1 files changed, 414 insertions, 226 deletions

diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index b3eeb66c0a5..9c8f7394c61 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -1,5 +1,5 @@
 /*
- *	Routines to indentify caches on Intel CPU.
+ *	Routines to identify caches on Intel CPU.
  *
  *	Changes:
  *	Venkatesh Pallipadi	: Adding cache identification through cpuid(4)
@@ -17,7 +17,7 @@
 
 #include <asm/processor.h>
 #include <linux/smp.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/smp.h>
 
 #define LVL_1_INST	1
@@ -37,7 +37,7 @@ struct _cache_table {
 /* All the cache descriptor types we care about (no TLB or
    trace cache entries) */
 
-static const struct _cache_table __cpuinitconst cache_table[] =
+static const struct _cache_table cache_table[] =
 {
 	{ 0x06, LVL_1_INST, 8 },	/* 4-way set assoc, 32 byte line size */
 	{ 0x08, LVL_1_INST, 16 },	/* 4-way set assoc, 32 byte line size */
@@ -45,6 +45,7 @@ static const struct _cache_table __cpuinitconst cache_table[] =
 	{ 0x0a, LVL_1_DATA, 8 },	/* 2 way set assoc, 32 byte line size */
 	{ 0x0c, LVL_1_DATA, 16 },	/* 4-way set assoc, 32 byte line size */
 	{ 0x0d, LVL_1_DATA, 16 },	/* 4-way set assoc, 64 byte line size */
+	{ 0x0e, LVL_1_DATA, 24 },	/* 6-way set assoc, 64 byte line size */
 	{ 0x21, LVL_2,      256 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x22, LVL_3,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x23, LVL_3,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
@@ -66,6 +67,7 @@ static const struct _cache_table __cpuinitconst cache_table[] =
 	{ 0x45, LVL_2,      MB(2) },	/* 4-way set assoc, 32 byte line size */
 	{ 0x46, LVL_3,      MB(4) },	/* 4-way set assoc, 64 byte line size */
 	{ 0x47, LVL_3,      MB(8) },	/* 8-way set assoc, 64 byte line size */
+	{ 0x48, LVL_2,      MB(3) },	/* 12-way set assoc, 64 byte line size */
 	{ 0x49, LVL_3,      MB(4) },	/* 16-way set assoc, 64 byte line size */
 	{ 0x4a, LVL_3,      MB(6) },	/* 12-way set assoc, 64 byte line size */
 	{ 0x4b, LVL_3,      MB(8) },	/* 16-way set assoc, 64 byte line size */
@@ -87,6 +89,7 @@ static const struct _cache_table __cpuinitconst cache_table[] =
 	{ 0x7c, LVL_2,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x7d, LVL_2,      MB(2) },	/* 8-way set assoc, 64 byte line size */
 	{ 0x7f, LVL_2,      512 },	/* 2-way set assoc, 64 byte line size */
+	{ 0x80, LVL_2,      512 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x82, LVL_2,      256 },	/* 8-way set assoc, 32 byte line size */
 	{ 0x83, LVL_2,      512 },	/* 8-way set assoc, 32 byte line size */
 	{ 0x84, LVL_2,      MB(1) },	/* 8-way set assoc, 32 byte line size */
@@ -148,24 +151,17 @@ union _cpuid4_leaf_ecx {
 	u32 full;
 };
 
-struct _cpuid4_info {
+struct _cpuid4_info_regs {
 	union _cpuid4_leaf_eax eax;
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
 	unsigned long size;
-	bool can_disable;
-	unsigned int l3_indices;
-	DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
+	struct amd_northbridge *nb;
 };
 
-/* subset of above _cpuid4_info w/o shared_cpu_map */
-struct _cpuid4_info_regs {
-	union _cpuid4_leaf_eax eax;
-	union _cpuid4_leaf_ebx ebx;
-	union _cpuid4_leaf_ecx ecx;
-	unsigned long size;
-	bool can_disable;
-	unsigned int l3_indices;
+struct _cpuid4_info {
+	struct _cpuid4_info_regs base;
+	DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
 };
 
 unsigned short			num_cache_leaves;
@@ -207,7 +203,7 @@ union l3_cache {
 	unsigned val;
 };
 
