/*
- * Routines to indentify caches on Intel CPU.
+ * Routines to indentify caches on Intel CPU.
*
- * Changes:
- * Venkatesh Pallipadi : Adding cache identification through cpuid(4)
- * Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
+ * Changes:
+ * Venkatesh Pallipadi : Adding cache identification through cpuid(4)
+ * Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
* Andi Kleen / Andreas Herrmann : CPUID4 emulation on AMD.
*/
#include <linux/compiler.h>
#include <linux/cpu.h>
#include <linux/sched.h>
+#include <linux/pci.h>
#include <asm/processor.h>
+#include <linux/smp.h>
+#include <asm/k8.h>
#include <asm/smp.h>
#define LVL_1_INST 1
#define LVL_3 4
#define LVL_TRACE 5
-struct _cache_table
-{
+struct _cache_table {
unsigned char descriptor;
char cache_type;
short size;
};
-/* all the cache descriptor types we care about (no TLB or trace cache entries) */
-static struct _cache_table cache_table[] __cpuinitdata =
+#define MB(x) ((x) * 1024)
+
+/* All the cache descriptor types we care about (no TLB or
+ trace cache entries) */
+
+static const struct _cache_table __cpuinitconst 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 */
+ { 0x09, LVL_1_INST, 32 }, /* 4-way set assoc, 64 byte line size */
{ 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 */
+ { 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, 1024 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x25, LVL_3, 2048 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x29, LVL_3, 4096 }, /* 8-way set assoc, sectored cache, 64 byte line size */
+ { 0x23, LVL_3, MB(1) }, /* 8-way set assoc, sectored cache, 64 byte line size */
+ { 0x25, LVL_3, MB(2) }, /* 8-way set assoc, sectored cache, 64 byte line size */
+ { 0x29, LVL_3, MB(4) }, /* 8-way set assoc, sectored cache, 64 byte line size */
{ 0x2c, LVL_1_DATA, 32 }, /* 8-way set assoc, 64 byte line size */
{ 0x30, LVL_1_INST, 32 }, /* 8-way set assoc, 64 byte line size */
{ 0x39, LVL_2, 128 }, /* 4-way set assoc, sectored cache, 64 byte line size */
{ 0x41, LVL_2, 128 }, /* 4-way set assoc, 32 byte line size */
{ 0x42, LVL_2, 256 }, /* 4-way set assoc, 32 byte line size */
{ 0x43, LVL_2, 512 }, /* 4-way set assoc, 32 byte line size */
- { 0x44, LVL_2, 1024 }, /* 4-way set assoc, 32 byte line size */
- { 0x45, LVL_2, 2048 }, /* 4-way set assoc, 32 byte line size */
- { 0x46, LVL_3, 4096 }, /* 4-way set assoc, 64 byte line size */
- { 0x47, LVL_3, 8192 }, /* 8-way set assoc, 64 byte line size */
- { 0x49, LVL_3, 4096 }, /* 16-way set assoc, 64 byte line size */
- { 0x4a, LVL_3, 6144 }, /* 12-way set assoc, 64 byte line size */
- { 0x4b, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */
- { 0x4c, LVL_3, 12288 }, /* 12-way set assoc, 64 byte line size */
- { 0x4d, LVL_3, 16384 }, /* 16-way set assoc, 64 byte line size */
- { 0x4e, LVL_2, 6144 }, /* 24-way set assoc, 64 byte line size */
+ { 0x44, LVL_2, MB(1) }, /* 4-way set assoc, 32 byte line size */
+ { 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 */
+ { 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 */
+ { 0x4c, LVL_3, MB(12) }, /* 12-way set assoc, 64 byte line size */
+ { 0x4d, LVL_3, MB(16) }, /* 16-way set assoc, 64 byte line size */
+ { 0x4e, LVL_2, MB(6) }, /* 24-way set assoc, 64 byte line size */
{ 0x60, LVL_1_DATA, 16 }, /* 8-way set assoc, sectored cache, 64 byte line size */
