detect_ht (struct cpuinfo_x86 *c)
arch/x86/kernel/cpu/intel.c +34 -0
@@ -610,6 +610,39 @@ static void __cpuinit intel_tlb_lookup(const unsigned char desc) } } +static void __cpuinit intel_tlb_flushall_shift_set (struct cpuinfo_x86 *c) +{ +if (!cpu_has_invlpg) { + tlb_flushall_shift =-1 ; +return ; + } +switch ((c->x86 <<8 ) + c->x86_model) { +case 0x60f :/* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ +case 0x616 :/* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ +case 0x617 :/* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ +case 0x61d :/* six-core 45 nm xeon "Dunnington" */ + tlb_flushall_shift =-1 ; +break ; +case 0x61a :/* 45 nm nehalem, "Bloomfield" */ +case 0x61e :/* 45 nm nehalem, "Lynnfield" */ +case 0x625 :/* 32 nm nehalem, "Clarkdale" */ +case 0x62c :/* 32 nm nehalem, "Gulftown" */ +case 0x62e :/* 45 nm nehalem-ex, "Beckton" */ +case 0x62f :/* 32 nm Xeon E7 */ + tlb_flushall_shift =6 ; +break ; +case 0x62a :/* SandyBridge */ +case 0x62d :/* SandyBridge, "Romely-EP" */ + tlb_flushall_shift =5 ; +break ; +case 0x63a :/* Ivybridge */ + tlb_flushall_shift =1 ; +break ; +default : + tlb_flushall_shift =6 ; + } +} +void __cpuinit intel_cpu_detect_tlb (struct cpuinfo_x86 *c) {int i, j, n;
@@ -630,6 +663,7 @@ void __cpuinit intel_cpu_detect_tlb(struct cpuinfo_x86 *c)for (j =1 ; j <16 ; j++)intel_tlb_lookup (desc[j]); } +intel_tlb_flushall_shift_set (c); }static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
arch/x86/mm/tlb.c +3 -4
@@ -316,8 +316,6 @@ void flush_tlb_mm(struct mm_struct *mm)preempt_enable (); } -#define FLUSHALL_BAR 16 -#ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline unsigned long has_large_page (struct mm_struct *mm,unsigned long start,unsigned long end)
@@ -352,7 +350,7 @@ void flush_tlb_range(struct vm_area_struct *vma, {struct mm_struct *mm; -if (!cpu_has_invlpg || vma->vm_flags &VM_HUGETLB ) { +if (vma->vm_flags &VM_HUGETLB || tlb_flushall_shift ==-1 ) { flush_all:flush_tlb_mm (vma->vm_mm);return ;
@@ -373,7 +371,8 @@ flush_all: act_entries = tlb_entries > mm->total_vm ? mm->total_vm : tlb_entries; -if ((end - start)/PAGE_SIZE > act_entries/FLUSHALL_BAR ) +if ((end - start) >>PAGE_SHIFT > + act_entries >> tlb_flushall_shift)local_flush_tlb ();else {if (has_large_page (mm, start, end)) {
include/asm-generic/tlb.h +2 -1
@@ -113,7 +113,8 @@ static inline int tlb_fast_mode(struct mmu_gather *tlb)void tlb_gather_mmu (struct mmu_gather *tlb,struct mm_struct *mm,bool fullmm);void tlb_flush_mmu (struct mmu_gather *tlb); -void tlb_finish_mmu (struct mmu_gather *tlb,unsigned long start,unsigned long end); +void tlb_finish_mmu (struct mmu_gather *tlb,unsigned long start, +unsigned long end);int __tlb_remove_page (struct mmu_gather *tlb,struct page *page);/* tlb_remove_page
Signature · 1 line
1.7.5.4
[tip:x86/mm] x86/tlb: add tlb_flushall_shift for specific CPU
Commit-ID: 2a8a825630ae02a847cff83b40b3cbacff548ef5 Gitweb: http://git.kernel.org/tip/2a8a825630ae02a847cff83b40b3cbacff548ef5 Author: Alex Shi <[email protected]> AuthorDate: Mon, 25 Jun 2012 14:08:22 +0800 Committer: H. Peter Anvin <[email protected]> CommitDate: Mon, 25 Jun 2012 20:53:17 -0700
x86/tlb: add tlb_flushall_shift for specific CPU
Testing show different CPU type(micro architectures and NUMA mode) has different balance points between the TLB flush all and multiple invlpg. And there also has cases the tlb flush change has no any help.
