mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Borislav Petkov <bp@amd64.org>
To: Alex Shi <alex.shi@intel.com>
Cc: rob@landley.net, tglx@linutronix.de, mingo@redhat.com,
	hpa@zytor.com, arnd@arndb.de, rostedt@goodmis.org,
	fweisbec@gmail.com, jeremy@goop.org, gregkh@linuxfoundation.org,
	riel@redhat.com, luto@mit.edu, avi@redhat.com,
	len.brown@intel.com, dhowells@redhat.com, fenghua.yu@intel.com,
	ak@linux.intel.com, cpw@sgi.com, steiner@sgi.com,
	akpm@linux-foundation.org, penberg@kernel.org, hughd@google.com,
	rientjes@google.com, kosaki.motohiro@jp.fujitsu.com,
	n-horiguchi@ah.jp.nec.com, paul.gortmaker@windriver.com,
	trenn@suse.de, tj@kernel.org, oleg@redhat.com, axboe@kernel.dk,
	a.p.zijlstra@chello.nl, kamezawa.hiroyu@jp.fujitsu.com,
	viro@zeniv.linux.org.uk, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v4 2/7] x86/tlb_info: get last level TLB entry number of CPU
Date: Thu, 10 May 2012 16:43:21 +0200	[thread overview]
Message-ID: <20120510144321.GA32700@aftab.osrc.amd.com> (raw)
In-Reply-To: <1336626013-28413-3-git-send-email-alex.shi@intel.com>

On Thu, May 10, 2012 at 01:00:08PM +0800, Alex Shi wrote:
> 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.
> 
> For all kinds of x86 vendor friendly, vendor specific code was moved to its
> specific files.
> 
> Signed-off-by: Alex Shi <alex.shi@intel.com>
> ---
>  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(-)
> 
> diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
> index 4fa7dcc..797faca 100644
> --- a/arch/x86/include/asm/processor.h
> +++ b/arch/x86/include/asm/processor.h
> @@ -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
> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
> index cf79302..0152082 100644
> --- a/arch/x86/kernel/cpu/common.c
> +++ b/arch/x86/kernel/cpu/common.c
> @@ -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)
> diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
> index 8bacc78..c8dc726 100644
> --- a/arch/x86/kernel/cpu/cpu.h
> +++ b/arch/x86/kernel/cpu/cpu.h
> @@ -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);
>  #endif /* ARCH_X86_CPU_H */
> diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
> index 3e6ff6c..86e6131 100644
> --- a/arch/x86/kernel/cpu/intel.c
> +++ b/arch/x86/kernel/cpu/intel.c
> @@ -491,6 +491,147 @@ static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned i
>  }
>  #endif
>  
> +#define TLB_INST_4K	0x01
> +#define TLB_INST_4M	0x02
> +#define TLB_INST_2M_4M	0x03
> +
> +#define TLB_INST_ALL	0x05
> +#define TLB_INST_1G	0x06
> +
> +#define TLB_DATA_4K	0x11
> +#define TLB_DATA_4M	0x12
> +#define TLB_DATA_2M_4M	0x13
> +#define TLB_DATA_4K_4M	0x14
> +
> +#define TLB_DATA_1G	0x16
> +
> +#define TLB_DATA0_4K	0x21
> +#define TLB_DATA0_4M	0x22
> +#define TLB_DATA0_2M_4M	0x23
> +
> +#define STLB_4K		0x41
> +
> +static const struct _tlb_table intel_tlb_table[] = {
> +	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
> +	{ 0x02, TLB_INST_4M,		2,	" TLB_INST 4 MByte pages, full associative" },
> +	{ 0x03, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way set associative" },
> +	{ 0x04, TLB_DATA_4M,		8,	" TLB_DATA 4 MByte pages, 4-way set associative" },
> +	{ 0x05, TLB_DATA_4M,		32,	" TLB_DATA 4 MByte pages, 4-way set associative" },