{ 0x66, LVL_1_DATA, 8 }, /* 4-way set assoc, sectored cache, 64 byte line size */
{ 0x67, LVL_1_DATA, 16 }, /* 4-way set assoc, sectored cache, 64 byte line size */
{ 0x71, LVL_TRACE, 16 }, /* 8-way set assoc */
{ 0x72, LVL_TRACE, 32 }, /* 8-way set assoc */
{ 0x73, LVL_TRACE, 64 }, /* 8-way set assoc */
- { 0x78, LVL_2, 1024 }, /* 4-way set assoc, 64 byte line size */
- { 0x79, LVL_2, 128 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x7a, LVL_2, 256 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x7b, LVL_2, 512 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x7c, LVL_2, 1024 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x7d, LVL_2, 2048 }, /* 8-way set assoc, 64 byte line size */
- { 0x7f, LVL_2, 512 }, /* 2-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, 1024 }, /* 8-way set assoc, 32 byte line size */
- { 0x85, LVL_2, 2048 }, /* 8-way set assoc, 32 byte line size */
- { 0x86, LVL_2, 512 }, /* 4-way set assoc, 64 byte line size */
- { 0x87, LVL_2, 1024 }, /* 8-way set assoc, 64 byte line size */
+ { 0x78, LVL_2, MB(1) }, /* 4-way set assoc, 64 byte line size */
+ { 0x79, LVL_2, 128 }, /* 8-way set assoc, sectored cache, 64 byte line size */
+ { 0x7a, LVL_2, 256 }, /* 8-way set assoc, sectored cache, 64 byte line size */
+ { 0x7b, LVL_2, 512 }, /* 8-way set assoc, sectored cache, 64 byte line size */
+ { 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 */
+ { 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 */
+ { 0x85, LVL_2, MB(2) }, /* 8-way set assoc, 32 byte line size */
+ { 0x86, LVL_2, 512 }, /* 4-way set assoc, 64 byte line size */
+ { 0x87, LVL_2, MB(1) }, /* 8-way set assoc, 64 byte line size */
+ { 0xd0, LVL_3, 512 }, /* 4-way set assoc, 64 byte line size */
+ { 0xd1, LVL_3, MB(1) }, /* 4-way set assoc, 64 byte line size */
+ { 0xd2, LVL_3, MB(2) }, /* 4-way set assoc, 64 byte line size */
+ { 0xd6, LVL_3, MB(1) }, /* 8-way set assoc, 64 byte line size */
+ { 0xd7, LVL_3, MB(2) }, /* 8-way set assoc, 64 byte line size */
+ { 0xd8, LVL_3, MB(4) }, /* 12-way set assoc, 64 byte line size */
+ { 0xdc, LVL_3, MB(2) }, /* 12-way set assoc, 64 byte line size */
+ { 0xdd, LVL_3, MB(4) }, /* 12-way set assoc, 64 byte line size */
+ { 0xde, LVL_3, MB(8) }, /* 12-way set assoc, 64 byte line size */
+ { 0xe2, LVL_3, MB(2) }, /* 16-way set assoc, 64 byte line size */
+ { 0xe3, LVL_3, MB(4) }, /* 16-way set assoc, 64 byte line size */
+ { 0xe4, LVL_3, MB(8) }, /* 16-way set assoc, 64 byte line size */
+ { 0xea, LVL_3, MB(12) }, /* 24-way set assoc, 64 byte line size */
+ { 0xeb, LVL_3, MB(18) }, /* 24-way set assoc, 64 byte line size */
+ { 0xec, LVL_3, MB(24) }, /* 24-way set assoc, 64 byte line size */
{ 0x00, 0, 0}
};
-enum _cache_type
-{
+enum _cache_type {
CACHE_TYPE_NULL = 0,
CACHE_TYPE_DATA = 1,
CACHE_TYPE_INST = 2,
union _cpuid4_leaf_ebx ebx;
union _cpuid4_leaf_ecx ecx;
unsigned long size;
- cpumask_t shared_cpu_map; /* future?: only cpus/node is needed */
+ bool can_disable;
+ unsigned int l3_indices;
+ DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
+};
+
+/* 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;
};
unsigned short num_cache_leaves;
Maybe later */
union l1_cache {
struct {
- unsigned line_size : 8;
- unsigned lines_per_tag : 8;
- unsigned assoc : 8;
- unsigned size_in_kb : 8;
+ unsigned line_size:8;
+ unsigned lines_per_tag:8;
+ unsigned assoc:8;
+ unsigned size_in_kb:8;
};
unsigned val;