This patch give a interface to let x86 vendor developers have a chance to set different shift for different CPU type.
like some machine in my hands, balance points is 16 entries on Romely-EP; while it is at 8 entries on Bloomfield NHM-EP; and is 256 on IVB mobile CPU. but on model 15 core2 Xeon using invlpg has nothing help.
For untested machine, do a conservative optimization, same as NHM CPU.
--- arch/x86/include/asm/processor.h | 2 ++ arch/x86/kernel/cpu/common.c | 14 ++++++++++++-- arch/x86/kernel/cpu/intel.c | 34 ++++++++++++++++++++++++++++++++++ arch/x86/mm/tlb.c | 7 +++---- include/asm-generic/tlb.h | 3 ++- 5 files changed, 53 insertions(+), 7 deletions(-)
arch/x86/include/asm/processor.h +2 -0
@@ -72,6 +72,8 @@ extern u16 __read_mostly tlb_lli_4m[NR_INFO];extern u16 __read_mostly tlb_lld_4k[NR_INFO ];extern u16 __read_mostly tlb_lld_2m[NR_INFO ];extern u16 __read_mostly tlb_lld_4m[NR_INFO ]; +extern s8 __read_mostly tlb_flushall_shift; +/* * CPU type and hardware bug flags. Kept separately for each CPU. * Members of this structure are referenced in head.S, so think twice
arch/x86/kernel/cpu/common.c +12 -2
@@ -459,16 +459,26 @@ u16 __read_mostly tlb_lld_4k[NR_INFO];u16 __read_mostly tlb_lld_2m[NR_INFO ];u16 __read_mostly tlb_lld_4m[NR_INFO ]; +/* +* tlb_flushall_shift shows the balance point in replacing cr3 write +* with multiple 'invlpg'. It will do this replacement when +* flush_tlb_lines <= active_lines/2^tlb_flushall_shift. +* If tlb_flushall_shift is -1, means the replacement will be disabled. +*/ +s8 __read_mostly tlb_flushall_shift =-1 ; +void __cpuinit cpu_detect_tlb (struct cpuinfo_x86 *c) {if (c->x86_vendor ==X86_VENDOR_INTEL )intel_cpu_detect_tlb (c);printk (KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ -"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" , +"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ +"tlb_flushall_shift is 0x%x\n" , tlb_lli_4k[ENTRIES ], tlb_lli_2m[ENTRIES ], tlb_lli_4m[ENTRIES ], tlb_lld_4k[ENTRIES ], - tlb_lld_2m[ENTRIES ], tlb_lld_4m[ENTRIES ]); + tlb_lld_2m[ENTRIES ], tlb_lld_4m[ENTRIES ], + tlb_flushall_shift); }void __cpuinit detect_ht (struct cpuinfo_x86 *c)
arch/x86/kernel/cpu/intel.c +34 -0
@@ -610,6 +610,39 @@ static void __cpuinit intel_tlb_lookup(const unsigned char desc) } } +static void __cpuinit intel_tlb_flushall_shift_set (struct cpuinfo_x86 *c) +{ +if (!cpu_has_invlpg) { + tlb_flushall_shift =-1 ; +return ; + } +switch ((c->x86 <<8 ) + c->x86_model) { +case 0x60f :/* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ +case 0x616 :/* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ +case 0x617 :/* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ +case 0x61d :/* six-core 45 nm xeon "Dunnington" */ + tlb_flushall_shift =-1 ; +break ; +case 0x61a :/* 45 nm nehalem, "Bloomfield" */ +case 0x61e :/* 45 nm nehalem, "Lynnfield" */ +case 0x625 :/* 32 nm nehalem, "Clarkdale" */ +case 0x62c :/* 32 nm nehalem, "Gulftown" */ +case 0x62e :/* 45 nm nehalem-ex, "Beckton" */ +case 0x62f :/* 32 nm Xeon E7 */ + tlb_flushall_shift =6 ; +break ; +case 0x62a :/* SandyBridge */ +case 0x62d :/* SandyBridge, "Romely-EP" */ + tlb_flushall_shift =5 ; +break ; +case 0x63a :/* Ivybridge */ + tlb_flushall_shift =1 ; +break ; +default : + tlb_flushall_shift =6 ; + } +} +void __cpuinit intel_cpu_detect_tlb (struct cpuinfo_x86 *c) {int i, j, n;
@@ -630,6 +663,7 @@ void __cpuinit intel_cpu_detect_tlb(struct cpuinfo_x86 *c)for (j =1 ; j <16 ; j++)intel_tlb_lookup (desc[j]); } +intel_tlb_flushall_shift_set (c); }static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