-static const unsigned short __cpuinitconst assocs[] = {
+static const unsigned short assocs[] = {
 	[1] = 1,
 	[2] = 2,
 	[4] = 4,
@@ -221,10 +217,10 @@ static const unsigned short __cpuinitconst assocs[] = {
 	[0xf] = 0xffff /* fully associative - no way to show this currently */
 };
 
-static const unsigned char __cpuinitconst levels[] = { 1, 1, 2, 3 };
-static const unsigned char __cpuinitconst types[] = { 1, 2, 3, 3 };
+static const unsigned char levels[] = { 1, 1, 2, 3 };
+static const unsigned char types[] = { 1, 2, 3, 3 };
 
-static void __cpuinit
+static void
 amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 		     union _cpuid4_leaf_ebx *ebx,
 		     union _cpuid4_leaf_ecx *ecx)
@@ -261,7 +257,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 		line_size = l2.line_size;
 		lines_per_tag = l2.lines_per_tag;
 		/* cpu_data has errata corrections for K7 applied */
-		size_in_kb = current_cpu_data.x86_cache_size;
+		size_in_kb = __this_cpu_read(cpu_info.x86_cache_size);
 		break;
 	case 3:
 		if (!l3.val)
@@ -283,7 +279,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	eax->split.type = types[leaf];
 	eax->split.level = levels[leaf];
 	eax->split.num_threads_sharing = 0;
-	eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
+	eax->split.num_cores_on_die = __this_cpu_read(cpu_info.x86_max_cores) - 1;
 
 
 	if (assoc == 0xffff)
@@ -297,125 +293,194 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 
 struct _cache_attr {
 	struct attribute attr;
-	ssize_t (*show)(struct _cpuid4_info *, char *);
-	ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
+	ssize_t (*show)(struct _cpuid4_info *, char *, unsigned int);
+	ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count,
+			 unsigned int);
 };
 
-#ifdef CONFIG_CPU_SUP_AMD
-static unsigned int __cpuinit amd_calc_l3_indices(void)
+#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS)
+/*
+ * L3 cache descriptors
+ */
+static void amd_calc_l3_indices(struct amd_northbridge *nb)
 {
-	/*
-	 * We're called over smp_call_function_single() and therefore
-	 * are on the correct cpu.
-	 */
-	int cpu = smp_processor_id();
-	int node = cpu_to_node(cpu);
-	struct pci_dev *dev = node_to_k8_nb_misc(node);
+	struct amd_l3_cache *l3 = &nb->l3_cache;
 	unsigned int sc0, sc1, sc2, sc3;
 	u32 val = 0;
 
-	pci_read_config_dword(dev, 0x1C4, &val);
+	pci_read_config_dword(nb->misc, 0x1C4, &val);
 
 	/* calculate subcache sizes */
-	sc0 = !(val & BIT(0));
-	sc1 = !(val & BIT(4));
-	sc2 = !(val & BIT(8))  + !(val & BIT(9));
-	sc3 = !(val & BIT(12)) + !(val & BIT(13));
+	l3->subcaches[0] = sc0 = !(val & BIT(0));
+	l3->subcaches[1] = sc1 = !(val & BIT(4));
+
+	if (boot_cpu_data.x86 == 0x15) {
+		l3->subcaches[0] = sc0 += !(val & BIT(1));
+		l3->subcaches[1] = sc1 += !(val & BIT(5));
+	}
 
-	return (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
+	l3->subcaches[2] = sc2 = !(val & BIT(8))  + !(val & BIT(9));
+	l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
+
+	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
-static void __cpuinit
-amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
+static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
 {
+	int node;
+
+	/* only for L3, and not in virtualized environments */
 	if (index < 3)
 		return;
 
-	if (boot_cpu_data.x86 == 0x11)
-		return;
+	node = amd_get_nb_id(smp_processor_id());
+	this_leaf->nb = node_to_amd_nb(node);
+	if (this_leaf->nb && !this_leaf->nb->l3_cache.indices)
+		amd_calc_l3_indices(this_leaf->nb);
+}
 
-	/* see errata #382 and #388 */
-	if ((boot_cpu_data.x86 == 0x10) &&
-	    ((boot_cpu_data.x86_model < 0x8) ||
-	     (boot_cpu_data.x86_mask  < 0x1)))
-		return;
+/*
+ * check whether a slot used for disabling an L3 index is occupied.
+ * @l3: L3 cache descriptor
+ * @slot: slot number (0..1)
+ *
+ * @returns: the disabled index if used or negative value if slot free.
+ */
+int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot)
+{
+	unsigned int reg = 0;
 