> +	{ 0x0b, TLB_INST_4M,		4,	" TLB_INST 4 MByte pages, 4-way set associative" },
> +	{ 0x4f, TLB_INST_4K,		32, 	" TLB_INST 4 KByte pages */" },
> +	{ 0x50, TLB_INST_ALL,		64, 	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
> +	{ 0x51, TLB_INST_ALL,		128,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
> +	{ 0x52, TLB_INST_ALL,		256,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
> +	{ 0x55, TLB_INST_2M_4M,		7, 	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
> +	{ 0x56, TLB_DATA0_4M,		16,	" TLB_DATA0 4 MByte pages, 4-way set associative" },
> +	{ 0x57, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, 4-way associative" },
> +	{ 0x59, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, fully associative" },
> +	{ 0x5a, TLB_DATA0_2M_4M,	32,	" TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative" },
> +	{ 0x5b, TLB_DATA_4K_4M,		64,	" TLB_DATA 4 KByte and 4 MByte pages" },
> +	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
> +	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
> +	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
> +	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
> +	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
> +	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
> +	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
> +	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
> +	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
> +	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
> +	{ 0x00, 0, 0 }
> +};
> +
> +void intel_tlb_lookup(const unsigned char desc)
> +{
> +	unsigned char k;
> +	if (desc == 0)
> +		return;
> +
> +	/* look up this descriptor in the table */
> +	for (k = 0; intel_tlb_table[k].descriptor != desc && \
> +			intel_tlb_table[k].descriptor != 0; k++)
> +		;
> +
> +	if (intel_tlb_table[k].tlb_type == 0)
> +		return;
> +
> +	switch (intel_tlb_table[k].tlb_type) {
> +	case STLB_4K:
> +		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
> +		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
> +		break;
> +	case TLB_INST_ALL:
> +		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
> +		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
> +		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
> +		break;
> +	case TLB_INST_4K:
> +		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
> +		break;
> +	case TLB_INST_4M:
> +		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
> +		break;
> +	case TLB_INST_2M_4M:
> +		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
> +		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
> +		break;
> +	case TLB_DATA_4K:
> +	case TLB_DATA0_4K:
> +		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
> +		break;
> +	case TLB_DATA_4M:
> +	case TLB_DATA0_4M:
> +		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
> +		break;
> +	case TLB_DATA_2M_4M:
> +	case TLB_DATA0_2M_4M:
> +		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
> +		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
> +		break;
> +	case TLB_DATA_4K_4M:
> +		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
> +		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
> +			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
> +		break;
> +	}
> +}
> +
> +void intel_cpu_detect_tlb(struct cpuinfo_x86 *c)