arch/x86/mm/tlb.c +3 -4
@@ -316,8 +316,6 @@ void flush_tlb_mm(struct mm_struct *mm)preempt_enable (); } -#define FLUSHALL_BAR 16 -#ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline unsigned long has_large_page (struct mm_struct *mm,unsigned long start,unsigned long end)
@@ -352,7 +350,7 @@ void flush_tlb_range(struct vm_area_struct *vma, {struct mm_struct *mm; -if (!cpu_has_invlpg || vma->vm_flags &VM_HUGETLB ) { +if (vma->vm_flags &VM_HUGETLB || tlb_flushall_shift ==-1 ) { flush_all:flush_tlb_mm (vma->vm_mm);return ;
@@ -373,7 +371,8 @@ flush_all: act_entries = tlb_entries > mm->total_vm ? mm->total_vm : tlb_entries; -if ((end - start)/PAGE_SIZE > act_entries/FLUSHALL_BAR ) +if ((end - start) >>PAGE_SHIFT > + act_entries >> tlb_flushall_shift)local_flush_tlb ();else {if (has_large_page (mm, start, end)) {
include/asm-generic/tlb.h +2 -1
@@ -113,7 +113,8 @@ static inline int tlb_fast_mode(struct mmu_gather *tlb)void tlb_gather_mmu (struct mmu_gather *tlb,struct mm_struct *mm,bool fullmm);void tlb_flush_mmu (struct mmu_gather *tlb); -void tlb_finish_mmu (struct mmu_gather *tlb,unsigned long start,unsigned long end); +void tlb_finish_mmu (struct mmu_gather *tlb,unsigned long start, +unsigned long end);int __tlb_remove_page (struct mmu_gather *tlb,struct page *page);/* tlb_remove_page
PATCH v9 5/9 x86/tlb: add tlb_flushall_shift knob into debugfs
In reply to Alex Shikernel will replace cr3 rewrite with invlpg when
tlb_flush_entries <= active_tlb_entries / 2^tlb_flushall_factor
if tlb_flushall_factor is -1, kernel won't do this replacement.
User can modify its value according to specific CPU/applications.
Thanks for Borislav providing the help message ofCONFIG_DEBUG_TLBFLUSH.
--- arch/x86/Kconfig.debug | 19 +++++++++++++++++ arch/x86/mm/tlb.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+), 0 deletions(-)
arch/x86/Kconfig.debug +19 -0
@@ -129,6 +129,25 @@ config DOUBLEFAULT option saves about 4k and might cause you much additional grey hair. +config DEBUG_TLBFLUSH + bool "Set upper limit of TLB entries to flush one-by-one" + depends on DEBUG_KERNEL && (X86_64 || X86_INVLPG) + ---help--- + + X86-only for now. + + This option allows the user to tune the amount of TLB entries the + kernel flushes one-by-one instead of doing a full TLB flush. In + certain situations, the former is cheaper. This is controlled by the + tlb_flushall_shift knob under /sys/kernel/debug/x86. If you set it + to -1, the code flushes the whole TLB unconditionally. Otherwise, + for positive values of it, the kernel will use single TLB entry + invalidating instructions according to the following formula: + + flush_entries <= active_tlb_entries / 2^tlb_flushall_shift + + If in doubt, say "N". + config IOMMU_DEBUG bool "Enable IOMMU debugging" depends on GART_IOMMU && DEBUG_KERNEL
arch/x86/mm/tlb.c +51 -0
60 lines not on this page · raw message
Signature · 1 line
1.7.5.4
[tip:x86/mm] x86/tlb: add tlb_flushall_shift knob into debugfs
Commit-ID: 126abdc40ba5257c5ba1e6e04b809c3626034ee9 Gitweb: http://git.kernel.org/tip/126abdc40ba5257c5ba1e6e04b809c3626034ee9 Author: Alex Shi <[email protected]> AuthorDate: Mon, 25 Jun 2012 14:08:23 +0800 Committer: H. Peter Anvin <[email protected]> CommitDate: Mon, 25 Jun 2012 20:53:18 -0700
x86/tlb: add tlb_flushall_shift knob into debugfs
kernel will replace cr3 rewrite with invlpg when
tlb_flush_entries <= active_tlb_entries / 2^tlb_flushall_factor
if tlb_flushall_factor is -1, kernel won't do this replacement.