-	this_leaf->can_disable = true;
-	this_leaf->l3_indices  = amd_calc_l3_indices();
+	pci_read_config_dword(nb->misc, 0x1BC + slot * 4, &reg);
+
+	/* check whether this slot is activated already */
+	if (reg & (3UL << 30))
+		return reg & 0xfff;
+
+	return -1;
 }
 
 static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
-				  unsigned int index)
+				  unsigned int slot)
 {
-	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
-	int node = amd_get_nb_id(cpu);
-	struct pci_dev *dev = node_to_k8_nb_misc(node);
-	unsigned int reg = 0;
+	int index;
 
-	if (!this_leaf->can_disable)
+	if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
 		return -EINVAL;
 
-	if (!dev)
-		return -EINVAL;
+	index = amd_get_l3_disable_slot(this_leaf->base.nb, slot);
+	if (index >= 0)
+		return sprintf(buf, "%d\n", index);
 
-	pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
-	return sprintf(buf, "0x%08x\n", reg);
+	return sprintf(buf, "FREE\n");
 }
 
-#define SHOW_CACHE_DISABLE(index)					\
+#define SHOW_CACHE_DISABLE(slot)					\
 static ssize_t								\
-show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf)	\
+show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf,	\
+			  unsigned int cpu)				\
 {									\
-	return show_cache_disable(this_leaf, buf, index);		\
+	return show_cache_disable(this_leaf, buf, slot);		\
 }
 SHOW_CACHE_DISABLE(0)
 SHOW_CACHE_DISABLE(1)
 
-static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
-	const char *buf, size_t count, unsigned int index)
+static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
+				 unsigned slot, unsigned long idx)
 {
-	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
-	int node = amd_get_nb_id(cpu);
-	struct pci_dev *dev = node_to_k8_nb_misc(node);
-	unsigned long val = 0;
+	int i;
+
+	idx |= BIT(30);
+
+	/*
+	 *  disable index in all 4 subcaches
+	 */
+	for (i = 0; i < 4; i++) {
+		u32 reg = idx | (i << 20);
+
+		if (!nb->l3_cache.subcaches[i])
+			continue;
+
+		pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
 
-#define SUBCACHE_MASK	(3UL << 20)
-#define SUBCACHE_INDEX	0xfff
+		/*
+		 * We need to WBINVD on a core on the node containing the L3
+		 * cache which indices we disable therefore a simple wbinvd()
+		 * is not sufficient.
+		 */
+		wbinvd_on_cpu(cpu);
 
-	if (!this_leaf->can_disable)
+		reg |= BIT(31);
+		pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
+	}
+}
+
+/*
+ * disable a L3 cache index by using a disable-slot
+ *
+ * @l3:    L3 cache descriptor
+ * @cpu:   A CPU on the node containing the L3 cache
+ * @slot:  slot number (0..1)
+ * @index: index to disable
+ *
+ * @return: 0 on success, error status on failure
+ */
+int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot,
+			    unsigned long index)
+{
+	int ret = 0;
+
+	/*  check if @slot is already used or the index is already disabled */
+	ret = amd_get_l3_disable_slot(nb, slot);
+	if (ret >= 0)
+		return -EEXIST;
+
+	if (index > nb->l3_cache.indices)
 		return -EINVAL;
 
+	/* check whether the other slot has disabled the same index already */
+	if (index == amd_get_l3_disable_slot(nb, !slot))
+		return -EEXIST;
+
+	amd_l3_disable_index(nb, cpu, slot, index);
+
+	return 0;
+}
+
+static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
+				  const char *buf, size_t count,
+				  unsigned int slot)
+{
+	unsigned long val = 0;
+	int cpu, err = 0;
+
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!dev)
+	if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
 		return -EINVAL;
 
-	if (strict_strtoul(buf, 10, &val) < 0)
-		return -EINVAL;
+	cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
 
-	/* do not allow writes outside of allowed bits */
-	if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
-	    ((val & SUBCACHE_INDEX) > this_leaf->l3_indices))
+	if (strict_strtoul(buf, 10, &val) < 0)
 		return -EINVAL;
 