};
union l2_cache {
struct {
- unsigned line_size : 8;
- unsigned lines_per_tag : 4;
- unsigned assoc : 4;
- unsigned size_in_kb : 16;
+ unsigned line_size:8;
+ unsigned lines_per_tag:4;
+ unsigned assoc:4;
+ unsigned size_in_kb:16;
};
unsigned val;
};
union l3_cache {
struct {
- unsigned line_size : 8;
- unsigned lines_per_tag : 4;
- unsigned assoc : 4;
- unsigned res : 2;
- unsigned size_encoded : 14;
+ unsigned line_size:8;
+ unsigned lines_per_tag:4;
+ unsigned assoc:4;
+ unsigned res:2;
+ unsigned size_encoded:14;
};
unsigned val;
};
-static unsigned short assocs[] __cpuinitdata = {
- [1] = 1, [2] = 2, [4] = 4, [6] = 8,
- [8] = 16, [0xa] = 32, [0xb] = 48,
+static const unsigned short __cpuinitconst assocs[] = {
+ [1] = 1,
+ [2] = 2,
+ [4] = 4,
+ [6] = 8,
+ [8] = 16,
+ [0xa] = 32,
+ [0xb] = 48,
[0xc] = 64,
- [0xf] = 0xffff // ??
+ [0xd] = 96,
+ [0xe] = 128,
+ [0xf] = 0xffff /* fully associative - no way to show this currently */
};
-static unsigned char levels[] __cpuinitdata = { 1, 1, 2, 3 };
-static unsigned char types[] __cpuinitdata = { 1, 2, 3, 3 };
+static const unsigned char __cpuinitconst levels[] = { 1, 1, 2, 3 };
+static const unsigned char __cpuinitconst types[] = { 1, 2, 3, 3 };
-static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
- union _cpuid4_leaf_ebx *ebx,
- union _cpuid4_leaf_ecx *ecx)
+static void __cpuinit
+amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
+ union _cpuid4_leaf_ebx *ebx,
+ union _cpuid4_leaf_ecx *ecx)
{
unsigned dummy;
unsigned line_size, lines_per_tag, assoc, size_in_kb;
case 0:
if (!l1->val)
return;
- assoc = l1->assoc;
+ assoc = assocs[l1->assoc];
line_size = l1->line_size;
lines_per_tag = l1->lines_per_tag;
size_in_kb = l1->size_in_kb;
case 2:
if (!l2.val)
return;
- assoc = l2.assoc;
+ assoc = assocs[l2.assoc];
line_size = l2.line_size;
lines_per_tag = l2.lines_per_tag;
/* cpu_data has errata corrections for K7 applied */
case 3:
if (!l3.val)
return;
- assoc = l3.assoc;
+ assoc = assocs[l3.assoc];
line_size = l3.line_size;
lines_per_tag = l3.lines_per_tag;
size_in_kb = l3.size_encoded * 512;
+ if (boot_cpu_has(X86_FEATURE_AMD_DCM)) {
+ size_in_kb = size_in_kb >> 1;
+ assoc = assoc >> 1;
+ }
break;
default:
return;
eax->split.is_self_initializing = 1;
eax->split.type = types[leaf];
eax->split.level = levels[leaf];
- if (leaf == 3)
- eax->split.num_threads_sharing = current_cpu_data.x86_max_cores - 1;
- else
- eax->split.num_threads_sharing = 0;
+ eax->split.num_threads_sharing = 0;
eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
- if (assoc == 0xf)
+ if (assoc == 0xffff)
eax->split.is_fully_associative = 1;
ebx->split.coherency_line_size = line_size - 1;
- ebx->split.ways_of_associativity = assocs[assoc] - 1;
+ ebx->split.ways_of_associativity = assoc - 1;
ebx->split.physical_line_partition = lines_per_tag - 1;
ecx->split.number_of_sets = (size_in_kb * 1024) / line_size /
(ebx->split.ways_of_associativity + 1) - 1;
}
-static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+struct _cache_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct _cpuid4_info *, char *);
+ ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
+};
+
+#ifdef CONFIG_CPU_SUP_AMD
+static unsigned int __cpuinit amd_calc_l3_indices(void)
+{
+ /*
+ * 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);
+ unsigned int sc0, sc1, sc2, sc3;
+ u32 val = 0;
+