User can modify its value according to specific CPU/applications.
Thanks for Borislav providing the help message ofCONFIG_DEBUG_TLBFLUSH.
--- arch/x86/Kconfig.debug | 19 +++++++++++++++++ arch/x86/mm/tlb.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+), 0 deletions(-)
arch/x86/Kconfig.debug +19 -0
@@ -129,6 +129,25 @@ config DOUBLEFAULT option saves about 4k and might cause you much additional grey hair. +config DEBUG_TLBFLUSH + bool "Set upper limit of TLB entries to flush one-by-one" + depends on DEBUG_KERNEL && (X86_64 || X86_INVLPG) + ---help--- + + X86-only for now. + + This option allows the user to tune the amount of TLB entries the + kernel flushes one-by-one instead of doing a full TLB flush. In + certain situations, the former is cheaper. This is controlled by the + tlb_flushall_shift knob under /sys/kernel/debug/x86. If you set it + to -1, the code flushes the whole TLB unconditionally. Otherwise, + for positive values of it, the kernel will use single TLB entry + invalidating instructions according to the following formula: + + flush_entries <= active_tlb_entries / 2^tlb_flushall_shift + + If in doubt, say "N". + config IOMMU_DEBUG bool "Enable IOMMU debugging" depends on GART_IOMMU && DEBUG_KERNEL
arch/x86/mm/tlb.c +51 -0
60 lines not on this page · raw message
PATCH v9 6/9 mm/mmu_gather: enable tlb flush range in generic mmu_gather
In reply to Alex ShiThis patch enabled the tlb flush range support in generic mmu layer.
Most of arch has self tlb flush range support, like ARM/IA64 etc. X86 arch has no this support in hardware yet. But another instruction 'invlpg' can implement this function in some degree. So, enable this feather in generic layer for x86 now. and maybe useful for other archs in further.
Generic mmu_gather struct is protected by macro HAVE_GENERIC_MMU_GATHER. Other archs that has flush range supported own self mmu_gather struct. So, now this change is safe for them.
In future we may unify this struct and related functions on multiple archs.
Thanks for Peter Zijlstra time and time reminder for multiple architecture code safe!
--- include/asm-generic/tlb.h | 2 ++ mm/memory.c | 9 +++++++++ 2 files changed, 11 insertions(+), 0 deletions(-)
include/asm-generic/tlb.h +2 -0
@@ -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 */
mm/memory.c +9 -0
@@ -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;
Signature · 1 line
1.7.5.4
[tip:x86/mm] mm/mmu_gather: enable tlb flush range in generic mmu_gather
Commit-ID: 6d80ee50c281d02be090cf429294b32dab0b23b7 Gitweb: http://git.kernel.org/tip/6d80ee50c281d02be090cf429294b32dab0b23b7 Author: Alex Shi <[email protected]> AuthorDate: Mon, 25 Jun 2012 14:08:24 +0800 Committer: H. Peter Anvin <[email protected]> CommitDate: Mon, 25 Jun 2012 20:53:19 -0700
mm/mmu_gather: enable tlb flush range in generic mmu_gather
This patch enabled the tlb flush range support in generic mmu layer.
Most of arch has self tlb flush range support, like ARM/IA64 etc. X86 arch has no this support in hardware yet. But another instruction 'invlpg' can implement this function in some degree. So, enable this feather in generic layer for x86 now. and maybe useful for other archs in further.
Generic mmu_gather struct is protected by macro HAVE_GENERIC_MMU_GATHER. Other archs that has flush range supported own self mmu_gather struct. So, now this change is safe for them.