-	val |= BIT(30);
-	pci_write_config_dword(dev, 0x1BC + index * 4, val);
-	/*
-	 * We need to WBINVD on a core on the node containing the L3 cache which
-	 * indices we disable therefore a simple wbinvd() is not sufficient.
-	 */
-	wbinvd_on_cpu(cpu);
-	pci_write_config_dword(dev, 0x1BC + index * 4, val | BIT(31));
+	err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val);
+	if (err) {
+		if (err == -EEXIST)
+			pr_warning("L3 slot %d in use/index already disabled!\n",
+				   slot);
+		return err;
+	}
 	return count;
 }
 
-#define STORE_CACHE_DISABLE(index)					\
+#define STORE_CACHE_DISABLE(slot)					\
 static ssize_t								\
-store_cache_disable_##index(struct _cpuid4_info *this_leaf,		\
-			    const char *buf, size_t count)		\
+store_cache_disable_##slot(struct _cpuid4_info *this_leaf,		\
+			   const char *buf, size_t count,		\
+			   unsigned int cpu)				\
 {									\
-	return store_cache_disable(this_leaf, buf, count, index);	\
+	return store_cache_disable(this_leaf, buf, count, slot);	\
 }
 STORE_CACHE_DISABLE(0)
 STORE_CACHE_DISABLE(1)
@@ -425,26 +490,58 @@ static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
 static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
 		show_cache_disable_1, store_cache_disable_1);
 
-#else	/* CONFIG_CPU_SUP_AMD */
-static void __cpuinit
-amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
+static ssize_t
+show_subcaches(struct _cpuid4_info *this_leaf, char *buf, unsigned int cpu)
 {
-};
-#endif /* CONFIG_CPU_SUP_AMD */
+	if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		return -EINVAL;
+
+	return sprintf(buf, "%x\n", amd_get_subcaches(cpu));
+}
+
+static ssize_t
+store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count,
+		unsigned int cpu)
+{
+	unsigned long val;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		return -EINVAL;
+
+	if (strict_strtoul(buf, 16, &val) < 0)
+		return -EINVAL;
+
+	if (amd_set_subcaches(cpu, val))
+		return -EINVAL;
+
+	return count;
+}
+
+static struct _cache_attr subcaches =
+	__ATTR(subcaches, 0644, show_subcaches, store_subcaches);
+
+#else
+#define amd_init_l3_cache(x, y)
+#endif  /* CONFIG_AMD_NB && CONFIG_SYSFS */
 
 static int
-__cpuinit cpuid4_cache_lookup_regs(int index,
-				   struct _cpuid4_info_regs *this_leaf)
+cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf)
 {
-	union _cpuid4_leaf_eax 	eax;
-	union _cpuid4_leaf_ebx 	ebx;
-	union _cpuid4_leaf_ecx 	ecx;
+	union _cpuid4_leaf_eax	eax;
+	union _cpuid4_leaf_ebx	ebx;
+	union _cpuid4_leaf_ecx	ecx;
 	unsigned		edx;
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
-		amd_cpuid4(index, &eax, &ebx, &ecx);
-		if (boot_cpu_data.x86 >= 0x10)
-			amd_check_l3_disable(index, this_leaf);
+		if (cpu_has_topoext)
+			cpuid_count(0x8000001d, index, &eax.full,
+				    &ebx.full, &ecx.full, &edx);
+		else
+			amd_cpuid4(index, &eax, &ebx, &ecx);
+		amd_init_l3_cache(this_leaf, index);
 	} else {
 		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
 	}
@@ -462,22 +559,40 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
 	return 0;
 }
 
-static int __cpuinit find_num_cache_leaves(void)
+static int find_num_cache_leaves(struct cpuinfo_x86 *c)
 {
-	unsigned int		eax, ebx, ecx, edx;
+	unsigned int		eax, ebx, ecx, edx, op;
 	union _cpuid4_leaf_eax	cache_eax;
 	int 			i = -1;
 
+	if (c->x86_vendor == X86_VENDOR_AMD)
+		op = 0x8000001d;
+	else
+		op = 4;
+
 	do {
 		++i;
-		/* Do cpuid(4) loop to find out num_cache_leaves */
-		cpuid_count(4, i, &eax, &ebx, &ecx, &edx);
+		/* Do cpuid(op) loop to find out num_cache_leaves */
+		cpuid_count(op, i, &eax, &ebx, &ecx, &edx);
 		cache_eax.full = eax;
 	} while (cache_eax.split.type != CACHE_TYPE_NULL);
 	return i;
 }
 
-unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
+void init_amd_cacheinfo(struct cpuinfo_x86 *c)
+{
+
+	if (cpu_has_topoext) {
+		num_cache_leaves = find_num_cache_leaves(c);
+	} else if (c->extended_cpuid_level >= 0x80000006) {
+		if (cpuid_edx(0x80000006) & 0xf000)
+			num_cache_leaves = 4;
+		else
+			num_cache_leaves = 3;
+	}
+}
+
+unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 {
 	/* Cache sizes */
 	unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0;
@@ -493,7 +608,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 
 		if (is_initialized == 0) {
 			/* Init num_cache_leaves from boot CPU */
-			num_cache_leaves = find_num_cache_leaves();
+			num_cache_leaves = find_num_cache_leaves(c);
 			is_initialized++;
 		}
 
@@ -502,36 +617,34 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 		 * parameters cpuid leaf to find the cache details
 		 */
 		for (i = 0; i < num_cache_leaves; i++) {
-			struct _cpuid4_info_regs this_leaf;
+			struct _cpuid4_info_regs this_leaf = {};
 			int retval;
 
 			retval = cpuid4_cache_lookup_regs(i, &this_leaf);
-			if (retval >= 0) {
-				switch (this_leaf.eax.split.level) {
-				case 1:
-					if (this_leaf.eax.split.type ==
-							CACHE_TYPE_DATA)
-						new_l1d = this_leaf.size/1024;
-					else if (this_leaf.eax.split.type ==
-							CACHE_TYPE_INST)
-						new_l1i = this_leaf.size/1024;
-					break;
-				case 2:
-					new_l2 = this_leaf.size/1024;
-					num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
-					index_msb = get_count_order(num_threads_sharing);
-					l2_id = c->apicid >> index_msb;
-					break;
-				case 3:
-					new_l3 = this_leaf.size/1024;
-					num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
-					index_msb = get_count_order(
-							num_threads_sharing);
-					l3_id = c->apicid >> index_msb;
-					break;
-				default:
-					break;
-				}
+			if (retval < 0)
+				continue;
+
+			switch (this_leaf.eax.split.level) {
+			case 1:
+				if (this_leaf.eax.split.type == CACHE_TYPE_DATA)
+					new_l1d = this_leaf.size/1024;
+				else if (this_leaf.eax.split.type == CACHE_TYPE_INST)
+					new_l1i = this_leaf.size/1024;
+				break;
+			case 2:
+				new_l2 = this_leaf.size/1024;
+				num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
+				index_msb = get_count_order(num_threads_sharing);
+				l2_id = c->apicid & ~((1 << index_msb) - 1);
+				break;
+			case 3:
+				new_l3 = this_leaf.size/1024;
+				num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
+				index_msb = get_count_order(num_threads_sharing);
+				l3_id = c->apicid & ~((1 << index_msb) - 1);
+				break;
+			default:
+				break;
 			}
 		}
 	}
@@ -617,6 +730,18 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 #endif
 	}
 
+#ifdef CONFIG_X86_HT
+	/*
+	 * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
+	 * turns means that the only possibility is SMT (as indicated in
+	 * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
+	 * that SMT shares all caches, we can unconditionally set cpu_llc_id to
+	 * c->phys_proc_id.
+	 */
+	if (per_cpu(cpu_llc_id, cpu) == BAD_APICID)
+		per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+#endif
+
 	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
 
 	return l2;
@@ -629,28 +754,70 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info);
 #define CPUID4_INFO_IDX(x, y)	(&((per_cpu(ici_cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP
-static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+
+static int cache_shared_amd_cpu_map_setup(unsigned int cpu, int index)
 {
-	struct _cpuid4_info	*this_leaf, *sibling_leaf;
-	unsigned long num_threads_sharing;
-	int index_msb, i, sibling;
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	struct _cpuid4_info *this_leaf;
+	int i, sibling;
+
+	if (cpu_has_topoext) {
+		unsigned int apicid, nshared, first, last;
+
+		if (!per_cpu(ici_cpuid4_info, cpu))
+			return 0;
+
+		this_leaf = CPUID4_INFO_IDX(cpu, index);
+		nshared = this_leaf->base.eax.split.num_threads_sharing + 1;
+		apicid = cpu_data(cpu).apicid;
+		first = apicid - (apicid % nshared);
+		last = first + nshared - 1;
 