+ pci_read_config_dword(dev, 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));
+
+ return (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
+}
+
+static void __cpuinit
+amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
+{
+ if (index < 3)
+ return;
+
+ if (boot_cpu_data.x86 == 0x11)
+ return;
+
+ /* see errata #382 and #388 */
+ if ((boot_cpu_data.x86 == 0x10) &&
+ ((boot_cpu_data.x86_model < 0x8) ||
+ (boot_cpu_data.x86_mask < 0x1)))
+ return;
+
+ this_leaf->can_disable = true;
+ this_leaf->l3_indices = amd_calc_l3_indices();
+}
+
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
+ unsigned int index)
+{
+ 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;
+
+ if (!this_leaf->can_disable)
+ return -EINVAL;
+
+ if (!dev)
+ return -EINVAL;
+
+ pci_read_config_dword(dev, 0x1BC + index * 4, ®);
+ return sprintf(buf, "0x%08x\n", reg);
+}
+
+#define SHOW_CACHE_DISABLE(index) \
+static ssize_t \
+show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \
+{ \
+ return show_cache_disable(this_leaf, buf, index); \
+}
+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)
+{
+ 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;
+
+#define SUBCACHE_MASK (3UL << 20)
+#define SUBCACHE_INDEX 0xfff
+
+ if (!this_leaf->can_disable)
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!dev)
+ return -EINVAL;
+
+ if (strict_strtoul(buf, 10, &val) < 0)
+ return -EINVAL;
+
+ /* do not allow writes outside of allowed bits */
+ if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
+ ((val & SUBCACHE_INDEX) > this_leaf->l3_indices))
+ 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));
+ return count;
+}
+
+#define STORE_CACHE_DISABLE(index) \
+static ssize_t \
+store_cache_disable_##index(struct _cpuid4_info *this_leaf, \
+ const char *buf, size_t count) \
+{ \
+ return store_cache_disable(this_leaf, buf, count, index); \
+}
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
+
+static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
+ show_cache_disable_0, store_cache_disable_0);
+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)
+{
+};
+#endif /* CONFIG_CPU_SUP_AMD */
+
+static int
+__cpuinit 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;
unsigned edx;
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
amd_cpuid4(index, &eax, &ebx, &ecx);
- else
- cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
+ if (boot_cpu_data.x86 >= 0x10)
+ amd_check_l3_disable(index, this_leaf);
+ } else {
+ cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
+ }
+
if (eax.split.type == CACHE_TYPE_NULL)
return -EIO; /* better error ? */
this_leaf->eax = eax;
this_leaf->ebx = ebx;
this_leaf->ecx = ecx;
- this_leaf->size = (ecx.split.number_of_sets + 1) *
- (ebx.split.coherency_line_size + 1) *
- (ebx.split.physical_line_partition + 1) *
- (ebx.split.ways_of_associativity + 1);
+ this_leaf->size = (ecx.split.number_of_sets + 1) *
+ (ebx.split.coherency_line_size + 1) *
+ (ebx.split.physical_line_partition + 1) *
+ (ebx.split.ways_of_associativity + 1);
return 0;
}
unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
{
- unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */
+ /* Cache sizes */
+ unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0;
unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
* parameters cpuid leaf to find the cache details
*/
for (i = 0; i < num_cache_leaves; i++) {
- struct _cpuid4_info this_leaf;