In future we may unify this struct and related functions on multiple archs.
Thanks for Peter Zijlstra time and time reminder for multiple architecture code safe!
--- include/asm-generic/tlb.h | 2 ++ mm/memory.c | 9 +++++++++ 2 files changed, 11 insertions(+), 0 deletions(-)
include/asm-generic/tlb.h +2 -0
@@ -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 */
mm/memory.c +9 -0
@@ -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;
PATCH v9 7/9 x86/tlb: enable tlb flush range support for x86
In reply to Alex ShiNot 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 macro 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%
--- arch/x86/include/asm/tlb.h | 9 +++- arch/x86/include/asm/tlbflush.h | 17 +++++- arch/x86/mm/tlb.c | 112 ++++++++++++++++----------------------- 3 files changed, 68 insertions(+), 70 deletions(-)
arch/x86/include/asm/tlb.h +8 -1
@@ -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>
arch/x86/include/asm/tlbflush.h +14 -3
@@ -105,6 +105,13 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,__flush_tlb (); } +static inline void flush_tlb_mm_range (struct vm_area_struct *vma, +unsigned long start,unsigned long end,unsigned long vmflag) +{ +if (mm == current->active_mm) +__flush_tlb (); +} + static inline void native_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long start,
@@ -122,12 +129,16 @@ static inline void reset_lazy_tlbstate(void)#define local_flush_tlb () __flush_tlb() +#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_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()
arch/x86/mm/tlb.c +46 -66
137 lines not on this page · raw message
Signature · 1 line
1.7.5.4
[tip:x86/mm] x86/tlb: enable tlb flush range support for x86
Commit-ID: 638b9be5cc9ea3d70238a3b4f1b31f191036b2ec Gitweb: http://git.kernel.org/tip/638b9be5cc9ea3d70238a3b4f1b31f191036b2ec Author: Alex Shi <[email protected]> AuthorDate: Mon, 25 Jun 2012 14:08:25 +0800 Committer: H. Peter Anvin <[email protected]> CommitDate: Mon, 25 Jun 2012 20:53:20 -0700
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 macro 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%
--- arch/x86/include/asm/tlb.h | 9 +++- arch/x86/include/asm/tlbflush.h | 17 +++++- arch/x86/mm/tlb.c | 112 ++++++++++++++++----------------------- 3 files changed, 68 insertions(+), 70 deletions(-)
arch/x86/include/asm/tlb.h +8 -1
@@ -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>
arch/x86/include/asm/tlbflush.h +14 -3
@@ -105,6 +105,13 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,__flush_tlb (); } +static inline void flush_tlb_mm_range (struct vm_area_struct *vma, +unsigned long start,unsigned long end,unsigned long vmflag) +{ +if (mm == current->active_mm) +__flush_tlb (); +} + static inline void native_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long start,
@@ -122,12 +129,16 @@ static inline void reset_lazy_tlbstate(void)#define local_flush_tlb () __flush_tlb() +#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_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()
arch/x86/mm/tlb.c +46 -66
137 lines not on this page · raw message
PATCH v9 8/9 x86/tlb: replace INVALIDATE_TLB_VECTOR by CALL_FUNCTION_VECTOR
In reply to Alex ShiThere are 32 INVALIDATE_TLB_VECTOR now in kernel. That is quite big amount of vector in IDT. But it is still not enough, since modern x86 sever has more cpu number. That still causes heavy lock contentation in TLB flushing.
The patch using generic smp call function to replace it. That saved 32 vector number in IDT, and resolved the lock contentation in TLB flushing on large system.
In the NHM EX machine 4P * 8cores * HT = 64 CPUs, hackbench pthread has 3% performance increase.