-	if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
-		for_each_cpu(i, c->llc_shared_map) {
+		for_each_online_cpu(i) {
+			apicid = cpu_data(i).apicid;
+			if ((apicid < first) || (apicid > last))
+				continue;
+			if (!per_cpu(ici_cpuid4_info, i))
+				continue;
+			this_leaf = CPUID4_INFO_IDX(i, index);
+
+			for_each_online_cpu(sibling) {
+				apicid = cpu_data(sibling).apicid;
+				if ((apicid < first) || (apicid > last))
+					continue;
+				set_bit(sibling, this_leaf->shared_cpu_map);
+			}
+		}
+	} else if (index == 3) {
+		for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
 			if (!per_cpu(ici_cpuid4_info, i))
 				continue;
 			this_leaf = CPUID4_INFO_IDX(i, index);
-			for_each_cpu(sibling, c->llc_shared_map) {
+			for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
 				if (!cpu_online(sibling))
 					continue;
 				set_bit(sibling, this_leaf->shared_cpu_map);
 			}
 		}
-		return;
+	} else
+		return 0;
+
+	return 1;
+}
+
+static void cache_shared_cpu_map_setup(unsigned int cpu, int index)
+{
+	struct _cpuid4_info *this_leaf, *sibling_leaf;
+	unsigned long num_threads_sharing;
+	int index_msb, i;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		if (cache_shared_amd_cpu_map_setup(cpu, index))
+			return;
 	}
+
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
-	num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
+	num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing;
 
 	if (num_threads_sharing == 1)
 		cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map));
@@ -672,7 +839,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 		}
 	}
 }
-static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
+static void cache_remove_shared_cpu_map(unsigned int cpu, int index)
 {
 	struct _cpuid4_info	*this_leaf, *sibling_leaf;
 	int sibling;
@@ -685,16 +852,16 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
 	}
 }
 #else
-static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+static void cache_shared_cpu_map_setup(unsigned int cpu, int index)
 {
 }
 
-static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
+static void cache_remove_shared_cpu_map(unsigned int cpu, int index)
 {
 }
 #endif
 
-static void __cpuinit free_cache_attributes(unsigned int cpu)
+static void free_cache_attributes(unsigned int cpu)
 {
 	int i;
 
@@ -705,24 +872,15 @@ static void __cpuinit free_cache_attributes(unsigned int cpu)
 	per_cpu(ici_cpuid4_info, cpu) = NULL;
 }
 
-static int
-__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
-{
-	struct _cpuid4_info_regs *leaf_regs =
-		(struct _cpuid4_info_regs *)this_leaf;
-
-	return cpuid4_cache_lookup_regs(index, leaf_regs);
-}
-
-static void __cpuinit get_cpu_leaves(void *_retval)
+static void get_cpu_leaves(void *_retval)
 {
 	int j, *retval = _retval, cpu = smp_processor_id();
 
 	/* Do cpuid and store the results */
 	for (j = 0; j < num_cache_leaves; j++) {
-		struct _cpuid4_info *this_leaf;
-		this_leaf = CPUID4_INFO_IDX(cpu, j);
-		*retval = cpuid4_cache_lookup(j, this_leaf);
+		struct _cpuid4_info *this_leaf = CPUID4_INFO_IDX(cpu, j);
+
+		*retval = cpuid4_cache_lookup_regs(j, &this_leaf->base);
 		if (unlikely(*retval < 0)) {
 			int i;
 
@@ -734,7 +892,7 @@ static void __cpuinit get_cpu_leaves(void *_retval)
 	}
 }
 
-static int __cpuinit detect_cache_attributes(unsigned int cpu)
+static int detect_cache_attributes(unsigned int cpu)
 {
 	int			retval;
 
@@ -757,8 +915,7 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
-
-extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */
+#include <linux/cpu.h>
 
 /* pointer to kobject for cpuX/cache */
 static DEFINE_PER_CPU(struct kobject *, ici_cache_kobject);
@@ -774,21 +931,22 @@ static DEFINE_PER_CPU(struct _index_kobject *, ici_index_kobject);
 #define INDEX_KOBJECT_PTR(x, y)		(&((per_cpu(ici_index_kobject, x))[y]))
 
