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.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Link: http://lkml.kernel.org/r/1340845344-27557-2-git-send-email-alex.shi@intel.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

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

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 (this_cpu->c_detect_tlb)
+		this_cpu->c_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

@@ -20,10 +20,19 @@ struct cpu_dev {
 	void		(*c_bsp_init)(struct cpuinfo_x86 *);
 	void		(*c_init)(struct cpuinfo_x86 *);
 	void		(*c_identify)(struct cpuinfo_x86 *);
+	void		(*c_detect_tlb)(struct cpuinfo_x86 *);
 	unsigned int	(*c_size_cache)(struct cpuinfo_x86 *, unsigned int);
 	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"))) = \

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[] __cpuinitconst = {
+	{ 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 }
+};
+
+static void __cpuinit 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;
+	}
+}
+
+static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c)
+{
+	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" },
@@ -546,6 +687,7 @@ static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
 	},
 	.c_size_cache	= intel_size_cache,
 #endif
+	.c_detect_tlb	= intel_detect_tlb,
 	.c_early_init   = early_init_intel,
 	.c_init		= init_intel,
 	.c_x86_vendor	= X86_VENDOR_INTEL,