Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86/mm changes from Peter Anvin:
 "The big change here is the patchset by Alex Shi to use INVLPG to flush
  only the affected pages when we only need to flush a small page range.

  It also removes the special INVALIDATE_TLB_VECTOR interrupts (32
  vectors!) and replace it with an ordinary IPI function call."

Fix up trivial conflicts in arch/x86/include/asm/apic.h (added code next
to changed line)

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/tlb: Fix build warning and crash when building for !SMP
  x86/tlb: do flush_tlb_kernel_range by 'invlpg'
  x86/tlb: replace INVALIDATE_TLB_VECTOR by CALL_FUNCTION_VECTOR
  x86/tlb: enable tlb flush range support for x86
  mm/mmu_gather: enable tlb flush range in generic mmu_gather
  x86/tlb: add tlb_flushall_shift knob into debugfs
  x86/tlb: add tlb_flushall_shift for specific CPU
  x86/tlb: fall back to flush all when meet a THP large page
  x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range
  x86/tlb_info: get last level TLB entry number of CPU
  x86: Add read_mostly declaration/definition to variables from smp.h
  x86: Define early read-mostly per-cpu macros

3 files changed, 216 insertions, 0 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5bbc082c47ad..46d8786d655e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -452,6 +452,35 @@ 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];
+
+/*
+ * 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 (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_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_flushall_shift);
+}
+
 void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_HT
@@ -911,6 +940,8 @@ 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 8bacc7826fb3..4041c24ae7db 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/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"))) = \
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3e6ff6cbf42a..0a4ce2980a5a 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -491,6 +491,181 @@ 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_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;
+	}
+}
+
+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]);
+	}
+	intel_tlb_flushall_shift_set(c);
+}
+
 static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
 	.c_vendor	= "Intel",
 	.c_ident	= { "GenuineIntel" },
@@ -546,6 +721,7 @@ 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,