 #define show_one_plus(file_name, object, val)				\
-static ssize_t show_##file_name						\
-			(struct _cpuid4_info *this_leaf, char *buf)	\
+static ssize_t show_##file_name(struct _cpuid4_info *this_leaf, char *buf, \
+				unsigned int cpu)			\
 {									\
 	return sprintf(buf, "%lu\n", (unsigned long)this_leaf->object + val); \
 }
 
-show_one_plus(level, eax.split.level, 0);
-show_one_plus(coherency_line_size, ebx.split.coherency_line_size, 1);
-show_one_plus(physical_line_partition, ebx.split.physical_line_partition, 1);
-show_one_plus(ways_of_associativity, ebx.split.ways_of_associativity, 1);
-show_one_plus(number_of_sets, ecx.split.number_of_sets, 1);
+show_one_plus(level, base.eax.split.level, 0);
+show_one_plus(coherency_line_size, base.ebx.split.coherency_line_size, 1);
+show_one_plus(physical_line_partition, base.ebx.split.physical_line_partition, 1);
+show_one_plus(ways_of_associativity, base.ebx.split.ways_of_associativity, 1);
+show_one_plus(number_of_sets, base.ecx.split.number_of_sets, 1);
 
-static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf,
+			 unsigned int cpu)
 {
-	return sprintf(buf, "%luK\n", this_leaf->size / 1024);
+	return sprintf(buf, "%luK\n", this_leaf->base.size / 1024);
 }
 
 static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
@@ -810,19 +968,22 @@ static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
 	return n;
 }
 
-static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf)
+static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf,
+					  unsigned int cpu)
 {
 	return show_shared_cpu_map_func(leaf, 0, buf);
 }
 
-static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf)
+static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf,
+					   unsigned int cpu)
 {
 	return show_shared_cpu_map_func(leaf, 1, buf);
 }
 
-static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf,
+			 unsigned int cpu)
 {
-	switch (this_leaf->eax.split.type) {
+	switch (this_leaf->base.eax.split.type) {
 	case CACHE_TYPE_DATA:
 		return sprintf(buf, "Data\n");
 	case CACHE_TYPE_INST:
@@ -851,30 +1012,54 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
-#define DEFAULT_SYSFS_CACHE_ATTRS	\
-	&type.attr,			\
-	&level.attr,			\
-	&coherency_line_size.attr,	\
-	&physical_line_partition.attr,	\
-	&ways_of_associativity.attr,	\
-	&number_of_sets.attr,		\
-	&size.attr,			\
-	&shared_cpu_map.attr,		\
-	&shared_cpu_list.attr
-
 static struct attribute *default_attrs[] = {
-	DEFAULT_SYSFS_CACHE_ATTRS,
+	&type.attr,
+	&level.attr,
+	&coherency_line_size.attr,
+	&physical_line_partition.attr,
+	&ways_of_associativity.attr,
+	&number_of_sets.attr,
+	&size.attr,
+	&shared_cpu_map.attr,
+	&shared_cpu_list.attr,
 	NULL
 };
 
-static struct attribute *default_l3_attrs[] = {
-	DEFAULT_SYSFS_CACHE_ATTRS,
-#ifdef CONFIG_CPU_SUP_AMD
-	&cache_disable_0.attr,
-	&cache_disable_1.attr,
+#ifdef CONFIG_AMD_NB
+static struct attribute **amd_l3_attrs(void)
+{
+	static struct attribute **attrs;
+	int n;
+
+	if (attrs)
+		return attrs;
+
+	n = ARRAY_SIZE(default_attrs);
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+		n += 2;
+
+	if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		n += 1;
+
+	attrs = kzalloc(n * sizeof (struct attribute *), GFP_KERNEL);
+	if (attrs == NULL)
+		return attrs = default_attrs;
+
+	for (n = 0; default_attrs[n]; n++)
+		attrs[n] = default_attrs[n];
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
+		attrs[n++] = &cache_disable_0.attr;
+		attrs[n++] = &cache_disable_1.attr;
+	}
+
+	if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		attrs[n++] = &subcaches.attr;
+
+	return attrs;
+}
 #endif
-	NULL
-};
 
 static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 {
@@ -884,7 +1069,7 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 
 	ret = fattr->show ?
 		fattr->show(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
-			buf) :
+			buf, this_leaf->cpu) :
 		0;
 	return ret;
 }
@@ -898,7 +1083,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 
 	ret = fattr->store ?
 		fattr->store(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
-			buf, count) :
+			buf, count, this_leaf->cpu) :
 		0;
 	return ret;
 }
@@ -917,7 +1102,7 @@ static struct kobj_type ktype_percpu_entry = {
 	.sysfs_ops	= &sysfs_ops,
 };
 