-
+ struct _cpuid4_info_regs this_leaf;
int retval;
- retval = cpuid4_cache_lookup(i, &this_leaf);
+ retval = cpuid4_cache_lookup_regs(i, &this_leaf);
if (retval >= 0) {
- switch(this_leaf.eax.split.level) {
- case 1:
+ switch (this_leaf.eax.split.level) {
+ case 1:
if (this_leaf.eax.split.type ==
CACHE_TYPE_DATA)
new_l1d = this_leaf.size/1024;
CACHE_TYPE_INST)
new_l1i = this_leaf.size/1024;
break;
- case 2:
+ 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:
+ 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);
+ index_msb = get_count_order(
+ num_threads_sharing);
l3_id = c->apicid >> index_msb;
break;
- default:
+ default:
break;
}
}
/* Number of times to iterate */
n = cpuid_eax(2) & 0xFF;
- for ( i = 0 ; i < n ; i++ ) {
+ for (i = 0 ; i < n ; i++) {
cpuid(2, ®s[0], ®s[1], ®s[2], ®s[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;
- }
+ 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++ ) {
+ for (j = 1 ; j < 16 ; j++) {
unsigned char des = dp[j];
unsigned char k = 0;
/* look up this descriptor in the table */
- while (cache_table[k].descriptor != 0)
- {
+ while (cache_table[k].descriptor != 0) {
if (cache_table[k].descriptor == des) {
if (only_trace && cache_table[k].cache_type != LVL_TRACE)
break;
#endif
}
- if (trace)
- printk (KERN_INFO "CPU: Trace cache: %dK uops", trace);
- else if ( l1i )
- printk (KERN_INFO "CPU: L1 I cache: %dK", l1i);
-
- if (l1d)
- printk(", L1 D cache: %dK\n", l1d);
- else
- printk("\n");
-
- if (l2)
- printk(KERN_INFO "CPU: L2 cache: %dK\n", l2);
-
- if (l3)
- printk(KERN_INFO "CPU: L3 cache: %dK\n", l3);
-
c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
return l2;
}
+#ifdef CONFIG_SYSFS
+
/* pointer to _cpuid4_info array (for each cache leaf) */
-static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
-#define CPUID4_INFO_IDX(x, y) (&((per_cpu(cpuid4_info, x))[y]))
+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)
{
struct _cpuid4_info *this_leaf, *sibling_leaf;
unsigned long num_threads_sharing;
- int index_msb, i;
+ int index_msb, i, sibling;
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
+ for_each_cpu(i, c->llc_shared_map) {
+ if (!per_cpu(ici_cpuid4_info, i))
+ continue;
+ this_leaf = CPUID4_INFO_IDX(i, index);
+ for_each_cpu(sibling, c->llc_shared_map) {
+ if (!cpu_online(sibling))
+ continue;
+ set_bit(sibling, this_leaf->shared_cpu_map);
+ }
+ }
+ return;
+ }
this_leaf = CPUID4_INFO_IDX(cpu, index);
num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
if (num_threads_sharing == 1)
- cpu_set(cpu, this_leaf->shared_cpu_map);
+ cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map));
else {
index_msb = get_count_order(num_threads_sharing);
for_each_online_cpu(i) {
if (cpu_data(i).apicid >> index_msb ==
c->apicid >> index_msb) {
- cpu_set(i, this_leaf->shared_cpu_map);
- if (i != cpu && per_cpu(cpuid4_info, i)) {
- sibling_leaf = CPUID4_INFO_IDX(i, index);
- cpu_set(cpu, sibling_leaf->shared_cpu_map);
+ cpumask_set_cpu(i,
+ to_cpumask(this_leaf->shared_cpu_map));
+ if (i != cpu && per_cpu(ici_cpuid4_info, i)) {
+ sibling_leaf =
+ CPUID4_INFO_IDX(i, index);
+ cpumask_set_cpu(cpu, to_cpumask(
+ sibling_leaf->shared_cpu_map));
}
}
}
int sibling;
this_leaf = CPUID4_INFO_IDX(cpu, index);
- for_each_cpu_mask(sibling, this_leaf->shared_cpu_map) {
- sibling_leaf = CPUID4_INFO_IDX(sibling, index);
- cpu_clear(cpu, sibling_leaf->shared_cpu_map);