cpu_detect_tlb() is __cpuinit and it calls into this one, maybe this
whole facility should be __cpuinit/__cpuinitdata because its results
land in the tlb_ll*_* arrays and all those functions and table can be
thrown away then because they're not needed anymore.

> +{
> +	int i, j, n;
> +	unsigned int regs[4];
> +	unsigned char *desc = (unsigned char *)regs;
> +	/* Number of times to iterate */
> +	n = cpuid_eax(2) & 0xFF;
> +
> +	for (i = 0 ; i < n ; i++) {
> +		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
> +
> +		/* If bit 31 is set, this is an unknown format */
> +		for (j = 0 ; j < 3 ; j++)
> +			if (regs[j] & (1 << 31))
> +				regs[j] = 0;
> +
> +		/* Byte 0 is level count, not a descriptor */
> +		for (j = 1 ; j < 16 ; j++)
> +			intel_tlb_lookup(desc[j]);
> +	}
> +}
> +
>  static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
>  	.c_vendor	= "Intel",
>  	.c_ident	= { "GenuineIntel" },
> -- 
> 1.7.5.4
> 
> 

-- 
Regards/Gruss,
Boris.

Advanced Micro Devices GmbH
Einsteinring 24, 85609 Dornach
GM: Alberto Bozzo
Reg: Dornach, Landkreis Muenchen
HRB Nr. 43632 WEEE Registernr: 129 19551

  reply	other threads:[~2012-05-10 14:43 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-05-10  5:00 [PATCH v4 0/7] tlb flush optimization Alex Shi
2012-05-10  5:00 ` [PATCH v4 1/7] x86/tlb: unify TLB_FLUSH_ALL definition Alex Shi
2012-05-10 18:46   ` Rob Landley
2012-05-11 18:33     ` H. Peter Anvin
2012-05-10  5:00 ` [PATCH v4 2/7] x86/tlb_info: get last level TLB entry number of CPU Alex Shi
2012-05-10 14:43   ` Borislav Petkov [this message]
2012-05-11  0:33     ` Alex Shi
2012-05-10 15:58   ` Borislav Petkov
2012-05-11  0:38     ` Alex Shi
2012-05-10  5:00 ` [PATCH v4 3/7] x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range Alex Shi
2012-05-10  7:53   ` Borislav Petkov
2012-05-10  8:50     ` Alex Shi
2012-05-10 21:42       ` Rob Landley
2012-05-10  8:42   ` Borislav Petkov
2012-05-10  9:04     ` Alex Shi
2012-05-12  8:01       ` Alex Shi
2012-05-13 11:13         ` Borislav Petkov
2012-05-15  1:06           ` Alex Shi
2012-05-15 10:33             ` Borislav Petkov
2012-05-15 11:16               ` Peter Zijlstra
2012-05-15 11:56                 ` Borislav Petkov
2012-05-15 12:00                   ` Peter Zijlstra
2012-05-15 13:58                     ` Alex Shi
2012-05-10  5:00 ` [PATCH v4 4/7] x86/tlb: fall back to flush all when meet a THP large page Alex Shi
2012-05-10  9:29   ` Peter Zijlstra
2012-05-10 10:40     ` Borislav Petkov
2012-05-11  0:44       ` Alex Shi
2012-05-11  9:03         ` Peter Zijlstra
2012-05-11 16:28   ` Andrea Arcangeli
2012-05-12  7:58     ` Alex Shi
2012-05-10  5:00 ` [PATCH v4 5/7] x86/tlb: add tlb flush all factor for specific CPU Alex Shi
2012-05-10  9:35   ` Peter Zijlstra
2012-05-11  0:47     ` Alex Shi
2012-05-10  9:37   ` Peter Zijlstra
2012-05-11  0:48     ` Alex Shi
2012-05-10  9:38   ` Peter Zijlstra
2012-05-10 10:42     ` Borislav Petkov
2012-05-11  0:50       ` Alex Shi
2012-05-11  0:49     ` Alex Shi
2012-05-11  9:04       ` Peter Zijlstra
2012-05-11  9:04         ` Peter Zijlstra
2012-05-11 12:51           ` Alex Shi
2012-05-10  5:00 ` [PATCH v4 6/7] x86/tlb: optimizing flush_tlb_mm Alex Shi
2012-05-10  8:27   ` Peter Zijlstra
2012-05-10  5:00 ` [PATCH v4 7/7] x86/tlb: add tlb_flushall_factor into sysfs for user testing/tuning Alex Shi
2012-05-10  8:27   ` Borislav Petkov
2012-05-11  0:52     ` Alex Shi
2012-05-11  9:51       ` Borislav Petkov
2012-05-11 12:53         ` Alex Shi
2012-05-10 15:13   ` Greg KH
2012-05-11  0:59     ` Alex Shi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20120510144321.GA32700@aftab.osrc.amd.com \
    --to=bp@amd64.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=alex.shi@intel.com \
    --cc=arnd@arndb.de \
    --cc=avi@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=cpw@sgi.com \
    --cc=dhowells@redhat.com \
    --cc=fenghua.yu@intel.com \
    --cc=fweisbec@gmail.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hpa@zytor.com \
    --cc=hughd@google.com \
    --cc=jeremy@goop.org \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=kosaki.motohiro@jp.fujitsu.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@mit.edu \
    --cc=mingo@redhat.com \
    --cc=n-horiguchi@ah.jp.nec.com \
    --cc=oleg@redhat.com \
    --cc=paul.gortmaker@windriver.com \
    --cc=penberg@kernel.org \
    --cc=riel@redhat.com \
    --cc=rientjes@google.com \
    --cc=rob@landley.net \
    --cc=rostedt@goodmis.org \
    --cc=steiner@sgi.com \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=trenn@suse.de \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®