-static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu)
+static void cpuid4_cache_sysfs_exit(unsigned int cpu)
 {
 	kfree(per_cpu(ici_cache_kobject, cpu));
 	kfree(per_cpu(ici_index_kobject, cpu));
@@ -926,7 +1111,7 @@ static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu)
 	free_cache_attributes(cpu);
 }
 
-static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu)
+static int cpuid4_cache_sysfs_init(unsigned int cpu)
 {
 	int err;
 
@@ -958,9 +1143,9 @@ err_out:
 static DECLARE_BITMAP(cache_dev_map, NR_CPUS);
 
 /* Add/Remove cache interface for CPU device */
-static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
+static int cache_add_dev(struct device *dev)
 {
-	unsigned int cpu = sys_dev->id;
+	unsigned int cpu = dev->id;
 	unsigned long i, j;
 	struct _index_kobject *this_object;
 	struct _cpuid4_info   *this_leaf;
@@ -972,7 +1157,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 
 	retval = kobject_init_and_add(per_cpu(ici_cache_kobject, cpu),
 				      &ktype_percpu_entry,
-				      &sys_dev->kobj, "%s", "cache");
+				      &dev->kobj, "%s", "cache");
 	if (retval < 0) {
 		cpuid4_cache_sysfs_exit(cpu);
 		return retval;
@@ -985,11 +1170,11 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 
 		this_leaf = CPUID4_INFO_IDX(cpu, i);
 
-		if (this_leaf->can_disable)
-			ktype_cache.default_attrs = default_l3_attrs;
-		else
-			ktype_cache.default_attrs = default_attrs;
-
+		ktype_cache.default_attrs = default_attrs;
+#ifdef CONFIG_AMD_NB
+		if (this_leaf->base.nb)
+			ktype_cache.default_attrs = amd_l3_attrs();
+#endif
 		retval = kobject_init_and_add(&(this_object->kobj),
 					      &ktype_cache,
 					      per_cpu(ici_cache_kobject, cpu),
@@ -1009,9 +1194,9 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 	return 0;
 }
 
-static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
+static void cache_remove_dev(struct device *dev)
 {
-	unsigned int cpu = sys_dev->id;
+	unsigned int cpu = dev->id;
 	unsigned long i;
 
 	if (per_cpu(ici_cpuid4_info, cpu) == NULL)
@@ -1026,47 +1211,50 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
 	cpuid4_cache_sysfs_exit(cpu);
 }
 
-static int __cpuinit cacheinfo_cpu_callback(struct notifier_block *nfb,
-					unsigned long action, void *hcpu)
+static int cacheinfo_cpu_callback(struct notifier_block *nfb,
+				  unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
-	struct sys_device *sys_dev;
+	struct device *dev;
 
-	sys_dev = get_cpu_sysdev(cpu);
+	dev = get_cpu_device(cpu);
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		cache_add_dev(sys_dev);
+		cache_add_dev(dev);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		cache_remove_dev(sys_dev);
+		cache_remove_dev(dev);
 		break;
 	}
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata cacheinfo_cpu_notifier = {
+static struct notifier_block cacheinfo_cpu_notifier = {
 	.notifier_call = cacheinfo_cpu_callback,
 };
 
-static int __cpuinit cache_sysfs_init(void)
+static int __init cache_sysfs_init(void)
 {
-	int i;
+	int i, err = 0;
 
 	if (num_cache_leaves == 0)
 		return 0;
 
+	cpu_notifier_register_begin();
 	for_each_online_cpu(i) {
-		int err;
-		struct sys_device *sys_dev = get_cpu_sysdev(i);
+		struct device *dev = get_cpu_device(i);
 
-		err = cache_add_dev(sys_dev);
+		err = cache_add_dev(dev);
 		if (err)
-			return err;
+			goto out;
 	}
-	register_hotcpu_notifier(&cacheinfo_cpu_notifier);
-	return 0;
+	__register_hotcpu_notifier(&cacheinfo_cpu_notifier);
+
+out:
+	cpu_notifier_register_done();
+	return err;
 }
 
 device_initcall(cache_sysfs_init);