+ for_each_cpu(sibling, to_cpumask(this_leaf->shared_cpu_map)) {
+ sibling_leaf = CPUID4_INFO_IDX(sibling, index);
+ cpumask_clear_cpu(cpu,
+ to_cpumask(sibling_leaf->shared_cpu_map));
}
}
#else
-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 __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+{
+}
+
+static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
+{
+}
#endif
static void __cpuinit free_cache_attributes(unsigned int cpu)
for (i = 0; i < num_cache_leaves; i++)
cache_remove_shared_cpu_map(cpu, i);
- kfree(per_cpu(cpuid4_info, cpu));
- per_cpu(cpuid4_info, cpu) = NULL;
+ kfree(per_cpu(ici_cpuid4_info, cpu));
+ per_cpu(ici_cpuid4_info, cpu) = NULL;
}
-static int __cpuinit detect_cache_attributes(unsigned int cpu)
+static int
+__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
{
- struct _cpuid4_info *this_leaf;
- unsigned long j;
- int retval;
- cpumask_t oldmask;
-
- if (num_cache_leaves == 0)
- return -ENOENT;
+ struct _cpuid4_info_regs *leaf_regs =
+ (struct _cpuid4_info_regs *)this_leaf;
- per_cpu(cpuid4_info, cpu) = kzalloc(
- sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL);
- if (per_cpu(cpuid4_info, cpu) == NULL)
- return -ENOMEM;
+ return cpuid4_cache_lookup_regs(index, leaf_regs);
+}
- oldmask = current->cpus_allowed;
- retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
- if (retval)
- goto out;
+static void __cpuinit 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);
- if (unlikely(retval < 0)) {
+ *retval = cpuid4_cache_lookup(j, this_leaf);
+ if (unlikely(*retval < 0)) {
int i;
for (i = 0; i < j; i++)
}
cache_shared_cpu_map_setup(cpu, j);
}
- set_cpus_allowed_ptr(current, &oldmask);
+}
+
+static int __cpuinit detect_cache_attributes(unsigned int cpu)
+{
+ int retval;
-out:
+ if (num_cache_leaves == 0)
+ return -ENOENT;
+
+ per_cpu(ici_cpuid4_info, cpu) = kzalloc(
+ sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL);
+ if (per_cpu(ici_cpuid4_info, cpu) == NULL)
+ return -ENOMEM;
+
+ smp_call_function_single(cpu, get_cpu_leaves, &retval, true);
if (retval) {
- kfree(per_cpu(cpuid4_info, cpu));
- per_cpu(cpuid4_info, cpu) = NULL;
+ kfree(per_cpu(ici_cpuid4_info, cpu));
+ per_cpu(ici_cpuid4_info, cpu) = NULL;
}
return retval;
}
-#ifdef CONFIG_SYSFS
-
#include <linux/kobject.h>
#include <linux/sysfs.h>
extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */
/* pointer to kobject for cpuX/cache */
-static DEFINE_PER_CPU(struct kobject *, cache_kobject);
+static DEFINE_PER_CPU(struct kobject *, ici_cache_kobject);
struct _index_kobject {
struct kobject kobj;
};
/* pointer to array of kobjects for cpuX/cache/indexY */
-static DEFINE_PER_CPU(struct _index_kobject *, index_kobject);
-#define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(index_kobject, x))[y]))
+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) \
{ \
- return sprintf (buf, "%lu\n", (unsigned long)this_leaf->object + val); \
+ return sprintf(buf, "%lu\n", (unsigned long)this_leaf->object + val); \
}
show_one_plus(level, eax.split.level, 0);
static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf)
{
- return sprintf (buf, "%luK\n", this_leaf->size / 1024);
+ return sprintf(buf, "%luK\n", this_leaf->size / 1024);
}
static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
int n = 0;
if (len > 1) {
- cpumask_t *mask = &this_leaf->shared_cpu_map;
+ const struct cpumask *mask;
- n = type?