--- arch/x86/include/asm/entry_arch.h | 9 -- arch/x86/include/asm/irq_vectors.h | 11 -- arch/x86/kernel/entry_64.S | 18 --- arch/x86/kernel/irqinit.c | 73 ----------- arch/x86/mm/tlb.c | 238 +++++++----------------------------- 5 files changed, 45 insertions(+), 304 deletions(-)
arch/x86/include/asm/entry_arch.h +0 -9
@@ -15,15 +15,6 @@ BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR) BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR) BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR) BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR) - -.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \ -16 ,17 ,18 ,19 ,20 ,21 ,22 ,23 ,24 ,25 ,26 ,27 ,28 ,29 ,30 ,31 -.if NUM_INVALIDATE_TLB_VECTORS > \idx -BUILD_INTERRUPT3(invalidate_interrupt\idx, - (INVALIDATE_TLB_VECTOR_START)+\idx, - smp_invalidate_interrupt) -.endif -.endr#endif BUILD_INTERRUPT (x86_platform_ipi,X86_PLATFORM_IPI_VECTOR )
arch/x86/include/asm/irq_vectors.h +0 -11
@@ -119,17 +119,6 @@*/ #define LOCAL_TIMER_VECTOR 0xef -/* up to 32 vectors used for spreading out TLB flushes: */ -#if NR_CPUS <=32 -# define NUM_INVALIDATE_TLB_VECTORS (NR_CPUS) -#else -# define NUM_INVALIDATE_TLB_VECTORS (32) -#endif - -#define INVALIDATE_TLB_VECTOR_END (0xee) -#define INVALIDATE_TLB_VECTOR_START \ - (INVALIDATE_TLB_VECTOR_END-NUM_INVALIDATE_TLB_VECTORS+1) -#define NR_VECTORS 256#define FPU_IRQ 13
arch/x86/kernel/entry_64.S +0 -18
@@ -1048,24 +1048,6 @@ apicinterrupt LOCAL_TIMER_VECTOR \ apicinterrupt X86_PLATFORM_IPI_VECTOR \ x86_platform_ipi smp_x86_platform_ipi -#ifdef CONFIG_SMP - ALIGN - INTR_FRAME -.irp idx,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \ - 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31 -.if NUM_INVALIDATE_TLB_VECTORS > \idx -ENTRY(invalidate_interrupt\idx) - pushq_cfi $~(INVALIDATE_TLB_VECTOR_START+\idx) - jmp .Lcommon_invalidate_interrupt0 - CFI_ADJUST_CFA_OFFSET -8 -END(invalidate_interrupt\idx) -.endif -.endr - CFI_ENDPROC -apicinterrupt INVALIDATE_TLB_VECTOR_START, \ - invalidate_interrupt0, smp_invalidate_interrupt -#endif - apicinterrupt THRESHOLD_APIC_VECTOR \ threshold_interrupt smp_threshold_interrupt apicinterrupt THERMAL_APIC_VECTOR \
arch/x86/kernel/irqinit.c +0 -73
79 lines not on this page · raw message
arch/x86/mm/tlb.c +47 -195
295 lines not on this page · raw message
Signature · 1 line
1.7.5.4
[tip:x86/mm] x86/tlb: replace INVALIDATE_TLB_VECTOR by CALL_FUNCTION_VECTOR
Commit-ID: a47f0e5c7c240b72c3f6ee883206280b0eeee7ab Gitweb: http://git.kernel.org/tip/a47f0e5c7c240b72c3f6ee883206280b0eeee7ab Author: Alex Shi <[email protected]> AuthorDate: Mon, 25 Jun 2012 14:08:26 +0800 Committer: H. Peter Anvin <[email protected]> CommitDate: Mon, 25 Jun 2012 20:53:20 -0700
x86/tlb: replace INVALIDATE_TLB_VECTOR by CALL_FUNCTION_VECTOR
There are 32 INVALIDATE_TLB_VECTOR now in kernel. That is quite big amount of vector in IDT. But it is still not enough, since modern x86 sever has more cpu number. That still causes heavy lock contentation in TLB flushing.
The patch using generic smp call function to replace it. That saved 32 vector number in IDT, and resolved the lock contentation in TLB flushing on large system.
In the NHM EX machine 4P * 8cores * HT = 64 CPUs, hackbench pthread has 3% performance increase.