- cpulist_scnprintf(buf, len-2, *mask):
- cpumask_scnprintf(buf, len-2, *mask);
+ mask = to_cpumask(this_leaf->shared_cpu_map);
+ n = type ?
+ cpulist_scnprintf(buf, len-2, mask) :
+ cpumask_scnprintf(buf, len-2, mask);
buf[n++] = '\n';
buf[n] = '\0';
}
return show_shared_cpu_map_func(leaf, 1, buf);
}
-static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) {
- switch(this_leaf->eax.split.type) {
- case CACHE_TYPE_DATA:
+static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
+{
+ switch (this_leaf->eax.split.type) {
+ case CACHE_TYPE_DATA:
return sprintf(buf, "Data\n");
- break;
- case CACHE_TYPE_INST:
+ case CACHE_TYPE_INST:
return sprintf(buf, "Instruction\n");
- break;
- case CACHE_TYPE_UNIFIED:
+ case CACHE_TYPE_UNIFIED:
return sprintf(buf, "Unified\n");
- break;
- default:
+ default:
return sprintf(buf, "Unknown\n");
- break;
}
}
-struct _cache_attr {
- struct attribute attr;
- ssize_t (*show)(struct _cpuid4_info *, char *);
- ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
-};
+#define to_object(k) container_of(k, struct _index_kobject, kobj)
+#define to_attr(a) container_of(a, struct _cache_attr, attr)
#define define_one_ro(_name) \
static struct _cache_attr _name = \
define_one_ro(shared_cpu_map);
define_one_ro(shared_cpu_list);
-static struct attribute * default_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,
+#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,
NULL
};
-#define to_object(k) container_of(k, struct _index_kobject, kobj)
-#define to_attr(a) container_of(a, struct _cache_attr, attr)
+static struct attribute *default_l3_attrs[] = {
+ DEFAULT_SYSFS_CACHE_ATTRS,
+#ifdef CONFIG_CPU_SUP_AMD
+ &cache_disable_0.attr,
+ &cache_disable_1.attr,
+#endif
+ NULL
+};
-static ssize_t show(struct kobject * kobj, struct attribute * attr, char * buf)
+static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
{
struct _cache_attr *fattr = to_attr(attr);
struct _index_kobject *this_leaf = to_object(kobj);
ret = fattr->show ?
fattr->show(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
buf) :
- 0;
+ 0;
return ret;
}
-static ssize_t store(struct kobject * kobj, struct attribute * attr,
- const char * buf, size_t count)
+static ssize_t store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t count)
{
- return 0;
+ struct _cache_attr *fattr = to_attr(attr);
+ struct _index_kobject *this_leaf = to_object(kobj);
+ ssize_t ret;
+
+ ret = fattr->store ?