--- arch/x86/include/asm/entry_arch.h | 9 -- arch/x86/include/asm/irq_vectors.h | 11 -- arch/x86/kernel/entry_64.S | 18 --- arch/x86/kernel/irqinit.c | 73 ----------- arch/x86/mm/tlb.c | 238 +++++++----------------------------- 5 files changed, 45 insertions(+), 304 deletions(-)
arch/x86/include/asm/entry_arch.h +0 -9
@@ -15,15 +15,6 @@ BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR) BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR) BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR) BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR) - -.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \ -16 ,17 ,18 ,19 ,20 ,21 ,22 ,23 ,24 ,25 ,26 ,27 ,28 ,29 ,30 ,31 -.if NUM_INVALIDATE_TLB_VECTORS > \idx -BUILD_INTERRUPT3(invalidate_interrupt\idx, - (INVALIDATE_TLB_VECTOR_START)+\idx, - smp_invalidate_interrupt) -.endif -.endr#endif BUILD_INTERRUPT (x86_platform_ipi,X86_PLATFORM_IPI_VECTOR )
arch/x86/include/asm/irq_vectors.h +0 -11
@@ -119,17 +119,6 @@*/ #define LOCAL_TIMER_VECTOR 0xef -/* up to 32 vectors used for spreading out TLB flushes: */ -#if NR_CPUS <=32 -# define NUM_INVALIDATE_TLB_VECTORS (NR_CPUS) -#else -# define NUM_INVALIDATE_TLB_VECTORS (32) -#endif - -#define INVALIDATE_TLB_VECTOR_END (0xee) -#define INVALIDATE_TLB_VECTOR_START \ - (INVALIDATE_TLB_VECTOR_END-NUM_INVALIDATE_TLB_VECTORS+1) -#define NR_VECTORS 256#define FPU_IRQ 13
arch/x86/kernel/entry_64.S +0 -18
@@ -1048,24 +1048,6 @@ apicinterrupt LOCAL_TIMER_VECTOR \ apicinterrupt X86_PLATFORM_IPI_VECTOR \ x86_platform_ipi smp_x86_platform_ipi -#ifdef CONFIG_SMP - ALIGN - INTR_FRAME -.irp idx,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \ - 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31 -.if NUM_INVALIDATE_TLB_VECTORS > \idx -ENTRY(invalidate_interrupt\idx) - pushq_cfi $~(INVALIDATE_TLB_VECTOR_START+\idx) - jmp .Lcommon_invalidate_interrupt0 - CFI_ADJUST_CFA_OFFSET -8 -END(invalidate_interrupt\idx) -.endif -.endr - CFI_ENDPROC -apicinterrupt INVALIDATE_TLB_VECTOR_START, \ - invalidate_interrupt0, smp_invalidate_interrupt -#endif - apicinterrupt THRESHOLD_APIC_VECTOR \ threshold_interrupt smp_threshold_interrupt apicinterrupt THERMAL_APIC_VECTOR \
arch/x86/kernel/irqinit.c +0 -73
79 lines not on this page · raw message
arch/x86/mm/tlb.c +47 -195
295 lines not on this page · raw message
PATCH v9 9/9 x86/tlb: do flush_tlb_kernel_range by 'invlpg'
In reply to Alex ShiThis patch do flush_tlb_kernel_range by 'invlpg'. The performance pay and gain was analyzed in previous patch
(x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range).
In the testing: http://lkml.org/lkml/2012/6/21/10
The pay is mostly covered by long kernel path, but the gain is still quite clear, memory access in user APP can increase 30+% when kernel execute this funtion.