+ fattr->store(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
+ buf, count) :
+ 0;
+ return ret;
}
-static struct sysfs_ops sysfs_ops = {
+static const struct sysfs_ops sysfs_ops = {
.show = show,
.store = store,
};
static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu)
{
- kfree(per_cpu(cache_kobject, cpu));
- kfree(per_cpu(index_kobject, cpu));
- per_cpu(cache_kobject, cpu) = NULL;
- per_cpu(index_kobject, cpu) = NULL;
+ kfree(per_cpu(ici_cache_kobject, cpu));
+ kfree(per_cpu(ici_index_kobject, cpu));
+ per_cpu(ici_cache_kobject, cpu) = NULL;
+ per_cpu(ici_index_kobject, cpu) = NULL;
free_cache_attributes(cpu);
}
return err;
/* Allocate all required memory */
- per_cpu(cache_kobject, cpu) =
+ per_cpu(ici_cache_kobject, cpu) =
kzalloc(sizeof(struct kobject), GFP_KERNEL);
- if (unlikely(per_cpu(cache_kobject, cpu) == NULL))
+ if (unlikely(per_cpu(ici_cache_kobject, cpu) == NULL))
goto err_out;
- per_cpu(index_kobject, cpu) = kzalloc(
- sizeof(struct _index_kobject ) * num_cache_leaves, GFP_KERNEL);
- if (unlikely(per_cpu(index_kobject, cpu) == NULL))
+ per_cpu(ici_index_kobject, cpu) = kzalloc(
+ sizeof(struct _index_kobject) * num_cache_leaves, GFP_KERNEL);
+ if (unlikely(per_cpu(ici_index_kobject, cpu) == NULL))
goto err_out;
return 0;
return -ENOMEM;
}
-static cpumask_t cache_dev_map = CPU_MASK_NONE;
+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)
unsigned int cpu = sys_dev->id;
unsigned long i, j;
struct _index_kobject *this_object;
+ struct _cpuid4_info *this_leaf;
int retval;
retval = cpuid4_cache_sysfs_init(cpu);
if (unlikely(retval < 0))
return retval;
- retval = kobject_init_and_add(per_cpu(cache_kobject, cpu),
+ retval = kobject_init_and_add(per_cpu(ici_cache_kobject, cpu),
&ktype_percpu_entry,
&sys_dev->kobj, "%s", "cache");
if (retval < 0) {
}
for (i = 0; i < num_cache_leaves; i++) {
- this_object = INDEX_KOBJECT_PTR(cpu,i);
+ this_object = INDEX_KOBJECT_PTR(cpu, i);
this_object->cpu = cpu;
this_object->index = i;
+
+ 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;
+
retval = kobject_init_and_add(&(this_object->kobj),
&ktype_cache,
- per_cpu(cache_kobject, cpu),
+ per_cpu(ici_cache_kobject, cpu),
"index%1lu", i);
if (unlikely(retval)) {
- for (j = 0; j < i; j++) {
- kobject_put(&(INDEX_KOBJECT_PTR(cpu,j)->kobj));
- }
- kobject_put(per_cpu(cache_kobject, cpu));
+ for (j = 0; j < i; j++)
+ kobject_put(&(INDEX_KOBJECT_PTR(cpu, j)->kobj));
+ kobject_put(per_cpu(ici_cache_kobject, cpu));
cpuid4_cache_sysfs_exit(cpu);
return retval;
}
kobject_uevent(&(this_object->kobj), KOBJ_ADD);
}
- cpu_set(cpu, cache_dev_map);
+ cpumask_set_cpu(cpu, to_cpumask(cache_dev_map));
- kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
+ kobject_uevent(per_cpu(ici_cache_kobject, cpu), KOBJ_ADD);
return 0;
}
unsigned int cpu = sys_dev->id;
unsigned long i;
- if (per_cpu(cpuid4_info, cpu) == NULL)
+ if (per_cpu(ici_cpuid4_info, cpu) == NULL)
return;
- if (!cpu_isset(cpu, cache_dev_map))
+ if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map)))
return;
- cpu_clear(cpu, cache_dev_map);
+ cpumask_clear_cpu(cpu, to_cpumask(cache_dev_map));
for (i = 0; i < num_cache_leaves; i++)
- kobject_put(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));
- kobject_put(per_cpu(cache_kobject, cpu));
+ kobject_put(&(INDEX_KOBJECT_PTR(cpu, i)->kobj));
+ kobject_put(per_cpu(ici_cache_kobject, cpu));
cpuid4_cache_sysfs_exit(cpu);
}
return NOTIFY_OK;
}
-static struct notifier_block __cpuinitdata cacheinfo_cpu_notifier =
-{
+static struct notifier_block __cpuinitdata cacheinfo_cpu_notifier = {
.notifier_call = cacheinfo_cpu_callback,
};