--- arch/x86/include/asm/tlbflush.h | 13 +++++++------ arch/x86/mm/tlb.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 6 deletions(-)
arch/x86/include/asm/tlbflush.h +7 -6
@@ -123,6 +123,12 @@ 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>
@@ -139,6 +145,7 @@ extern void flush_tlb_current_task(void);extern void flush_tlb_page (struct vm_area_struct *,unsigned long );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()
@@ -168,10 +175,4 @@ static inline void reset_lazy_tlbstate(void) native_flush_tlb_others(mask, mm, start, end)#endif -static inline void flush_tlb_kernel_range (unsigned long start, -unsigned long end) -{ -flush_tlb_all (); -} -#endif /* _ASM_X86_TLBFLUSH_H */
arch/x86/mm/tlb.c +30 -0
@@ -264,6 +264,36 @@ void flush_tlb_all(void)on_each_cpu (do_flush_tlb_all,NULL ,1 ); } +static void do_kernel_range_flush (void *info) +{ +struct flush_tlb_info *f = info; +unsigned long addr; + +/* flush range by one by one 'invlpg' */ +for (addr = f->flush_start; addr < f->flush_end; addr +=PAGE_SIZE ) +__flush_tlb_single (addr); +} + +void flush_tlb_kernel_range (unsigned long start,unsigned long end) +{ +unsigned act_entries; +struct flush_tlb_info info; + +/* In modern CPU, last level tlb used for both data/ins */ + act_entries = tlb_lld_4k[ENTRIES ]; + +/* tlb_flushall_shift is on balance point, details in commit log */ +if (end ==TLB_FLUSH_ALL || tlb_flushall_shift ==-1 || + (end - start) >>PAGE_SHIFT > act_entries >> tlb_flushall_shift) + +on_each_cpu (do_flush_tlb_all,NULL ,1 ); +else { + info.flush_start = start; + info.flush_end = end; +on_each_cpu (do_kernel_range_flush, &info,1 ); + } +} +#ifdef CONFIG_DEBUG_TLBFLUSH static ssize_t tlbflush_read_file (struct file *file,char __user *user_buf,size_t count,loff_t *ppos)
Signature · 1 line
1.7.5.4
[tip:x86/mm] x86/tlb: do flush_tlb_kernel_range by 'invlpg'
Commit-ID: b3ce6624a8364343e55d54cd3a2973d614b17256 Gitweb: http://git.kernel.org/tip/b3ce6624a8364343e55d54cd3a2973d614b17256 Author: Alex Shi <[email protected]> AuthorDate: Mon, 25 Jun 2012 14:08:27 +0800 Committer: H. Peter Anvin <[email protected]> CommitDate: Mon, 25 Jun 2012 20:53:21 -0700
x86/tlb: do flush_tlb_kernel_range by 'invlpg'
This patch do flush_tlb_kernel_range by 'invlpg'. The performance pay and gain was analyzed in previous patch
(x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range).
In the testing: http://lkml.org/lkml/2012/6/21/10
The pay is mostly covered by long kernel path, but the gain is still quite clear, memory access in user APP can increase 30+% when kernel execute this funtion.
--- arch/x86/include/asm/tlbflush.h | 13 +++++++------ arch/x86/mm/tlb.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 6 deletions(-)
arch/x86/include/asm/tlbflush.h +7 -6
@@ -123,6 +123,12 @@ 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>
@@ -139,6 +145,7 @@ extern void flush_tlb_current_task(void);extern void flush_tlb_page (struct vm_area_struct *,unsigned long );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()
@@ -168,10 +175,4 @@ static inline void reset_lazy_tlbstate(void) native_flush_tlb_others(mask, mm, start, end)#endif -static inline void flush_tlb_kernel_range (unsigned long start, -unsigned long end) -{ -flush_tlb_all (); -} -#endif /* _ASM_X86_TLBFLUSH_H */
arch/x86/mm/tlb.c +30 -0
@@ -264,6 +264,36 @@ void flush_tlb_all(void)on_each_cpu (do_flush_tlb_all,NULL ,1 ); } +static void do_kernel_range_flush (void *info) +{ +struct flush_tlb_info *f = info; +unsigned long addr; + +/* flush range by one by one 'invlpg' */ +for (addr = f->flush_start; addr < f->flush_end; addr +=PAGE_SIZE ) +__flush_tlb_single (addr); +} + +void flush_tlb_kernel_range (unsigned long start,unsigned long end) +{ +unsigned act_entries; +struct flush_tlb_info info; + +/* In modern CPU, last level tlb used for both data/ins */ + act_entries = tlb_lld_4k[ENTRIES ]; + +/* tlb_flushall_shift is on balance point, details in commit log */ +if (end ==TLB_FLUSH_ALL || tlb_flushall_shift ==-1 || + (end - start) >>PAGE_SHIFT > act_entries >> tlb_flushall_shift) + +on_each_cpu (do_flush_tlb_all,NULL ,1 ); +else { + info.flush_start = start; + info.flush_end = end; +on_each_cpu (do_kernel_range_flush, &info,1 ); + } +} +#ifdef CONFIG_DEBUG_TLBFLUSH static ssize_t tlbflush_read_file (struct file *file,char __user *user_buf,size_t count,loff_t *ppos)